Mercurial > repos > vipints > deseq_hts

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/README	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,82 @@
+------------------------------------------------------
+DESeq2-hts: A Galaxy wrapper for DESeq2 version 1.0.19
+------------------------------------------------------
+
+Description:
+------------
+    DESeq2 can be used as a web service embedded in a Galaxy instance.
+    We call it as DESeq2-hts.
+
+Requirements:
+-------------
+    MATLAB/OCTAVE and Python :- Preprocessing of sequencing reads and GFF files
+    R, Bio-conductor package :- Required for DESeq2
+    SCIPY, NUMPY :- for python
+    SAMTOOLS :- Sequencing read processing
+
+Contents:
+---------
+    ./src
+    All relevant scripts for DESeq-hts are located in the subdirectory
+    src. src/deseq2-hts.sh is the main script to start DESeq2-hts. The
+    preprocessing of BAM and GFF file start before the R DESeq2 script.
+	Please follow the shell script to understand the details.
+
+    ./galaxy
+    Galaxy tool configuration file can be found galaxy folder. Please
+    make necessary editing for .xml file and remaining .sh files and
+    perform few tests.
+
+    ./setup.sh
+    Setup script for DESeq2-hts.
+
+    ./mex
+    matlab executable files.
+
+    ./bin
+    Contains deseq2_config.sh file which is used for the configuration of
+    DESeq2-hts. According to your platform, the default file will be changed.
+
+    ./test_data
+    This sub-directory contains all data for running a functional test in
+    Galaxy framework. You may need to move these test files into the test-data
+    directory.
+
+    ./tools
+    A python based GFF parsing program. Also contains small utils programs.
+
+Getting started:
+----------------
+    Check for all requirements first, then
+
+    a) Run ./setup.sh and setup paths and configuration options for DESeq2-hts.
+
+    b) Inside the mex folder execute the make file to create platform dependent .mex files
+	    cd mex/Makefile
+	    make [interpreter]
+            make octave for octave
+            make matlab for matlab
+            make all for octave and matlab
+
+    c) Edit the Galaxy tool configuration file to adjust the path if necessary.
+
+Licenses:
+---------
+    If **DESeq2** is used to obtain results for scientific publications it should be cited as [1].
+
+    This wrapper program (DESeq2-hts) is free software; you can redistribute it and/or modify it
+    under the terms of the GNU General Public License as published by the Free Software Foundation;
+    either version 3 of the License, or (at your option) any later version.
+
+    Written (W) 2009-2012 Jonas Behr, Regina Bohnert, Andre Kahles, Gunnar Raetsch, Vipin T. Sreedharan
+    Copyright (C) 2009-2012 Friedrich Miescher Laboratory of the Max Planck Society, Tubingen, Germany and
+                  2013 cBio Memorial Sloan Kettering Cancer Center, New York City, USA.
+
+References:
+-----------
+    [1] Anders, S and Huber, W (2010): `Differential expression analysis for sequence count data`.
+
+Contact:
+--------
+    vipin [at] cbio.mskcc.org
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/bin/deseq2_config.sh	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,18 @@
+#!/bin/bash
+export DESEQ2_VERSION=1.0.19
+export DESEQ2_PATH=
+export DESEQ2_SRC_PATH=$DESEQ2_PATH/src
+export DESEQ2_BIN_PATH=$DESEQ2_PATH/bin
+export INTERPRETER=
+export MATLAB_BIN_PATH=
+export MATLAB_MEX_PATH=
+export MATLAB_INCLUDE_DIR=
+export OCTAVE_BIN_PATH=
+export OCTAVE_MKOCT=
+export SAMTOOLS_DIR=
+export PYTHON_PATH=/usr/bin/python
+export SCIPY_PATH=
+export R_PATH=
+export LD_LIBRARY_PATH=
+export ENVIRONMENT=galaxy
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/bin/deseq2_config.sh.sample	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,17 @@
+#!/bin/bash
+export DESEQ2_VERSION=1.0.19
+export DESEQ2_PATH=/home/galaxy/software/DESeq2-hts/
+export DESEQ2_SRC_PATH=$DESEQ2_PATH/src
+export DESEQ2_BIN_PATH=$DESEQ2_PATH/bin
+export INTERPRETER=octave
+export MATLAB_BIN_PATH=
+export MATLAB_MEX_PATH=
+export MATLAB_INCLUDE_DIR=
+export OCTAVE_BIN_PATH=/home/galaxy/software/octave/source/octave-3.6.3/octave
+export OCTAVE_MKOCT=/home/galaxy/software/bin/mkoctfile
+export SAMTOOLS_DIR=/home/galaxy/software/samtools-0.1.19/
+export PYTHON_PATH=/usr/bin/python
+export SCIPY_PATH=/home/galaxy/software/lib/python2.6/site-packages/
+export R_PATH=/home/galaxy/software/bin/R
+export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/oqtansTools/oqtans_dep/octave-3.6.2_64/lib/octave/3.6.2/
+export ENVIRONMENT=galaxy
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/bin/genarglist.sh	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,13 @@
+#/bin/bash
+##
+# Copyright (C) 2009-2013 Max Planck Society and Memorial Sloan Kettering Cancer Center
+##
+until [ -z $1 ] ; do
+	if [ $# != 1 ];
+	then
+		echo -n "'$1', "
+	else
+		echo -n "'$1'"
+	fi
+	shift
+done
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/bin/genes_cell2struct	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,7 @@
+#!/bin/bash
+# deseq-hts wrapper script to start the interpreter with the correct list of arguments
+# Copyright (C) 2010-2012 Max Planck Society
+set -e
+PROG=`basename $0`
+DIR=`dirname $0`
+exec ${DIR}/start_interpreter.sh ${PROG} "`${DIR}/genarglist.sh $@`"
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/bin/get_read_counts	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,7 @@
+#!/bin/bash
+# deseq-hts wrapper script to start the interpreter with the correct list of arguments
+# Copyright (C) 2010-2012 Max Planck Society
+set -e
+PROG=`basename $0`
+DIR=`dirname $0`
+exec ${DIR}/start_interpreter.sh ${PROG} "`${DIR}/genarglist.sh $@`"
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/bin/start_interpreter.sh	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,26 @@
+#/bin/bash
+##
+# Copyright (C) 2009-2013 Max Planck Society and Memorial Sloan Kettering Cancer Center
+##
+
+set -e
+
+. `dirname $0`/deseq2_config.sh
+
+export MATLAB_RETURN_FILE=`mktemp`
+
+if [ "$INTERPRETER" == 'octave' ];
+then
+	echo exit | ${OCTAVE_BIN_PATH} --no-window-system --silent --eval "global SHELL_INTERPRETER_INVOKE; SHELL_INTERPRETER_INVOKE=1; addpath $DESEQ2_SRC_PATH; deseq_config; $1($2); exit;" || (echo starting Octave failed; rm -f $MATLAB_RETURN_FILE; exit -1) ;
+fi
+
+if [ "$INTERPRETER" == 'matlab' ];
+then
+	echo exit | ${MATLAB_BIN_PATH} -nodisplay -r "global SHELL_INTERPRETER_INVOKE; SHELL_INTERPRETER_INVOKE=1; addpath $DESEQ2_SRC_PATH; deseq_config; $1($2); exit;" || (echo starting Matlab failed; rm -f $MATLAB_RETURN_FILE; exit -1) ;
+fi
+
+test -f $MATLAB_RETURN_FILE || exit 0
+ret=`cat $MATLAB_RETURN_FILE` ;
+rm -f $MATLAB_RETURN_FILE
+exit $ret
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/galaxy/deseq2.xml	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,106 @@
+<tool id="deseq2-hts" name="DESeq2" version="1.0.19">
+  <description> Differential gene expression analysis based on the negative binomial distribution</description>
+  <command interpreter="bash">
+./../src/deseq2-hts.sh $anno_input_selected $deseq_out $deseq_out.extra_files_path/gene_map.mat
+$distype
+#for $i in $replicate_groups
+#for $j in $i.replicates
+$j.bam_alignment:#slurp
+#end for
+
+#end for
+    >> $Log_File </command>
+  <inputs>
+	<param format="gff,gtf,gff3" name="anno_input_selected" type="data" label="Genome annotation in GFF file" help="A tab delimited format for storing sequence features and annotations"/>
+   <repeat name="replicate_groups" title="Replicate group" min="2">
+     <repeat name="replicates" title="Replicate">
+      <param format="bam" name="bam_alignment" type="data" label="BAM alignment file" help="BAM alignment file. Can be generated from SAM files using the SAMTools."/>
+     </repeat>
+   </repeat>
+
+    <param name="distype" type="select" label="Select fitting of dispersions to the mean intensity">
+            <option value="parametric">Parametric</option>
+            <option value="local">Local</option>
+            <option value="mean" selected="true">Mean</option>
+    </param>
+
+  </inputs>
+
+  <outputs>
+    <data format="txt" name="deseq_out" label="${tool.name} on ${on_string}: Differential Expression"/>
+    <data format="txt" name="Log_File" label="${tool.name} on ${on_string}: log"/>
+  </outputs>
+
+  <tests>
+    <test>
+	./deseq2-hts.sh ../test_data/deseq_c_elegans_WS200-I-regions.gff3 ../test_data/deseq_c_elegans_WS200-I-regions_deseq.txt ../test_data/genes.mat ../test_data/deseq_c_elegans_WS200-I-regions-SRX001872.bam ../test_data/deseq_c_elegans_WS200-I-regions-SRX001875.bam
+
+      <param name="anno_input_selected" value="deseq_c_elegans_WS200-I-regions.gff3" ftype="gff3" />
+      <param name="bam_alignments1" value="deseq_c_elegans_WS200-I-regions-SRX001872.bam" ftype="bam" />
+      <param name="bam_alignments2" value="deseq_c_elegans_WS200-I-regions-SRX001875.bam" ftype="bam" />
+      <output name="deseq_out" file="deseq_c_elegans_WS200-I-regions_deseq.txt" />
+    </test>
+  </tests>
+
+  <help>
+
+.. class:: infomark
+
+**What it does**
+
+DESeq2_ Estimate variance-mean dependence in count data from high-throughput sequencing assays and test for differential expression based on a model using the negative binomial distribution.
+
+.. _DESeq2: http://bioconductor.org/packages/2.12/bioc/html/DESeq2.html
+
+`DESeq2` requires:
+
+Genome annotation in GFF file type, containing the necessary information about the transcripts that are to be quantified.
+
+The BAM alignment files grouped into replicate groups, each containing several replicates. BAM files store the read alignments, The program will also work with only two groups containing only a single replicate each. However, this analysis has less statistical power and is therefore not recommended!
+
+------
+
+**Licenses**
+
+If **DESeq2** is used to obtain results for scientific publications it
+should be cited as [1]_.
+
+**References**
+
+.. [1] Anders, S and Huber, W (2010): `Differential expression analysis for sequence count data`_.
+
+.. _Differential expression analysis for sequence count data: http://dx.doi.org/10.1186/gb-2010-11-10-r106
+
+------
+
+.. class:: infomark
+
+**About formats**
+
+**GFF/GTF format** General Feature Format/Gene Transfer Format is a format for describing genes and other features associated with DNA, RNA and protein sequences. GFF3 lines have nine tab-separated fields:
+
+1. seqid - The name of a chromosome or scaffold.
+2. source - The program that generated this feature.
+3. type - The name of this type of feature. Some examples of standard feature types are "gene", "CDS", "protein", "mRNA", and "exon".
+4. start - The starting position of the feature in the sequence. The first base is numbered 1.
+5. stop - The ending position of the feature (inclusive).
+6. score - A score between 0 and 1000. If there is no score value, enter ".".
+7. strand - Valid entries include '+', '-', or '.' (for don't know/care).
+8. phase - If the feature is a coding exon, frame should be a number between 0-2 that represents the reading frame of the first base. If the feature is not a coding exon, the value should be '.'.
+9. attributes - All lines with the same group are linked together into a single item.
+
+For more information see http://www.sequenceontology.org/gff3.shtml
+
+**BAM format** The Sequence Alignment/Map (SAM) format is a
+tab-limited text format that stores large nucleotide sequence
+alignments. BAM is the binary version of a SAM file that allows for
+fast and intensive data processing. The format specification and the
+description of SAMtools can be found on
+http://samtools.sourceforge.net/.
+
+------
+
+DESeq2-hts Wrapper Version 0.2 (Aug 2013)
+
+</help>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/mex/Makefile	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,38 @@
+include ../bin/deseq2_config.sh
+
+MEX=${MATLAB_MEX_PATH}
+MKOCTFILE=${OCTAVE_MKOCT}
+MATLAB_INCL=${MATLAB_INCLUDE_DIR}
+SAMDIR=${SAMTOOLS_DIR}
+
+
+all:	get_reads.mex get_bam_properties.mex interval_overlap.mex get_reads.mexa64 get_bam_properties.mexa64 interval_overlap.mexa64
+octave:	get_reads.mex get_bam_properties.mex interval_overlap.mex
+matlab:	get_reads.mexa64 get_bam_properties.mexa64 interval_overlap.mexa64
+
+
+get_reads.mexa64:	get_reads.cpp get_reads_direct.cpp mex_input.cpp read.cpp
+	rm -f *.o
+	${MEX} -g -O get_reads.cpp get_reads_direct.cpp mex_input.cpp read.cpp -I${SAMDIR} -L${SAMDIR} -lbam -lz -lcurses -I$(MATLAB_INCL)
+
+get_bam_properties.mexa64:	get_bam_properties.cpp
+	rm -f *.o
+	${MEX} -g -O get_bam_properties.cpp -I$(MATLAB_INCL)
+
+interval_overlap.mexa64:	interval_overlap.cpp
+	${MEX} -g -O interval_overlap.cpp -I$(MATLAB_INCL)
+
+get_reads.mex:	get_reads.cpp get_reads_direct.cpp mex_input.cpp read.cpp
+	rm -f *.o
+	${MKOCTFILE} -g --mex get_reads.cpp get_reads_direct.cpp mex_input.cpp read.cpp -I${SAMDIR} -L${SAMDIR} -lbam -lz -lcurses
+
+get_bam_properties.mex:	get_bam_properties.cpp
+	rm -f *.o
+	${MKOCTFILE} -g --mex get_bam_properties.cpp
+
+interval_overlap.mex: interval_overlap.cpp
+	rm -f *.o
+	${MKOCTFILE} -g --mex interval_overlap.cpp
+
+clean:
+	rm -f *.o *.mexa64 *.mex
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/mex/get_bam_properties.cpp	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,216 @@
+/*
+*  This program is free software; you can redistribute it and/or modify
+*  it under the terms of the GNU General Public License as published by
+*  the Free Software Foundation; either version 3 of the License, or
+*  (at your option) any later version.
+*
+*   Written (W) 2009-2011 Regina Bohnert
+*   Copyright (C) 2009-2011 Max Planck Society
+*/
+
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <ctype.h>
+#include <assert.h>
+
+#include <vector>
+  using std::vector;
+#include <string>
+  using std::string;
+#include <algorithm>
+  using std::find;
+  using std::min;
+
+#include <mex.h>
+
+
+char *get_string(const mxArray *prhs);
+
+typedef unsigned int uint32_t;
+typedef unsigned char uint8_t;
+
+/*
+ * [read_len num_reads] = get_bam_properties(fname, path_samtools, contig_name)
+ *
+ * -- input --
+ * prhs[0] file name of paired reads in BAM format (sorted by read id)
+ * prhs[1] path to samtools
+ * prhs[2] contig name
+ *
+ * -- output --
+ * plhs[0] length of read
+ * plhs[1] number of unique reads
+*/
+void mexFunction(int nlhs, mxArray *plhs[], int nrhs, const mxArray *prhs[]) {
+  // checks for the right number of arguments
+  if (nrhs !=3 || nlhs > 2) {
+    mexErrMsgTxt("number of input and output args should be 3 and 2\nUSAGE:\n     [read_len, num_reads] = get_bam_properties(fname, path_samtools, contig_name)\n");
+    return;
+  }
+
+  signal(SIGCHLD, SIG_IGN); // avoid zombies
+
+  // read input arguments
+  char *fname = get_string(prhs[0]);
+  char *path_samtools = get_string(prhs[1]);
+  char *contig_name = get_string(prhs[2]);
+  char command[10000];
+
+  sprintf(command, "%s./samtools view %s %s 2>/dev/null", path_samtools, fname, contig_name);
+  //printf("%s\n", command);
+
+  // get number of unique reads
+  int status;
+  uint32_t num_unique_reads = 0;
+  char command2[10000];
+  sprintf(command2, "%s | cut -f 1 | sort -u | wc -l", command);
+  FILE* fp = popen(command2, "r");
+  if (fp == NULL) {
+    mexErrMsgTxt("Error using popen\n");
+  }
+  int num_scans = 1;
+  num_scans = fscanf(fp, "%d", &num_unique_reads);
+  if (num_scans != 1) {
+    rewind(fp);
+    char ret[1000];
+    fgets(ret, 1000, fp);
+    fprintf(stdout, "%s", ret);
+    mexErrMsgTxt("Could not determine number of reads\n");
+  }
+  status = pclose(fp);
+  //printf("%i", num_unique_reads);
+
+  // select reads for given positions and strand
+  int num_rows_selected = min((int) num_unique_reads, 100);
+  sprintf(command, "%s | head -n %i | cut -f 1-11", command, num_rows_selected);
+  fp = popen(command, "r");
+  if (fp == NULL) {
+    mexErrMsgTxt("Error using popen\n");
+  }
+  /* SAM format
+     1: read id, 2: flag, 3: reference name, 4: start (1-based, incl.), 5: mapping quality,
+     6: CIGAR, 7: mate reference name, 8: mate start (1-based, incl.), 9: insert size, 10: read, 11: quality
+     12+: additional tags
+  */
+  uint32_t read_idx = 0, row_idx = 0, num_col = 0;
+  uint32_t flag = 0, start_pos = 0, map_score = 0, mate_end_pos = 0, num_matches = 0, num_del = 0, num_ins = 0, ins_size = 0;
+  char ri [1000], read_contig_name [1000], cg [1000], mate_read_id [1000], read [1000], read_qual [1000];
+  string last_read_id;
+  vector<uint32_t> block_lengths, block_starts;
+  vector<string> read_ids;
+  vector<string>::iterator it;
+
+  uint32_t read_len = 0;
+  bool empty_line = true;
+  int num_rows = 0;
+  while(empty_line && num_rows < num_rows_selected) {
+    num_col = fscanf(fp, "%s\t%i\t%s\t%i\t%i\t%s\t%s\t%i\t%i\t%s\t%s", &ri, &flag, &read_contig_name, &start_pos, &map_score, &cg, &mate_read_id, &mate_end_pos, &ins_size, &read, &read_qual);
+    if (num_col != 11) {
+      mexErrMsgTxt("error reading SAM line\n");
+    }
+
+    string cigar = (string) cg;
+    // ignore lines with reads w/o mapping information
+    if (start_pos == 0 || cigar.compare("*")==0) {
+      continue;
+    }
+    // parse CIGAR
+    uint last_c = 0;
+    string last_str;
+    num_matches = 0;
+    char *end = NULL;
+    uint32_t tmp_nm = 0, tmp_nd = 0, tmp_ni = 0;
+    uint32_t last_block_start = 0, last_block_length = 0, last_intron_len = 0;
+    block_lengths.clear(); block_starts.clear();
+
+    for (uint c = 0; c < cigar.size(); c++) {
+      switch (cigar[c]) {
+      case 'M':
+	last_str = cigar.substr(last_c, c-last_c);
+	tmp_nm = strtoul(last_str.c_str(), &end, 10);
+	if (*end != '\0')
+	  mexErrMsgTxt("error: number of mismatches\n");
+	end = NULL;
+	last_block_length += tmp_nm;
+	num_matches += tmp_nm;
+	last_c = c + 1;
+	break;
+      case 'I':
+	last_str = cigar.substr(last_c, c-last_c);
+	tmp_ni = strtoul(last_str.c_str(), &end, 10);
+	if (*end != '\0')
+	  mexErrMsgTxt("error: number of insertions\n");
+	end = NULL;
+	num_ins += tmp_ni;
+	last_c = c + 1;
+	break;
+      case 'D':
+	last_str = cigar.substr(last_c, c-last_c);
+	tmp_nd = strtoul(last_str.c_str(), &end, 10);
+	if (*end != '\0')
+	  mexErrMsgTxt("error: number of deletions\n");
+	end = NULL;
+	num_del += tmp_nd;
+	last_block_length += tmp_nd;
+	last_c = c + 1;
+	break;
+      case 'N':
+	last_str = cigar.substr(last_c, c-last_c);
+	last_intron_len = strtoul(last_str.c_str(), &end, 10);
+	end = NULL;
+	last_c = c + 1;
+	break;
+      case 'S':
+	break;
+      case 'H':
+	break;
+      case 'P':
+	break;
+      default:
+	break;
+      }
+      if (cigar[c] == 'N' || c==cigar.size()-1) {
+	block_starts.push_back(last_block_start);
+	last_block_start = last_block_start + last_block_length + last_intron_len;
+	last_intron_len = 0;
+	block_lengths.push_back(last_block_length);
+	last_block_length = 0;
+      }
+    }
+    read_len = 0;
+    for (uint n = 0; n < block_lengths.size(); n++) {
+      read_len += block_lengths[n];
+    }
+    empty_line = false;
+  } // end of stream parsing
+
+  status = pclose(fp);
+
+  if (empty_line)
+    mexErrMsgTxt("Could not determine read length\n");
+
+  plhs[0] = mxCreateDoubleScalar((double) read_len);
+  plhs[1] = mxCreateDoubleScalar((double) num_unique_reads);
+
+  return;
+}
+
+
+char *get_string(const mxArray *prhs) {
+  char *buf;
+  int buflen;
+  if (!prhs)
+    mexErrMsgTxt("get_string called with NULL pointer arg");
+  if (!mxIsChar(prhs))
+    mexErrMsgTxt("input is not a string");
+  if (mxGetM(prhs) != 1)
+    mexErrMsgTxt("input is not a row vector");
+  buflen = mxGetN(prhs) + 1;
+  buf = (char*) malloc(buflen);
+  /* copy the string from prhs into buf and add terminating NULL char */
+  if (mxGetString(prhs, buf, buflen))
+    mexErrMsgTxt("not enough space");
+  return buf;
+}
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/mex/get_reads.cpp	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,293 @@
+/*
+*  This program is free software; you can redistribute it and/or modify
+*  it under the terms of the GNU General Public License as published by
+*  the Free Software Foundation; either version 3 of the License, or
+*  (at your option) any later version.
+*
+*   Written (W) 2010-2011 Jonas Behr, Regina Bohnert, Gunnar Raetsch
+*   Copyright (C) 2010-2011 Max Planck Society
+*/
+
+
+#include <stdio.h>
+#include <string.h>
+#include <signal.h>
+#include <mex.h>
+#include <algorithm>
+#include <vector>
+	using std::vector;
+#include "get_reads_direct.h"
+#include "mex_input.h"
+#include "read.h"
+
+#define MAXLINE 10000
+
+/*
+ * input:
+ * 1 bam file
+ * 2 chromosome
+ * 3 region start (1-based index)
+ * 4 region end (1-based index)
+ * 5 strand (either '+' or '-' or '0')
+ * [6] collapse flag: if true the reads are collapsed to a coverage track
+ * [7] subsample percentage: percentage of reads to be subsampled (in per mill)
+ * [8] intron length filter
+ * [9] exon length filter
+ * [10] mismatch filter
+ * [11] bool: use mapped reads for coverage
+ * [12] bool: use spliced reads for coverage
+ * [13] return maxminlen
+ * [14] return pair coverage
+ *
+ * output:
+ * 1 coverage
+ * [2] intron cell array
+ * [3] pair coverage
+ * [4] pair list
+ *
+ * example call:
+ * [cov introns] = get_reads('polyA_left_I+_el15_mm1_spliced.bam', 'I', 10000, 12000, '-', 1, 30);
+ */
+void mexFunction(int nlhs, mxArray *plhs[], int nrhs, const mxArray *prhs[]) {
+
+  if (nrhs<5 || nrhs>14 || (nlhs<1 || nlhs>4)) {
+    fprintf(stderr, "usage: [x [introns] [pair]] = get_reads(fname, chr, start, end, strand, [collapse], [subsample], [max intron length], [min exonlength], [max mismatches], [mapped], [spliced], [maxminlen], [pair]);\n");
+    return;
+  }
+
+  /* obligatory arguments
+   * **********************/
+  char *fname = get_string(prhs[0]);
+	//fprintf(stdout, "arg1: %s\n", fname);
+  char *chr = get_string(prhs[1]);
+	//fprintf(stdout, "arg2: %s\n", chr);
+  int from_pos = get_int(prhs[2]);
+	//fprintf(stdout, "arg3: %d\n", from_pos);
+  int to_pos = get_int(prhs[3]);
+	//fprintf(stdout, "arg4: %d\n", to_pos);
+  char *strand = get_string(prhs[4]);
+	//fprintf(stdout, "arg5: %s\n", strand);
+
+  if (from_pos>to_pos)
+     mexErrMsgTxt("Start (arg 3) must be <= end (arg 4)\n");
+
+  if (strand[0]!='+' && strand[0]!='-' && strand[0]!='0')
+    mexErrMsgTxt("Unknown strand (arg 5): either + or - or 0");
+
+  /* optional arguments
+   * ******************/
+  int collapse = 0;
+  if (nrhs>=6)
+    collapse = get_int(prhs[5]);
+
+  int subsample = 1000;
+  if (nrhs>=7)
+    subsample = get_int(prhs[6]);
+
+  int intron_len_filter = 1e9;
+  if (nrhs>=8)
+    intron_len_filter = get_int(prhs[7]);
+
+  int exon_len_filter = -1;
+  if (nrhs>=9)
+    exon_len_filter = get_int(prhs[8]);
+
+  int filter_mismatch = 1e9;
+  if (nrhs>=10)
+    filter_mismatch = get_int(prhs[9]);
+
+  int mapped = 1;
+  if (nrhs>=11)
+    mapped = get_int(prhs[10]);
+
+  int spliced = 1;
+  if (nrhs>=12)
+    spliced = get_int(prhs[11]);
+
+  int maxminlen = 0;
+  if (nrhs>=13)
+    maxminlen = get_int(prhs[12]);
+
+  int pair_cov = 0;
+	if (nrhs>=14)
+		pair_cov = get_int(prhs[13]);
+
+  /* call function to get reads
+   * **************************/
+  char region[MAXLINE];
+  sprintf(region, "%s:%i-%i", chr, from_pos, to_pos);
+
+  vector<CRead*> all_reads;
+
+  get_reads_from_bam(fname, region, &all_reads, strand[0], subsample);
+
+  /* filter reads
+   * **************/
+  int left = 0;
+  int right = 0;
+
+  vector<CRead*> reads;
+  for (int i=0; i<all_reads.size(); i++) {
+    if (all_reads[i]->left)
+      left++;
+    if (all_reads[i]->right)
+      right++;
+    if (all_reads[i]->max_intron_len()<intron_len_filter && all_reads[i]->min_exon_len()>exon_len_filter && all_reads[i]->get_mismatches()<=filter_mismatch)
+      reads.push_back(all_reads[i]);
+  }
+
+
+  /* prepare output
+   * **************/
+  int num_rows = reads.size();
+  int num_pos = to_pos-from_pos+1;
+
+  if (pair_cov==1 && nlhs>=3) {
+    // sort reads by read_id
+    printf("\n\nleft:%i right:%i \n\n", left, right);
+    sort(reads.begin(), reads.end(), CRead::compare_by_read_id);
+  }
+
+  // read coverages collapsed
+  if (collapse) {
+    plhs[0] = mxCreateNumericMatrix(1, num_pos, mxUINT32_CLASS, mxREAL);
+    uint32_t *mask_ret = (uint32_t*) mxGetData(plhs[0]);
+    if (num_pos>0 && mask_ret==NULL)
+      mexErrMsgTxt("Error allocating memory\n");
+    if (mapped && spliced) {
+      for (int i=0; i<reads.size(); i++) {
+	reads[i]->get_coverage(from_pos, to_pos, mask_ret);
+      }
+    } else {
+      for (int i=0; i<reads.size(); i++) {
+	ssize_t num_exons = reads[i]->block_starts.size();
+	if ((num_exons==1 && mapped) || (num_exons>1 && spliced))
+	  reads[i]->get_coverage(from_pos, to_pos, mask_ret);
+      }
+    }
+  }
+  // reads not collapsed
+  else {
+    uint32_t nzmax = 0; // maximal number of nonzero elements
+    int len = to_pos-from_pos+1;
+    for (uint i=0; i<reads.size(); i++) {
+      for (uint n = 0; n < reads[i]->block_starts.size(); n++) {
+	uint32_t from, to;
+	if (reads[i]->block_starts[n]+reads[i]->start_pos-from_pos >= 0)
+	  from = reads[i]->block_starts[n]+reads[i]->start_pos-from_pos;
+	else
+	  from = 0;
+	if (reads[i]->block_starts[n]+reads[i]->start_pos-from_pos+reads[i]->block_lengths[n] >= 0)
+	  to = reads[i]->block_starts[n]+reads[i]->start_pos-from_pos+reads[i]->block_lengths[n];
+	else
+	  to = 0;
+	for (int bp=from; bp<to&bp<len; bp++) {
+	  nzmax++;
+	}
+      }
+    }
+    // 1st row: row indices
+    // 2nd row: column indices
+    plhs[0] = mxCreateDoubleMatrix(2, nzmax, mxREAL);
+    double *mask_ret = (double*) mxGetData(plhs[0]);
+    if (nzmax>0 && mask_ret==NULL)
+      mexErrMsgTxt("Error allocating memory\n");
+    uint32_t mask_ret_c = 0; // counter
+    for (uint i=0; i<reads.size(); i++) {
+      reads[i]->get_reads_sparse(from_pos, to_pos, mask_ret, mask_ret_c, i);
+    }
+    if (mask_ret_c!=2*nzmax)
+      mexErrMsgTxt("Error filling index arrays for sparse matrix\n");
+  }
+  // introns
+  if (maxminlen==0 && nlhs>=2) {
+      vector<int> intron_list;
+      for (int i=0; i<reads.size(); i++) {
+        reads[i]->get_introns(&intron_list);
+      }
+
+      plhs[1] = mxCreateNumericMatrix(2, intron_list.size()/2, mxUINT32_CLASS, mxREAL);
+      uint32_t *p_intron_list = (uint32_t*) mxGetData(plhs[1]);
+      for (int p = 0; p<intron_list.size(); p++) {
+        p_intron_list[p] = intron_list[p];
+      }
+      intron_list.clear();
+    } else if (nlhs>=2) {
+      vector<uint32_t> intron_starts;
+      vector<uint32_t> intron_ends;
+      vector<uint32_t> block_len1;
+      vector<uint32_t> block_len2;
+      for (int i=0; i<reads.size(); i++) {
+        reads[i]->get_introns(&intron_starts, &intron_ends, &block_len1, &block_len2);
+      }
+
+      plhs[1] = mxCreateNumericMatrix(4, intron_starts.size(), mxINT32_CLASS, mxREAL);
+      uint32_t *p_intron_list = (uint32_t*) mxGetData(plhs[1]);
+      for (int p = 0; p<intron_starts.size(); p++) {
+        p_intron_list[4*p] = intron_starts[p];
+        p_intron_list[(4*p)+1] = intron_ends[p];
+        p_intron_list[(4*p)+2] = block_len1[p];
+        p_intron_list[(4*p)+3] = block_len2[p];
+      }
+      intron_starts.clear() ;
+      intron_ends.clear() ;
+      block_len1.clear() ;
+      block_len2.clear() ;
+  }
+  if (pair_cov==1 && nlhs>=3) {
+    plhs[2] = mxCreateNumericMatrix(1, num_pos, mxUINT32_CLASS, mxREAL);
+    uint32_t *p_pair_map = (uint32_t*) mxGetData(plhs[2]);
+    if (num_pos>0 && p_pair_map==NULL)
+      mexErrMsgTxt("Error allocating memory\n");
+
+    vector<int> pair_ids;
+
+    int take_cnt = 0;
+    int discard_cnt = 0;
+    // find consecutive reads with the same id
+    for (int i=0; i<((int) reads.size())-1; i++) {
+      int j = i+1;
+      while(j<reads.size() && strcmp(reads[i]->read_id, reads[j]->read_id) == 0) {
+        if ((reads[i]->left && reads[j]->right) || (reads[j]->left && reads[i]->right) && (reads[i]->reverse != reads[j]->reverse)) {
+	      if (reads[i]->get_last_position()==-1 || reads[j]->get_last_position()==-1)
+	        break;
+          if (reads[i]->get_last_position()<reads[j]->start_pos && reads[j]->start_pos-reads[i]->get_last_position()<60000) {
+            int from = std::max(0, reads[i]->get_last_position()-from_pos);
+            int to = std::min(num_pos-1, reads[j]->start_pos-from_pos);
+            pair_ids.push_back(i);
+            pair_ids.push_back(j);
+            for (int k=from; k<to; k++)
+              p_pair_map[k]++;
+            take_cnt++;
+          } else if (reads[i]->start_pos>reads[j]->get_last_position() && reads[j]->get_last_position()-reads[i]->start_pos<60000) {
+            int from = std::max(0, reads[j]->get_last_position()-from_pos);
+            int to = std::min(num_pos-1, reads[i]->start_pos-from_pos);
+            pair_ids.push_back(i);
+            pair_ids.push_back(j);
+            for (int k=from; k<to; k++)
+              p_pair_map[k]++;
+            take_cnt++;
+          } else
+            discard_cnt++;
+        }
+        else
+          discard_cnt++;
+        j++;
+      }
+    }
+    printf("take:%i, discard:%i \n", take_cnt, discard_cnt);
+
+    if (nlhs>=4) {
+      plhs[3] = mxCreateNumericMatrix(2, pair_ids.size()/2, mxUINT32_CLASS, mxREAL);
+      uint32_t *pair_ids_ret = (uint32_t*) mxGetData(plhs[3]);
+      if (pair_ids.size()>0 && pair_ids_ret==NULL)
+        mexErrMsgTxt("Error allocating memory\n");
+      for (int i=0; i<pair_ids.size(); i++) {
+        pair_ids_ret[i] = pair_ids[i];
+      }
+    }
+  }
+  for (int i=0; i<all_reads.size(); i++)
+    delete all_reads[i];
+}
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/mex/get_reads_direct.cpp	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,298 @@
+/*
+*  This program is free software; you can redistribute it and/or modify
+*  it under the terms of the GNU General Public License as published by
+*  the Free Software Foundation; either version 3 of the License, or
+*  (at your option) any later version.
