Mercurial > repos > iuc > scpipe

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scpipe.R	Wed Aug 15 13:54:40 2018 -0400
@@ -0,0 +1,149 @@
+options( show.error.messages=F, error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )
+
+# we need that to not crash galaxy with an UTF8 error on German LC settings.
+loc <- Sys.setlocale("LC_MESSAGES", "en_US.UTF-8")
+
+suppressPackageStartupMessages({
+    library(scPipe)
+    library(SingleCellExperiment)
+    library(optparse)
+    library(readr)
+    library(ggplot2)
+    library(plotly)
+    library(DT)
+    library(scater)
+    library(scran)
+    library(scales)
+    library(Rtsne)
+})
+
+option_list <- list(
+    make_option(c("-fasta","--fasta"), type="character", help="Genome fasta file"),
+    make_option(c("-exons","--exons"), type="character", help="Exon annotation gff3 file"),
+    make_option(c("-barcodes","--barcodes"), type="character", help="Cell barcodes csv file"),
+    make_option(c("-read1","--read1"), type="character", help="Read 1 fastq.gz"),
+    make_option(c("-read2","--read2"), type="character", help="Read 2 fastq.gz"),
+    make_option(c("-samplename","--samplename"), type="character", help="Name to use for sample"),
+    make_option(c("-bs1","--bs1"), type="integer", help="Barcode start in Read 1"),
+    make_option(c("-bl1","--bl1"), type="integer", help="Barcode length in Read 1"),
+    make_option(c("-bs2","--bs2"), type="integer", help="Barcode start in Read 2"),
+    make_option(c("-bl2","--bl2"), type="integer", help="Barcode length in Read 2"),
+    make_option(c("-us","--us"), type="integer", help="UMI start in Read 2"),
+    make_option(c("-ul","--ul"), type="integer", help="UMI length in Read 2"),
+    make_option(c("-rmlow","--rmlow"), type="logical", help="Remove reads with N in barcode or UMI"),
+    make_option(c("-rmN","--rmN"), type="logical", help="Remove reads with low quality"),
+    make_option(c("-minq","--minq"), type="integer", help="Minimum read quality"),
+    make_option(c("-numbq","--numbq"), type="integer", help="Maximum number of bases below minq"),
+    make_option(c("-stnd","--stnd"), type="logical", help="Perform strand-specific mapping"),
+    make_option(c("-max_mis","--max_mis"), type="integer", help="Maximum mismatch allowed in barcode"),
+    make_option(c("-UMI_cor","--UMI_cor"), type="integer", help="Correct UMI sequence error"),
+    make_option(c("-gene_fl","--gene_fl"), type="logical", help="Remove low abundant genes"),
+    make_option(c("-max_reads","--max_reads"), type="integer", help="Maximum reads processed"),
+    make_option(c("-min_count","--min_count"), type="integer", help="Minimum count to keep"),
+    make_option(c("-report","--report"), type="logical", help="HTML report of plots"),
+    make_option(c("-rdata","--rdata"), type="logical", help="Output RData file"),
+    make_option(c("-nthreads","--nthreads"), type="integer", help="Number of threads")
+  )
+
+parser <- OptionParser(usage = "%prog [options] file", option_list=option_list)
+args = parse_args(parser)
+
+fa_fn = args$fasta
+anno_fn = args$exons
+fq_R1 = args$read1
+fq_R2 = args$read2
+read_structure = list(
+    bs1 = args$bs1,   # barcode start position in fq_R1, -1 indicates no barcode
+    bl1 = args$bl1,    # barcode length in fq_R1, 0 since no barcode present
+    bs2 = args$bs2,    # barcode start position in fq_R2
+    bl2 = args$bl2,   # barcode length in fq_R2
+    us = args$us,    # UMI start position in fq_R2
+    ul = args$ul     # UMI length
+)
+
+if (args$us == -1) {
+  has_umi = FALSE
+} else {
+  has_umi = TRUE
+}
+
+filter_settings=list(rmlow=args$rmlow, rmN=args$rmN, minq=args$minq, numbq=args$numbq)
+
+# Outputs
+out_dir = "."
+fasta_index = file.path(out_dir, paste0(fa_fn, ".fasta_index"))
+combined_fastq = file.path(out_dir, "combined.fastq")
+aligned_bam = file.path(out_dir, "aligned.bam")
+mapped_bam = file.path(out_dir, "aligned.mapped.bam")
+
+
+print("Trimming barcodes")
+sc_trim_barcode(combined_fastq,
+                fq_R1,
+                fq_R2,
+                read_structure=read_structure,
+                filter_settings=filter_settings)
+
+print("Building genome index")
+Rsubread::buildindex(basename=fasta_index, reference=fa_fn)
+
+print("Aligning reads to genome")
+Rsubread::align(index=fasta_index,
+    readfile1=combined_fastq,
+    output_file=aligned_bam,
+    nthreads=args$nthreads)
+
+if (!is.null(args$barcodes)) {
+  barcode_anno=args$barcodes
+} else {
+  print("Detecting barcodes")
+  # detect 10X barcodes and generate sample_index.csv file
+  barcode_anno = "sample_index.csv"
+  sc_detect_bc(
+      infq=combined_fastq,
+      outcsv=barcode_anno,
+      bc_len=read_structure$bl2,
+      max_reads=args$max_reads,
+      min_count=args$min_count,
+      max_mismatch=args$max_mis
+  )
+}
+
+print("Assigning reads to exons")
+sc_exon_mapping(aligned_bam, mapped_bam, anno_fn, bc_len=read_structure$bl2, UMI_len=read_structure$ul, stnd=args$stnd)
+
+print("De-multiplexing data")
+sc_demultiplex(mapped_bam, out_dir, barcode_anno, has_UMI=has_umi)
+
+print("Counting genes")
+sc_gene_counting(out_dir, barcode_anno, UMI_cor=args$UMI_cor, gene_fl=args$gene_fl)
+
+print("Creating SingleCellExperiment object")
+sce <- create_sce_by_dir(out_dir)
+
+if (!is.null(args$report)) {
+print("Creating report")
+create_report(sample_name=args$samplename,
+   outdir=out_dir,
+   r1=fq_R1,
+   r2=fq_R2,
+   outfq=combined_fastq,
+   read_structure=read_structure,
+   filter_settings=filter_settings,
+   align_bam=aligned_bam,
+   genome_index=fasta_index,
+   map_bam=mapped_bam,
+   exon_anno=anno_fn,
+   stnd=args$stnd,
+   fix_chr=FALSE,
+   barcode_anno=barcode_anno,
+   max_mis=args$max_mis,
+   UMI_cor=args$UMI_cor,
+   gene_fl=args$gene_fl)
+}
+
+if (!is.null(args$rdata) ) {
+    save(sce, file = file.path(out_dir,"scPipe_analysis.RData"))
+}
+
+sessionInfo()
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/scpipe.xml	Wed Aug 15 13:54:40 2018 -0400
@@ -0,0 +1,264 @@
+<tool id="scpipe" name="scPipe" version="1.0.0">
+    <description>- preprocessing pipeline for single cell RNA-seq</description>
+    <requirements>
+        <requirement type="package" version="1.0.0">bioconductor-scpipe</requirement>
+        <requirement type="package" version="1.28.1">bioconductor-rsubread</requirement>
+        <requirement type="package" version="1.20">r-knitr</requirement>
+        <requirement type="package" version="1.10">r-rmarkdown</requirement>
+        <requirement type="package" version="1.1.1">r-readr</requirement>
+        <requirement type="package" version="4.7.1">r-plotly</requirement>
+        <requirement type="package" version="0.4">r-dt</requirement>
+        <requirement type="package" version="1.6.0">bioconductor-scater</requirement>
+        <requirement type="package" version="1.6.2">bioconductor-scran</requirement>
+        <requirement type="package" version="0.13">r-rtsne</requirement>
+        <!-- Using older version of ggplot2 as getting error like this with 3.0.0:
+        https://github.com/ggobi/ggally/issues/263  -->
+        <requirement type="package" version="2.2.1">r-ggplot2</requirement>
+        <requirement type="package" version="1.6.0">r-optparse</requirement>
+    </requirements>
+    <version_command><![CDATA[