+*
+*   Written (W) 2010-2011 Jonas Behr, Regina Bohnert, Gunnar Raetsch
+*   Copyright (C) 2010-2011 Max Planck Society
+*/
+
+
+#include <stdio.h>
+#include <assert.h>
+#include "sam.h"
+#include "get_reads_direct.h"
+
+#include <vector>
+  using std::vector;
+#include <string>
+  using std::string;
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+typedef struct {
+	int beg, end;
+	samfile_t *in;
+} tmpstruct_t;
+
+typedef struct {
+    uint64_t u, v;
+} pair64_t;
+
+static inline int is_overlap(uint32_t beg, uint32_t end, const bam1_t *b)
+{
+    uint32_t rbeg = b->core.pos;
+    uint32_t rend = b->core.n_cigar? bam_calend(&b->core, bam1_cigar(b)) : b->core.pos + 1;
+    return (rend > beg && rbeg < end);
+}
+
+pair64_t * get_chunk_coordinates(const bam_index_t *idx, int tid, int beg, int end, int* cnt_off);
+
+  int bam_fetch_reads(bamFile fp, const bam_index_t *idx, int tid, int beg, int end, void *data, bam_header_t* header, vector<CRead*>* reads, char strand);
+
+// callback for bam_plbuf_init()
+static int pileup_func(uint32_t tid, uint32_t pos, int n, const bam_pileup1_t *pl, void *data)
+{
+	//tmpstruct_t *tmp = (tmpstruct_t*)data;
+	//if ((int)pos >= tmp->beg && (int)pos < tmp->end)
+	//	printf("%s\t%d\t%d\n", tmp->in->header->target_name[tid], pos + 1, n);
+	return 0;
+}
+#ifdef __cplusplus
+}
+#endif
+int parse_sam_line(char* line, CRead* read);
+//int set_strand(char c);
+//void parse_cigar(bam1_t* b, CRead* read);
+void parse_cigar(bam1_t* b, CRead* read, bam_header_t* header);
+
+
+int get_reads_from_bam(char* filename, char* region, vector<CRead*>* reads, char strand, int lsubsample)
+{
+	subsample = lsubsample;
+	//set_strand(strand);
+
+	srand (time(NULL));
+	//srand (1234);
+	tmpstruct_t tmp;
+	tmp.in = samopen(filename, "rb", 0);
+	if (tmp.in == 0) {
+		fprintf(stderr, "Fail to open BAM file %s\n", filename);
+		return 1;
+	}
+	int ref;
+	bam_index_t *idx;
+	bam_plbuf_t *buf;
+	idx = bam_index_load(filename); // load BAM index
+	if (idx == 0) {
+		fprintf(stderr, "BAM indexing file is not available.\n");
+		return 1;
+	}
+	bam_parse_region(tmp.in->header, region, &ref,
+	                 &tmp.beg, &tmp.end); // parse the region
+	if (ref < 0) {
+		fprintf(stderr, "Invalid region %s\n", region);
+		return 1;
+	}
+
+	buf = bam_plbuf_init(pileup_func, &tmp); // initialize pileup
+
+	bam_fetch_reads(tmp.in->x.bam, idx, ref, tmp.beg, tmp.end, buf, tmp.in->header, reads, strand);
+	//fprintf(stdout, "intron_list: %d \n", intron_list->size());
+
+	bam_plbuf_push(0, buf); // finalize pileup
+	bam_index_destroy(idx);
+	bam_plbuf_destroy(buf);
+	samclose(tmp.in);
+	return 0;
+}
+
+
+int bam_fetch_reads(bamFile fp, const bam_index_t *idx, int tid, int beg, int end, void *data, bam_header_t* header, vector<CRead*>* reads, char strand)
+{
+	int n_off;
+	pair64_t *off = get_chunk_coordinates(idx, tid, beg, end, &n_off);
+	if (off == 0) return 0;
+	{
+		// retrive alignments
+		uint64_t curr_off;
+		int i, ret, n_seeks;
+		n_seeks = 0; i = -1; curr_off = 0;
+		bam1_t *b = (bam1_t*)calloc(1, sizeof(bam1_t));
+		for (;;) {
+			if (curr_off == 0 || curr_off >= off[i].v) { // then jump to the next chunk
+				if (i == n_off - 1) break; // no more chunks
+				if (i >= 0) assert(curr_off == off[i].v); // otherwise bug
+				if (i < 0 || off[i].v != off[i+1].u) { // not adjacent chunks; then seek
+					bam_seek(fp, off[i+1].u, SEEK_SET);
+					curr_off = bam_tell(fp);
+					++n_seeks;
+				}
+				++i;
+			}
+			if ((ret = bam_read1(fp, b)) > 0) {
+				curr_off = bam_tell(fp);
+				if (b->core.tid != tid || b->core.pos >= end) break; // no need to proceed
+				else if (is_overlap(beg, end, b))
+				{
+					int rr = rand();
+					if ((rr%1000 < subsample))
+					{
+						CRead* read = new CRead();
+						parse_cigar(b, read, header);
+
+						if (strand == '0' || strand==read->strand[0] || read->strand[0]=='0')
+						{
+							read->left = (b->core.flag & left_flag_mask) >0;
+							read->right = (b->core.flag & right_flag_mask) >0;
+							read->reverse = (b->core.flag & reverse_flag_mask) >0;
+							reads->push_back(read);
+						}
+						else
+						{
+							delete read;
+						}
+						//else if (read->strand[0]=='0'&&((b->core.flag & g_flag_off) >0))
+						//{
+						//	//fprintf(stdout, "(-)-strand; read->strand[0]==0, num_exons: %i \n", read->block_starts.size());
+						//	// this flag means that the read has been reversed for alignment
+						//	// flag bit set and (-)-strand requested
+						//	reads->push_back(read);
+						//}
+						//else if (read->strand[0]=='0'&&(g_flag_on>0&&(b->core.flag & g_flag_on)==0))
+						//{
+						//	//fprintf(stdout, "(+)-strand; read->strand[0]==0, num_exons: %i \n", read->block_starts.size());
+						//	// (+)-strand requested and flag bit not set
+						//	reads->push_back(read);
+						//}
+					}
+				}
+			} else break; // end of file
+		}
+//		fprintf(stderr, "[bam_fetch] # seek calls: %d\n", n_seeks);
+		bam_destroy1(b);
+	}
+	free(off);
+	return 0;
+}
+
+void parse_cigar(bam1_t* b, CRead* read, bam_header_t* header)
+{
+	read->start_pos = b->core.pos+1;
+	read->set_strand('0');
+	read->read_id = new char[100];
+	sprintf(read->read_id, "%s\0", bam1_qname(b));
+
+	for (int k = 0; k < b->core.n_cigar; ++k)
+	{
+		int op = bam1_cigar(b)[k] & BAM_CIGAR_MASK; // operation
+		int l = bam1_cigar(b)[k] >> BAM_CIGAR_SHIFT; // length
+		//fprintf(stdout, "op:%d l:%d\n", op, l);
+		if (op == BAM_CMATCH)
+		{
+			if (k==0)
+			{
+				read->block_lengths.push_back(l);
+				read->block_starts.push_back(0);
+			}
+			else
+			{
+				int op_prev = bam1_cigar(b)[k-1] & BAM_CIGAR_MASK;
+				int l_prev = bam1_cigar(b)[k-1] >> BAM_CIGAR_SHIFT;
+				if (op_prev==BAM_CREF_SKIP)// intron before
+				{
+					if (read->block_lengths.size()>=1)
+					{
+						int last_block_start = (*(read->block_starts.end()-1));
+						int intron_start = last_block_start+(*(read->block_lengths.end()-1));
+						read->block_lengths.push_back(l);
+						read->block_starts.push_back(intron_start+l_prev);
+					}
+					else
+					{
+						// start of first block was not a match
+						read->block_lengths.push_back(l);
+						read->block_starts.push_back(0);
+					}
+				}
+				else
+				{
+					if (read->block_lengths.size()>=1 && op == BAM_CDEL)// if it is an insertion then the matching block is not inreased
+						(*(read->block_lengths.end()-1))+=l;
+					else
+					{
+						//char *samline = bam_format1(header, b);
+						//printf("header: %s \n", samline);
+					}
+				}
+			}
+		}
+		else if (op == BAM_CDEL)
+		{
+			if (k>0 && read->block_lengths.size()>=1)
+				(*(read->block_lengths.end()-1))+=l;
+		}
+		else if (op == BAM_CREF_SKIP)//intron
+		{}
+		else if (op == BAM_CINS || op == BAM_CSOFT_CLIP)
+		{}
+	}
+	// parse auxiliary data
+    uint8_t* s = bam1_aux(b);
+	uint8_t* end = b->data + b->data_len;
+	while (s < end)
+	{
+		 uint8_t type, key[2];
+		 key[0] = s[0]; key[1] = s[1];
+		 s += 2; type = *s; ++s;
+		 //fprintf(stdout, "\n%c%c:%c\n", key[0], key[1], type);
+		 if (type == 'A')
+		 {
+			if ( key[0] =='X' && key[1] == 'S')
+			{
+				read->set_strand((char) *s);
+			}
+		 	++s;
+		 }
+		else if (type == 'C')
+		{
+			if ( key[0] =='H' && key[1] == '0')
+			{
+				uint8_t matches = *s;
+				read->matches = (int) matches;
+			}
+			if ( key[0] =='N' && key[1] == 'M')
+			{
+				uint8_t mismatches = *s;
+				read->mismatches = (int) mismatches;
+			}
+			if ( key[0] =='H' && key[1] == 'I')
+			{
+				uint8_t mai = *s;
+				read->multiple_alignment_index = (int) mai;
+			}
+
+			++s;
+		}
+		else if (type == 'c') { ++s; }
+		else if (type == 'S') { s += 2;	}
+		else if (type == 's') { s += 2;	}
+		else if (type == 'I') { s += 4; }
+		else if (type == 'i') { s += 4; }
+		else if (type == 'f') { s += 4;	}
+		else if (type == 'd') { s += 8;	}
+		else if (type == 'Z') { ++s; }
+		else if (type == 'H') { ++s; }
+	}
+}
+
+//int set_strand(char c)
+//{
+//	if (c=='+')
+//	{
+//		char* fl = (char*) "0x0010";
+//		g_flag_on = strtol(fl, 0, 0);
+//		g_flag_off = 0;
+//	}
+//	else if (c=='-')
+//	{
+//		char* fl = (char*) "0x0010";
+//		g_flag_off = strtol(fl, 0, 0);
+//		g_flag_on = 0;
+//	}
+//	return 0;
+//}
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/mex/get_reads_direct.h	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,29 @@
+/*
+*  This program is free software; you can redistribute it and/or modify
+*  it under the terms of the GNU General Public License as published by
+*  the Free Software Foundation; either version 3 of the License, or
+*  (at your option) any later version.
+*
+*   Written (W) 2010-2011 Jonas Behr, Regina Bohnert, Gunnar Raetsch
+*   Copyright (C) 2010-2011 Max Planck Society
+*/
+
+
+#ifndef __GET_READS_DIRECT_H__
+#define __GET_READS_DIRECT_H__
+
+#include <vector>
+  using std::vector;
+#include "read.h"
+
+//static int g_flag_on = 0, g_flag_off = 0;
+static int left_flag_mask = strtol((char*) "0x40", 0, 0);
+static int right_flag_mask = strtol((char*) "0x80", 0, 0);
+static int reverse_flag_mask = strtol((char*) "0x10", 0, 0);
+
+static int subsample = 1000;
+//static int collapse = 0;
+
+int get_reads_from_bam(char* filename, char* region, vector<CRead*>* reads, char strand, int lsubsample);
+
+#endif
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/mex/interval_overlap.cpp	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,217 @@
+/*
+*  This program is free software; you can redistribute it and/or modify
+*  it under the terms of the GNU General Public License as published by
+*  the Free Software Foundation; either version 3 of the License, or
+*  (at your option) any later version.
+*
+*   Written (W) 2010-2011 Jonas Behr
+*   Copyright (C) 2010-2011 Max Planck Society
+*/
+
+
+#include <stdio.h>
+#include <stdarg.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <ctype.h>
+#include <sys/stat.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <time.h>
+#include <math.h>
+#include <limits>
+#include <mex.h>
+#include <assert.h>
+#include <vector>
+  using std::vector;
+#include <algorithm>
+  using std::sort;
+  using std::min;
+  using std::max;
+
+typedef struct {
+    int start;
+    int stop;
+	int idx;
+	int set_id;
+} interval_t;
+
+bool compare (interval_t i, interval_t j)
+{
+	return (i.start<j.start);
+}
+
+bool overlaps(interval_t a, interval_t b)
+{
+	int v = min(a.stop,b.stop) - max(a.start,b.start) + 1;
+	return (v >= 1);
+}
+bool leftOf(interval_t a, interval_t b)
+{
+	return (a.stop < b.start);
+}
+
+void scan(interval_t f, vector<interval_t>* Wf, interval_t g, vector<interval_t>* Wg, vector<int>* overlap)
+{
+	vector<interval_t>::iterator i;
+	i=Wg->begin();
+	while (i<Wg->end())
+	{
+		interval_t g2 = *i;
+		if (leftOf(g2,f))
+		{
+			Wg->erase(i);// inefficient if Wg is large
+			// this moves all elements, therefore i is not incremented
+		}
+		else if (overlaps(g2,f))
+		{
+			if (g2.set_id==1)
+			{
+				//printf("overlap: [%i | %i, %i] [%i | %i, %i]\n", g2.idx, g2.start, g2.stop, f.idx, f.start, f.stop);
+				overlap->push_back(g2.idx);
+				overlap->push_back(f.idx);
+			}
+			else if (f.set_id==1)
+			{
+				//printf("overlap: [%i | %i, %i] [%i | %i, %i]\n", f.idx, f.start, f.stop, g2.idx, g2.start, g2.stop);
+				overlap->push_back(f.idx);
+				overlap->push_back(g2.idx);
+			}
+			i++;
+		}
+		else
+		{
+			printf("never happens??\n");
+			i++;
+		}
+	}
+	if (!leftOf(f, g))
+	{
+		Wf->push_back(f);
+		//printf("push: [%i, %i] size:%i\n", f.start, f.stop, Wf->size());
+	}
+}
+
+/*
+ * prhs[0] first interval set starts
+ * prhs[1] first interval set stops
+ * prhs[2] second interval set starts
+ * prhs[3] second interval set stops
+ *
+ * return:
+ * plhs[0] one based index in first interval set overlapping with a interval in the second set
+ * plhs[1] corresponding index in the second set
+ *
+*/
+void mexFunction(int nlhs, mxArray *plhs[], int nrhs, const mxArray *prhs[])
+{
+	if (nrhs!=4)
+		mexErrMsgTxt("Expected 4 arguments: starts1, stops1, starts2, stops2 \n");
+	if (nlhs!=2)
+		mexErrMsgTxt("Expected 2 output arguments \n");
+
+	int num_intervals1 = mxGetNumberOfElements(prhs[0]);
+	assert(num_intervals1 == mxGetNumberOfElements(prhs[1]));
+	int num_intervals2 = mxGetNumberOfElements(prhs[2]);
+	assert(num_intervals2 == mxGetNumberOfElements(prhs[3]));
+
+	//printf("num_intervals1: %i\n", num_intervals1);
+	//printf("num_intervals2: %i\n", num_intervals2);
+
+	double* starts1 = mxGetPr(prhs[0]);
+	double* stops1  = mxGetPr(prhs[1]);
+	double* starts2 = mxGetPr(prhs[2]);
+	double* stops2  = mxGetPr(prhs[3]);
+
+	vector<interval_t> intervals1;
+	for (int i=0; i<num_intervals1; i++)
+	{
+		interval_t interval;
+		interval.start = starts1[i];
+		interval.stop = stops1[i];
+		interval.set_id = 1;
+		interval.idx = i+1;
+		intervals1.push_back(interval);
+		//printf("int1: [%i, %i] \n",intervals1[i].start, intervals1[i].stop);
+	}
+	interval_t i;
+	i.start = std::numeric_limits<int>::max();
+	i.stop = std::numeric_limits<int>::max();
+	i.set_id = std::numeric_limits<int>::max();
+	i.idx = std::numeric_limits<int>::max();
+	intervals1.push_back(i);
+
+	//printf("num_intervals1: %i\n", intervals1.size());
+	vector<interval_t> intervals2;
+	for (int i=0; i<num_intervals2; i++)
+	{
+		interval_t interval;
+		interval.start = starts2[i];
+		interval.stop = stops2[i];
+		interval.set_id = 2;
+		interval.idx = i+1;
+		intervals2.push_back(interval);
+		//printf("int2: [%i, %i] \n",intervals2[i].start, intervals2[i].stop);
+	}
+	intervals2.push_back(i);
+	//printf("num_intervals2: %i\n", intervals2.size());
+
+	sort(intervals1.begin(), intervals1.end(), compare);
+	sort(intervals2.begin(), intervals2.end(), compare);
+
+
+	vector<int> overlap;
+	vector<interval_t> Wx;
+	vector<interval_t> Wy;
+	vector<interval_t>::iterator x = intervals1.begin();
+	vector<interval_t>::iterator y = intervals2.begin();
+	while (x<intervals1.end() && y<intervals2.end())
+	{
+		//vector<interval_t>::iterator x;
+		//vector<interval_t>::iterator y;
+		//if (it1>intervals1.end())
+		//	x = inf_interval();
+		//else
+		//	x = it1;
+		//if (it2>intervals2.end())
+		//	y = inf_interval();
+		//else
+		//	y=it2;
+
+		if (x->start <= y->start)
+		{
+				scan(*x, &Wx, *y, &Wy, &overlap);
+				x++;
+		}
+		else
+		{
+			if (y<=intervals2.end())
+			{
+				scan(*y, &Wy, *x, &Wx, &overlap);
+				y++;
+			}
+		}
+	}
+
+	plhs[0] = mxCreateDoubleMatrix(1, overlap.size()/2, mxREAL);
+    double* idx1 = mxGetPr(plhs[0]);
+
+	plhs[1] = mxCreateDoubleMatrix(1, overlap.size()/2, mxREAL);
+    double* idx2 = mxGetPr(plhs[1]);
+
+	for (int i=0; i<overlap.size(); i+=2)
+	{
+		//printf("ov: %i [%i, %i] \n", i, overlap[i], overlap[i+1]);
+		idx1[i/2] = (double) overlap[i];
+		idx2[i/2] = (double) overlap[i+1];
+	}
+}
+
+
+
+
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/mex/mex_input.cpp	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,60 @@
+/*
+*  This program is free software; you can redistribute it and/or modify
+*  it under the terms of the GNU General Public License as published by
+*  the Free Software Foundation; either version 3 of the License, or
+*  (at your option) any later version.
+*
+*   Written (W) 2010-2011 Jonas Behr, Regina Bohnert, Gunnar Raetsch
+*   Copyright (C) 2010-2011 Max Planck Society
+*/
+
+
+#include <stdio.h>
+#include <mex.h>
+#include "mex_input.h"
+
+char *get_string(const mxArray *prhs) {
+  char *buf;
+  int buflen;
+  if (!prhs)
+    mexErrMsgTxt("get_string called with NULL pointer arg");
+  if (!mxIsChar(prhs))
+    mexErrMsgTxt("input is not a string");
+  if (mxGetM(prhs) != 1)
+    mexErrMsgTxt("input is not a row vector");
+  buflen = mxGetN(prhs) + 1;
+  buf = (char*) malloc(buflen);
+  /* copy the string from prhs into buf and add terminating NULL char */
+  if (mxGetString(prhs, buf, buflen))
+    mexErrMsgTxt("not enough space");
+  return buf;
+}
+
+bool get_bool(const mxArray *prhs)
+{
+	const int M = mxGetM(prhs);
+	const int N = mxGetN(prhs);
+	double *f = (double*) mxGetPr(prhs);
+
+	if (!prhs)
+		mexErrMsgTxt("Arg is NULL pointer");
+	if (M != 1 || N != 1)
+		mexErrMsgTxt("Arg is not a scalar");
+	if (f[0] != 0)
+		return true;
+	return false;
+}
+
+int get_int(const mxArray *prhs)
+{
+	const int M = mxGetM(prhs);
+	const int N = mxGetN(prhs);
+	double *f = (double*) mxGetPr(prhs);
+
+	if (!prhs)
+		mexErrMsgTxt("Arg is NULL pointer");
+	if (M != 1 || N != 1)
+		mexErrMsgTxt("Arg is not a scalar");
+
+	return (int) f[0];
+}
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/mex/mex_input.h	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,20 @@
+/*
+*  This program is free software; you can redistribute it and/or modify
+*  it under the terms of the GNU General Public License as published by
+*  the Free Software Foundation; either version 3 of the License, or
+*  (at your option) any later version.
+*
+*   Written (W) 2010-2011 Jonas Behr, Regina Bohnert, Gunnar Raetsch
+*   Copyright (C) 2010-2011 Max Planck Society
+*/
+
+
+#include <stdio.h>
+#include <mex.h>
+
+#ifndef __MEX_INPUT_h__
+#define __MEX_INPUT_h__
+	char *get_string(const mxArray *prhs);
+	bool get_bool(const mxArray *prhs);
+	int get_int(const mxArray *prhs);
+#endif
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/mex/read.cpp	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,214 @@
+/*
+*  This program is free software; you can redistribute it and/or modify
+*  it under the terms of the GNU General Public License as published by
+*  the Free Software Foundation; either version 3 of the License, or
+*  (at your option) any later version.
+*
+*   Written (W) 2010-2011 Jonas Behr, Regina Bohnert, Gunnar Raetsch
+*   Copyright (C) 2010-2011 Max Planck Society
+*/
+
+
+#include "read.h"
+
+CRead::CRead() {
+	read_id = NULL;
+	sam_line = NULL;
+	start_pos = 0;
+	matches = 0;
+	mismatches = 0;
+	multiple_alignment_index = 0;
+	strand = NULL;
+	left = false;
+	right = false;
+	reverse = false;
+}
+
+CRead::~CRead() {
+	delete[] read_id;
+	delete[] sam_line;
+	delete[] strand;
+}
+
+/*
+ * Augments 'coverage' array at the positions covered by the read in the queried interval.
+ */
+void CRead::get_coverage(int p_start_pos, int p_end_pos, uint32_t* coverage)
+{
+  //                    block1                block2
+  //   |=====|======|============|===========|======|====|
+  //         ^      ^                                    ^
+  //  p_start_pos   |                            p_end_pos
+  //            start_pos
+  //         |0000001111111111111000000000000111111100000|
+  //                           *coverage
+  int len = p_end_pos-p_start_pos+1;
+  for (uint32_t n = 0; n < block_starts.size(); n++) {
+    int32_t from, to;
+    from = block_starts[n]+start_pos-p_start_pos;
+    to = block_starts[n]+start_pos-p_start_pos+block_lengths[n];
+    if (from < 0)
+      from = 0;
+    if (to < 0)
+		continue;
+    else if (to > len)
+		to = len;
+    for (int bp=from; bp<to; bp++) {
+      coverage[bp]++;
+    }
+  }
+}
+int CRead::get_last_position()
+{
+	if (block_starts.size()>0) // this if for some reason zero in case of softclips
+		return start_pos+block_starts.back()+block_lengths.back();
+	return -1;
+}
+
+/*
+ * Adds the column indices (= positions) covered by the read to 'reads' array in current row (= read).
+ * These indices can be used to build up a sparse matrix of reads x positions.
+ */
+void CRead::get_reads_sparse(int p_start_pos, int p_end_pos, double* reads, uint32_t & reads_c, uint32_t row_idx) {
+  int len = p_end_pos-p_start_pos+1;
+  for (uint32_t n = 0; n < block_starts.size(); n++) {
+    uint32_t from, to;
+    if (block_starts[n]+start_pos-p_start_pos >= 0)
+      from = block_starts[n]+start_pos-p_start_pos;
+    else
+      from = 0;
+    if (block_starts[n]+start_pos-p_start_pos+block_lengths[n] >= 0)
+      to = block_starts[n]+start_pos-p_start_pos+block_lengths[n];
+    else
+      to = 0;
+    for (int bp=from; bp<to&bp<len; bp++) {
+      reads[reads_c] = row_idx+1; // row indices for sparse matrix
+      reads[reads_c+1] = bp+1; // column indices for sparse matrix
+      reads_c += 2;
+    }
+  }
+}
+
+void CRead::get_acc_splice_sites(vector<int>* acc_pos)
+{
+	if (strand[0]=='+')
+	{
+		for (int k=1;k<block_starts.size(); k++)
+			acc_pos->push_back(start_pos+block_starts[k]-1);
+	}
+	else if (strand[0]=='-')
+	{
+		for (int k=1;k<block_starts.size(); k++)
+			acc_pos->push_back(start_pos+block_starts[k-1]+block_lengths[k-1]-2);
+	}
+}
+
+void CRead::get_don_splice_sites(vector<int>* don_pos)
+{
+
+	if (strand[0]=='+')
+	{
+		for (int k=1;k<block_starts.size(); k++)
+			don_pos->push_back(start_pos+block_starts[k-1]+block_lengths[k-1]-2);
+	}
+	else if (strand[0]=='-')
+	{
+		for (int k=1;k<block_starts.size(); k++)
+			don_pos->push_back(start_pos+block_starts[k]-1);
+	}
+}
+
+int CRead::min_exon_len()
+{
+	int min = 1e8;
+	for (int k=0;k<block_starts.size(); k++)
+		if (block_lengths[k]<min)
+			min = block_lengths[k];
+	return min;
+}
+
+int CRead::max_intron_len()
+{
+	int max = 0;
+	for (int k=1;k<block_starts.size(); k++)
+		if (block_starts[k]-(block_starts[k-1]+block_lengths[k-1])>max)
+			max = block_starts[k]-(block_starts[k-1]+block_lengths[k-1]);
+	return max;
+}
+
+/*
+ * Adds start and end of introns in the read consecutively to the 'introns' vector.
+ */
+void CRead::get_introns(vector<int>* introns)
+{
+  for (int i=1; i<block_starts.size(); i++)
+  {
+    int istart = block_starts[i-1]+block_lengths[i-1]+start_pos;
+    int iend = block_starts[i]+start_pos-1;
+    introns->push_back(istart);
+    introns->push_back(iend);
+    //fprintf(stdout, "%i intron: %d->%d\n", i, istart, iend);
+  }
+}
+void CRead::get_introns(vector<uint32_t>* intron_starts, vector<uint32_t>* intron_ends, vector<uint32_t>* block_len1, vector<uint32_t>* block_len2)
+{
+  for (int i=1; i<block_starts.size(); i++)
+  {
+    uint32_t istart = block_starts[i-1]+block_lengths[i-1]+start_pos;
+    uint32_t iend = block_starts[i]+start_pos-1;
+    intron_starts->push_back(istart);
+    intron_ends->push_back(iend);
+    block_len1->push_back(block_lengths[i-1]) ;
+    block_len2->push_back(block_lengths[i]) ;
+  }
+}
+
+bool CRead::operator==(const CRead& read) const
+{
+	if (block_starts.size()!=read.block_starts.size())
+		return false;
+	if (block_lengths.size()!=read.block_lengths.size())
+		return false;
+	if (start_pos!=read.start_pos)
+		return false;
+	if (strand[0] != read.strand[0])
+		return false;
+	for (int i=0; i<block_starts.size(); i++)
+		if (block_starts[i]!=read.block_starts[i])
+			return false;
+	for (int i=0; i<block_lengths.size(); i++)
+		if (block_lengths[i]!=read.block_lengths[i])
+			return false;
+	return true;
+}
+
+void CRead::print()
+{
+	fprintf(stdout, "start_pos: %d\n", start_pos);
+	fprintf(stdout, "starts:");
+	for (int i=0; i<block_starts.size(); i++)
+	{
+		fprintf(stdout, " %d", block_starts[i]);
+	}
+	fprintf(stdout, "\n");
+
+	fprintf(stdout, "lengths:");
+	for (int i=0; i<block_starts.size(); i++)
+	{
+		fprintf(stdout, " %d", block_lengths[i]);
+	}
+	fprintf(stdout, "\n");
+}
+
+void CRead::set_strand(char s)
+{
+	delete[] strand;
+	strand = new char [2];
+	strand[0] = s;
+	strand[1] = '0';
+}
+
+int CRead::get_mismatches()
+{
+	return mismatches ;
+}
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/mex/read.h	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,72 @@
+/*
+*  This program is free software; you can redistribute it and/or modify
+*  it under the terms of the GNU General Public License as published by
+*  the Free Software Foundation; either version 3 of the License, or
+*  (at your option) any later version.
+*
+*   Written (W) 2010-2011 Jonas Behr, Regina Bohnert, Gunnar Raetsch
+*   Copyright (C) 2010-2011 Max Planck Society
+*/
+
+
+#ifndef __READ_H__
+#define __READ_H__
+
+#include <stdint.h>
+#include <cctype>
+#include <stdio.h>
+#include <vector>
+  using std::vector;
+
+
+class CRead {
+ public:
+  /** constructor
+   */
+  CRead();
+  ~CRead();
+
+  vector<int> block_starts;
+  vector<int> block_lengths;
+  char* read_id;
+  char* sam_line;
+  int start_pos;
+  char * strand;
+  int matches;
+  int mismatches;
+  int multiple_alignment_index;
+  bool left;
+  bool right;
+  bool reverse;
+
+  void get_coverage(int p_start_pos, int p_end_pos, uint32_t* coverage);
+  int get_last_position();
+  void get_reads_sparse(int p_start_pos, int p_end_pos, double* reads, uint32_t & reads_c, uint32_t row_idx);
+  void get_introns(vector<int>* introns);
+  void get_introns(vector<uint32_t>* intron_starts, vector<uint32_t>* intron_ends, vector<uint32_t>* block_len1, vector<uint32_t>* block_len2);
+  void get_acc_splice_sites(vector<int>* acc_pos);
+  void get_don_splice_sites(vector<int>* acc_pos);
+  int max_intron_len();
+  int min_exon_len();
+  bool operator==(const CRead& read) const;
+  void print();
+  void set_strand(char s);
+  int get_mismatches();
+  static bool compare_by_read_id(const CRead* read1, const CRead* read2)
+  {
+	if (!read1->read_id)
+		return true;
+	if (!read2->read_id)
+		return false;
+
+	int cnt1=0;
+	while (read1->read_id[cnt1]!='\0')
+		cnt1++;
+	int cnt2 = 0;
+	while (read2->read_id[cnt2]!='\0')
+		cnt2++;
+
+	return std::lexicographical_compare(read1->read_id,read1->read_id+cnt1,read2->read_id,read2->read_id+cnt2);
+  };
+};
+#endif
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/setup_deseq2-hts.sh	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,192 @@
+#!/bin/bash
+set -e
+
+DIR=`dirname $0`
+. ${DIR}/./bin/deseq2_config.sh
+
+echo ==========================================
+echo  DESeq2-hts setup script \(DESeq2 version $DESEQ2_VERSION\)
+echo ==========================================
+echo
+echo DESeq2-hts base directory \(currently set to \"$DESEQ2_PATH\", suggest to set to \"`pwd`\", used if left empty\)
+read DESEQ2_PATH
+if [ "$DESEQ2_PATH" == "" ];
+then
+	DESEQ2_PATH=`pwd`
+fi
+echo '=>' Setting DESeq2-hts base directory to \"$DESEQ2_PATH\"
+echo
+echo SAMTools directory \(currently set to \"$SAMTOOLS_DIR\", system version used if left empty\)
+read SAMTOOLS_DIR
+if [ "$SAMTOOLS_DIR" == "" ];
+then
+	if [ "$(which samtools)" != "" ] ;
+	then
+		SAMTOOLS_DIR=$(dirname $(which samtools))
+	else
+		echo samtools not found
+		exit -1 ;
+	fi
+fi
+echo '=>' Setting SAMTools directory to \"$SAMTOOLS_DIR\"
+echo
+
+echo Path to the python binary \(currently set to \"$PYTHON_PATH\", system version used, if left empty\)
+read PYTHON_PATH
+if [ "$PYTHON_PATH" == "" ];
+then
+    PYTHON_PATH=`which python`
+	if [ "$PYTHON_PATH" == "" ];
+	then
+		echo python not found
+		exit -1
+	fi
+fi
+echo '=>' Setting Python path to \"$PYTHON_PATH\"
+echo
+
+echo Path to the R binary \(currently set to \"$R_PATH\", system version used, if left empty\)
+read R_PATH
+if [ "$R_PATH" == "" ];
+then
+    R_PATH=`which R`
+	if [ "$R_PATH" == "" ];
+	then
+		echo R not found
+		exit -1
+	fi
+fi
+echo '=>' Setting R path to \"$R_PATH\"
+echo
+
+echo Path to Scipy library files \(currently set to \"$SCIPY_PATH\", system version is used if left empty\)
+read SCIPY_PATH
+echo '=>' Setting Scipy path to \"$SCIPY_PATH\"
+echo
+
+echo Which interpreter should be used \(\"octave\" or \"matlab\"\)
+read INTERPRETER
+if [ "$INTERPRETER" != 'octave' -a  "$INTERPRETER" != 'matlab' ];
+then
+	echo Unrecognized choice: \"$INTERPRETER\"
+	echo Aborting
+	false
+fi
+echo '=>' Setting interpreter to \"$INTERPRETER\"
+echo
+
+if [ "$INTERPRETER" == 'octave' ];
+then
+	echo Please enter the full path to octave \(currently set to \"$OCTAVE_BIN_PATH\", system version used, if left empty\)
+	read OCTAVE_BIN_PATH
+	if [ "$OCTAVE_BIN_PATH" == "" ];
+	then
+	    OCTAVE_BIN_PATH=`which octave`
+		if [ "$OCTAVE_BIN_PATH" == "" ];
+		then
+			echo octave not found
+			exit -1
+		fi
+	fi
+	echo '=>' Setting octave\'s path to \"$OCTAVE_BIN_PATH\"
+	echo
+	echo Please enter the full path to mkoctfile \(currently set to \"$OCTAVE_MKOCT\", system version used, if left empty\)
+	read OCTAVE_MKOCT
+	if [ "$OCTAVE_MKOCT" == "" ];
+	then
+	    OCTAVE_MKOCT=`which mkoctfile`
+		if [ "$OCTAVE_MKOCT" == "" ];
+		then
+			OCTAVE_MKOCT=$(dirname $OCTAVE_BIN_PATH)/mkoctfile
+			if [ ! -f OCTAVE_MKOCT ];
+			then
+				echo mkoctfile not found
+				exit -1
+			fi
+		fi
+	fi
+	echo '=>' Setting mkoctfile\'s path to \"$OCTAVE_MKOCT\"
+	echo
+	MATLAB_BIN_PATH=
+fi
+if [ "$INTERPRETER" == 'matlab' ];
+then
+	echo Please enter the full path to matlab \(currently set to \"$MATLAB_BIN_PATH\", system version used, if left empty\)
+	read MATLAB_BIN_PATH
+	if [ "${MATLAB_BIN_PATH}" == "" ];
+	then
+		MATLAB_BIN_PATH=`which matlab`
+		if [ "$MATLAB_BIN_PATH" == "" ];
+		then
+			echo matlab not found
+			exit -1
+		fi
+	fi
+	if [ ! -f $MATLAB_BIN_PATH ];
+	then
+		echo matlab not found
+		exit -1
+	fi
+	echo '=>' Setting matlab\'s path to \"$MATLAB_BIN_PATH\"
+	echo
+	echo Please enter the full path to mex binary \(currently set to \"$MATLAB_MEX_PATH\", system version used if left empty\)
+	read MATLAB_MEX_PATH
+	if [ "$MATLAB_MEX_PATH" == "" ];
+	then
+		MATLAB_MEX_PATH=`which mex`
+		if [ "$MATLAB_MEX_PATH" == "" ];
+		then
+			echo mex not found
+			exit -1
+		fi
+	fi
+	if [ ! -f "$MATLAB_MEX_PATH" ];
+	then
+		echo mex not found
+		exit -1
+	fi
+	echo '=>' Setting mex\' path to \"$MATLAB_MEX_PATH\"
+	echo
+	echo Please enter the full path to the matlab include directory \(currently set to \"$MATLAB_INCLUDE_DIR\", system version used, if left empty\)
+	read MATLAB_INCLUDE_DIR
+	if [ "$MATLAB_INCLUDE_DIR" == "" ];
+	then
+		MATLAB_INCLUDE_DIR=$(dirname $MATLAB_BIN_PATH)/../extern/include
+	fi
+	if [ ! -d "$MATLAB_INCLUDE_DIR" ];
+	then
+		echo matlab include dir not found
+		exit -1
+	fi
+	echo '=>' Setting matlab\'s include directory to \"$MATLAB_INCLUDE_DIR\"
+	echo
+	OCTAVE_BIN_PATH=
+fi
+
+cp -p bin/deseq2_config.sh bin/deseq2_config.sh.bk
+grep -v -e OCTAVE_BIN_PATH -e OCTAVE_MKOCT -e MATLAB_BIN_PATH -e MATLAB_MEX_PATH -e MATLAB_INCLUDE_DIR \
+    -e DESEQ2_PATH -e DESEQ2_SRC_PATH -e DESEQ2_BIN_PATH \
+    -e INTERPRETER -e SAMTOOLS_DIR -e PYTHON_PATH -e SCIPY_PATH -e R_PATH -e $DESEQ2_VERSION bin/deseq2_config.sh.bk  \
+    > bin/deseq2_config.sh
+echo
+echo
+echo generating config file
+
+echo export DESEQ2_VERSION=$DESEQ2_VERSION >> bin/deseq2_config.sh
+echo export DESEQ2_PATH=$DESEQ2_PATH >> bin/deseq2_config.sh
+echo export DESEQ2_SRC_PATH=${DESEQ2_PATH}/src >> bin/deseq2_config.sh
+echo export DESEQ2_BIN_PATH=${DESEQ2_PATH}/bin >> bin/deseq2_config.sh
+echo export INTERPRETER=$INTERPRETER >> bin/deseq2_config.sh
+echo export MATLAB_BIN_PATH=$MATLAB_BIN_PATH >> bin/deseq2_config.sh
+echo export MATLAB_MEX_PATH=$MATLAB_MEX_PATH >> bin/deseq2_config.sh
+echo export MATLAB_INCLUDE_DIR=$MATLAB_INCLUDE_DIR >> bin/deseq2_config.sh
+echo export OCTAVE_BIN_PATH=$OCTAVE_BIN_PATH >> bin/deseq2_config.sh
+echo export OCTAVE_MKOCT=$OCTAVE_MKOCT >> bin/deseq2_config.sh
+echo export SAMTOOLS_DIR=$SAMTOOLS_DIR >> bin/deseq2_config.sh
+echo export PYTHON_PATH=$PYTHON_PATH >> bin/deseq2_config.sh
+echo export SCIPY_PATH=$SCIPY_PATH >> bin/deseq2_config.sh
+echo export R_PATH=$R_PATH >> bin/deseq2_config.sh
+
+echo
+echo Done.
+echo
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/src/deseq2-hts.sh	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,88 @@
+#/bin/bash
+##
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# Copyright (C) 2009-2013 Max Planck Society & Memorial Sloan-Kettering Cancer Center
+##
+
+set -e
+
+PROG=`basename $0`
+DIR=`dirname $0`
+
+. ${DIR}/../bin/deseq2_config.sh
+
+echo
+echo ${PROG}: Oqtans http://galaxy.cbio.mskcc.org Galaxy wrapper for the DESeq2 version $DESEQ2_VERSION.
+echo
+echo DESeq2 performs differential gene expression analysis based on the negative binomial distribution.
+echo
+
+ANNO_INPUT=${1}
+shift
+DESEQ_RES_FILE=${1}
+shift
+GENES_FN=${1}
+shift
+
+mkdir -p `dirname $GENES_FN`
+touch ${GENES_FN}
+
+echo %%%%%%%%%%%%%%%%%%%%%%%
+echo % 1. Data preparation %
+echo %%%%%%%%%%%%%%%%%%%%%%%
+echo
+echo load the genome annotation in GFF3 format and create an annotation object
+${PYTHON_PATH} ${DIR}/../tools/GFFParser.py ${ANNO_INPUT} ${GENES_FN}
+echo
+echo genome annotation stored in $GENES_FN
+echo
+
+FITTYP=${1}
+shift
+
+echo %%%%%%%%%%%%%%%%%%%%
+echo % 2. Read counting %
+echo %%%%%%%%%%%%%%%%%%%%
+echo
+echo checking for BAM index...
+for REPLICATE_GROUP in $@
+do
+    IFS=':'
+    for BAM_FILE in ${REPLICATE_GROUP}
+    do
+        echo
+        if [ ! -f ${BAM_FILE}.bai ]
+        then
+            echo "Indexing $BAM_FILE"
+            ${SAMTOOLS_DIR}/samtools index $BAM_FILE
+        else
+            echo "$BAM_FILE already indexed"
+        fi
+        echo
+    done
+done
+echo counting reads overlapping exons using given alignments...
+tmpfile=`mktemp --tmpdir=/tmp`
+
+echo "${DIR}/../bin/get_read_counts ${GENES_FN} $tmpfile $@"
+${DIR}/../bin/get_read_counts ${GENES_FN} $tmpfile "$@"
+echo counted reads map to each feature.
+echo
+
+echo %%%%%%%%%%%%%%%%%%%%%%%%%%%
+echo % 3. Differential testing %
+echo %%%%%%%%%%%%%%%%%%%%%%%%%%%
+echo
+echo testing genes for differential expression using given read alignments
+
+
+echo "cat ${DIR}/../src/difftest_deseq2.R | $R_PATH --slave --args $tmpfile ${DESEQ_RES_FILE} $#"
+(cat ${DIR}/../src/difftest_deseq2.R | $R_PATH --slave --args ${FITTYP} $tmpfile ${DESEQ_RES_FILE} 2>&1 || (echo R script execution failed 1>&2))
+
+echo %%%%%%%%
+echo % Done %
+echo %%%%%%%%
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/src/deseq_config.m	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,55 @@
+function deseq_config
+% DESEQ2_CONFIG   Sets a few global variables with system dependent paths.
+%
+%
+% This program is free software; you can redistribute it and/or modify
+% it under the terms of the GNU General Public License as published by
+% the Free Software Foundation; either version 3 of the License, or
+% (at your option) any later version.
+%
+% Written (W) 2009-2011 Regina Bohnert, Gunnar Raetsch
+% Copyright (C) 2009-2011 Max Planck Society
+%
+
+% paths
+global DESEQ2_PATH DESEQ2_SRC_PATH
+
+% interpreter paths
+global INTERPRETER MATLAB_BIN_PATH OCTAVE_BIN_PATH
+
+% SAMTools path
+global SAMTOOLS_DIR
+
+% configuration (adapt to the user's configuration)
+DESEQ2_PATH = getenv('DESEQ2_PATH');
+DESEQ2_SRC_PATH = getenv('DESEQ2_SRC_PATH');
+INTERPRETER = getenv('INTERPRETER');
+MATLAB_BIN_PATH = getenv('MATLAB_BIN_PATH');
+OCTAVE_BIN_PATH = getenv('OCTAVE_BIN_PATH');
+SAMTOOLS_DIR = getenv('SAMTOOLS_DIR');
+
+% switch off a few expected warnings
+addpath(sprintf('%s/tools', DESEQ2_PATH));
+engine='';
+lserve=license;
+if ~isequal(lserve, 'GNU General Public License'),
+    engine='matlab';
+else
+    engine='octave';
+end;
+if isequal(engine, 'octave'),
+  warning('off', 'Octave:precedence-change');
+  warning('off', 'Octave:function-name-clash');
+  warning('off', '');
+  warning('off', 'Octave:num-to-str');
+  warning('off', 'Octave:function-name-clash');
+  warning('off', 'Octave:divide-by-zero');
+  warning('off', 'Octave:future-time-stamp');
+  warning('off', 'Octave:assign-as-truth-value');
+else
+  warning('off', 'MATLAB:typeaheadBufferOverflow');
+end
+
+% make sure no process stops with a debug prompt
+global g_ignore_keyboard
+g_ignore_keyboard = 1;
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/src/difftest_deseq2.R	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,78 @@
+### load DESeq package
+suppressMessages(require("DESeq2"))
+
+### get arguments 1: INFILE, 2: OUTFILE 3:SIZE
+args <- commandArgs()
+FITTYP<-args[4]
+INFILE<-args[5]
+OUTFILE<-args[6]
+
+INFILE_COUNTS=c(paste(INFILE, "_COUNTS.tab", sep=""))
+INFILE_CONDS=c(paste(INFILE, "_CONDITIONS.tab", sep=""))
+
+### read count data from file
+countsTable <- read.delim( INFILE_COUNTS, header=TRUE, stringsAsFactors=TRUE)
+condsTable <- read.delim( INFILE_CONDS, header=TRUE, stringsAsFactors=TRUE)
+
+tagnames <- countsTable[-(1:2), 1]
+#print(tagnames)
+
+## use gene IDs as row names
+rownames( countsTable ) <- countsTable$gene
+countsTable <- countsTable[ , -1 ]
+#print(countsTable)
+
+conditions<-factor( condsTable[ , 2] )
+#print(conditions)
+
+## unique condition to define the pair of tests
+uniq_conds <- unique(conditions)
+#print(uniq_conds)
+
+## all possible pairs of conditions
+pw_tests <- list()
+for(i in 1:(length(uniq_conds)-1)) {
+    for(j in (i+1):length(uniq_conds)) {
+        pw_tests[[length(pw_tests)+1]] <- c(uniq_conds[i], uniq_conds[j])
+    }
+}
+#print(pw_tests)
+
+tab <- NULL
+## testing all possible pairs of conditions
+for(i in 1:length(pw_tests)) {
+    ## header name
+    test_pair_name <- c(paste(pw_tests[[i]][1], "__vs__", pw_tests[[i]][2], sep=""))
+    #print(test_pair_name)
+    ## colnames respective to the test pair
+    sub.data <- subset(condsTable, (conditions %in% c(pw_tests[[i]][1],pw_tests[[i]][2])))
+    #print(sub.data)
+    #print(sub.data[[1]]) # sample file name
+    #print(sub.data[[2]]) # condition
+    #print(sub.data[[3]]) # replicates
+    colData <- data.frame(row.names=sub.data[[1]], condition=sub.data[[2]], libType=sub.data[[3]])
+    #print(colData)
+    #print(countsTable[(sub.data[[1]])])
+    dds <- DESeqDataSetFromMatrix(countData=countsTable[(sub.data[[1]])], colData=colData, design=~condition)
+    colData(dds)$condition <- factor(colData(dds)$condition, levels=unique(sub.data[[2]]))
+    dds <- DESeq(dds, fitType=FITTYP)
+    ## concatenate the results
+    tested_pairs <- results(dds)
+    #print(typeof(tested_pairs))
+
+    colnames(tested_pairs) <- paste(test_pair_name, colnames(tested_pairs), sep=":")
+    #print(colnames(tested_pairs))
+    #print(tested_pairs)
+
+    tab_tmp <- tested_pairs[tagnames,]
+    if(is.null(tab)) {
+        tab<- as.data.frame(tab_tmp)
+    }
+    else tab<- cbind(tab, as.data.frame(tab_tmp))
+}
+## TODO cbind creates a X character to the string start place.
+colnames(tab) <- gsub("^X", "", colnames(tab))
+## adding gene names to the row
+tab <- cbind(Feature=row.names(tab_tmp), tab)
+## priting the result
+write.table(tab, OUTFILE, quote=F, sep="\t", row.names=F)
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/src/genes_cell2struct.m	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,28 @@
+function genes_cell2struct(anno_fname)
+% GENES_CELL2STRUCT   Converts genes stored as a cell to struct.