+echo $(R --version | grep version | grep -v GNU)", scPipe version" $(R --vanilla --slave -e "library(scPipe); cat(sessionInfo()\$otherPkgs\$scPipe\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", Rsubread version" $(R --vanilla --slave -e "library(Rsubread); cat(sessionInfo()\$otherPkgs\$Rsubread\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", knitr version" $(R --vanilla --slave -e "library(knitr); cat(sessionInfo()\$otherPkgs\$knitr\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", rmarkdown version" $(R --vanilla --slave -e "library(rmarkdown); cat(sessionInfo()\$otherPkgs\$rmarkdown\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", readr version" $(R --vanilla --slave -e "library(readr); cat(sessionInfo()\$otherPkgs\$readr\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", plotly version" $(R --vanilla --slave -e "library(plotly); cat(sessionInfo()\$otherPkgs\$plotly\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", DT version" $(R --vanilla --slave -e "library(DT); cat(sessionInfo()\$otherPkgs\$DT\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", scater version" $(R --vanilla --slave -e "library(scater); cat(sessionInfo()\$otherPkgs\$scater\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", scran version" $(R --vanilla --slave -e "library(scran); cat(sessionInfo()\$otherPkgs\$scran\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", rtsne version" $(R --vanilla --slave -e "library(Rtsne); cat(sessionInfo()\$otherPkgs\$Rtsne\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", ggplot2 version" $(R --vanilla --slave -e "library(ggplot2); cat(sessionInfo()\$otherPkgs\$ggplot2\$Version)" 2> /dev/null | grep -v -i "WARNING: ")", optparse version" $(R --vanilla --slave -e "library(optparse); cat(sessionInfo()\$otherPkgs\$optparse\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
+    ]]></version_command>
+    <command detect_errors="exit_code"><![CDATA[
+#import re
+
+## Link input files
+
+#if $ref_fasta.fasta_source == "history":
+    #set $fasta_name = re.sub('[^\w\-\s]', '_', str($ref_fasta.ref_fa_hist.element_identifier))
+    ln -s '$ref_fasta.ref_fa_hist' '$fasta_name' &&
+#else:
+    #set $fasta_name = re.sub('[^\w\-\s]', '_', str($ref_fasta.ref_fa_builtin.element_identifier))
+    ln -s '$ref_fasta.ref_fa_builtin.fields.path' '$fasta_name' &&
+#end if
+
+#set $anno_name = re.sub('[^\w\-\s]', '_', str($exons.element_identifier))
+#set $anno_name = $anno_name + ".gff3"
+ln -s '${exons}' '$anno_name' &&
+
+#if $paired_format.paired_format_selector == 'paired_collection':
+    #set $in1 = $paired_format.paired_input.forward
+    #set $in2 = $paired_format.paired_input.reverse
+    #set $in1_name = re.sub('[^\w\-\s]', '_', str($paired_format.paired_input.name))
+    #set $in2_name = re.sub('[^\w\-\s]', '_', str("%s_%s" % ($paired_format.paired_input.name, "R2")))
+    #set out1 = $output_paired_coll.forward
+    #set out2 = $output_paired_coll.reverse
+    ln -s '$in1' '$in1_name' &&
+    ln -s '$in2' '$in2_name' &&
+#else
+    #set $in1_name = re.sub('[^\w\-\s]', '_', str($in1.element_identifier))
+    ln -s '$in1' '$in1_name' &&
+
+    #if str($paired_format.paired_format_selector) == 'paired':
+        #set $in2_name = re.sub('[^\w\-\s]', '_', str($in2.element_identifier))
+        ln -s '$in2' '$in2_name' &&
+    #end if
+#end if
+
+#if $rscript:
+    cp '$__tool_directory__/scpipe.R' '$out_rscript' &&
+#end if
+
+TAB=\$(printf '\t') &&
+
+#if $barcodes:
+    sed -i.bak -e "s/\${TAB}/,/g" '$barcodes' &&
+#end if
+
+## Run scPipe
+
+Rscript '$__tool_directory__/scpipe.R'
+
+--fasta '$fasta_name'
+--exons '$anno_name'
+--samplename '$in1_name'
+--read1 '$in1_name'
+--read2 '$in2_name'
+--bs1 $bs1
+--bl1 $bl1
+--bs2 $bs2
+--bl2 $bl2
+--us $us
+--ul $ul
+
+#if $barcodes:
+    --barcodes '$barcodes'
+#end if
+
+#if $report:
+    --report '$report'
+#end if
+
+#if $rdata:
+    --rdata '$rdata'
+#end if
+
+--rmlow $adv.rmlow
+--rmN $adv.rmN
+--minq $adv.minq
+--numbq $adv.numbq
+--stnd $adv.stnd
+--max_mis $adv.max_mis
+--UMI_cor $adv.UMI_cor
+--gene_fl $adv.gene_fl
+--max_reads $adv.max_reads
+--min_count $adv.min_count
+--nthreads \${GALAXY_SLOTS:-2}
+
+&&
+sed -e "s/,/\${TAB}/g" gene_count.csv > gene_count.tsv
+
+]]></command>
+
+    <inputs>
+        <conditional name="ref_fasta">
+            <param name="fasta_source" type="select" label="Reference genome FASTA">