+%
+%   genes_cell2struct(anno_fname)
+%
+%   -- input --
+%   anno_fname:   name of file where genes as cell are stored
+%
+%   -- output --
+%   genes as a struct
+
+load(anno_fname, 'genes');
+if iscell(genes)
+  genes_cell = genes;
+  clear genes;
+  for g = 1:length(genes_cell),
+    gene = genes_cell{g};
+    for e = 1:length(gene.exons)
+      gene.exons{e} = double(gene.exons{e});
+    end
+    gene.exons = reshape(gene.exons, 1, length(gene.exons));
+    gene.id = double(gene.id);
+    gene.start = double(gene.start);
+    gene.stop = double(gene.stop);
+    genes(g) = gene;
+  end
+save(anno_fname, 'genes');
+end
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/src/get_read_counts.m	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,172 @@
+function get_read_counts(anno_dir, outfile, varargin)
+%
+% -- input --
+% anno_dir: directory of genes
+% outfile: output file
+% varargin: list of BAM files (at least two)
+
+% DESeq paths
+global DESEQ2_PATH DESEQ2_SRC_PATH
+
+% interpreter paths
+global INTERPRETER MATLAB_BIN_PATH OCTAVE_BIN_PATH
+
+% SAMTools path
+global SAMTOOLS_DIR
+
+%%%% paths
+addpath(sprintf('%s/tools', DESEQ2_PATH));
+addpath(sprintf('%s/mex', DESEQ2_PATH));
+addpath(sprintf('%s', DESEQ2_SRC_PATH));
+
+deseq_config;
+
+%%% read list of replicate groups from variable length argument list
+rg_list = cell(1,size(varargin, 2));
+file_list = cell();
+file_cond_ids = [];
+file_rep_ids = [];
+for idx = 1:size(varargin, 2)
+    rg_list(idx) = varargin(idx);
+end
+idx = strmatch('', rg_list, 'exact');
+rg_list(idx) = [];
+for idx = 1:length(rg_list),
+    items = separate(rg_list{idx}, ':');
+    for idx2 = 1:length(items)
+		if isempty(deblank(items{idx2})),
+			continue;
+   	    end;
+        file_list{end + 1} = items{idx2};
+        file_cond_ids(end + 1) = idx;
+        file_rep_ids(end + 1) = idx2;
+    end;
+end;
+clear idx idx2;
+
+%%%%% adapt to number of input arguments
+file_num = length(file_list);
+RESULTS = cell(1, file_num);
+
+%%%% get annotation file
+load(sprintf('%s', anno_dir));
+
+%%%%% mask overlapping gene regions -> later not counted
+[genes] = mask_dubl(genes,0);
+
+%%%% remove genes with no annotated exons or where no
+idx = find(arrayfun(@(x)(~isempty(x.exons)*~isempty(x.start)*~isempty(x.stop)), genes));
+fprintf('removed %i of %i genes, which had either no exons annotated or lacked a start or stop position\n', size(genes, 2) - size(idx, 2), size(genes, 2))
+genes = genes(idx);
+clear idx;
+
+%%%% check if genes have field chr_num
+if ~isfield(genes, 'chr_num')
+	chrms = unique({genes(:).chr});
+	for i = 1:length(genes)
+		genes(i).chr_num = strmatch(genes(i).chr, chrms, 'exact');
+	end;
+end;
+
+%%%% iterate over all given bam files
+for f_idx = 1:file_num
+    expr1_bam = fullfile('', file_list{f_idx});
+    STAT = cell(size(genes, 2),1);
+    for i=1:size(genes,2)
+        RESULT = cell(1,7);
+        gene = genes(i);
+        RESULT{4} = f_idx;
+        RESULT{1} = gene.name;
+        if isempty(gene.exons)
+            RESULT{2} = inf;
+            RESULT{3} = inf;
+            RESULT{5} = [inf,inf];
+            STAT{i} = RESULT;
+            continue;
+        elseif or(isempty(gene.start),isempty(gene.stop))
+		    RESULT{2} = inf;
+		    RESULT{3} = inf;
+		    RESULT{5} = [inf,inf];
+		    STAT{i} = RESULT;
+		    continue;
+        end
+        if ~isempty(gene.chr_num),
+		    [mask1, read_intron_list] = get_reads(expr1_bam, gene.chr, gene.start, gene.stop, '0');
+		    clear read_intron_list;
+	    else
+		    mask1 = [];
+        end;
+
+        if isempty(mask1)
+            reads1 = zeros(0,gene.stop-gene.start+1);
+        else
+            reads1 = sparse(mask1(1,:)',mask1(2,:)',ones(size(mask1,2),1),max(mask1(1,:)),gene.stop-gene.start+1);
+        end
+	    if ~isempty(reads1);
+		    [reads1,FLAG] = remove_reads_from_other_genes(reads1,gene);
+	    end
+        L = size(reads1);
+        RESULT{2}=[size(reads1,1)]; % number of all reads falling in that gene
+        EXON_IDX=zeros(1,gene.stop-gene.start+1);
+        for t=1:size(gene.transcripts,2)
+            for e=1:size(gene.exons{t},1)
+                EXON_IDX((gene.exons{t}(e,1)-gene.start+1):(gene.exons{t}(e,2)-gene.start+1))=1;
+            end
+        end
+        reads1 = reads1(sum(reads1(:,find(EXON_IDX)),2)>0,:);
+        L1 = sum(EXON_IDX);
+        RESULT{3}=[size(reads1,1)]; % number of reads overlapping to exons
+        RESULT{5}=[L, L1]; % size of reads1, number of exonic positions
+        % old and weighted poisson new ,weighted regions reads and
+        % unexplained reads
+        clear reads1;
+        STAT{i} = RESULT;
+    end;
+    RESULTS{f_idx} = STAT;
+end;
+
+S=size(genes,2);
+READCOUNTS_ALL=zeros(S, file_num);
+READCOUNTS_EXON=zeros(S, file_num);
+LENGTH_ALL=zeros(S,file_num);
+LEN_EXON=zeros(S, file_num);
+
+for j=1:file_num,
+  for i=1:S
+    T=RESULTS{j}{i};
+    if isempty(T)
+        continue
+    else
+        READCOUNTS_ALL(i,j)=T{2};
+        READCOUNTS_EXON(i,j)=T{3};
+        LENGTH_ALL(i,j)=T{5}(1);
+        LEN_EXON(i,j)=T{5}(2);
+    end
+  end
+end
+
+%%%%% write results for all bam files
+fid_conditions = fopen(sprintf('%s_CONDITIONS.tab', outfile), 'w');
+fid_counts = fopen(sprintf('%s_COUNTS.tab', outfile) ,'w');
+fprintf(fid_counts,'gene');
+fprintf(fid_conditions, 'file\tcondition\treplicate\n');
+for j = 1:length(file_list)
+    fname = file_list{j} ;
+    fname = separate(fname, '/');
+    fname = fname{end};
+    fname = strrep(fname, '.bam', '') ;
+    fprintf(fid_counts,'\t%s', fname);
+    fprintf(fid_conditions, '%s\t%i\t%i\n', fname, file_cond_ids(j), file_rep_ids(j));
+end;
+fprintf(fid_counts,'\n') ;
+
+for i = 1:size(genes,2)
+    fprintf(fid_counts,'%s',genes(i).name);
+    for j = 1:length(file_list),
+      fprintf(fid_counts,'\t%i', READCOUNTS_EXON(i,j));
+    end
+    fprintf(fid_counts,'\n');
+end
+fclose(fid_counts);
+fclose(fid_conditions);
+exit;
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/src/mask_dubl.m	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,81 @@
+function [new_genes]=mask_dubl(genes,THRESH);
+
+CHROMOSOMES={};
+COUNTER=1;
+for i=1:size(genes,2)
+  CHROMOSOMES{COUNTER}=genes(i).chr;
+  COUNTER=COUNTER+1;
+end
+CHROMOSOMES=unique(CHROMOSOMES);
+
+
+INFO=zeros(size(genes,2),4);
+for i=1:size(genes,2)
+  CHR_VAL=0;
+  for chr= 1:length(CHROMOSOMES)
+    if  strcmp(genes(i).chr,CHROMOSOMES(chr))
+      CHR_VAL=chr;
+    end
+  end
+  INFO(i,:)=[i,genes(i).start,genes(i).stop, CHR_VAL];
+end
+
+COUNTER=1;
+new_genes=genes;
+for chr= 1:length(CHROMOSOMES)
+  GENES_ON_CHR=INFO(INFO(:,4)==chr,:);
+  [TEMP,POS]=sort(GENES_ON_CHR(:,2));
+  GENES_ON_CHR=GENES_ON_CHR(POS,:);
+  STARTS=GENES_ON_CHR(:,2);
+  STOPS=GENES_ON_CHR(:,3);
+  for i=1:(size(GENES_ON_CHR,1))
+    MIN_START=find(STOPS>=STARTS(i),1,'first');
+    MAX_STOP=find(STARTS<=STOPS(i),1,'last');
+    if MIN_START==i
+      MIN_START=[];
+    end
+    if MAX_STOP==i
+      MAX_STOP=[];
+    end
+    EXONS=[];
+    if not (isempty(MIN_START))
+      for CURR=MIN_START:(i-1)
+	if(not(isempty(genes(GENES_ON_CHR(CURR,1)).transcripts)))
+	  for tra=1:size(genes(GENES_ON_CHR(CURR,1)).transcripts,2)
+	    if(not(isempty(genes(GENES_ON_CHR(CURR,1)).exons)))
+	      EXONS=[EXONS;genes(GENES_ON_CHR(CURR,1)).exons{tra}];
+	    else
+	      EXONS=[EXONS;genes(GENES_ON_CHR(CURR,1)).start,genes(GENES_ON_CHR(CURR,1)).stop];
+	    end
+	  end
+	else
+	  EXONS=[EXONS;genes(GENES_ON_CHR(CURR,1)).start,genes(GENES_ON_CHR(CURR,1)).stop];
+	end
+      end
+    end
+    if not (isempty(MAX_STOP))
+      for CURR=(i+1):MAX_STOP
+	if(not(isempty(genes(GENES_ON_CHR(CURR,1)).transcripts)))
+	  for tra=1:size(genes(GENES_ON_CHR(CURR,1)).transcripts,2)
+	    if(not(isempty(genes(GENES_ON_CHR(CURR,1)).exons)))
+	      EXONS=[EXONS;genes(GENES_ON_CHR(CURR,1)).exons{tra}];
+	    else
+	      EXONS=[EXONS;genes(GENES_ON_CHR(CURR,1)).start,genes(GENES_ON_CHR(CURR,1)).stop];
+	    end
+	  end
+	else
+	  EXONS=[EXONS;genes(GENES_ON_CHR(CURR,1)).start,genes(GENES_ON_CHR(CURR,1)).stop];
+	end
+
+      end
+    end
+    if  not (isempty([MAX_STOP,MIN_START]))
+      EXONS=EXONS(EXONS(:,2)>=STARTS(i),:);
+      EXONS=EXONS(EXONS(:,1)<=STOPS(i),:);
+      new_genes(GENES_ON_CHR(i,1)).non_unique_regions=EXONS;
+    else
+        new_genes(GENES_ON_CHR(i,1)).non_unique_regions=[];
+    end
+  end
+  COUNTER=COUNTER+1;
+end
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/src/remove_reads_from_other_genes.m	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,21 @@
+function [READS_OUT,FLAG]=remove_reads_from_other_genes(READS,GENE)
+%This funtion removes the reads in READS which could ome from other
+%annotated genes. FLAG is 1 if this was sucsesfull and 0 otherwise
+READS_IN=READS;
+if isfield(GENE,'non_unique_regions')
+  EXONS=GENE.non_unique_regions;
+  IDX=zeros(1,GENE.stop-GENE.start+1);
+
+  for i=1:size(EXONS,1)
+    START=max(EXONS(i,1),GENE.start)-GENE.start+1;
+    STOP=min(EXONS(i,2),GENE.stop)-GENE.start+1;
+    IDX(START:STOP)=1;
+  end
+  READS=READS(not(sum(READS(:,IDX>0),2)==sum(READS,2)),:);
+  FLAG=1;
+  READS_OUT=READS;
+else
+  READS_OUT=READS_IN;
+  FLAG=0;
+end
+
Binary file deseq-hts_2.0/test_data/deseq_c_elegans_WS200-I-regions-SRX001872.bam has changed
Binary file deseq-hts_2.0/test_data/deseq_c_elegans_WS200-I-regions-SRX001872.bam.bai has changed
Binary file deseq-hts_2.0/test_data/deseq_c_elegans_WS200-I-regions-SRX001875.bam has changed
Binary file deseq-hts_2.0/test_data/deseq_c_elegans_WS200-I-regions-SRX001875.bam.bai has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/test_data/deseq_c_elegans_WS200-I-regions.gff3	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,747 @@
+##gff-version 3
+##Seqid	Source	Type	Start	End	Score	Phase	Attributes
+I	Coding_transcript	gene	11495	16831	.	+	.	ID=Gene:Gene:Y74C9A.2.2
+I	Coding_transcript	mRNA	11495	16793	.	+	.	ID=Transcript:Gene:Y74C9A.2.2.1;Parent=Gene:Gene:Y74C9A.2.2
+I	Coding_transcript	five_prime_UTR	11495	11561	.	+	.	ID=five_prime_UTR:Gene:Y74C9A.2.2.1;Parent=Transcript:Gene:Y74C9A.2.2.1
+I	Coding_transcript	five_prime_UTR	11618	11640	.	+	.	ID=five_prime_UTR:Gene:Y74C9A.2.2.1;Parent=Transcript:Gene:Y74C9A.2.2.1
+I	Coding_transcript	CDS	11641	11689	.	+	0	ID=CDS:Gene:Y74C9A.2.2.1;Parent=Transcript:Gene:Y74C9A.2.2.1
+I	Coding_transcript	CDS	14951	15160	.	+	2	ID=CDS:Gene:Y74C9A.2.2.1;Parent=Transcript:Gene:Y74C9A.2.2.1
+I	Coding_transcript	CDS	16473	16585	.	+	2	ID=CDS:Gene:Y74C9A.2.2.1;Parent=Transcript:Gene:Y74C9A.2.2.1
+I	Coding_transcript	three_prime_UTR	16702	16793	.	+	.	ID=three_prime_UTR:Gene:Y74C9A.2.2.1;Parent=Transcript:Gene:Y74C9A.2.2.1
+I	Coding_transcript	mRNA	11499	16790	.	+	.	ID=Transcript:Gene:Y74C9A.2.2.2;Parent=Gene:Gene:Y74C9A.2.2
+I	Coding_transcript	five_prime_UTR	11499	11557	.	+	.	ID=five_prime_UTR:Gene:Y74C9A.2.2.2;Parent=Transcript:Gene:Y74C9A.2.2.2
+I	Coding_transcript	five_prime_UTR	11618	11640	.	+	.	ID=five_prime_UTR:Gene:Y74C9A.2.2.2;Parent=Transcript:Gene:Y74C9A.2.2.2
+I	Coding_transcript	CDS	11641	11689	.	+	0	ID=CDS:Gene:Y74C9A.2.2.2;Parent=Transcript:Gene:Y74C9A.2.2.2
+I	Coding_transcript	CDS	14951	15160	.	+	2	ID=CDS:Gene:Y74C9A.2.2.2;Parent=Transcript:Gene:Y74C9A.2.2.2
+I	Coding_transcript	CDS	16473	16585	.	+	2	ID=CDS:Gene:Y74C9A.2.2.2;Parent=Transcript:Gene:Y74C9A.2.2.2
+I	Coding_transcript	three_prime_UTR	16586	16790	.	+	.	ID=three_prime_UTR:Gene:Y74C9A.2.2.2;Parent=Transcript:Gene:Y74C9A.2.2.2
+I	Coding_transcript	mRNA	11499	16831	.	+	.	ID=Transcript:Gene:Y74C9A.2.2.3;Parent=Gene:Gene:Y74C9A.2.2
+I	Coding_transcript	five_prime_UTR	11499	11561	.	+	.	ID=five_prime_UTR:Gene:Y74C9A.2.2.3;Parent=Transcript:Gene:Y74C9A.2.2.3
+I	Coding_transcript	five_prime_UTR	11618	11640	.	+	.	ID=five_prime_UTR:Gene:Y74C9A.2.2.3;Parent=Transcript:Gene:Y74C9A.2.2.3
+I	Coding_transcript	CDS	11641	11689	.	+	0	ID=CDS:Gene:Y74C9A.2.2.3;Parent=Transcript:Gene:Y74C9A.2.2.3
+I	Coding_transcript	CDS	14951	15160	.	+	2	ID=CDS:Gene:Y74C9A.2.2.3;Parent=Transcript:Gene:Y74C9A.2.2.3
+I	Coding_transcript	CDS	16473	16585	.	+	2	ID=CDS:Gene:Y74C9A.2.2.3;Parent=Transcript:Gene:Y74C9A.2.2.3
+I	Coding_transcript	three_prime_UTR	16586	16831	.	+	.	ID=three_prime_UTR:Gene:Y74C9A.2.2.3;Parent=Transcript:Gene:Y74C9A.2.2.3
+I	Coding_transcript	mRNA	11505	16790	.	+	.	ID=Transcript:Gene:Y74C9A.2.2.4;Parent=Gene:Gene:Y74C9A.2.2
+I	Coding_transcript	five_prime_UTR	11505	11561	.	+	.	ID=five_prime_UTR:Gene:Y74C9A.2.2.4;Parent=Transcript:Gene:Y74C9A.2.2.4
+I	Coding_transcript	five_prime_UTR	11623	11640	.	+	.	ID=five_prime_UTR:Gene:Y74C9A.2.2.4;Parent=Transcript:Gene:Y74C9A.2.2.4
+I	Coding_transcript	CDS	11641	11689	.	+	0	ID=CDS:Gene:Y74C9A.2.2.4;Parent=Transcript:Gene:Y74C9A.2.2.4
+I	Coding_transcript	CDS	14951	15160	.	+	2	ID=CDS:Gene:Y74C9A.2.2.4;Parent=Transcript:Gene:Y74C9A.2.2.4
+I	Coding_transcript	CDS	16473	16585	.	+	2	ID=CDS:Gene:Y74C9A.2.2.4;Parent=Transcript:Gene:Y74C9A.2.2.4
+I	Coding_transcript	three_prime_UTR	16586	16790	.	+	.	ID=three_prime_UTR:Gene:Y74C9A.2.2.4;Parent=Transcript:Gene:Y74C9A.2.2.4
+I	Coding_transcript	mRNA	11618	16804	.	+	.	ID=Transcript:Gene:Y74C9A.2.2.5;Parent=Gene:Gene:Y74C9A.2.2
+I	Coding_transcript	five_prime_UTR	11618	11640	.	+	.	ID=five_prime_UTR:Gene:Y74C9A.2.2.5;Parent=Transcript:Gene:Y74C9A.2.2.5
+I	Coding_transcript	CDS	11641	11689	.	+	0	ID=CDS:Gene:Y74C9A.2.2.5;Parent=Transcript:Gene:Y74C9A.2.2.5
+I	Coding_transcript	CDS	14951	15160	.	+	2	ID=CDS:Gene:Y74C9A.2.2.5;Parent=Transcript:Gene:Y74C9A.2.2.5
+I	Coding_transcript	CDS	16473	16585	.	+	2	ID=CDS:Gene:Y74C9A.2.2.5;Parent=Transcript:Gene:Y74C9A.2.2.5
+I	Coding_transcript	three_prime_UTR	16586	16804	.	+	.	ID=three_prime_UTR:Gene:Y74C9A.2.2.5;Parent=Transcript:Gene:Y74C9A.2.2.5
+I	Coding_transcript	gene	47472	49416	.	+	.	ID=Gene:Gene:Y48G1C.12
+I	Coding_transcript	mRNA	47472	49416	.	+	.	ID=Transcript:Gene:Y48G1C.12.1;Parent=Gene:Gene:Y48G1C.12
+I	Coding_transcript	CDS	47472	47610	.	+	0	ID=CDS:Gene:Y48G1C.12.1;Parent=Transcript:Gene:Y48G1C.12.1
+I	Coding_transcript	CDS	47696	47858	.	+	2	ID=CDS:Gene:Y48G1C.12.1;Parent=Transcript:Gene:Y48G1C.12.1
+I	Coding_transcript	CDS	48348	48530	.	+	1	ID=CDS:Gene:Y48G1C.12.1;Parent=Transcript:Gene:Y48G1C.12.1
+I	Coding_transcript	CDS	49251	49416	.	+	1	ID=CDS:Gene:Y48G1C.12.1;Parent=Transcript:Gene:Y48G1C.12.1
+I	Coding_transcript	gene	71858	81071	.	+	.	ID=Gene:Gene:Y48G1C.2.1
+I	Coding_transcript	mRNA	71858	81071	.	+	.	ID=Transcript:Gene:Y48G1C.2.1.1;Parent=Gene:Gene:Y48G1C.2.1
+I	Coding_transcript	five_prime_UTR	71858	71932	.	+	.	ID=five_prime_UTR:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	five_prime_UTR	72511	72590	.	+	.	ID=five_prime_UTR:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	five_prime_UTR	72647	72648	.	+	.	ID=five_prime_UTR:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	CDS	72649	72897	.	+	0	ID=CDS:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	CDS	72941	73017	.	+	0	ID=CDS:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	CDS	73605	73766	.	+	1	ID=CDS:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	CDS	74625	74808	.	+	1	ID=CDS:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	CDS	75171	75490	.	+	0	ID=CDS:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	CDS	75951	76112	.	+	1	ID=CDS:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	CDS	76949	77153	.	+	1	ID=CDS:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	CDS	77713	77799	.	+	0	ID=CDS:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	CDS	79313	79447	.	+	0	ID=CDS:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	CDS	80306	80344	.	+	0	ID=CDS:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	three_prime_UTR	80345	81071	.	+	.	ID=three_prime_UTR:Gene:Y48G1C.2.1.1;Parent=Transcript:Gene:Y48G1C.2.1.1
+I	Coding_transcript	mRNA	71878	81063	.	+	.	ID=Transcript:Gene:Y48G1C.2.1.2;Parent=Gene:Gene:Y48G1C.2.1
+I	Coding_transcript	five_prime_UTR	71878	71932	.	+	.	ID=five_prime_UTR:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	five_prime_UTR	72511	72590	.	+	.	ID=five_prime_UTR:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	five_prime_UTR	72647	72648	.	+	.	ID=five_prime_UTR:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	CDS	72649	72897	.	+	0	ID=CDS:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	CDS	72941	73017	.	+	0	ID=CDS:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	CDS	73605	73766	.	+	1	ID=CDS:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	CDS	74625	74808	.	+	1	ID=CDS:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	CDS	75171	75490	.	+	0	ID=CDS:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	CDS	75951	76112	.	+	1	ID=CDS:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	CDS	76949	77153	.	+	1	ID=CDS:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	CDS	77713	77799	.	+	0	ID=CDS:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	CDS	79313	79447	.	+	0	ID=CDS:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	CDS	80306	80344	.	+	0	ID=CDS:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	three_prime_UTR	80345	80561	.	+	.	ID=three_prime_UTR:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	three_prime_UTR	80814	81063	.	+	.	ID=three_prime_UTR:Gene:Y48G1C.2.1.2;Parent=Transcript:Gene:Y48G1C.2.1.2
+I	Coding_transcript	mRNA	72511	80344	.	+	.	ID=Transcript:Gene:Y48G1C.2.1.3;Parent=Gene:Gene:Y48G1C.2.1
+I	Coding_transcript	five_prime_UTR	72511	72590	.	+	.	ID=five_prime_UTR:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	five_prime_UTR	72647	72648	.	+	.	ID=five_prime_UTR:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	CDS	72649	72897	.	+	0	ID=CDS:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	CDS	72941	73017	.	+	0	ID=CDS:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	CDS	73605	73766	.	+	1	ID=CDS:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	CDS	74625	74808	.	+	1	ID=CDS:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	CDS	75171	75490	.	+	0	ID=CDS:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	CDS	75951	76112	.	+	1	ID=CDS:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	CDS	76949	77153	.	+	1	ID=CDS:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	CDS	77713	77799	.	+	0	ID=CDS:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	CDS	79313	79447	.	+	0	ID=CDS:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	CDS	80306	80344	.	+	0	ID=CDS:Gene:Y48G1C.2.1.3;Parent=Transcript:Gene:Y48G1C.2.1.3
+I	Coding_transcript	gene	86841	90607	.	+	.	ID=Gene:Gene:Y48G1C.11
+I	Coding_transcript	mRNA	86841	90607	.	+	.	ID=Transcript:Gene:Y48G1C.11.1;Parent=Gene:Gene:Y48G1C.11
+I	Coding_transcript	CDS	86841	86904	.	+	0	ID=CDS:Gene:Y48G1C.11.1;Parent=Transcript:Gene:Y48G1C.11.1
+I	Coding_transcript	CDS	87034	87223	.	+	2	ID=CDS:Gene:Y48G1C.11.1;Parent=Transcript:Gene:Y48G1C.11.1
+I	Coding_transcript	CDS	87520	87734	.	+	1	ID=CDS:Gene:Y48G1C.11.1;Parent=Transcript:Gene:Y48G1C.11.1
+I	Coding_transcript	CDS	88268	88500	.	+	2	ID=CDS:Gene:Y48G1C.11.1;Parent=Transcript:Gene:Y48G1C.11.1
+I	Coding_transcript	CDS	88566	88706	.	+	0	ID=CDS:Gene:Y48G1C.11.1;Parent=Transcript:Gene:Y48G1C.11.1
+I	Coding_transcript	CDS	89372	89584	.	+	0	ID=CDS:Gene:Y48G1C.11.1;Parent=Transcript:Gene:Y48G1C.11.1
+I	Coding_transcript	CDS	90419	90607	.	+	0	ID=CDS:Gene:Y48G1C.11.1;Parent=Transcript:Gene:Y48G1C.11.1
+I	Coding_transcript	gene	91380	92877	.	+	.	ID=Gene:Gene:Y48G1C.9.1
+I	Coding_transcript	mRNA	91380	92654	.	+	.	ID=Transcript:Gene:Y48G1C.9.1.1;Parent=Gene:Gene:Y48G1C.9.1
+I	Coding_transcript	five_prime_UTR	91380	91408	.	+	.	ID=five_prime_UTR:Gene:Y48G1C.9.1.1;Parent=Transcript:Gene:Y48G1C.9.1.1
+I	Coding_transcript	CDS	91409	91594	.	+	0	ID=CDS:Gene:Y48G1C.9.1.1;Parent=Transcript:Gene:Y48G1C.9.1.1
+I	Coding_transcript	CDS	92523	92648	.	+	0	ID=CDS:Gene:Y48G1C.9.1.1;Parent=Transcript:Gene:Y48G1C.9.1.1
+I	Coding_transcript	three_prime_UTR	92649	92654	.	+	.	ID=three_prime_UTR:Gene:Y48G1C.9.1.1;Parent=Transcript:Gene:Y48G1C.9.1.1
+I	Coding_transcript	mRNA	91404	92877	.	+	.	ID=Transcript:Gene:Y48G1C.9.1.2;Parent=Gene:Gene:Y48G1C.9.1
+I	Coding_transcript	five_prime_UTR	91404	91408	.	+	.	ID=five_prime_UTR:Gene:Y48G1C.9.1.2;Parent=Transcript:Gene:Y48G1C.9.1.2
+I	Coding_transcript	CDS	91409	91594	.	+	0	ID=CDS:Gene:Y48G1C.9.1.2;Parent=Transcript:Gene:Y48G1C.9.1.2
+I	Coding_transcript	CDS	92523	92648	.	+	0	ID=CDS:Gene:Y48G1C.9.1.2;Parent=Transcript:Gene:Y48G1C.9.1.2
+I	Coding_transcript	three_prime_UTR	92649	92877	.	+	.	ID=three_prime_UTR:Gene:Y48G1C.9.1.2;Parent=Transcript:Gene:Y48G1C.9.1.2
+I	Coding_transcript	gene	113807	114681	.	+	.	ID=Gene:Gene:F53G12.8
+I	Coding_transcript	mRNA	113807	114681	.	+	.	ID=Transcript:Gene:F53G12.8.1;Parent=Gene:Gene:F53G12.8
+I	Coding_transcript	CDS	113807	113863	.	+	0	ID=CDS:Gene:F53G12.8.1;Parent=Transcript:Gene:F53G12.8.1
+I	Coding_transcript	CDS	114085	114423	.	+	0	ID=CDS:Gene:F53G12.8.1;Parent=Transcript:Gene:F53G12.8.1
+I	Coding_transcript	CDS	114544	114681	.	+	0	ID=CDS:Gene:F53G12.8.1;Parent=Transcript:Gene:F53G12.8.1
+I	Coding_transcript	gene	115739	117438	.	+	.	ID=Gene:Gene:F53G12.7
+I	Coding_transcript	mRNA	115739	117438	.	+	.	ID=Transcript:Gene:F53G12.7.1;Parent=Gene:Gene:F53G12.7
+I	Coding_transcript	CDS	115739	115915	.	+	0	ID=CDS:Gene:F53G12.7.1;Parent=Transcript:Gene:F53G12.7.1