+                <option value="cached" selected="true">Use a built-in genome</option>
+                <option value="history">Use a FASTA from history</option>
+            </param>
+            <when value="cached">
+                <param name="ref_fa_builtin" type="select" label="Select a built-in FASTA" help="If your genome of interest is not listed, contact your Galaxy administrator">
+                    <options from_data_table="all_fasta">
+                        <filter type="sort_by" column="2" />
+                        <validator type="no_options" message="No FASTA is available for the selected input dataset" />
+                    </options>
+                </param>
+            </when>
+            <when value="history">
+                <param name="ref_fa_hist" type="data" format="fasta" label="Select a history FASTA" />
+            </when>
+        </conditional>
+        <param name="exons" type="data" format="gff3" label="Exon annotation GFF3 file" help="Current supported sources: ENSEMBL, GENCODE and RefSeq"/>
+
+        <conditional name="paired_format">
+            <param name="paired_format_selector" type="select" label="Paired reads or Paired collection">
+                <option value="paired">Paired</option>
+                <option value="paired_collection">Paired Collection</option>
+            </param>
+            <when value="paired">
+                <param name="in1" type="data" format="fastq.gz,fastq" label="Input Read 1" help="Read 1 should contain the transcripts in fastq.gz format"/>
+                <param name="in2" type="data" format="fastq.gz,fastq" label="Input Read 2" help="Read 2 should contain UMI and barcodes in fastq.gz format"/>
+            </when>
+            <when value="paired_collection">
+                <param name="paired_input" type="data_collection" collection_type="paired" format="fastq.gz,fastq" label="Select paired collection(s)"/>
+            </when>
+        </conditional>
+        <param name="barcodes" type="data" format="tabular,tsv" optional="True" label="Cell barcodes file" help="Optional file of cell barcodes. Should contain at least two columns, where the first column has the cell id and the second column contains the barcode sequence."/>
+        <param argument="--bs1" type="integer" min="-1" value="-1" label="Barcode start Read 1" help="Barcode start position in Read 1. Positions are 0-indexed so the first base is considered base 0, -1 indicates no barcode. Default: -1" />
+        <param argument="--bl1" type="integer" min="0" value="0" label="Barcode length Read 1" help="Barcode length in Read 1, 0 if no barcode present. Default: 0" />
+        <param argument="--bs2" type="integer" min="-1" value="6" label="Barcode start Read 2" help="Barcode start position in Read 2. Positions are 0-indexed so the first base is considered base 0, -1 indicates no barcode.  Default: 6" />
+        <param argument="--bl2" type="integer" min="0" value="8" label="Barcode length Read 2" help="Barcode length in Read 2, 0 if no barcode present. Default: 8" />
+        <param argument="--us" type="integer" min="-1" value="0" label="UMI start Read 2" help="UMI start position in Read 2. Positions are 0-indexed so the first base is considered base 0, -1 indicates no UMI.  Default: 0" />
+        <param argument="--ul" type="integer" min="0" value="6" label="UMI length Read 2" help="UMI length in Read 2, 0 if no UMI present. Default: 6" />
+        <param name="report" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="True" label="Output HTML Report?" help="If this option is set to Yes, a HTML report containing QC metrics will be output. Default: Yes" />
+        <param name="rscript" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="False" label="Output Rscript?" help="If this option is set to Yes, the Rscript used to annotate the IDs will be provided as a text file in the output. Default: No" />
+        <param name="rdata" type="boolean" truevalue="True" falsevalue="False" checked="False" label="Output RData file?"