+I	Coding_transcript	CDS	116432	116666	.	+	0	ID=CDS:Gene:F53G12.7.1;Parent=Transcript:Gene:F53G12.7.1
+I	Coding_transcript	CDS	116719	116974	.	+	2	ID=CDS:Gene:F53G12.7.1;Parent=Transcript:Gene:F53G12.7.1
+I	Coding_transcript	CDS	117086	117401	.	+	1	ID=CDS:Gene:F53G12.7.1;Parent=Transcript:Gene:F53G12.7.1
+I	Coding_transcript	three_prime_UTR	117402	117438	.	+	.	ID=three_prime_UTR:Gene:F53G12.7.1;Parent=Transcript:Gene:F53G12.7.1
+I	Coding_transcript	gene	127297	134263	.	+	.	ID=Gene:Gene:F53G12.5b
+I	Coding_transcript	mRNA	127297	134263	.	+	.	ID=Transcript:Gene:F53G12.5b.1;Parent=Gene:Gene:F53G12.5b
+I	Coding_transcript	CDS	127297	127336	.	+	0	ID=CDS:Gene:F53G12.5b.1;Parent=Transcript:Gene:F53G12.5b.1
+I	Coding_transcript	CDS	127385	127436	.	+	2	ID=CDS:Gene:F53G12.5b.1;Parent=Transcript:Gene:F53G12.5b.1
+I	Coding_transcript	CDS	128697	128896	.	+	1	ID=CDS:Gene:F53G12.5b.1;Parent=Transcript:Gene:F53G12.5b.1
+I	Coding_transcript	CDS	128945	129124	.	+	2	ID=CDS:Gene:F53G12.5b.1;Parent=Transcript:Gene:F53G12.5b.1
+I	Coding_transcript	CDS	129176	129333	.	+	2	ID=CDS:Gene:F53G12.5b.1;Parent=Transcript:Gene:F53G12.5b.1
+I	Coding_transcript	CDS	132103	132553	.	+	0	ID=CDS:Gene:F53G12.5b.1;Parent=Transcript:Gene:F53G12.5b.1
+I	Coding_transcript	CDS	132612	132693	.	+	2	ID=CDS:Gene:F53G12.5b.1;Parent=Transcript:Gene:F53G12.5b.1
+I	Coding_transcript	CDS	133414	133582	.	+	1	ID=CDS:Gene:F53G12.5b.1;Parent=Transcript:Gene:F53G12.5b.1
+I	Coding_transcript	three_prime_UTR	133583	134263	.	+	.	ID=three_prime_UTR:Gene:F53G12.5b.1;Parent=Transcript:Gene:F53G12.5b.1
+I	Coding_transcript	mRNA	128693	133809	.	+	.	ID=Transcript:Gene:F53G12.5b.2;Parent=Gene:Gene:F53G12.5b
+I	Coding_transcript	five_prime_UTR	128693	128697	.	+	.	ID=five_prime_UTR:Gene:F53G12.5b.2;Parent=Transcript:Gene:F53G12.5b.2
+I	Coding_transcript	CDS	128698	128896	.	+	0	ID=CDS:Gene:F53G12.5b.2;Parent=Transcript:Gene:F53G12.5b.2
+I	Coding_transcript	CDS	128945	129124	.	+	2	ID=CDS:Gene:F53G12.5b.2;Parent=Transcript:Gene:F53G12.5b.2
+I	Coding_transcript	CDS	129167	129333	.	+	2	ID=CDS:Gene:F53G12.5b.2;Parent=Transcript:Gene:F53G12.5b.2
+I	Coding_transcript	CDS	132103	132553	.	+	0	ID=CDS:Gene:F53G12.5b.2;Parent=Transcript:Gene:F53G12.5b.2
+I	Coding_transcript	CDS	132612	132693	.	+	2	ID=CDS:Gene:F53G12.5b.2;Parent=Transcript:Gene:F53G12.5b.2
+I	Coding_transcript	CDS	133414	133582	.	+	1	ID=CDS:Gene:F53G12.5b.2;Parent=Transcript:Gene:F53G12.5b.2
+I	Coding_transcript	three_prime_UTR	133583	133809	.	+	.	ID=three_prime_UTR:Gene:F53G12.5b.2;Parent=Transcript:Gene:F53G12.5b.2
+I	Coding_transcript	mRNA	128697	133582	.	+	.	ID=Transcript:Gene:F53G12.5b.3;Parent=Gene:Gene:F53G12.5b
+I	Coding_transcript	five_prime_UTR	128697	128697	.	+	.	ID=five_prime_UTR:Gene:F53G12.5b.3;Parent=Transcript:Gene:F53G12.5b.3
+I	Coding_transcript	CDS	128698	128896	.	+	0	ID=CDS:Gene:F53G12.5b.3;Parent=Transcript:Gene:F53G12.5b.3
+I	Coding_transcript	CDS	128945	129124	.	+	2	ID=CDS:Gene:F53G12.5b.3;Parent=Transcript:Gene:F53G12.5b.3
+I	Coding_transcript	CDS	129167	129333	.	+	2	ID=CDS:Gene:F53G12.5b.3;Parent=Transcript:Gene:F53G12.5b.3
+I	Coding_transcript	CDS	132103	132553	.	+	0	ID=CDS:Gene:F53G12.5b.3;Parent=Transcript:Gene:F53G12.5b.3
+I	Coding_transcript	CDS	132612	132693	.	+	2	ID=CDS:Gene:F53G12.5b.3;Parent=Transcript:Gene:F53G12.5b.3
+I	Coding_transcript	CDS	133414	133582	.	+	1	ID=CDS:Gene:F53G12.5b.3;Parent=Transcript:Gene:F53G12.5b.3
+I	Coding_transcript	gene	134337	137282	.	+	.	ID=Gene:Gene:F53G12.4
+I	Coding_transcript	mRNA	134337	137282	.	+	.	ID=Transcript:Gene:F53G12.4.1;Parent=Gene:Gene:F53G12.4
+I	Coding_transcript	five_prime_UTR	134337	134353	.	+	.	ID=five_prime_UTR:Gene:F53G12.4.1;Parent=Transcript:Gene:F53G12.4.1
+I	Coding_transcript	CDS	134354	134428	.	+	0	ID=CDS:Gene:F53G12.4.1;Parent=Transcript:Gene:F53G12.4.1
+I	Coding_transcript	CDS	134506	134581	.	+	0	ID=CDS:Gene:F53G12.4.1;Parent=Transcript:Gene:F53G12.4.1
+I	Coding_transcript	CDS	135549	135898	.	+	2	ID=CDS:Gene:F53G12.4.1;Parent=Transcript:Gene:F53G12.4.1
+I	Coding_transcript	CDS	136235	136712	.	+	0	ID=CDS:Gene:F53G12.4.1;Parent=Transcript:Gene:F53G12.4.1
+I	Coding_transcript	CDS	137209	137282	.	+	2	ID=CDS:Gene:F53G12.4.1;Parent=Transcript:Gene:F53G12.4.1
+I	Coding_transcript	gene	137845	144565	.	+	.	ID=Gene:Gene:F53G12.3
+I	Coding_transcript	mRNA	137845	144565	.	+	.	ID=Transcript:Gene:F53G12.3.1;Parent=Gene:Gene:F53G12.3
+I	Coding_transcript	CDS	137845	137886	.	+	0	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	138017	138143	.	+	0	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	138193	138351	.	+	2	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	138393	138782	.	+	2	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	138829	139032	.	+	2	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	139080	139331	.	+	2	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	139378	139669	.	+	2	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	139769	139982	.	+	1	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	140136	140292	.	+	0	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	140371	140496	.	+	2	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	140554	140870	.	+	2	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	140916	141213	.	+	0	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	141681	141854	.	+	2	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	141900	142023	.	+	2	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	142067	142230	.	+	1	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	142278	142477	.	+	2	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	142547	142671	.	+	0	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	142729	142939	.	+	1	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	143007	143684	.	+	0	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	144265	144396	.	+	0	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	CDS	144440	144565	.	+	0	ID=CDS:Gene:F53G12.3.1;Parent=Transcript:Gene:F53G12.3.1
+I	Coding_transcript	gene	173412	175988	.	+	.	ID=Gene:Gene:F56C11.6b
+I	Coding_transcript	mRNA	173412	175932	.	+	.	ID=Transcript:Gene:F56C11.6b.1;Parent=Gene:Gene:F56C11.6b
+I	Coding_transcript	five_prime_UTR	173412	173508	.	+	.	ID=five_prime_UTR:Gene:F56C11.6b.1;Parent=Transcript:Gene:F56C11.6b.1
+I	Coding_transcript	five_prime_UTR	173561	173725	.	+	.	ID=five_prime_UTR:Gene:F56C11.6b.1;Parent=Transcript:Gene:F56C11.6b.1
+I	Coding_transcript	five_prime_UTR	173775	173873	.	+	.	ID=five_prime_UTR:Gene:F56C11.6b.1;Parent=Transcript:Gene:F56C11.6b.1
+I	Coding_transcript	CDS	173874	174312	.	+	0	ID=CDS:Gene:F56C11.6b.1;Parent=Transcript:Gene:F56C11.6b.1
+I	Coding_transcript	CDS	174605	174832	.	+	2	ID=CDS:Gene:F56C11.6b.1;Parent=Transcript:Gene:F56C11.6b.1
+I	Coding_transcript	CDS	174878	175053	.	+	2	ID=CDS:Gene:F56C11.6b.1;Parent=Transcript:Gene:F56C11.6b.1
+I	Coding_transcript	CDS	175097	175241	.	+	0	ID=CDS:Gene:F56C11.6b.1;Parent=Transcript:Gene:F56C11.6b.1
+I	Coding_transcript	CDS	175579	175708	.	+	2	ID=CDS:Gene:F56C11.6b.1;Parent=Transcript:Gene:F56C11.6b.1
+I	Coding_transcript	CDS	175755	175932	.	+	1	ID=CDS:Gene:F56C11.6b.1;Parent=Transcript:Gene:F56C11.6b.1
+I	Coding_transcript	mRNA	173412	175988	.	+	.	ID=Transcript:Gene:F56C11.6b.2;Parent=Gene:Gene:F56C11.6b
+I	Coding_transcript	five_prime_UTR	173412	173421	.	+	.	ID=five_prime_UTR:Gene:F56C11.6b.2;Parent=Transcript:Gene:F56C11.6b.2
+I	Coding_transcript	CDS	173422	173508	.	+	0	ID=CDS:Gene:F56C11.6b.2;Parent=Transcript:Gene:F56C11.6b.2
+I	Coding_transcript	CDS	173561	173725	.	+	0	ID=CDS:Gene:F56C11.6b.2;Parent=Transcript:Gene:F56C11.6b.2
+I	Coding_transcript	CDS	173775	174312	.	+	0	ID=CDS:Gene:F56C11.6b.2;Parent=Transcript:Gene:F56C11.6b.2
+I	Coding_transcript	CDS	174605	174832	.	+	2	ID=CDS:Gene:F56C11.6b.2;Parent=Transcript:Gene:F56C11.6b.2
+I	Coding_transcript	CDS	174878	175053	.	+	2	ID=CDS:Gene:F56C11.6b.2;Parent=Transcript:Gene:F56C11.6b.2
+I	Coding_transcript	CDS	175097	175241	.	+	0	ID=CDS:Gene:F56C11.6b.2;Parent=Transcript:Gene:F56C11.6b.2
+I	Coding_transcript	CDS	175579	175708	.	+	2	ID=CDS:Gene:F56C11.6b.2;Parent=Transcript:Gene:F56C11.6b.2
+I	Coding_transcript	CDS	175755	175932	.	+	1	ID=CDS:Gene:F56C11.6b.2;Parent=Transcript:Gene:F56C11.6b.2
+I	Coding_transcript	three_prime_UTR	175933	175988	.	+	.	ID=three_prime_UTR:Gene:F56C11.6b.2;Parent=Transcript:Gene:F56C11.6b.2
+I	Coding_transcript	gene	178538	182159	.	+	.	ID=Gene:Gene:F56C11.5b
+I	Coding_transcript	mRNA	178538	182159	.	+	.	ID=Transcript:Gene:F56C11.5b.1;Parent=Gene:Gene:F56C11.5b
+I	Coding_transcript	five_prime_UTR	178538	178566	.	+	.	ID=five_prime_UTR:Gene:F56C11.5b.1;Parent=Transcript:Gene:F56C11.5b.1
+I	Coding_transcript	CDS	178567	178620	.	+	0	ID=CDS:Gene:F56C11.5b.1;Parent=Transcript:Gene:F56C11.5b.1
+I	Coding_transcript	CDS	180600	180698	.	+	0	ID=CDS:Gene:F56C11.5b.1;Parent=Transcript:Gene:F56C11.5b.1
+I	Coding_transcript	CDS	181251	181514	.	+	0	ID=CDS:Gene:F56C11.5b.1;Parent=Transcript:Gene:F56C11.5b.1
+I	Coding_transcript	CDS	181663	181767	.	+	0	ID=CDS:Gene:F56C11.5b.1;Parent=Transcript:Gene:F56C11.5b.1
+I	Coding_transcript	CDS	181814	181966	.	+	0	ID=CDS:Gene:F56C11.5b.1;Parent=Transcript:Gene:F56C11.5b.1
+I	Coding_transcript	three_prime_UTR	181967	182159	.	+	.	ID=three_prime_UTR:Gene:F56C11.5b.1;Parent=Transcript:Gene:F56C11.5b.1
+I	Coding_transcript	mRNA	180394	181966	.	+	.	ID=Transcript:Gene:F56C11.5b.2;Parent=Gene:Gene:F56C11.5b
+I	Coding_transcript	CDS	180394	180465	.	+	0	ID=CDS:Gene:F56C11.5b.2;Parent=Transcript:Gene:F56C11.5b.2
+I	Coding_transcript	CDS	180600	180698	.	+	0	ID=CDS:Gene:F56C11.5b.2;Parent=Transcript:Gene:F56C11.5b.2
+I	Coding_transcript	CDS	181251	181514	.	+	0	ID=CDS:Gene:F56C11.5b.2;Parent=Transcript:Gene:F56C11.5b.2
+I	Coding_transcript	CDS	181663	181767	.	+	0	ID=CDS:Gene:F56C11.5b.2;Parent=Transcript:Gene:F56C11.5b.2
+I	Coding_transcript	CDS	181814	181966	.	+	0	ID=CDS:Gene:F56C11.5b.2;Parent=Transcript:Gene:F56C11.5b.2
+I	Coding_transcript	gene	216005	219099	.	+	.	ID=Gene:Gene:Y48G1BL.1
+I	Coding_transcript	mRNA	216005	219099	.	+	.	ID=Transcript:Gene:Y48G1BL.1.1;Parent=Gene:Gene:Y48G1BL.1
+I	Coding_transcript	five_prime_UTR	216005	216092	.	+	.	ID=five_prime_UTR:Gene:Y48G1BL.1.1;Parent=Transcript:Gene:Y48G1BL.1.1
+I	Coding_transcript	five_prime_UTR	216145	216180	.	+	.	ID=five_prime_UTR:Gene:Y48G1BL.1.1;Parent=Transcript:Gene:Y48G1BL.1.1
+I	Coding_transcript	CDS	216181	216277	.	+	0	ID=CDS:Gene:Y48G1BL.1.1;Parent=Transcript:Gene:Y48G1BL.1.1
+I	Coding_transcript	CDS	216331	216910	.	+	2	ID=CDS:Gene:Y48G1BL.1.1;Parent=Transcript:Gene:Y48G1BL.1.1
+I	Coding_transcript	CDS	218110	218205	.	+	1	ID=CDS:Gene:Y48G1BL.1.1;Parent=Transcript:Gene:Y48G1BL.1.1
+I	Coding_transcript	CDS	218772	218955	.	+	1	ID=CDS:Gene:Y48G1BL.1.1;Parent=Transcript:Gene:Y48G1BL.1.1
+I	Coding_transcript	three_prime_UTR	218956	219099	.	+	.	ID=three_prime_UTR:Gene:Y48G1BL.1.1;Parent=Transcript:Gene:Y48G1BL.1.1
+I	Coding_transcript	gene	291216	305461	.	+	.	ID=Gene:Gene:C53D5.1c.1
+I	Coding_transcript	mRNA	291216	305081	.	+	.	ID=Transcript:Gene:C53D5.1c.1.1;Parent=Gene:Gene:C53D5.1c.1
+I	Coding_transcript	five_prime_UTR	291216	291308	.	+	.	ID=five_prime_UTR:Gene:C53D5.1c.1.1;Parent=Transcript:Gene:C53D5.1c.1.1
+I	Coding_transcript	five_prime_UTR	295793	295851	.	+	.	ID=five_prime_UTR:Gene:C53D5.1c.1.1;Parent=Transcript:Gene:C53D5.1c.1.1
+I	Coding_transcript	five_prime_UTR	302596	302671	.	+	.	ID=five_prime_UTR:Gene:C53D5.1c.1.1;Parent=Transcript:Gene:C53D5.1c.1.1
+I	Coding_transcript	CDS	302672	302705	.	+	0	ID=CDS:Gene:C53D5.1c.1.1;Parent=Transcript:Gene:C53D5.1c.1.1
+I	Coding_transcript	CDS	302762	302831	.	+	2	ID=CDS:Gene:C53D5.1c.1.1;Parent=Transcript:Gene:C53D5.1c.1.1
+I	Coding_transcript	CDS	303204	303729	.	+	1	ID=CDS:Gene:C53D5.1c.1.1;Parent=Transcript:Gene:C53D5.1c.1.1
+I	Coding_transcript	CDS	303789	303910	.	+	0	ID=CDS:Gene:C53D5.1c.1.1;Parent=Transcript:Gene:C53D5.1c.1.1
+I	Coding_transcript	CDS	304094	304256	.	+	1	ID=CDS:Gene:C53D5.1c.1.1;Parent=Transcript:Gene:C53D5.1c.1.1
+I	Coding_transcript	CDS	304929	305081	.	+	0	ID=CDS:Gene:C53D5.1c.1.1;Parent=Transcript:Gene:C53D5.1c.1.1
+I	Coding_transcript	mRNA	291216	305461	.	+	.	ID=Transcript:Gene:C53D5.1c.1.2;Parent=Gene:Gene:C53D5.1c.1
+I	Coding_transcript	five_prime_UTR	291216	291248	.	+	.	ID=five_prime_UTR:Gene:C53D5.1c.1.2;Parent=Transcript:Gene:C53D5.1c.1.2
+I	Coding_transcript	CDS	291249	291308	.	+	0	ID=CDS:Gene:C53D5.1c.1.2;Parent=Transcript:Gene:C53D5.1c.1.2
+I	Coding_transcript	CDS	295793	295851	.	+	0	ID=CDS:Gene:C53D5.1c.1.2;Parent=Transcript:Gene:C53D5.1c.1.2
+I	Coding_transcript	CDS	302596	302705	.	+	1	ID=CDS:Gene:C53D5.1c.1.2;Parent=Transcript:Gene:C53D5.1c.1.2
+I	Coding_transcript	CDS	302762	302831	.	+	2	ID=CDS:Gene:C53D5.1c.1.2;Parent=Transcript:Gene:C53D5.1c.1.2
+I	Coding_transcript	CDS	303204	303729	.	+	1	ID=CDS:Gene:C53D5.1c.1.2;Parent=Transcript:Gene:C53D5.1c.1.2
+I	Coding_transcript	CDS	303789	303910	.	+	0	ID=CDS:Gene:C53D5.1c.1.2;Parent=Transcript:Gene:C53D5.1c.1.2
+I	Coding_transcript	CDS	304094	304256	.	+	1	ID=CDS:Gene:C53D5.1c.1.2;Parent=Transcript:Gene:C53D5.1c.1.2
+I	Coding_transcript	CDS	304929	305081	.	+	0	ID=CDS:Gene:C53D5.1c.1.2;Parent=Transcript:Gene:C53D5.1c.1.2
+I	Coding_transcript	three_prime_UTR	305082	305461	.	+	.	ID=three_prime_UTR:Gene:C53D5.1c.1.2;Parent=Transcript:Gene:C53D5.1c.1.2
+I	Coding_transcript	mRNA	295364	305081	.	+	.	ID=Transcript:Gene:C53D5.1c.1.3;Parent=Gene:Gene:C53D5.1c.1
+I	Coding_transcript	five_prime_UTR	295364	295367	.	+	.	ID=five_prime_UTR:Gene:C53D5.1c.1.3;Parent=Transcript:Gene:C53D5.1c.1.3
+I	Coding_transcript	CDS	295368	295421	.	+	0	ID=CDS:Gene:C53D5.1c.1.3;Parent=Transcript:Gene:C53D5.1c.1.3
+I	Coding_transcript	CDS	295793	295851	.	+	0	ID=CDS:Gene:C53D5.1c.1.3;Parent=Transcript:Gene:C53D5.1c.1.3
+I	Coding_transcript	CDS	302596	302705	.	+	1	ID=CDS:Gene:C53D5.1c.1.3;Parent=Transcript:Gene:C53D5.1c.1.3
+I	Coding_transcript	CDS	302762	302831	.	+	2	ID=CDS:Gene:C53D5.1c.1.3;Parent=Transcript:Gene:C53D5.1c.1.3
+I	Coding_transcript	CDS	303204	303729	.	+	1	ID=CDS:Gene:C53D5.1c.1.3;Parent=Transcript:Gene:C53D5.1c.1.3
+I	Coding_transcript	CDS	303789	303910	.	+	0	ID=CDS:Gene:C53D5.1c.1.3;Parent=Transcript:Gene:C53D5.1c.1.3
+I	Coding_transcript	CDS	304094	304256	.	+	1	ID=CDS:Gene:C53D5.1c.1.3;Parent=Transcript:Gene:C53D5.1c.1.3
+I	Coding_transcript	CDS	304929	305081	.	+	0	ID=CDS:Gene:C53D5.1c.1.3;Parent=Transcript:Gene:C53D5.1c.1.3
+I	Coding_transcript	mRNA	302596	305081	.	+	.	ID=Transcript:Gene:C53D5.1c.1.4;Parent=Gene:Gene:C53D5.1c.1
+I	Coding_transcript	five_prime_UTR	302596	302671	.	+	.	ID=five_prime_UTR:Gene:C53D5.1c.1.4;Parent=Transcript:Gene:C53D5.1c.1.4
+I	Coding_transcript	CDS	302672	302705	.	+	0	ID=CDS:Gene:C53D5.1c.1.4;Parent=Transcript:Gene:C53D5.1c.1.4
+I	Coding_transcript	CDS	302762	302831	.	+	2	ID=CDS:Gene:C53D5.1c.1.4;Parent=Transcript:Gene:C53D5.1c.1.4
+I	Coding_transcript	CDS	303204	303729	.	+	1	ID=CDS:Gene:C53D5.1c.1.4;Parent=Transcript:Gene:C53D5.1c.1.4
+I	Coding_transcript	CDS	303789	303910	.	+	0	ID=CDS:Gene:C53D5.1c.1.4;Parent=Transcript:Gene:C53D5.1c.1.4
+I	Coding_transcript	CDS	304094	304256	.	+	1	ID=CDS:Gene:C53D5.1c.1.4;Parent=Transcript:Gene:C53D5.1c.1.4
+I	Coding_transcript	CDS	304929	305081	.	+	0	ID=CDS:Gene:C53D5.1c.1.4;Parent=Transcript:Gene:C53D5.1c.1.4
+I	Coding_transcript	gene	347484	348360	.	+	.	ID=Gene:Gene:Y48G1A.2
+I	Coding_transcript	mRNA	347484	348360	.	+	.	ID=Transcript:Gene:Y48G1A.2.1;Parent=Gene:Gene:Y48G1A.2
+I	Coding_transcript	five_prime_UTR	347484	347577	.	+	.	ID=five_prime_UTR:Gene:Y48G1A.2.1;Parent=Transcript:Gene:Y48G1A.2.1
+I	Coding_transcript	CDS	347578	347584	.	+	0	ID=CDS:Gene:Y48G1A.2.1;Parent=Transcript:Gene:Y48G1A.2.1
+I	Coding_transcript	CDS	347633	347709	.	+	2	ID=CDS:Gene:Y48G1A.2.1;Parent=Transcript:Gene:Y48G1A.2.1
+I	Coding_transcript	CDS	347765	347986	.	+	0	ID=CDS:Gene:Y48G1A.2.1;Parent=Transcript:Gene:Y48G1A.2.1
+I	Coding_transcript	CDS	348045	348152	.	+	0	ID=CDS:Gene:Y48G1A.2.1;Parent=Transcript:Gene:Y48G1A.2.1
+I	Coding_transcript	three_prime_UTR	348153	348360	.	+	.	ID=three_prime_UTR:Gene:Y48G1A.2.1;Parent=Transcript:Gene:Y48G1A.2.1
+I	Coding_transcript	gene	364522	368511	.	+	.	ID=Gene:Gene:R119.7
+I	Coding_transcript	mRNA	364522	368511	.	+	.	ID=Transcript:Gene:R119.7.1;Parent=Gene:Gene:R119.7
+I	Coding_transcript	CDS	364522	364682	.	+	0	ID=CDS:Gene:R119.7.1;Parent=Transcript:Gene:R119.7.1
+I	Coding_transcript	CDS	364739	365194	.	+	1	ID=CDS:Gene:R119.7.1;Parent=Transcript:Gene:R119.7.1
+I	Coding_transcript	CDS	365534	365599	.	+	1	ID=CDS:Gene:R119.7.1;Parent=Transcript:Gene:R119.7.1
+I	Coding_transcript	CDS	365647	365963	.	+	1	ID=CDS:Gene:R119.7.1;Parent=Transcript:Gene:R119.7.1
+I	Coding_transcript	CDS	366656	367212	.	+	2	ID=CDS:Gene:R119.7.1;Parent=Transcript:Gene:R119.7.1
+I	Coding_transcript	CDS	367749	367943	.	+	0	ID=CDS:Gene:R119.7.1;Parent=Transcript:Gene:R119.7.1
+I	Coding_transcript	three_prime_UTR	367944	368511	.	+	.	ID=three_prime_UTR:Gene:R119.7.1;Parent=Transcript:Gene:R119.7.1
+I	Coding_transcript	gene	382836	388540	.	+	.	ID=Gene:Gene:R119.6
+I	Coding_transcript	mRNA	382836	388540	.	+	.	ID=Transcript:Gene:R119.6.1;Parent=Gene:Gene:R119.6
+I	Coding_transcript	CDS	382836	382916	.	+	0	ID=CDS:Gene:R119.6.1;Parent=Transcript:Gene:R119.6.1
+I	Coding_transcript	CDS	382992	383067	.	+	0	ID=CDS:Gene:R119.6.1;Parent=Transcript:Gene:R119.6.1
+I	Coding_transcript	CDS	383124	383377	.	+	2	ID=CDS:Gene:R119.6.1;Parent=Transcript:Gene:R119.6.1
+I	Coding_transcript	CDS	383432	383567	.	+	0	ID=CDS:Gene:R119.6.1;Parent=Transcript:Gene:R119.6.1
+I	Coding_transcript	CDS	384628	385228	.	+	2	ID=CDS:Gene:R119.6.1;Parent=Transcript:Gene:R119.6.1
+I	Coding_transcript	CDS	386079	386339	.	+	1	ID=CDS:Gene:R119.6.1;Parent=Transcript:Gene:R119.6.1
+I	Coding_transcript	CDS	388049	388153	.	+	1	ID=CDS:Gene:R119.6.1;Parent=Transcript:Gene:R119.6.1
+I	Coding_transcript	CDS	388380	388437	.	+	1	ID=CDS:Gene:R119.6.1;Parent=Transcript:Gene:R119.6.1
+I	Coding_transcript	three_prime_UTR	388438	388540	.	+	.	ID=three_prime_UTR:Gene:R119.6.1;Parent=Transcript:Gene:R119.6.1
+I	Coding_transcript	gene	488619	489908	.	+	.	ID=Gene:Gene:W04C9.2
+I	Coding_transcript	mRNA	488619	489908	.	+	.	ID=Transcript:Gene:W04C9.2.1;Parent=Gene:Gene:W04C9.2
+I	Coding_transcript	CDS	488619	488726	.	+	0	ID=CDS:Gene:W04C9.2.1;Parent=Transcript:Gene:W04C9.2.1
+I	Coding_transcript	CDS	488771	488836	.	+	0	ID=CDS:Gene:W04C9.2.1;Parent=Transcript:Gene:W04C9.2.1
+I	Coding_transcript	CDS	488885	488947	.	+	0	ID=CDS:Gene:W04C9.2.1;Parent=Transcript:Gene:W04C9.2.1
+I	Coding_transcript	CDS	489703	489774	.	+	0	ID=CDS:Gene:W04C9.2.1;Parent=Transcript:Gene:W04C9.2.1
+I	Coding_transcript	three_prime_UTR	489775	489908	.	+	.	ID=three_prime_UTR:Gene:W04C9.2.1;Parent=Transcript:Gene:W04C9.2.1
+I	Coding_transcript	gene	489987	496153	.	+	.	ID=Gene:Gene:W04C9.1
+I	Coding_transcript	mRNA	489987	496153	.	+	.	ID=Transcript:Gene:W04C9.1.1;Parent=Gene:Gene:W04C9.1
+I	Coding_transcript	five_prime_UTR	489987	490053	.	+	.	ID=five_prime_UTR:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	CDS	490054	490205	.	+	0	ID=CDS:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	CDS	491200	491305	.	+	1	ID=CDS:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	CDS	491353	491562	.	+	0	ID=CDS:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	CDS	491613	491727	.	+	0	ID=CDS:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	CDS	491839	492163	.	+	2	ID=CDS:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	CDS	492228	492354	.	+	1	ID=CDS:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	CDS	492870	493559	.	+	0	ID=CDS:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	CDS	494263	494346	.	+	0	ID=CDS:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	CDS	494395	494709	.	+	0	ID=CDS:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	CDS	495831	496070	.	+	0	ID=CDS:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	three_prime_UTR	496071	496153	.	+	.	ID=three_prime_UTR:Gene:W04C9.1.1;Parent=Transcript:Gene:W04C9.1.1
+I	Coding_transcript	gene	534461	535347	.	+	.	ID=Gene:Gene:Y65B4BR.8
+I	Coding_transcript	mRNA	534461	535347	.	+	.	ID=Transcript:Gene:Y65B4BR.8.1;Parent=Gene:Gene:Y65B4BR.8
+I	Coding_transcript	CDS	534461	534572	.	+	0	ID=CDS:Gene:Y65B4BR.8.1;Parent=Transcript:Gene:Y65B4BR.8.1
+I	Coding_transcript	CDS	534621	534727	.	+	2	ID=CDS:Gene:Y65B4BR.8.1;Parent=Transcript:Gene:Y65B4BR.8.1
+I	Coding_transcript	CDS	534775	534973	.	+	0	ID=CDS:Gene:Y65B4BR.8.1;Parent=Transcript:Gene:Y65B4BR.8.1
+I	Coding_transcript	CDS	535034	535197	.	+	2	ID=CDS:Gene:Y65B4BR.8.1;Parent=Transcript:Gene:Y65B4BR.8.1
+I	Coding_transcript	three_prime_UTR	535198	535347	.	+	.	ID=three_prime_UTR:Gene:Y65B4BR.8.1;Parent=Transcript:Gene:Y65B4BR.8.1
+I	Coding_transcript	gene	2931462	2947153	.	+	.	ID=Gene:Gene:Y71F9AM.4a
+I	Coding_transcript	mRNA	2931462	2947153	.	+	.	ID=Transcript:Gene:Y71F9AM.4a.1;Parent=Gene:Gene:Y71F9AM.4a