+            help="Output all the data used by R to construct the tables and plots, can be loaded into R. Default: No">
+        </param>
+        <section name="adv" title="Advanced Options">
+            <param argument="--rmlow" type="boolean" truevalue="True" falsevalue="False" checked="True" label="Remove reads with N in barcode or UMI. Default: Yes" />
+            <param argument="--rmN" type="boolean" truevalue="True" falsevalue="False" checked="True" label="Remove reads with low quality. Default: Yes" />
+            <param argument="--minq" type="integer" min="0" value="20" label="Minimum read quality. Default: 20" />
+            <param argument="--numbq" type="integer" min="0" value="2" label="Maximum number of bases below minq. Default: 2" />
+            <param argument="--stnd" type="boolean" truevalue="True" falsevalue="False" checked="True" label="Perform strand-specific mapping. Default: Yes" />
+            <param argument="--max_mis" type="integer" min="0" value="1" label="Maximum mismatch allowed in barcode. Default: 1" />
+            <param argument="--UMI_cor" type="integer" min="0" value="1" label="Correct UMI sequence error" help="0 means no correction, 1 means simple correction and merge UMI with distance 1. Default: 1" />
+            <param argument="--gene_fl" type="boolean" truevalue="True" falsevalue="False" checked="False" label="Remove low abundant genes" help="Low abundant is defined as only one copy of one UMI for this gene. Default: No" />
+            <param argument="--max_reads" type="integer" min="0" value="1000000" label="Maximum reads processed" help="Maximum reads processed if detecting barcodes. Default: 1,000,000" />
+            <param argument="--min_count" type="integer" min="0" value="10" label="Minimum count to keep" help="Minimum count to keep if detecting barcodes. Barcode will be discarded if it has lower count. This should be set according to --max_reads. Default: 10" />
+        </section>
+    </inputs>
+
+    <outputs>
+        <data name="out_matrix" format="tabular" from_work_dir="gene_count.tsv" label="${tool.name} on ${on_string}: Count Matrix" />
+        <data name="out_report" format="html" from_work_dir="report.nb.html" label="${tool.name} on ${on_string}: HTML Report" >
+            <filter>report</filter>
+        </data>
+        <data name="out_rscript" format="txt" from_work_dir="out_rscript.txt" label="${tool.name} on ${on_string}: Rscript">
+            <filter>rscript</filter>
+        </data>
+        <data name="out_rdata" format="rdata" from_work_dir="scPipe_analysis.RData" label="${tool.name} on ${on_string}: RData file">
+            <filter>rdata</filter>
+        </data>
+    </outputs>
+
+    <tests>
+        <!-- Ensure outputs work -->
+        <test>
+            <param name="fasta_source" value="history"/>
+            <param name="ref_fa_hist" ftype="fasta" value="mm10_MT19.fa.gz"/>
+            <param name="exons" ftype="gff3" value="mm10_MT19.gff3.gz"/>
+            <param name="paired_format_selector" value="paired" />
+            <param name="in1" ftype="fastqsanger.gz" value="CB51_MT19_R1.gz"/>
+            <param name="in2" ftype="fastqsanger.gz" value="CB51_MT19_R2.gz"/>
+            <param name="us" value="-1"/>
+            <param name="max_reads" value="5000000"/>
+            <param name="min_count" value="100"/>
+            <param name="report" value="True" />
+            <output name="out_matrix" >
+                <assert_contents>
+                    <has_text text="ENSMUSG00000024940" />
+                </assert_contents>
+            </output>
+            <output name="out_report" >
+                <assert_contents>
+                    <has_text text="scPipe report for sample" />
+                </assert_contents>
+            </output>
+        </test>
+    </tests>
+    <help><![CDATA[
+.. class:: infomark
+
+**What it does**
+
+scPipe_ is an `R/Bioconductor package`_ that integrates barcode demultiplexing, read alignment, UMI-aware gene-level quantification and quality control of raw sequencing data generated by multiple protocols that include CEL-seq, MARS-seq, Chromium 10X, Drop-seq and Smart-seq. scPipe produces a count matrix that is essential for downstream analysis along with an HTML report that summarises data quality. These results can be used as input for downstream analyses including normalization, visualization and statistical testing.