+I	Coding_transcript	CDS	2931462	2931549	.	+	0	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2931617	2931783	.	+	2	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2932810	2932974	.	+	0	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2933904	2934137	.	+	0	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2935626	2935717	.	+	0	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2935988	2936131	.	+	1	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2936561	2936882	.	+	1	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2937759	2937919	.	+	0	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2938443	2938677	.	+	1	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2942825	2943021	.	+	0	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2943072	2943204	.	+	1	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2944077	2944223	.	+	0	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2944275	2944382	.	+	0	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	CDS	2946747	2946938	.	+	0	ID=CDS:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	three_prime_UTR	2946939	2947153	.	+	.	ID=three_prime_UTR:Gene:Y71F9AM.4a.1;Parent=Transcript:Gene:Y71F9AM.4a.1
+I	Coding_transcript	mRNA	2935624	2944611	.	+	.	ID=Transcript:Gene:Y71F9AM.4a.2;Parent=Gene:Gene:Y71F9AM.4a
+I	Coding_transcript	five_prime_UTR	2935624	2935717	.	+	.	ID=five_prime_UTR:Gene:Y71F9AM.4a.2;Parent=Transcript:Gene:Y71F9AM.4a.2
+I	Coding_transcript	five_prime_UTR	2935988	2936042	.	+	.	ID=five_prime_UTR:Gene:Y71F9AM.4a.2;Parent=Transcript:Gene:Y71F9AM.4a.2
+I	Coding_transcript	CDS	2936043	2936131	.	+	0	ID=CDS:Gene:Y71F9AM.4a.2;Parent=Transcript:Gene:Y71F9AM.4a.2
+I	Coding_transcript	CDS	2936561	2936882	.	+	1	ID=CDS:Gene:Y71F9AM.4a.2;Parent=Transcript:Gene:Y71F9AM.4a.2
+I	Coding_transcript	CDS	2937759	2937919	.	+	0	ID=CDS:Gene:Y71F9AM.4a.2;Parent=Transcript:Gene:Y71F9AM.4a.2
+I	Coding_transcript	CDS	2938443	2938677	.	+	1	ID=CDS:Gene:Y71F9AM.4a.2;Parent=Transcript:Gene:Y71F9AM.4a.2
+I	Coding_transcript	CDS	2942825	2943021	.	+	0	ID=CDS:Gene:Y71F9AM.4a.2;Parent=Transcript:Gene:Y71F9AM.4a.2
+I	Coding_transcript	CDS	2943072	2943204	.	+	1	ID=CDS:Gene:Y71F9AM.4a.2;Parent=Transcript:Gene:Y71F9AM.4a.2
+I	Coding_transcript	CDS	2944077	2944223	.	+	0	ID=CDS:Gene:Y71F9AM.4a.2;Parent=Transcript:Gene:Y71F9AM.4a.2
+I	Coding_transcript	CDS	2944275	2944424	.	+	0	ID=CDS:Gene:Y71F9AM.4a.2;Parent=Transcript:Gene:Y71F9AM.4a.2
+I	Coding_transcript	three_prime_UTR	2944425	2944611	.	+	.	ID=three_prime_UTR:Gene:Y71F9AM.4a.2;Parent=Transcript:Gene:Y71F9AM.4a.2
+I	Coding_transcript	gene	2929778	2931362	.	+	.	ID=Gene:Gene:Y71F9AM.5b
+I	Coding_transcript	mRNA	2929778	2931362	.	+	.	ID=Transcript:Gene:Y71F9AM.5b.1;Parent=Gene:Gene:Y71F9AM.5b
+I	Coding_transcript	five_prime_UTR	2929778	2929840	.	+	.	ID=five_prime_UTR:Gene:Y71F9AM.5b.1;Parent=Transcript:Gene:Y71F9AM.5b.1
+I	Coding_transcript	CDS	2929841	2929885	.	+	0	ID=CDS:Gene:Y71F9AM.5b.1;Parent=Transcript:Gene:Y71F9AM.5b.1
+I	Coding_transcript	CDS	2929947	2930071	.	+	0	ID=CDS:Gene:Y71F9AM.5b.1;Parent=Transcript:Gene:Y71F9AM.5b.1
+I	Coding_transcript	CDS	2930175	2930367	.	+	1	ID=CDS:Gene:Y71F9AM.5b.1;Parent=Transcript:Gene:Y71F9AM.5b.1
+I	Coding_transcript	CDS	2931224	2931256	.	+	0	ID=CDS:Gene:Y71F9AM.5b.1;Parent=Transcript:Gene:Y71F9AM.5b.1
+I	Coding_transcript	three_prime_UTR	2931257	2931362	.	+	.	ID=three_prime_UTR:Gene:Y71F9AM.5b.1;Parent=Transcript:Gene:Y71F9AM.5b.1
+I	Coding_transcript	mRNA	2929785	2931344	.	+	.	ID=Transcript:Gene:Y71F9AM.5b.2;Parent=Gene:Gene:Y71F9AM.5b
+I	Coding_transcript	five_prime_UTR	2929785	2929840	.	+	.	ID=five_prime_UTR:Gene:Y71F9AM.5b.2;Parent=Transcript:Gene:Y71F9AM.5b.2
+I	Coding_transcript	CDS	2929841	2929885	.	+	0	ID=CDS:Gene:Y71F9AM.5b.2;Parent=Transcript:Gene:Y71F9AM.5b.2
+I	Coding_transcript	CDS	2929947	2930089	.	+	0	ID=CDS:Gene:Y71F9AM.5b.2;Parent=Transcript:Gene:Y71F9AM.5b.2
+I	Coding_transcript	CDS	2930175	2930367	.	+	1	ID=CDS:Gene:Y71F9AM.5b.2;Parent=Transcript:Gene:Y71F9AM.5b.2
+I	Coding_transcript	CDS	2931224	2931256	.	+	0	ID=CDS:Gene:Y71F9AM.5b.2;Parent=Transcript:Gene:Y71F9AM.5b.2
+I	Coding_transcript	three_prime_UTR	2931257	2931344	.	+	.	ID=three_prime_UTR:Gene:Y71F9AM.5b.2;Parent=Transcript:Gene:Y71F9AM.5b.2
+I	Coding_transcript	gene	537125	542200	.	+	.	ID=Gene:Gene:Y65B4BR.4b
+I	Coding_transcript	mRNA	537125	541634	.	+	.	ID=Transcript:Gene:Y65B4BR.4b.1;Parent=Gene:Gene:Y65B4BR.4b
+I	Coding_transcript	five_prime_UTR	537125	537140	.	+	.	ID=five_prime_UTR:Gene:Y65B4BR.4b.1;Parent=Transcript:Gene:Y65B4BR.4b.1
+I	Coding_transcript	CDS	537141	537246	.	+	0	ID=CDS:Gene:Y65B4BR.4b.1;Parent=Transcript:Gene:Y65B4BR.4b.1
+I	Coding_transcript	CDS	537306	537563	.	+	2	ID=CDS:Gene:Y65B4BR.4b.1;Parent=Transcript:Gene:Y65B4BR.4b.1
+I	Coding_transcript	CDS	537609	537838	.	+	2	ID=CDS:Gene:Y65B4BR.4b.1;Parent=Transcript:Gene:Y65B4BR.4b.1
+I	Coding_transcript	CDS	538705	538914	.	+	0	ID=CDS:Gene:Y65B4BR.4b.1;Parent=Transcript:Gene:Y65B4BR.4b.1
+I	Coding_transcript	CDS	539456	539730	.	+	0	ID=CDS:Gene:Y65B4BR.4b.1;Parent=Transcript:Gene:Y65B4BR.4b.1
+I	Coding_transcript	CDS	539804	540011	.	+	1	ID=CDS:Gene:Y65B4BR.4b.1;Parent=Transcript:Gene:Y65B4BR.4b.1
+I	Coding_transcript	CDS	540067	540387	.	+	0	ID=CDS:Gene:Y65B4BR.4b.1;Parent=Transcript:Gene:Y65B4BR.4b.1
+I	Coding_transcript	CDS	540726	540986	.	+	0	ID=CDS:Gene:Y65B4BR.4b.1;Parent=Transcript:Gene:Y65B4BR.4b.1
+I	Coding_transcript	CDS	541067	541288	.	+	0	ID=CDS:Gene:Y65B4BR.4b.1;Parent=Transcript:Gene:Y65B4BR.4b.1
+I	Coding_transcript	CDS	541347	541634	.	+	0	ID=CDS:Gene:Y65B4BR.4b.1;Parent=Transcript:Gene:Y65B4BR.4b.1
+I	Coding_transcript	mRNA	537125	542200	.	+	.	ID=Transcript:Gene:Y65B4BR.4b.2;Parent=Gene:Gene:Y65B4BR.4b
+I	Coding_transcript	five_prime_UTR	537125	537140	.	+	.	ID=five_prime_UTR:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	CDS	537141	537246	.	+	0	ID=CDS:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	CDS	537306	537563	.	+	2	ID=CDS:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	CDS	537609	537838	.	+	2	ID=CDS:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	CDS	538705	538914	.	+	0	ID=CDS:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	CDS	539456	539730	.	+	0	ID=CDS:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	CDS	539798	540011	.	+	1	ID=CDS:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	CDS	540067	540387	.	+	0	ID=CDS:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	CDS	540726	540986	.	+	0	ID=CDS:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	CDS	541067	541288	.	+	0	ID=CDS:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	CDS	541347	541634	.	+	0	ID=CDS:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	three_prime_UTR	541635	542200	.	+	.	ID=three_prime_UTR:Gene:Y65B4BR.4b.2;Parent=Transcript:Gene:Y65B4BR.4b.2
+I	Coding_transcript	gene	562739	565184	.	+	.	ID=Gene:Gene:Y65B4BR.1
+I	Coding_transcript	mRNA	562739	565184	.	+	.	ID=Transcript:Gene:Y65B4BR.1.1;Parent=Gene:Gene:Y65B4BR.1
+I	Coding_transcript	five_prime_UTR	562739	562765	.	+	.	ID=five_prime_UTR:Gene:Y65B4BR.1.1;Parent=Transcript:Gene:Y65B4BR.1.1
+I	Coding_transcript	CDS	562766	562872	.	+	0	ID=CDS:Gene:Y65B4BR.1.1;Parent=Transcript:Gene:Y65B4BR.1.1
+I	Coding_transcript	CDS	562923	563122	.	+	1	ID=CDS:Gene:Y65B4BR.1.1;Parent=Transcript:Gene:Y65B4BR.1.1
+I	Coding_transcript	CDS	563167	563333	.	+	2	ID=CDS:Gene:Y65B4BR.1.1;Parent=Transcript:Gene:Y65B4BR.1.1
+I	Coding_transcript	CDS	563377	563460	.	+	0	ID=CDS:Gene:Y65B4BR.1.1;Parent=Transcript:Gene:Y65B4BR.1.1
+I	Coding_transcript	CDS	563510	563583	.	+	0	ID=CDS:Gene:Y65B4BR.1.1;Parent=Transcript:Gene:Y65B4BR.1.1
+I	Coding_transcript	CDS	564612	565113	.	+	1	ID=CDS:Gene:Y65B4BR.1.1;Parent=Transcript:Gene:Y65B4BR.1.1
+I	Coding_transcript	three_prime_UTR	565114	565184	.	+	.	ID=three_prime_UTR:Gene:Y65B4BR.1.1;Parent=Transcript:Gene:Y65B4BR.1.1
+I	Coding_transcript	gene	618210	621466	.	+	.	ID=Gene:Gene:F56A6.1b
+I	Coding_transcript	mRNA	618210	621424	.	+	.	ID=Transcript:Gene:F56A6.1b.1;Parent=Gene:Gene:F56A6.1b
+I	Coding_transcript	CDS	618210	618360	.	+	0	ID=CDS:Gene:F56A6.1b.1;Parent=Transcript:Gene:F56A6.1b.1
+I	Coding_transcript	CDS	618418	618671	.	+	2	ID=CDS:Gene:F56A6.1b.1;Parent=Transcript:Gene:F56A6.1b.1
+I	Coding_transcript	CDS	618716	618915	.	+	0	ID=CDS:Gene:F56A6.1b.1;Parent=Transcript:Gene:F56A6.1b.1
+I	Coding_transcript	CDS	618962	619021	.	+	1	ID=CDS:Gene:F56A6.1b.1;Parent=Transcript:Gene:F56A6.1b.1
+I	Coding_transcript	CDS	619072	619190	.	+	1	ID=CDS:Gene:F56A6.1b.1;Parent=Transcript:Gene:F56A6.1b.1
+I	Coding_transcript	CDS	619250	619692	.	+	2	ID=CDS:Gene:F56A6.1b.1;Parent=Transcript:Gene:F56A6.1b.1
+I	Coding_transcript	CDS	619741	620027	.	+	0	ID=CDS:Gene:F56A6.1b.1;Parent=Transcript:Gene:F56A6.1b.1
+I	Coding_transcript	CDS	620073	620469	.	+	1	ID=CDS:Gene:F56A6.1b.1;Parent=Transcript:Gene:F56A6.1b.1
+I	Coding_transcript	CDS	620516	621175	.	+	0	ID=CDS:Gene:F56A6.1b.1;Parent=Transcript:Gene:F56A6.1b.1
+I	Coding_transcript	three_prime_UTR	621176	621424	.	+	.	ID=three_prime_UTR:Gene:F56A6.1b.1;Parent=Transcript:Gene:F56A6.1b.1
+I	Coding_transcript	mRNA	618210	621466	.	+	.	ID=Transcript:Gene:F56A6.1b.2;Parent=Gene:Gene:F56A6.1b
+I	Coding_transcript	CDS	618210	618360	.	+	0	ID=CDS:Gene:F56A6.1b.2;Parent=Transcript:Gene:F56A6.1b.2
+I	Coding_transcript	CDS	618418	618671	.	+	2	ID=CDS:Gene:F56A6.1b.2;Parent=Transcript:Gene:F56A6.1b.2
+I	Coding_transcript	CDS	618716	618915	.	+	0	ID=CDS:Gene:F56A6.1b.2;Parent=Transcript:Gene:F56A6.1b.2
+I	Coding_transcript	CDS	618962	619021	.	+	1	ID=CDS:Gene:F56A6.1b.2;Parent=Transcript:Gene:F56A6.1b.2
+I	Coding_transcript	CDS	619072	619190	.	+	1	ID=CDS:Gene:F56A6.1b.2;Parent=Transcript:Gene:F56A6.1b.2
+I	Coding_transcript	CDS	619250	619692	.	+	2	ID=CDS:Gene:F56A6.1b.2;Parent=Transcript:Gene:F56A6.1b.2
+I	Coding_transcript	CDS	619741	620027	.	+	0	ID=CDS:Gene:F56A6.1b.2;Parent=Transcript:Gene:F56A6.1b.2
+I	Coding_transcript	CDS	620073	620469	.	+	1	ID=CDS:Gene:F56A6.1b.2;Parent=Transcript:Gene:F56A6.1b.2
+I	Coding_transcript	CDS	620516	621171	.	+	0	ID=CDS:Gene:F56A6.1b.2;Parent=Transcript:Gene:F56A6.1b.2
+I	Coding_transcript	CDS	621218	621314	.	+	1	ID=CDS:Gene:F56A6.1b.2;Parent=Transcript:Gene:F56A6.1b.2
+I	Coding_transcript	three_prime_UTR	621315	621466	.	+	.	ID=three_prime_UTR:Gene:F56A6.1b.2;Parent=Transcript:Gene:F56A6.1b.2
+I	Coding_transcript	gene	720014	731077	.	+	.	ID=Gene:Gene:Y18H1A.6
+I	Coding_transcript	mRNA	720014	731077	.	+	.	ID=Transcript:Gene:Y18H1A.6.1;Parent=Gene:Gene:Y18H1A.6
+I	Coding_transcript	five_prime_UTR	720014	720080	.	+	.	ID=five_prime_UTR:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	720081	720256	.	+	0	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	720301	720435	.	+	1	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	720489	720602	.	+	1	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	720647	720787	.	+	1	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	720831	720942	.	+	1	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	722106	722204	.	+	0	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	722247	722358	.	+	0	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	724573	724769	.	+	2	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	725112	725228	.	+	0	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	725289	725395	.	+	0	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	726504	726873	.	+	1	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	730284	730535	.	+	0	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	CDS	730839	730940	.	+	0	ID=CDS:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	three_prime_UTR	730941	731077	.	+	.	ID=three_prime_UTR:Gene:Y18H1A.6.1;Parent=Transcript:Gene:Y18H1A.6.1
+I	Coding_transcript	gene	763627	770707	.	+	.	ID=Gene:Gene:T06A4.3a
+I	Coding_transcript	mRNA	763627	770707	.	+	.	ID=Transcript:Gene:T06A4.3a.1;Parent=Gene:Gene:T06A4.3a
+I	Coding_transcript	five_prime_UTR	763627	763676	.	+	.	ID=five_prime_UTR:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	CDS	763677	763826	.	+	0	ID=CDS:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	CDS	765140	765276	.	+	0	ID=CDS:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	CDS	765434	765647	.	+	1	ID=CDS:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	CDS	766050	766151	.	+	0	ID=CDS:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	CDS	766328	766447	.	+	0	ID=CDS:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	CDS	766529	766643	.	+	0	ID=CDS:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	CDS	767585	767736	.	+	2	ID=CDS:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	CDS	768167	768226	.	+	0	ID=CDS:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	CDS	768276	768450	.	+	0	ID=CDS:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	CDS	768502	768630	.	+	2	ID=CDS:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	CDS	770464	770627	.	+	2	ID=CDS:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	three_prime_UTR	770628	770707	.	+	.	ID=three_prime_UTR:Gene:T06A4.3a.1;Parent=Transcript:Gene:T06A4.3a.1
+I	Coding_transcript	mRNA	763677	768919	.	+	.	ID=Transcript:Gene:T06A4.3a.2;Parent=Gene:Gene:T06A4.3a
+I	Coding_transcript	CDS	763677	763826	.	+	0	ID=CDS:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	CDS	765140	765276	.	+	0	ID=CDS:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	CDS	765434	765647	.	+	1	ID=CDS:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	CDS	766050	766151	.	+	0	ID=CDS:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	CDS	766328	766447	.	+	0	ID=CDS:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	CDS	766529	766643	.	+	0	ID=CDS:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	CDS	767585	767736	.	+	2	ID=CDS:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	CDS	768167	768226	.	+	0	ID=CDS:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	CDS	768276	768450	.	+	0	ID=CDS:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	CDS	768502	768630	.	+	2	ID=CDS:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	CDS	768801	768814	.	+	2	ID=CDS:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	three_prime_UTR	768815	768919	.	+	.	ID=three_prime_UTR:Gene:T06A4.3a.2;Parent=Transcript:Gene:T06A4.3a.2
+I	Coding_transcript	gene	770894	776356	.	+	.	ID=Gene:Gene:T06A4.1b
+I	Coding_transcript	mRNA	770894	776346	.	+	.	ID=Transcript:Gene:T06A4.1b.1;Parent=Gene:Gene:T06A4.1b
+I	Coding_transcript	five_prime_UTR	770894	770968	.	+	.	ID=five_prime_UTR:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	CDS	770969	771060	.	+	0	ID=CDS:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	CDS	771453	771568	.	+	1	ID=CDS:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	CDS	771808	771913	.	+	2	ID=CDS:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	CDS	771970	772156	.	+	1	ID=CDS:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	CDS	773166	773387	.	+	0	ID=CDS:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	CDS	773437	773548	.	+	0	ID=CDS:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	CDS	773702	773989	.	+	2	ID=CDS:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	CDS	774970	775066	.	+	2	ID=CDS:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	CDS	775112	775574	.	+	1	ID=CDS:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	CDS	776166	776303	.	+	0	ID=CDS:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	three_prime_UTR	776304	776346	.	+	.	ID=three_prime_UTR:Gene:T06A4.1b.1;Parent=Transcript:Gene:T06A4.1b.1
+I	Coding_transcript	mRNA	770969	776356	.	+	.	ID=Transcript:Gene:T06A4.1b.2;Parent=Gene:Gene:T06A4.1b
+I	Coding_transcript	CDS	770969	771060	.	+	0	ID=CDS:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	CDS	771453	771568	.	+	1	ID=CDS:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	CDS	771808	771913	.	+	2	ID=CDS:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	CDS	771970	772156	.	+	1	ID=CDS:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	CDS	773166	773387	.	+	0	ID=CDS:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	CDS	773437	773548	.	+	0	ID=CDS:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	CDS	773702	773989	.	+	2	ID=CDS:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	CDS	774970	775066	.	+	2	ID=CDS:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	CDS	775112	775389	.	+	1	ID=CDS:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	CDS	775471	775574	.	+	2	ID=CDS:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	CDS	776166	776303	.	+	0	ID=CDS:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	three_prime_UTR	776304	776356	.	+	.	ID=three_prime_UTR:Gene:T06A4.1b.2;Parent=Transcript:Gene:T06A4.1b.2
+I	Coding_transcript	gene	853461	854133	.	+	.	ID=Gene:Gene:Y95B8A.8
+I	Coding_transcript	mRNA	853461	854133	.	+	.	ID=Transcript:Gene:Y95B8A.8.1;Parent=Gene:Gene:Y95B8A.8
+I	Coding_transcript	CDS	853461	853489	.	+	0	ID=CDS:Gene:Y95B8A.8.1;Parent=Transcript:Gene:Y95B8A.8.1
+I	Coding_transcript	CDS	853563	853628	.	+	1	ID=CDS:Gene:Y95B8A.8.1;Parent=Transcript:Gene:Y95B8A.8.1
+I	Coding_transcript	CDS	853699	853771	.	+	1	ID=CDS:Gene:Y95B8A.8.1;Parent=Transcript:Gene:Y95B8A.8.1
+I	Coding_transcript	CDS	853830	853932	.	+	0	ID=CDS:Gene:Y95B8A.8.1;Parent=Transcript:Gene:Y95B8A.8.1
+I	Coding_transcript	CDS	853988	854133	.	+	2	ID=CDS:Gene:Y95B8A.8.1;Parent=Transcript:Gene:Y95B8A.8.1
+I	Coding_transcript	gene	858489	871831	.	+	.	ID=Gene:Gene:Y95B8A.7
+I	Coding_transcript	mRNA	858489	871831	.	+	.	ID=Transcript:Gene:Y95B8A.7.1;Parent=Gene:Gene:Y95B8A.7
+I	Coding_transcript	five_prime_UTR	858489	858568	.	+	.	ID=five_prime_UTR:Gene:Y95B8A.7.1;Parent=Transcript:Gene:Y95B8A.7.1
+I	Coding_transcript	CDS	858569	858837	.	+	0	ID=CDS:Gene:Y95B8A.7.1;Parent=Transcript:Gene:Y95B8A.7.1
+I	Coding_transcript	CDS	861488	861921	.	+	1	ID=CDS:Gene:Y95B8A.7.1;Parent=Transcript:Gene:Y95B8A.7.1
+I	Coding_transcript	CDS	864406	864821	.	+	2	ID=CDS:Gene:Y95B8A.7.1;Parent=Transcript:Gene:Y95B8A.7.1
+I	Coding_transcript	CDS	865733	865936	.	+	0	ID=CDS:Gene:Y95B8A.7.1;Parent=Transcript:Gene:Y95B8A.7.1
+I	Coding_transcript	CDS	866765	866860	.	+	0	ID=CDS:Gene:Y95B8A.7.1;Parent=Transcript:Gene:Y95B8A.7.1
+I	Coding_transcript	CDS	868612	868723	.	+	0	ID=CDS:Gene:Y95B8A.7.1;Parent=Transcript:Gene:Y95B8A.7.1
+I	Coding_transcript	CDS	870196	870326	.	+	2	ID=CDS:Gene:Y95B8A.7.1;Parent=Transcript:Gene:Y95B8A.7.1
+I	Coding_transcript	CDS	871656	871820	.	+	0	ID=CDS:Gene:Y95B8A.7.1;Parent=Transcript:Gene:Y95B8A.7.1
+I	Coding_transcript	three_prime_UTR	871821	871831	.	+	.	ID=three_prime_UTR:Gene:Y95B8A.7.1;Parent=Transcript:Gene:Y95B8A.7.1
+I	Coding_transcript	gene	882920	890209	.	+	.	ID=Gene:Gene:Y95B8A.6a.2
+I	Coding_transcript	mRNA	882920	889792	.	+	.	ID=Transcript:Gene:Y95B8A.6a.2.1;Parent=Gene:Gene:Y95B8A.6a.2
+I	Coding_transcript	five_prime_UTR	882920	883166	.	+	.	ID=five_prime_UTR:Gene:Y95B8A.6a.2.1;Parent=Transcript:Gene:Y95B8A.6a.2.1
+I	Coding_transcript	five_prime_UTR	884906	885042	.	+	.	ID=five_prime_UTR:Gene:Y95B8A.6a.2.1;Parent=Transcript:Gene:Y95B8A.6a.2.1
+I	Coding_transcript	five_prime_UTR	886509	886608	.	+	.	ID=five_prime_UTR:Gene:Y95B8A.6a.2.1;Parent=Transcript:Gene:Y95B8A.6a.2.1
+I	Coding_transcript	CDS	886609	886709	.	+	0	ID=CDS:Gene:Y95B8A.6a.2.1;Parent=Transcript:Gene:Y95B8A.6a.2.1
+I	Coding_transcript	CDS	887882	888060	.	+	1	ID=CDS:Gene:Y95B8A.6a.2.1;Parent=Transcript:Gene:Y95B8A.6a.2.1
+I	Coding_transcript	CDS	888152	888348	.	+	2	ID=CDS:Gene:Y95B8A.6a.2.1;Parent=Transcript:Gene:Y95B8A.6a.2.1
+I	Coding_transcript	CDS	889676	889792	.	+	0	ID=CDS:Gene:Y95B8A.6a.2.1;Parent=Transcript:Gene:Y95B8A.6a.2.1
+I	Coding_transcript	mRNA	886213	890209	.	+	.	ID=Transcript:Gene:Y95B8A.6a.2.2;Parent=Gene:Gene:Y95B8A.6a.2
+I	Coding_transcript	five_prime_UTR	886213	886608	.	+	.	ID=five_prime_UTR:Gene:Y95B8A.6a.2.2;Parent=Transcript:Gene:Y95B8A.6a.2.2
+I	Coding_transcript	CDS	886609	886709	.	+	0	ID=CDS:Gene:Y95B8A.6a.2.2;Parent=Transcript:Gene:Y95B8A.6a.2.2
+I	Coding_transcript	CDS	887882	888060	.	+	1	ID=CDS:Gene:Y95B8A.6a.2.2;Parent=Transcript:Gene:Y95B8A.6a.2.2
+I	Coding_transcript	CDS	888152	888348	.	+	2	ID=CDS:Gene:Y95B8A.6a.2.2;Parent=Transcript:Gene:Y95B8A.6a.2.2
+I	Coding_transcript	CDS	889676	889792	.	+	0	ID=CDS:Gene:Y95B8A.6a.2.2;Parent=Transcript:Gene:Y95B8A.6a.2.2
+I	Coding_transcript	three_prime_UTR	889793	890209	.	+	.	ID=three_prime_UTR:Gene:Y95B8A.6a.2.2;Parent=Transcript:Gene:Y95B8A.6a.2.2
+I	Coding_transcript	mRNA	887841	889870	.	+	.	ID=Transcript:Gene:Y95B8A.6a.2.3;Parent=Gene:Gene:Y95B8A.6a.2
+I	Coding_transcript	five_prime_UTR	887841	888153	.	+	.	ID=five_prime_UTR:Gene:Y95B8A.6a.2.3;Parent=Transcript:Gene:Y95B8A.6a.2.3
+I	Coding_transcript	CDS	888154	888348	.	+	0	ID=CDS:Gene:Y95B8A.6a.2.3;Parent=Transcript:Gene:Y95B8A.6a.2.3
+I	Coding_transcript	CDS	889676	889792	.	+	0	ID=CDS:Gene:Y95B8A.6a.2.3;Parent=Transcript:Gene:Y95B8A.6a.2.3
+I	Coding_transcript	three_prime_UTR	889793	889870	.	+	.	ID=three_prime_UTR:Gene:Y95B8A.6a.2.3;Parent=Transcript:Gene:Y95B8A.6a.2.3
+I	Coding_transcript	gene	897288	905906	.	+	.	ID=Gene:Gene:Y95B8A.5
+I	Coding_transcript	mRNA	897288	905906	.	+	.	ID=Transcript:Gene:Y95B8A.5.1;Parent=Gene:Gene:Y95B8A.5
+I	Coding_transcript	five_prime_UTR	897288	897291	.	+	.	ID=five_prime_UTR:Gene:Y95B8A.5.1;Parent=Transcript:Gene:Y95B8A.5.1
+I	Coding_transcript	CDS	897292	897357	.	+	0	ID=CDS:Gene:Y95B8A.5.1;Parent=Transcript:Gene:Y95B8A.5.1
+I	Coding_transcript	CDS	898181	898351	.	+	0	ID=CDS:Gene:Y95B8A.5.1;Parent=Transcript:Gene:Y95B8A.5.1
+I	Coding_transcript	CDS	900615	900802	.	+	0	ID=CDS:Gene:Y95B8A.5.1;Parent=Transcript:Gene:Y95B8A.5.1
+I	Coding_transcript	CDS	903105	903192	.	+	1	ID=CDS:Gene:Y95B8A.5.1;Parent=Transcript:Gene:Y95B8A.5.1
+I	Coding_transcript	CDS	903255	903331	.	+	0	ID=CDS:Gene:Y95B8A.5.1;Parent=Transcript:Gene:Y95B8A.5.1