+Examples of the report output can be found here_.
+
+-----
+
+**Inputs**
+
+    * Reference genome in FASTA format
+    * Exon annotation in GFF3 format
+    * Paired-end FASTQ.GZ reads
+    * Cell barcodes TAB-separated file (Optional)
+
+*Read Structure*
+
+The default read structure represents CEL-seq
+paired-ended reads, with one cell barcode in Read 2 Start from
+6bp and UMI sequence in Read 2 Start from the first bp. So the
+read structure will be : `bs1=-1, bl1=0, bs2=6, bl2=8, us=0,
+ul=6`. `bs1=-1, bl1=0` means we don't have index in Read 1 so we
+set a negative value to start position and zero to the length.
+`bs2=6, bl2=8` means we have index in Read 2 which starts at 6bp
+with 8bp length. `us=0, ul=6` means we have UMI from the
+start of Read 2 and the length is 6bp. NOTE: the zero
+based index is used so the index of the sequence starts from zero. For a
+typical Drop-seq experiment the setting will be `bs1=-1,
+bl1=0, bs2=0, bl2=12, us=12, ul=8`, which means Read 1 only
+contains transcript and the first 12bp in Read 2 are index,
+followed by 8bp UMIs.
+
+-----
+
+**Outputs**
+
+    * Count matrix of genes in Tabular format
+
+Optionally you can choose to output
+
+    * HTML report (default is Yes)
+    * Rscript
+    * RData
+
+.. _scPipe: http://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1006361
+.. _R/Bioconductor package: https://bioconductor.org/packages/release/bioc/html/scPipe.html
+.. _here: http://bioinf.wehi.edu.au/scPipe/
+
+]]></help>
+    <citations>
+        <citation type="doi">10.1371/journal.pcbi.1006361</citation>
+    </citations>
+</tool>
Binary file test-data/CB51_MT19_R1.gz has changed
Binary file test-data/CB51_MT19_R2.gz has changed
Binary file test-data/mm10_MT19.fa.gz has changed
Binary file test-data/mm10_MT19.gff3.gz has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/all_fasta.loc.sample	Wed Aug 15 13:54:40 2018 -0400
@@ -0,0 +1,18 @@
+#This file lists the locations and dbkeys of all the genome and transcriptome fasta files
+#under the "genome" directory (a directory that contains a directory
+#for each build. This file has the format (white space characters are
+#TAB characters):
+#
+#<unique_build_id>	<dbkey>	<display_name>	<file_path>
+#
+#So, all_fasta.loc could look something like this:
+#
+#apiMel3	apiMel3	Honeybee (Apis mellifera): apiMel3	/path/to/genome/apiMel3/apiMel3.fa
+#hg19canon	hg19	Human (Homo sapiens): hg19 Canonical	/path/to/genome/hg19/hg19canon.fa
+#hg19full	hg19	Human (Homo sapiens): hg19 Full	/path/to/genome/hg19/hg19full.fa
+#hg19full.87       hg19    Human (Homo sapiens): hg19 Full Trans v87 /path/to/genome/hg19/hg19full.cdna.all.fa
+
+#Your all_fasta.loc file should contain an entry for each individual
+#fasta file. So there will be multiple fasta files for each build,
+#such as with hg19 above.
+#
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Wed Aug 15 13:54:40 2018 -0400
@@ -0,0 +1,7 @@
+<tables>
+    <!-- Locations of genome fasta files -->
+    <table name="all_fasta" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/all_fasta.loc" />
+    </table>
+</tables>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.test	Wed Aug 15 13:54:40 2018 -0400
@@ -0,0 +1,8 @@
+<tables>
+    <!-- Locations of genome fasta files -->
+    <table name="all_fasta" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/all_fasta.loc" />
+    </table>
+</tables>
+