+I	Coding_transcript	CDS	903384	903513	.	+	1	ID=CDS:Gene:Y95B8A.5.1;Parent=Transcript:Gene:Y95B8A.5.1
+I	Coding_transcript	CDS	904613	904846	.	+	0	ID=CDS:Gene:Y95B8A.5.1;Parent=Transcript:Gene:Y95B8A.5.1
+I	Coding_transcript	CDS	905736	905855	.	+	0	ID=CDS:Gene:Y95B8A.5.1;Parent=Transcript:Gene:Y95B8A.5.1
+I	Coding_transcript	three_prime_UTR	905856	905906	.	+	.	ID=three_prime_UTR:Gene:Y95B8A.5.1;Parent=Transcript:Gene:Y95B8A.5.1
+I	Coding_transcript	gene	1003891	1010767	.	+	.	ID=Gene:Gene:C54G6.2
+I	Coding_transcript	mRNA	1003891	1010767	.	+	.	ID=Transcript:Gene:C54G6.2.1;Parent=Gene:Gene:C54G6.2
+I	Coding_transcript	CDS	1003891	1004091	.	+	0	ID=CDS:Gene:C54G6.2.1;Parent=Transcript:Gene:C54G6.2.1
+I	Coding_transcript	CDS	1004703	1005062	.	+	0	ID=CDS:Gene:C54G6.2.1;Parent=Transcript:Gene:C54G6.2.1
+I	Coding_transcript	CDS	1006029	1006324	.	+	0	ID=CDS:Gene:C54G6.2.1;Parent=Transcript:Gene:C54G6.2.1
+I	Coding_transcript	CDS	1006461	1006548	.	+	1	ID=CDS:Gene:C54G6.2.1;Parent=Transcript:Gene:C54G6.2.1
+I	Coding_transcript	CDS	1007013	1007136	.	+	0	ID=CDS:Gene:C54G6.2.1;Parent=Transcript:Gene:C54G6.2.1
+I	Coding_transcript	CDS	1007188	1007273	.	+	2	ID=CDS:Gene:C54G6.2.1;Parent=Transcript:Gene:C54G6.2.1
+I	Coding_transcript	CDS	1008082	1008464	.	+	0	ID=CDS:Gene:C54G6.2.1;Parent=Transcript:Gene:C54G6.2.1
+I	Coding_transcript	CDS	1009524	1009755	.	+	1	ID=CDS:Gene:C54G6.2.1;Parent=Transcript:Gene:C54G6.2.1
+I	Coding_transcript	CDS	1009820	1009891	.	+	0	ID=CDS:Gene:C54G6.2.1;Parent=Transcript:Gene:C54G6.2.1
+I	Coding_transcript	CDS	1010207	1010293	.	+	0	ID=CDS:Gene:C54G6.2.1;Parent=Transcript:Gene:C54G6.2.1
+I	Coding_transcript	CDS	1010594	1010767	.	+	0	ID=CDS:Gene:C54G6.2.1;Parent=Transcript:Gene:C54G6.2.1
+I	Coding_transcript	gene	1018837	1019221	.	+	.	ID=Gene:Gene:Y34D9A.11
+I	Coding_transcript	mRNA	1018837	1019221	.	+	.	ID=Transcript:Gene:Y34D9A.11.1;Parent=Gene:Gene:Y34D9A.11
+I	Coding_transcript	five_prime_UTR	1018837	1018844	.	+	.	ID=five_prime_UTR:Gene:Y34D9A.11.1;Parent=Transcript:Gene:Y34D9A.11.1
+I	Coding_transcript	CDS	1018845	1019159	.	+	0	ID=CDS:Gene:Y34D9A.11.1;Parent=Transcript:Gene:Y34D9A.11.1
+I	Coding_transcript	three_prime_UTR	1019160	1019221	.	+	.	ID=three_prime_UTR:Gene:Y34D9A.11.1;Parent=Transcript:Gene:Y34D9A.11.1
+I	Coding_transcript	gene	1034474	1040870	.	+	.	ID=Gene:Gene:Y34D9A.3
+I	Coding_transcript	mRNA	1034474	1040870	.	+	.	ID=Transcript:Gene:Y34D9A.3.1;Parent=Gene:Gene:Y34D9A.3
+I	Coding_transcript	five_prime_UTR	1034474	1034474	.	+	.	ID=five_prime_UTR:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1034475	1034499	.	+	0	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1034549	1034646	.	+	2	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1034693	1034881	.	+	0	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1034934	1035065	.	+	0	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1035123	1035246	.	+	0	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1035306	1035398	.	+	2	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1037314	1037453	.	+	2	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1037508	1037715	.	+	0	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1039055	1039296	.	+	2	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1039340	1039883	.	+	0	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1040116	1040648	.	+	2	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	CDS	1040700	1040765	.	+	0	ID=CDS:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	three_prime_UTR	1040766	1040870	.	+	.	ID=three_prime_UTR:Gene:Y34D9A.3.1;Parent=Transcript:Gene:Y34D9A.3.1
+I	Coding_transcript	gene	1049596	1050714	.	+	.	ID=Gene:Gene:Y34D9A.6
+I	Coding_transcript	mRNA	1049596	1050714	.	+	.	ID=Transcript:Gene:Y34D9A.6.1;Parent=Gene:Gene:Y34D9A.6
+I	Coding_transcript	five_prime_UTR	1049596	1049604	.	+	.	ID=five_prime_UTR:Gene:Y34D9A.6.1;Parent=Transcript:Gene:Y34D9A.6.1
+I	Coding_transcript	CDS	1049605	1049688	.	+	0	ID=CDS:Gene:Y34D9A.6.1;Parent=Transcript:Gene:Y34D9A.6.1
+I	Coding_transcript	CDS	1050407	1050640	.	+	0	ID=CDS:Gene:Y34D9A.6.1;Parent=Transcript:Gene:Y34D9A.6.1
+I	Coding_transcript	three_prime_UTR	1050641	1050714	.	+	.	ID=three_prime_UTR:Gene:Y34D9A.6.1;Parent=Transcript:Gene:Y34D9A.6.1
+I	Coding_transcript	gene	1062295	1065271	.	+	.	ID=Gene:Gene:Y34D9A.2
+I	Coding_transcript	mRNA	1062295	1065271	.	+	.	ID=Transcript:Gene:Y34D9A.2.1;Parent=Gene:Gene:Y34D9A.2
+I	Coding_transcript	five_prime_UTR	1062295	1062448	.	+	.	ID=five_prime_UTR:Gene:Y34D9A.2.1;Parent=Transcript:Gene:Y34D9A.2.1
+I	Coding_transcript	CDS	1062449	1062757	.	+	0	ID=CDS:Gene:Y34D9A.2.1;Parent=Transcript:Gene:Y34D9A.2.1
+I	Coding_transcript	CDS	1063602	1064008	.	+	0	ID=CDS:Gene:Y34D9A.2.1;Parent=Transcript:Gene:Y34D9A.2.1
+I	Coding_transcript	CDS	1064656	1064920	.	+	1	ID=CDS:Gene:Y34D9A.2.1;Parent=Transcript:Gene:Y34D9A.2.1
+I	Coding_transcript	three_prime_UTR	1064921	1065271	.	+	.	ID=three_prime_UTR:Gene:Y34D9A.2.1;Parent=Transcript:Gene:Y34D9A.2.1
+I	Coding_transcript	gene	1068593	1075012	.	+	.	ID=Gene:Gene:R06A10.2.1
+I	Coding_transcript	mRNA	1068593	1075012	.	+	.	ID=Transcript:Gene:R06A10.2.1.1;Parent=Gene:Gene:R06A10.2.1
+I	Coding_transcript	five_prime_UTR	1068593	1068997	.	+	.	ID=five_prime_UTR:Gene:R06A10.2.1.1;Parent=Transcript:Gene:R06A10.2.1.1
+I	Coding_transcript	CDS	1068998	1069090	.	+	0	ID=CDS:Gene:R06A10.2.1.1;Parent=Transcript:Gene:R06A10.2.1.1
+I	Coding_transcript	CDS	1069416	1069577	.	+	0	ID=CDS:Gene:R06A10.2.1.1;Parent=Transcript:Gene:R06A10.2.1.1
+I	Coding_transcript	CDS	1070370	1070489	.	+	0	ID=CDS:Gene:R06A10.2.1.1;Parent=Transcript:Gene:R06A10.2.1.1
+I	Coding_transcript	CDS	1071472	1071569	.	+	0	ID=CDS:Gene:R06A10.2.1.1;Parent=Transcript:Gene:R06A10.2.1.1
+I	Coding_transcript	CDS	1071623	1071751	.	+	1	ID=CDS:Gene:R06A10.2.1.1;Parent=Transcript:Gene:R06A10.2.1.1
+I	Coding_transcript	CDS	1071801	1071935	.	+	1	ID=CDS:Gene:R06A10.2.1.1;Parent=Transcript:Gene:R06A10.2.1.1
+I	Coding_transcript	CDS	1072675	1072918	.	+	1	ID=CDS:Gene:R06A10.2.1.1;Parent=Transcript:Gene:R06A10.2.1.1
+I	Coding_transcript	CDS	1074199	1074345	.	+	0	ID=CDS:Gene:R06A10.2.1.1;Parent=Transcript:Gene:R06A10.2.1.1
+I	Coding_transcript	three_prime_UTR	1074346	1075012	.	+	.	ID=three_prime_UTR:Gene:R06A10.2.1.1;Parent=Transcript:Gene:R06A10.2.1.1
+I	Coding_transcript	mRNA	1068613	1074345	.	+	.	ID=Transcript:Gene:R06A10.2.1.2;Parent=Gene:Gene:R06A10.2.1
+I	Coding_transcript	five_prime_UTR	1068613	1068893	.	+	.	ID=five_prime_UTR:Gene:R06A10.2.1.2;Parent=Transcript:Gene:R06A10.2.1.2
+I	Coding_transcript	five_prime_UTR	1068976	1068997	.	+	.	ID=five_prime_UTR:Gene:R06A10.2.1.2;Parent=Transcript:Gene:R06A10.2.1.2
+I	Coding_transcript	CDS	1068998	1069090	.	+	0	ID=CDS:Gene:R06A10.2.1.2;Parent=Transcript:Gene:R06A10.2.1.2
+I	Coding_transcript	CDS	1069416	1069577	.	+	0	ID=CDS:Gene:R06A10.2.1.2;Parent=Transcript:Gene:R06A10.2.1.2
+I	Coding_transcript	CDS	1070370	1070489	.	+	0	ID=CDS:Gene:R06A10.2.1.2;Parent=Transcript:Gene:R06A10.2.1.2
+I	Coding_transcript	CDS	1071472	1071569	.	+	0	ID=CDS:Gene:R06A10.2.1.2;Parent=Transcript:Gene:R06A10.2.1.2
+I	Coding_transcript	CDS	1071623	1071751	.	+	1	ID=CDS:Gene:R06A10.2.1.2;Parent=Transcript:Gene:R06A10.2.1.2
+I	Coding_transcript	CDS	1071801	1071935	.	+	1	ID=CDS:Gene:R06A10.2.1.2;Parent=Transcript:Gene:R06A10.2.1.2
+I	Coding_transcript	CDS	1072675	1072918	.	+	1	ID=CDS:Gene:R06A10.2.1.2;Parent=Transcript:Gene:R06A10.2.1.2
+I	Coding_transcript	CDS	1074199	1074345	.	+	0	ID=CDS:Gene:R06A10.2.1.2;Parent=Transcript:Gene:R06A10.2.1.2
+I	Coding_transcript	gene	1128326	1131739	.	+	.	ID=Gene:Gene:ZK993.1
+I	Coding_transcript	mRNA	1128326	1131739	.	+	.	ID=Transcript:Gene:ZK993.1.1;Parent=Gene:Gene:ZK993.1
+I	Coding_transcript	five_prime_UTR	1128326	1128360	.	+	.	ID=five_prime_UTR:Gene:ZK993.1.1;Parent=Transcript:Gene:ZK993.1.1
+I	Coding_transcript	CDS	1128361	1128428	.	+	0	ID=CDS:Gene:ZK993.1.1;Parent=Transcript:Gene:ZK993.1.1
+I	Coding_transcript	CDS	1129212	1129396	.	+	1	ID=CDS:Gene:ZK993.1.1;Parent=Transcript:Gene:ZK993.1.1
+I	Coding_transcript	CDS	1129808	1130016	.	+	2	ID=CDS:Gene:ZK993.1.1;Parent=Transcript:Gene:ZK993.1.1
+I	Coding_transcript	CDS	1131224	1131289	.	+	0	ID=CDS:Gene:ZK993.1.1;Parent=Transcript:Gene:ZK993.1.1
+I	Coding_transcript	CDS	1131475	1131636	.	+	0	ID=CDS:Gene:ZK993.1.1;Parent=Transcript:Gene:ZK993.1.1
+I	Coding_transcript	three_prime_UTR	1131637	1131739	.	+	.	ID=three_prime_UTR:Gene:ZK993.1.1;Parent=Transcript:Gene:ZK993.1.1
+I	Coding_transcript	gene	1337021	1338121	.	+	.	ID=Gene:Gene:K12C11.6
+I	Coding_transcript	mRNA	1337021	1338121	.	+	.	ID=Transcript:Gene:K12C11.6.1;Parent=Gene:Gene:K12C11.6
+I	Coding_transcript	CDS	1337021	1337117	.	+	0	ID=CDS:Gene:K12C11.6.1;Parent=Transcript:Gene:K12C11.6.1
+I	Coding_transcript	CDS	1337256	1337373	.	+	2	ID=CDS:Gene:K12C11.6.1;Parent=Transcript:Gene:K12C11.6.1
+I	Coding_transcript	CDS	1337938	1338121	.	+	1	ID=CDS:Gene:K12C11.6.1;Parent=Transcript:Gene:K12C11.6.1
+I	Coding_transcript	gene	1340679	1341259	.	+	.	ID=Gene:Gene:K12C11.2.1
+I	Coding_transcript	mRNA	1340679	1341259	.	+	.	ID=Transcript:Gene:K12C11.2.1.1;Parent=Gene:Gene:K12C11.2.1
+I	Coding_transcript	five_prime_UTR	1340679	1340703	.	+	.	ID=five_prime_UTR:Gene:K12C11.2.1.1;Parent=Transcript:Gene:K12C11.2.1.1
+I	Coding_transcript	CDS	1340704	1340769	.	+	0	ID=CDS:Gene:K12C11.2.1.1;Parent=Transcript:Gene:K12C11.2.1.1
+I	Coding_transcript	CDS	1340826	1340926	.	+	0	ID=CDS:Gene:K12C11.2.1.1;Parent=Transcript:Gene:K12C11.2.1.1
+I	Coding_transcript	CDS	1340977	1341085	.	+	1	ID=CDS:Gene:K12C11.2.1.1;Parent=Transcript:Gene:K12C11.2.1.1
+I	Coding_transcript	three_prime_UTR	1341086	1341259	.	+	.	ID=three_prime_UTR:Gene:K12C11.2.1.1;Parent=Transcript:Gene:K12C11.2.1.1
+I	Coding_transcript	mRNA	1340704	1341253	.	+	.	ID=Transcript:Gene:K12C11.2.1.2;Parent=Gene:Gene:K12C11.2.1
+I	Coding_transcript	CDS	1340704	1340769	.	+	0	ID=CDS:Gene:K12C11.2.1.2;Parent=Transcript:Gene:K12C11.2.1.2
+I	Coding_transcript	CDS	1340826	1340926	.	+	0	ID=CDS:Gene:K12C11.2.1.2;Parent=Transcript:Gene:K12C11.2.1.2
+I	Coding_transcript	CDS	1340977	1341085	.	+	1	ID=CDS:Gene:K12C11.2.1.2;Parent=Transcript:Gene:K12C11.2.1.2
+I	Coding_transcript	three_prime_UTR	1341086	1341253	.	+	.	ID=three_prime_UTR:Gene:K12C11.2.1.2;Parent=Transcript:Gene:K12C11.2.1.2
+I	Coding_transcript	gene	1394570	1402943	.	+	.	ID=Gene:Gene:Y92H12BR.7
+I	Coding_transcript	mRNA	1394570	1402943	.	+	.	ID=Transcript:Gene:Y92H12BR.7.1;Parent=Gene:Gene:Y92H12BR.7
+I	Coding_transcript	CDS	1394570	1394781	.	+	0	ID=CDS:Gene:Y92H12BR.7.1;Parent=Transcript:Gene:Y92H12BR.7.1
+I	Coding_transcript	CDS	1395760	1395875	.	+	1	ID=CDS:Gene:Y92H12BR.7.1;Parent=Transcript:Gene:Y92H12BR.7.1
+I	Coding_transcript	CDS	1395940	1396113	.	+	2	ID=CDS:Gene:Y92H12BR.7.1;Parent=Transcript:Gene:Y92H12BR.7.1
+I	Coding_transcript	CDS	1397517	1397708	.	+	2	ID=CDS:Gene:Y92H12BR.7.1;Parent=Transcript:Gene:Y92H12BR.7.1
+I	Coding_transcript	CDS	1399169	1399348	.	+	2	ID=CDS:Gene:Y92H12BR.7.1;Parent=Transcript:Gene:Y92H12BR.7.1
+I	Coding_transcript	CDS	1402093	1402943	.	+	2	ID=CDS:Gene:Y92H12BR.7.1;Parent=Transcript:Gene:Y92H12BR.7.1
+I	Coding_transcript	gene	1405945	1413072	.	+	.	ID=Gene:Gene:Y92H12BR.6
+I	Coding_transcript	mRNA	1405945	1413072	.	+	.	ID=Transcript:Gene:Y92H12BR.6.1;Parent=Gene:Gene:Y92H12BR.6
+I	Coding_transcript	CDS	1405945	1406373	.	+	0	ID=CDS:Gene:Y92H12BR.6.1;Parent=Transcript:Gene:Y92H12BR.6.1
+I	Coding_transcript	CDS	1408458	1408637	.	+	0	ID=CDS:Gene:Y92H12BR.6.1;Parent=Transcript:Gene:Y92H12BR.6.1
+I	Coding_transcript	CDS	1411442	1411616	.	+	0	ID=CDS:Gene:Y92H12BR.6.1;Parent=Transcript:Gene:Y92H12BR.6.1
+I	Coding_transcript	CDS	1412612	1413033	.	+	2	ID=CDS:Gene:Y92H12BR.6.1;Parent=Transcript:Gene:Y92H12BR.6.1
+I	Coding_transcript	three_prime_UTR	1413034	1413072	.	+	.	ID=three_prime_UTR:Gene:Y92H12BR.6.1;Parent=Transcript:Gene:Y92H12BR.6.1
+I	Coding_transcript	gene	1416592	1425131	.	+	.	ID=Gene:Gene:Y92H12BR.3b
+I	Coding_transcript	mRNA	1416592	1424609	.	+	.	ID=Transcript:Gene:Y92H12BR.3b.1;Parent=Gene:Gene:Y92H12BR.3b
+I	Coding_transcript	CDS	1416592	1416738	.	+	0	ID=CDS:Gene:Y92H12BR.3b.1;Parent=Transcript:Gene:Y92H12BR.3b.1
+I	Coding_transcript	CDS	1416796	1416961	.	+	0	ID=CDS:Gene:Y92H12BR.3b.1;Parent=Transcript:Gene:Y92H12BR.3b.1
+I	Coding_transcript	CDS	1422689	1422993	.	+	2	ID=CDS:Gene:Y92H12BR.3b.1;Parent=Transcript:Gene:Y92H12BR.3b.1
+I	Coding_transcript	CDS	1424412	1424609	.	+	0	ID=CDS:Gene:Y92H12BR.3b.1;Parent=Transcript:Gene:Y92H12BR.3b.1
+I	Coding_transcript	mRNA	1416592	1425131	.	+	.	ID=Transcript:Gene:Y92H12BR.3b.2;Parent=Gene:Gene:Y92H12BR.3b
+I	Coding_transcript	CDS	1416592	1416738	.	+	0	ID=CDS:Gene:Y92H12BR.3b.2;Parent=Transcript:Gene:Y92H12BR.3b.2
+I	Coding_transcript	CDS	1416796	1416961	.	+	0	ID=CDS:Gene:Y92H12BR.3b.2;Parent=Transcript:Gene:Y92H12BR.3b.2
+I	Coding_transcript	CDS	1420212	1421309	.	+	2	ID=CDS:Gene:Y92H12BR.3b.2;Parent=Transcript:Gene:Y92H12BR.3b.2
+I	Coding_transcript	CDS	1422689	1422993	.	+	2	ID=CDS:Gene:Y92H12BR.3b.2;Parent=Transcript:Gene:Y92H12BR.3b.2
+I	Coding_transcript	CDS	1424412	1424609	.	+	0	ID=CDS:Gene:Y92H12BR.3b.2;Parent=Transcript:Gene:Y92H12BR.3b.2
+I	Coding_transcript	three_prime_UTR	1424610	1425131	.	+	.	ID=three_prime_UTR:Gene:Y92H12BR.3b.2;Parent=Transcript:Gene:Y92H12BR.3b.2
+I	Coding_transcript	gene	1483084	1490474	.	+	.	ID=Gene:Gene:F47G6.1
+I	Coding_transcript	mRNA	1483084	1490474	.	+	.	ID=Transcript:Gene:F47G6.1.1;Parent=Gene:Gene:F47G6.1
+I	Coding_transcript	five_prime_UTR	1483084	1483106	.	+	.	ID=five_prime_UTR:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	CDS	1483107	1483236	.	+	0	ID=CDS:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	CDS	1484720	1484877	.	+	2	ID=CDS:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	CDS	1484924	1485060	.	+	0	ID=CDS:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	CDS	1485927	1486012	.	+	1	ID=CDS:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	CDS	1486057	1486252	.	+	2	ID=CDS:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	CDS	1487180	1487411	.	+	1	ID=CDS:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	CDS	1487770	1488096	.	+	0	ID=CDS:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	CDS	1488425	1488676	.	+	0	ID=CDS:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	CDS	1489069	1489282	.	+	0	ID=CDS:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	CDS	1490282	1490322	.	+	2	ID=CDS:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	three_prime_UTR	1490323	1490474	.	+	.	ID=three_prime_UTR:Gene:F47G6.1.1;Parent=Transcript:Gene:F47G6.1.1
+I	Coding_transcript	gene	1514763	1527350	.	+	.	ID=Gene:Gene:Y92H12A.4
+I	Coding_transcript	mRNA	1514763	1527350	.	+	.	ID=Transcript:Gene:Y92H12A.4.1;Parent=Gene:Gene:Y92H12A.4
+I	Coding_transcript	CDS	1514763	1514900	.	+	0	ID=CDS:Gene:Y92H12A.4.1;Parent=Transcript:Gene:Y92H12A.4.1
+I	Coding_transcript	CDS	1514955	1515059	.	+	0	ID=CDS:Gene:Y92H12A.4.1;Parent=Transcript:Gene:Y92H12A.4.1
+I	Coding_transcript	CDS	1515111	1515186	.	+	0	ID=CDS:Gene:Y92H12A.4.1;Parent=Transcript:Gene:Y92H12A.4.1
+I	Coding_transcript	CDS	1515233	1515396	.	+	2	ID=CDS:Gene:Y92H12A.4.1;Parent=Transcript:Gene:Y92H12A.4.1
+I	Coding_transcript	CDS	1517534	1518121	.	+	0	ID=CDS:Gene:Y92H12A.4.1;Parent=Transcript:Gene:Y92H12A.4.1
+I	Coding_transcript	CDS	1520159	1520271	.	+	0	ID=CDS:Gene:Y92H12A.4.1;Parent=Transcript:Gene:Y92H12A.4.1
+I	Coding_transcript	CDS	1522175	1522459	.	+	1	ID=CDS:Gene:Y92H12A.4.1;Parent=Transcript:Gene:Y92H12A.4.1
+I	Coding_transcript	CDS	1524299	1524644	.	+	1	ID=CDS:Gene:Y92H12A.4.1;Parent=Transcript:Gene:Y92H12A.4.1
+I	Coding_transcript	CDS	1525846	1526006	.	+	0	ID=CDS:Gene:Y92H12A.4.1;Parent=Transcript:Gene:Y92H12A.4.1
+I	Coding_transcript	CDS	1526978	1527350	.	+	1	ID=CDS:Gene:Y92H12A.4.1;Parent=Transcript:Gene:Y92H12A.4.1
+I	Coding_transcript	gene	1610391	1619944	.	+	.	ID=Gene:Gene:Y73E7A.9
+I	Coding_transcript	mRNA	1610391	1619944	.	+	.	ID=Transcript:Gene:Y73E7A.9.1;Parent=Gene:Gene:Y73E7A.9
+I	Coding_transcript	CDS	1610391	1610504	.	+	0	ID=CDS:Gene:Y73E7A.9.1;Parent=Transcript:Gene:Y73E7A.9.1
+I	Coding_transcript	CDS	1610564	1610901	.	+	0	ID=CDS:Gene:Y73E7A.9.1;Parent=Transcript:Gene:Y73E7A.9.1
+I	Coding_transcript	CDS	1611487	1611595	.	+	1	ID=CDS:Gene:Y73E7A.9.1;Parent=Transcript:Gene:Y73E7A.9.1
+I	Coding_transcript	CDS	1611747	1611828	.	+	0	ID=CDS:Gene:Y73E7A.9.1;Parent=Transcript:Gene:Y73E7A.9.1
+I	Coding_transcript	CDS	1613478	1613896	.	+	2	ID=CDS:Gene:Y73E7A.9.1;Parent=Transcript:Gene:Y73E7A.9.1
+I	Coding_transcript	CDS	1616100	1616261	.	+	0	ID=CDS:Gene:Y73E7A.9.1;Parent=Transcript:Gene:Y73E7A.9.1
+I	Coding_transcript	CDS	1617834	1617969	.	+	0	ID=CDS:Gene:Y73E7A.9.1;Parent=Transcript:Gene:Y73E7A.9.1
+I	Coding_transcript	CDS	1619628	1619944	.	+	2	ID=CDS:Gene:Y73E7A.9.1;Parent=Transcript:Gene:Y73E7A.9.1
+I	Coding_transcript	gene	1629004	1633494	.	+	.	ID=Gene:Gene:Y73E7A.1a.1
+I	Coding_transcript	mRNA	1629004	1633494	.	+	.	ID=Transcript:Gene:Y73E7A.1a.1.1;Parent=Gene:Gene:Y73E7A.1a.1
+I	Coding_transcript	five_prime_UTR	1629004	1629022	.	+	.	ID=five_prime_UTR:Gene:Y73E7A.1a.1.1;Parent=Transcript:Gene:Y73E7A.1a.1.1
+I	Coding_transcript	CDS	1629023	1629118	.	+	0	ID=CDS:Gene:Y73E7A.1a.1.1;Parent=Transcript:Gene:Y73E7A.1a.1.1
+I	Coding_transcript	CDS	1629164	1629226	.	+	0	ID=CDS:Gene:Y73E7A.1a.1.1;Parent=Transcript:Gene:Y73E7A.1a.1.1
+I	Coding_transcript	CDS	1629283	1629410	.	+	0	ID=CDS:Gene:Y73E7A.1a.1.1;Parent=Transcript:Gene:Y73E7A.1a.1.1
+I	Coding_transcript	CDS	1630554	1630794	.	+	1	ID=CDS:Gene:Y73E7A.1a.1.1;Parent=Transcript:Gene:Y73E7A.1a.1.1
+I	Coding_transcript	CDS	1633222	1633365	.	+	0	ID=CDS:Gene:Y73E7A.1a.1.1;Parent=Transcript:Gene:Y73E7A.1a.1.1
+I	Coding_transcript	three_prime_UTR	1633366	1633494	.	+	.	ID=three_prime_UTR:Gene:Y73E7A.1a.1.1;Parent=Transcript:Gene:Y73E7A.1a.1.1
+I	Coding_transcript	mRNA	1629006	1633365	.	+	.	ID=Transcript:Gene:Y73E7A.1a.1.2;Parent=Gene:Gene:Y73E7A.1a.1
+I	Coding_transcript	five_prime_UTR	1629006	1629022	.	+	.	ID=five_prime_UTR:Gene:Y73E7A.1a.1.2;Parent=Transcript:Gene:Y73E7A.1a.1.2
+I	Coding_transcript	CDS	1629023	1629118	.	+	0	ID=CDS:Gene:Y73E7A.1a.1.2;Parent=Transcript:Gene:Y73E7A.1a.1.2
+I	Coding_transcript	CDS	1629164	1629226	.	+	0	ID=CDS:Gene:Y73E7A.1a.1.2;Parent=Transcript:Gene:Y73E7A.1a.1.2
+I	Coding_transcript	CDS	1629283	1629410	.	+	0	ID=CDS:Gene:Y73E7A.1a.1.2;Parent=Transcript:Gene:Y73E7A.1a.1.2
+I	Coding_transcript	CDS	1630554	1630794	.	+	1	ID=CDS:Gene:Y73E7A.1a.1.2;Parent=Transcript:Gene:Y73E7A.1a.1.2
+I	Coding_transcript	CDS	1633222	1633365	.	+	0	ID=CDS:Gene:Y73E7A.1a.1.2;Parent=Transcript:Gene:Y73E7A.1a.1.2
+I	Coding_transcript	mRNA	1629010	1633365	.	+	.	ID=Transcript:Gene:Y73E7A.1a.1.3;Parent=Gene:Gene:Y73E7A.1a.1
+I	Coding_transcript	five_prime_UTR	1629010	1629118	.	+	.	ID=five_prime_UTR:Gene:Y73E7A.1a.1.3;Parent=Transcript:Gene:Y73E7A.1a.1.3
+I	Coding_transcript	five_prime_UTR	1629164	1629225	.	+	.	ID=five_prime_UTR:Gene:Y73E7A.1a.1.3;Parent=Transcript:Gene:Y73E7A.1a.1.3
+I	Coding_transcript	five_prime_UTR	1629281	1629354	.	+	.	ID=five_prime_UTR:Gene:Y73E7A.1a.1.3;Parent=Transcript:Gene:Y73E7A.1a.1.3
+I	Coding_transcript	CDS	1629355	1629410	.	+	0	ID=CDS:Gene:Y73E7A.1a.1.3;Parent=Transcript:Gene:Y73E7A.1a.1.3
+I	Coding_transcript	CDS	1630554	1630794	.	+	1	ID=CDS:Gene:Y73E7A.1a.1.3;Parent=Transcript:Gene:Y73E7A.1a.1.3
+I	Coding_transcript	CDS	1633222	1633365	.	+	0	ID=CDS:Gene:Y73E7A.1a.1.3;Parent=Transcript:Gene:Y73E7A.1a.1.3
+I	Coding_transcript	gene	1652917	1655337	.	+	.	ID=Gene:Gene:Y71G12B.18
+I	Coding_transcript	mRNA	1652917	1655337	.	+	.	ID=Transcript:Gene:Y71G12B.18.1;Parent=Gene:Gene:Y71G12B.18
+I	Coding_transcript	CDS	1652917	1653000	.	+	0	ID=CDS:Gene:Y71G12B.18.1;Parent=Transcript:Gene:Y71G12B.18.1
+I	Coding_transcript	CDS	1653438	1653755	.	+	0	ID=CDS:Gene:Y71G12B.18.1;Parent=Transcript:Gene:Y71G12B.18.1
+I	Coding_transcript	CDS	1653901	1653981	.	+	0	ID=CDS:Gene:Y71G12B.18.1;Parent=Transcript:Gene:Y71G12B.18.1
+I	Coding_transcript	CDS	1654754	1654975	.	+	0	ID=CDS:Gene:Y71G12B.18.1;Parent=Transcript:Gene:Y71G12B.18.1
+I	Coding_transcript	CDS	1655026	1655334	.	+	0	ID=CDS:Gene:Y71G12B.18.1;Parent=Transcript:Gene:Y71G12B.18.1
+I	Coding_transcript	three_prime_UTR	1655335	1655337	.	+	.	ID=three_prime_UTR:Gene:Y71G12B.18.1;Parent=Transcript:Gene:Y71G12B.18.1
+I	Coding_transcript	gene	1681814	1685064	.	+	.	ID=Gene:Gene:Y71G12B.16
+I	Coding_transcript	mRNA	1681814	1685064	.	+	.	ID=Transcript:Gene:Y71G12B.16.1;Parent=Gene:Gene:Y71G12B.16
+I	Coding_transcript	CDS	1681814	1681899	.	+	0	ID=CDS:Gene:Y71G12B.16.1;Parent=Transcript:Gene:Y71G12B.16.1
+I	Coding_transcript	CDS	1682831	1683432	.	+	1	ID=CDS:Gene:Y71G12B.16.1;Parent=Transcript:Gene:Y71G12B.16.1
+I	Coding_transcript	CDS	1683480	1683521	.	+	2	ID=CDS:Gene:Y71G12B.16.1;Parent=Transcript:Gene:Y71G12B.16.1
+I	Coding_transcript	CDS	1684382	1684450	.	+	2	ID=CDS:Gene:Y71G12B.16.1;Parent=Transcript:Gene:Y71G12B.16.1
+I	Coding_transcript	CDS	1684829	1685064	.	+	2	ID=CDS:Gene:Y71G12B.16.1;Parent=Transcript:Gene:Y71G12B.16.1
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/test_data/deseq_c_elegans_WS200-I-regions.info	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,5 @@
+The files contain example data from 50 genes of the C. elegans genome on chromosome I.
+
+These files are:
+* the genome annotation in GFF3 format
+* two small set of aligned reads in SAM format (generated with PalMapper) from SRX001872 (http://www.ncbi.nlm.nih.gov/sra/SRX001872?report=full) and SRX001875 (http://www.ncbi.nlm.nih.gov/sra/SRX001875?report=full)
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/test_data/deseq_c_elegans_WS200-I-regions_deseq.txt	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,51 @@
+deseq_c_elegans_WS200.I.regions.SRX001872_vs._deseq_c_elegans_WS200.I.regions.SRX001875
+Gene:Gene:Y48G1BL.1	0.298162984580380
+Gene:Gene:F53G12.8	0.0100203770664889
+Gene:Gene:F56A6.1b	0.196356415924958
+Gene:Gene:F56C11.6b	0.131729472518535
+Gene:Gene:Y95B8A.7	0.82068108848155
+Gene:Gene:Y34D9A.2	0.0853090936357318
+Gene:Gene:R06A10.2.1	0.0729242320545049
+Gene:Gene:W04C9.2	0.566684334319464
+Gene:Gene:Y48G1C.2.1	0.600568879247855
+Gene:Gene:Y71G12B.18	0.436992089489852
+Gene:Gene:Y48G1C.9.1	0.653680190916246
+Gene:Gene:Y48G1C.12	0.962705668820165
+Gene:Gene:Y92H12A.4	0.71745387890079
+Gene:Gene:Y34D9A.6	0.554353505200952
+Gene:Gene:Y74C9A.2.2	0.193317121924372
+Gene:Gene:Y73E7A.1a.1	1
+Gene:Gene:Y48G1C.11	0.343541645863403
+Gene:Gene:ZK993.1	0.160531710602269
+Gene:Gene:Y73E7A.9	0.505459732270159
+Gene:Gene:Y34D9A.11	0.0963318383936614
+Gene:Gene:Y92H12BR.7	0.640348677865408
+Gene:Gene:Y92H12BR.3b	0.91026935144141
+Gene:Gene:Y65B4BR.8	0.838122463966569
+Gene:Gene:Y71F9AM.5b	0.971282320939981
+Gene:Gene:R119.7	0.0391196294523181
+Gene:Gene:F56C11.5b	0.457982589114528
+Gene:Gene:Y92H12BR.6	0.487521663730281
+Gene:Gene:Y95B8A.6a.2	0.927779341088235
+Gene:Gene:F53G12.7	0.196705810975026
+Gene:Gene:Y48G1A.2	0.453586101344411
+Gene:Gene:C53D5.1c.1	0.391738974840997
+Gene:Gene:Y34D9A.3	0.71006993005907
+Gene:Gene:Y18H1A.6	0.329792105744889
+Gene:Gene:T06A4.1b	0.295665526024382
+Gene:Gene:F53G12.3	0.631494248315874
+Gene:Gene:R119.6	0.651145530807306
+Gene:Gene:Y95B8A.5	0.512001544838653
+Gene:Gene:Y65B4BR.4b	0.904179315054261
+Gene:Gene:K12C11.2.1	0.364903241182862
+Gene:Gene:F53G12.5b	0.537007770889288
+Gene:Gene:Y95B8A.8	0.59137956260358
+Gene:Gene:T06A4.3a	0.171238758638891
+Gene:Gene:F53G12.4	0.949563214223464
+Gene:Gene:C54G6.2	0.0780422099961616
+Gene:Gene:W04C9.1	0.223549535364483
+Gene:Gene:K12C11.6	0.301231157430176
+Gene:Gene:F47G6.1	0.196694866924542
+Gene:Gene:Y71F9AM.4a	0.728480588565213
+Gene:Gene:Y71G12B.16	0.900935024006703
+Gene:Gene:Y65B4BR.1	0.475324346757848
Binary file deseq-hts_2.0/test_data/genes.mat has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/tools/GFFParser.py	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,379 @@
+#!/usr/bin/env python
+"""
+Extract genome annotation from a GFF (a tab delimited format for storing sequence features and annotations) file.
+
+Requirements:
+    Numpy :- http://numpy.org/
+    Scipy :- http://scipy.org/
+
+Copyright (C)
+
+2009-2012 Friedrich Miescher Laboratory of the Max Planck Society, Tubingen, Germany.
+2012-2013 Memorial Sloan-Kettering Cancer Center, New York City, USA.
+"""
+
+import re
+import os
+import sys
+import urllib
+import numpy as np
+import scipy.io as sio
+from collections import defaultdict
+import helper as utils
+
+def _attribute_tags(col9):
+    """
+    Split the key-value tags from the attribute column, it takes column number 9 from GTF/GFF file
+    """
+    info = defaultdict(list)
+    is_gff = False
+
+    if not col9:
+        return is_gff, info
+
+    # trim the line ending semi-colon  ucsc may have some white-space
+    col9 = col9.rstrip(';| ')
+    # attributes from 9th column
+    atbs = col9.split(" ; ")
+    if len(atbs) == 1:
+        atbs = col9.split("; ")
+        if len(atbs) == 1:
+            atbs = col9.split(";")
+    # check the GFF3 pattern which has key value pairs like:
+    gff3_pat = re.compile("\w+=")
+    # sometime GTF have: gene_id uc002zkg.1;
+    gtf_pat = re.compile("\s?\w+\s")
+
+    key_vals = []
+
+    if gff3_pat.match(atbs[0]): # gff3 pattern
+        is_gff = True
+        key_vals = [at.split('=') for at in atbs]
+    elif gtf_pat.match(atbs[0]): # gtf pattern
+        for at in atbs:
+            key_vals.append(at.strip().split(" ",1))
+    else:
+        # to handle attribute column has only single value
+        key_vals.append(['ID', atbs[0]])
+    # get key, val items
+    for item in key_vals:
+        key, val = item
+        # replace the double qoutes from feature identifier
+        val = re.sub('"', '', val)
+        # replace the web formating place holders to plain text format
+        info[key].extend([urllib.unquote(v) for v in val.split(',') if v])
+
+    return is_gff, info
+
+def _spec_features_keywd(gff_parts):
+    """
+    Specify the feature key word according to the GFF specifications
+    """
+    for t_id in ["transcript_id", "transcriptId", "proteinId"]:
+        try:
+            gff_parts["info"]["Parent"] = gff_parts["info"][t_id]
+            break
+        except KeyError:
+            pass
+    for g_id in ["gene_id", "geneid", "geneId", "name", "gene_name", "genename"]:
+        try:
+            gff_parts["info"]["GParent"] = gff_parts["info"][g_id]
+            break
+        except KeyError:
+            pass
+    ## TODO key words
+    for flat_name in ["Transcript", "CDS"]:
+        if gff_parts["info"].has_key(flat_name):
+            # parents
+            if gff_parts['type'] in [flat_name] or re.search(r'transcript', gff_parts['type'], re.IGNORECASE):
+                if not gff_parts['id']:
+                    gff_parts['id'] = gff_parts['info'][flat_name][0]
+                    #gff_parts["info"]["ID"] = [gff_parts["id"]]
+            # children
+            elif gff_parts["type"] in ["intron", "exon", "pseudogenic_exon", "three_prime_UTR",
+                        "coding_exon", "five_prime_UTR", "CDS", "stop_codon",
+                        "start_codon"]:
+                gff_parts["info"]["Parent"] = gff_parts["info"][flat_name]
+            break
+    return gff_parts
+
+def Parse(ga_file):
+    """
+    Parsing GFF/GTF file based on feature relationship, it takes the input file.
+    """
+    child_map = defaultdict(list)
+    parent_map = dict()
+
+    ga_handle = utils._open_file(ga_file)
+
+    for rec in ga_handle:
+        rec = rec.strip('\n\r')
+
+        # skip empty line fasta identifier and commented line
+        if not rec or rec[0] in  ['#', '>']:
+            continue
+        # skip the genome sequence
+        if not re.search('\t', rec):
+            continue
+
+        parts = rec.split('\t')
+        assert len(parts) >= 8, rec
+
+        # process the attribute column (9th column)
+        ftype, tags = _attribute_tags(parts[-1])
+        if not tags: # skip the line if no attribute column.
+	        continue
+
+        # extract fields
+        if parts[1]:
+            tags["source"] = parts[1]
+        if parts[7]:
+            tags["phase"] = parts[7]
+
+        gff_info = dict()
+        gff_info['info'] = dict(tags)
+        #gff_info["is_gff3"] = ftype
+        gff_info['chr'] = parts[0]
+
+        if parts[3] and parts[4]:
+            gff_info['location'] = [int(parts[3]) ,
+                        int(parts[4])]
+            gff_info['type'] = parts[2]
+            gff_info['id'] = tags.get('ID', [''])[0]
+            if parts[6] in ['?', '.']:
+                parts[6] = None
+            gff_info['strand'] = parts[6]
+
+            # key word according to the GFF spec.
+            if not ftype:
+                gff_info = _spec_features_keywd(gff_info)
+
+            # link the feature relationships
+            if gff_info['info'].has_key('Parent'):
+                for p in gff_info['info']['Parent']:
+                    if p == gff_info['id']:
+                        gff_info['id'] = ''
+                        break
+                rec_category = 'child'
+            elif gff_info['id']:
+                rec_category = 'parent'
+            else:
+                rec_category = 'record'
+
+            # depends on the record category organize the features
+            if rec_category == 'child':
+                for p in gff_info['info']['Parent']:
+                    # create the data structure based on source and feature id
+                    child_map[(gff_info['chr'], gff_info['info']['source'], p)].append(
+                                            dict( type = gff_info['type'],
+                                            location =  gff_info['location'],
+                                            strand = gff_info['strand'],
+                                            ID = gff_info['id'],
+                                            gene_id = gff_info['info'].get('GParent', '')
+                                            ))
+            elif rec_category == 'parent':
+                parent_map[(gff_info['chr'], gff_info['info']['source'], gff_info['id'])] = dict(
+                                            type = gff_info['type'],
+                                            location = gff_info['location'],
+                                            strand = gff_info['strand'],
+                                            name = tags.get('Name', [''])[0])
+            elif rec_category == 'record':
+                #TODO how to handle plain records?
+                c = 1
+    ga_handle.close()
+
+    # depends on file type create parent feature
+    if not ftype:
+        parent_map, child_map = _create_missing_feature_type(parent_map, child_map)
+
+    # connecting parent child relations
+    # // essentially the parent child features are here from any type of GTF/GFF2/GFF3 file
+    gene_mat = _format_gene_models(parent_map, child_map)
+
+    return gene_mat
+
+def _format_gene_models(parent_nf_map, child_nf_map):
+    """
+    Genarate GeneObject based on the parsed file contents
+
+    parent_map: parent features with source and chromosome information
+    child_map: transctipt and exon information are encoded
+    """
+    g_cnt = 0
+    gene = np.zeros((len(parent_nf_map),), dtype = utils.init_gene_DE())
+
+    for pkey, pdet in parent_nf_map.items():
+        # considering only gene features
+        if not re.search(r'gene', pdet.get('type', '')):
+            continue
+        # infer the gene start and stop if not there in the
+        if not pdet.get('location', []):
+            GNS, GNE = [], []
+            # multiple number of transcripts
+            for L1 in child_nf_map[pkey]:
+                GNS.append(L1.get('location', [])[0])
+                GNE.append(L1.get('location', [])[1])
+            GNS.sort()
+            GNE.sort()
+            pdet['location'] = [GNS[0], GNE[-1]]
+        orient = pdet.get('strand', '')
+
+        gene[g_cnt]['id'] = g_cnt +1
+        gene[g_cnt]['chr'] = pkey[0]
+        gene[g_cnt]['source'] = pkey[1]
+        gene[g_cnt]['name'] = pkey[-1]
+        gene[g_cnt]['start'] = pdet.get('location', [])[0]
+        gene[g_cnt]['stop'] = pdet.get('location', [])[1]
+        gene[g_cnt]['strand'] = orient
+
+        # default value
+        gene[g_cnt]['is_alt_spliced'] = 0
+        if len(child_nf_map[pkey]) > 1:
+            gene[g_cnt]['is_alt_spliced'] = 1
+
+        # complete sub-feature for all transcripts
+        dim = len(child_nf_map[pkey])
+        TRS = np.zeros((dim,), dtype=np.object)
+        EXON = np.zeros((dim,), dtype=np.object)
+
+        # fetching corresponding transcripts
+        for xq, Lv1 in enumerate(child_nf_map[pkey]):
+
+            TID = Lv1.get('ID', '')
+            TRS[xq]= np.array([TID])
+
+            orient = Lv1.get('strand', '')
+
+            # fetching different sub-features
+            child_feat = defaultdict(list)
+            for Lv2 in child_nf_map[(pkey[0], pkey[1], TID)]:
+                E_TYP = Lv2.get('type', '')
+                child_feat[E_TYP].append(Lv2.get('location'))
+
+            # make exon coordinate from cds and utr regions
+            if not child_feat.get('exon'):
+                if child_feat.get('CDS'):
+                    exon_cod = utils.make_Exon_cod( orient,
+                                NonetoemptyList(child_feat.get('five_prime_UTR')),
+                                NonetoemptyList(child_feat.get('CDS')),
+                                NonetoemptyList(child_feat.get('three_prime_UTR')))
+                    child_feat['exon'] = exon_cod
+                else:
+                    # searching through keys to find a pattern describing exon feature
+                    ex_key_pattern = [k for k in child_feat if k.endswith("exon")]
+                    child_feat['exon'] = child_feat[ex_key_pattern[0]]
+                    # TODO only UTR's
+
+            # make general ascending order of coordinates
+            if orient == '-':
+                for etype, excod in child_feat.items():
+                    if len(excod) > 1:
+                        if excod[0][0] > excod[-1][0]:
+                            excod.reverse()
+                            child_feat[etype] = excod
+
+            # add sub-feature # make array for export to different out
+            EXON[xq] = np.array(child_feat.get('exon'), np.float64)
+
+        # add sub-features to the parent gene feature
+        gene[g_cnt]['transcripts'] = TRS
+        gene[g_cnt]['exons'] = EXON
+
+        gene[g_cnt]['gene_info'] = dict( ID = pkey[-1],
+                                Name = pdet.get('name'),
+                                Source = pkey[1])
+        g_cnt += 1
+
+    ## deleting empty gene records from the main array
+    for XP, ens in enumerate(gene):
+        if ens[0]==0:
+            break
+
+    XQC = range(XP, len(gene)+1)
+    gene = np.delete(gene, XQC)
+
+    return gene
+
+def NonetoemptyList(XS):
+    """
+    Convert a None type to empty list
+    """
+    return [] if XS is None else XS
+
+def _create_missing_feature_type(p_feat, c_feat):
+    """
+    GFF/GTF file defines only child features. This function tries to create
+    the parent feature from the information provided in the attribute column.
+
+    example:
+    chr21   hg19_knownGene  exon    9690071 9690100 0.000000        +       .       gene_id "uc002zkg.1"; transcript_id "uc002zkg.1";
+    chr21   hg19_knownGene  exon    9692178 9692207 0.000000        +       .       gene_id "uc021wgt.1"; transcript_id "uc021wgt.1";
+    chr21   hg19_knownGene  exon    9711935 9712038 0.000000        +       .       gene_id "uc011abu.2"; transcript_id "uc011abu.2";
+
+    This function gets the parsed feature annotations.
+    """
+    child_n_map = defaultdict(list)
+    for fid, det in c_feat.items():
+        # get the details from grand child
+        GID = STRD = None
+        SPOS, EPOS = [], []
+        TYP = dict()
+        for gchild in det:
+            GID = gchild.get('gene_id', [''])[0]
+            SPOS.append(gchild.get('location', [])[0])
+            EPOS.append(gchild.get('location', [])[1])
+            STRD = gchild.get('strand', '')
+            TYP[gchild.get('type', '')] = 1
+        SPOS.sort()
+        EPOS.sort()
+
+        # infer transcript type
+        transcript_type = 'transcript'
+        transcript_type = 'mRNA' if TYP.get('CDS', '') or TYP.get('cds', '') else transcript_type
+
+        # gene id and transcript id are same
+        transcript_id = fid[-1]
+        if GID == transcript_id:
+            transcript_id = 'Transcript:' + str(GID)
+
+        # level -1 feature type
+        p_feat[(fid[0], fid[1], GID)] = dict( type = 'gene',
+                                            location = [], ## infer location based on multiple transcripts
+                                            strand = STRD,
+                                            name = GID )
+        # level -2 feature type
+        child_n_map[(fid[0], fid[1], GID)].append(
+                                            dict( type = transcript_type,
+                                            location =  [SPOS[0], EPOS[-1]],
+                                            strand = STRD,
+                                            ID = transcript_id,
+                                            gene_id = '' ))
+        # reorganizing the grand child
+        for gchild in det:
+            child_n_map[(fid[0], fid[1], transcript_id)].append(
+                                            dict( type = gchild.get('type', ''),
+                                            location =  gchild.get('location'),
+                                            strand = gchild.get('strand'),
+                                            ID = gchild.get('ID'),
+                                            gene_id = '' ))
+    return p_feat, child_n_map
+
+
+## General instruction to use the above functions:
+## Usage: GFFParser.py in.gff3 out.mat
+
+try:
+    gff_file = sys.argv[1]
+    out_mat = sys.argv[2]
+except:
+    print __doc__
+    sys.exit(-1)
+
+## Parse the file accoring to the type and returns the genes informations --
+gene_struct = Parse(gff_file)
+
+## Write the gene annotations to a matlab struct array format --
+sio.savemat(out_mat,
+    mdict = dict(genes = gene_struct),
+    format = '5',
+    oned_as = 'row')
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/tools/helper.py	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,179 @@
+#!/usr/bin/env python
+"""
+Common utility functions
+"""
+
+import os
+import re
+import sys
+import gzip
+import bz2
+import numpy
+
+def init_gene_DE():
+    """
+    Initializing the gene structure for DE
+    """
+    gene_det = [('id', 'f8'),
+                    ('chr', 'S15'),
+                    ('exons', numpy.dtype),
+                    ('gene_info', numpy.dtype),
+                    ('is_alt_spliced', 'f8'),
+                    ('name', 'S25'),
+                    ('source', 'S25'),
+                    ('start', 'f8'),
+                    ('stop', 'f8'),
+                    ('strand', 'S2'),
+                    ('transcripts', numpy.dtype)]
+
+    return gene_det
+
+def _open_file(fname):
+    """
+    Open the file (supports .gz .bz2) and returns the handler
+    """
+    try:
+        if os.path.splitext(fname)[1] == ".gz":
+            FH = gzip.open(fname, 'rb')
+        elif os.path.splitext(fname)[1] == ".bz2":
+            FH = bz2.BZ2File(fname, 'rb')
+        else:
+            FH = open(fname, 'rU')
+    except Exception as error:
+        sys.exit(error)
+    return FH
+
+def make_Exon_cod(strand_p, five_p_utr, cds_cod, three_p_utr):
+    """
+    Create exon cordinates from UTR's and CDS region
+    """
+    exon_pos = []
+    if strand_p == '+':
+        utr5_start, utr5_end = 0, 0
+        if five_p_utr != []:
+            utr5_start, utr5_end = five_p_utr[-1][0], five_p_utr[-1][1]
+        cds_5start, cds_5end = cds_cod[0][0], cds_cod[0][1]
+        jun_exon = []
+        if cds_5start-utr5_end == 0 or cds_5start-utr5_end == 1:
+            jun_exon = [utr5_start, cds_5end]
+        if len(cds_cod) == 1:
+            five_prime_flag = 0
+            if jun_exon != []:
+                five_p_utr = five_p_utr[:-1]
+                five_prime_flag = 1
+            for utr5 in five_p_utr:
+                exon_pos.append(utr5)
+            jun_exon = []
+            utr3_start, utr3_end = 0, 0
+            if three_p_utr != []:
+                utr3_start = three_p_utr[0][0]
+                utr3_end = three_p_utr[0][1]
+            if utr3_start-cds_5end == 0 or utr3_start-cds_5end == 1:
+                jun_exon = [cds_5start, utr3_end]
+            three_prime_flag = 0
+            if jun_exon != []:
+                cds_cod = cds_cod[:-1]
+                three_p_utr = three_p_utr[1:]
+                three_prime_flag = 1
+            if five_prime_flag == 1 and three_prime_flag == 1:
+                exon_pos.append([utr5_start, utr3_end])
+            if five_prime_flag == 1 and three_prime_flag == 0:
+                exon_pos.append([utr5_start, cds_5end])
+                cds_cod = cds_cod[:-1]
+            if five_prime_flag == 0 and three_prime_flag == 1:
+                exon_pos.append([cds_5start, utr3_end])
+            for cds in cds_cod:
+                exon_pos.append(cds)
+            for utr3 in three_p_utr:
+                exon_pos.append(utr3)
+        else:
+            if jun_exon != []:
+                five_p_utr = five_p_utr[:-1]
+                cds_cod = cds_cod[1:]
+            for utr5 in five_p_utr:
+                exon_pos.append(utr5)
+            exon_pos.append(jun_exon) if jun_exon != [] else ''
+            jun_exon = []
+            utr3_start, utr3_end = 0, 0
+            if three_p_utr != []:
+                utr3_start = three_p_utr[0][0]
+                utr3_end = three_p_utr[0][1]
+            cds_3start = cds_cod[-1][0]
+            cds_3end = cds_cod[-1][1]
+            if utr3_start-cds_3end == 0 or utr3_start-cds_3end == 1:
+                jun_exon = [cds_3start, utr3_end]
+            if jun_exon != []:
+                cds_cod = cds_cod[:-1]
+                three_p_utr = three_p_utr[1:]
+            for cds in cds_cod:
+                exon_pos.append(cds)
+            exon_pos.append(jun_exon) if jun_exon != [] else ''
+            for utr3 in three_p_utr:
+                exon_pos.append(utr3)
+    elif strand_p == '-':
+        utr3_start, utr3_end = 0, 0
+        if three_p_utr != []:
+            utr3_start = three_p_utr[-1][0]
+            utr3_end = three_p_utr[-1][1]
+        cds_3start = cds_cod[0][0]
+        cds_3end = cds_cod[0][1]
+        jun_exon = []
+        if cds_3start-utr3_end == 0 or cds_3start-utr3_end == 1:
+            jun_exon = [utr3_start, cds_3end]
+        if len(cds_cod) == 1:
+            three_prime_flag = 0
+            if jun_exon != []:
+                three_p_utr = three_p_utr[:-1]
+                three_prime_flag = 1
+            for utr3 in three_p_utr:
+                exon_pos.append(utr3)
+            jun_exon = []
+            (utr5_start, utr5_end) = (0, 0)
+            if five_p_utr != []:
+                utr5_start = five_p_utr[0][0]
+                utr5_end = five_p_utr[0][1]
+            if utr5_start-cds_3end == 0 or utr5_start-cds_3end == 1:
+                jun_exon = [cds_3start, utr5_end]
+            five_prime_flag = 0
+            if jun_exon != []:
+                cds_cod = cds_cod[:-1]
+                five_p_utr = five_p_utr[1:]
+                five_prime_flag = 1
+            if three_prime_flag == 1 and five_prime_flag == 1:
+                exon_pos.append([utr3_start, utr5_end])
+            if three_prime_flag == 1 and five_prime_flag == 0:
+                exon_pos.append([utr3_start, cds_3end])
+                cds_cod = cds_cod[:-1]
+            if three_prime_flag == 0 and five_prime_flag == 1:
+                exon_pos.append([cds_3start, utr5_end])
+            for cds in cds_cod:
+                exon_pos.append(cds)
+            for utr5 in five_p_utr:
+                exon_pos.append(utr5)
+        else:
+            if jun_exon != []:
+                three_p_utr = three_p_utr[:-1]
+                cds_cod = cds_cod[1:]
+            for utr3 in three_p_utr:
+                exon_pos.append(utr3)
+            if jun_exon != []:
+                exon_pos.append(jun_exon)
+            jun_exon = []
+            (utr5_start, utr5_end) = (0, 0)
+            if five_p_utr != []:
+                utr5_start = five_p_utr[0][0]
+                utr5_end = five_p_utr[0][1]
+            cds_5start = cds_cod[-1][0]
+            cds_5end = cds_cod[-1][1]
+            if utr5_start-cds_5end == 0 or utr5_start-cds_5end == 1:
+                jun_exon = [cds_5start, utr5_end]
+            if jun_exon != []:
+                cds_cod = cds_cod[:-1]
+                five_p_utr = five_p_utr[1:]
+            for cds in cds_cod:
+                exon_pos.append(cds)
+            if jun_exon != []:
+                exon_pos.append(jun_exon)
+            for utr5 in five_p_utr:
+                exon_pos.append(utr5)
+    return exon_pos
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/deseq-hts_2.0/tools/separate.m	Tue Oct 08 08:15:34 2013 -0400
@@ -0,0 +1,7 @@
+function f = separate(str, delim)
+
+f={};
+idx=[0 find(str==delim) length(str)+1];
+for i=1:length(idx)-1
+    f{i}=deblank(str(idx(i)+1:idx(i+1)-1));
+end;