| Previous changeset 2:6a9b026cb378 (2022-05-20) Next changeset 4:326429ea1d33 (2023-09-03) |
|
Commit message:
planemo upload commit 94b0cd1fff0826c6db3e7dc0c91c0c5a8be8bb0c |
|
added:
cpt-macros.xml gff3.py gff3_fix_sixpack.py gff3_fix_sixpack.xml macros.xml test-data/miro.6pfix.gff3 test-data/miro.cds.gff3 test-data/miro.cds6pfix.gff3 test-data/miro.gff3 |
|
removed:
cpt_fix_sixpack/cpt-macros.xml cpt_fix_sixpack/gff3.py cpt_fix_sixpack/gff3_fix_sixpack.py cpt_fix_sixpack/gff3_fix_sixpack.xml cpt_fix_sixpack/macros.xml cpt_fix_sixpack/test-data/miro.6pfix.gff3 cpt_fix_sixpack/test-data/miro.cds.gff3 cpt_fix_sixpack/test-data/miro.cds6pfix.gff3 cpt_fix_sixpack/test-data/miro.gff3 |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 cpt-macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cpt-macros.xml Mon Jun 05 02:42:28 2023 +0000 |
| [ |
| @@ -0,0 +1,115 @@ +<macros> + <xml name="gff_requirements"> + <requirements> + <requirement type="package" version="2.7">python</requirement> + <requirement type="package" version="1.65">biopython</requirement> + <requirement type="package" version="2.12.1">requests</requirement> + <requirement type="package" version="1.2.2">cpt_gffparser</requirement> + <yield/> + </requirements> + <version_command> + <![CDATA[ + cd '$__tool_directory__' && git rev-parse HEAD + ]]> + </version_command> + </xml> + <xml name="citation/mijalisrasche"> + <citation type="doi">10.1371/journal.pcbi.1008214</citation> + <citation type="bibtex">@unpublished{galaxyTools, + author = {E. Mijalis, H. Rasche}, + title = {CPT Galaxy Tools}, + year = {2013-2017}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } + </citation> + </xml> + <xml name="citations"> + <citations> + <citation type="doi">10.1371/journal.pcbi.1008214</citation> + <citation type="bibtex"> + @unpublished{galaxyTools, + author = {E. Mijalis, H. Rasche}, + title = {CPT Galaxy Tools}, + year = {2013-2017}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } + </citation> + <yield/> + </citations> + </xml> + <xml name="citations-crr"> + <citations> + <citation type="doi">10.1371/journal.pcbi.1008214</citation> + <citation type="bibtex"> + @unpublished{galaxyTools, + author = {C. Ross}, + title = {CPT Galaxy Tools}, + year = {2020-}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } + </citation> + <yield/> + </citations> + </xml> + <xml name="citations-2020"> + <citations> + <citation type="doi">10.1371/journal.pcbi.1008214</citation> + <citation type="bibtex"> + @unpublished{galaxyTools, + author = {E. Mijalis, H. Rasche}, + title = {CPT Galaxy Tools}, + year = {2013-2017}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } + </citation> + <citation type="bibtex"> + @unpublished{galaxyTools, + author = {A. Criscione}, + title = {CPT Galaxy Tools}, + year = {2019-2021}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } + </citation> + <yield/> + </citations> + </xml> + <xml name="citations-2020-AJC-solo"> + <citations> + <citation type="doi">10.1371/journal.pcbi.1008214</citation> + <citation type="bibtex"> + @unpublished{galaxyTools, + author = {A. Criscione}, + title = {CPT Galaxy Tools}, + year = {2019-2021}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } + </citation> + <yield/> + </citations> + </xml> + <xml name="citations-clm"> + <citations> + <citation type="doi">10.1371/journal.pcbi.1008214</citation> + <citation type="bibtex"> + @unpublished{galaxyTools, + author = {C. Maughmer}, + title = {CPT Galaxy Tools}, + year = {2017-2020}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } + </citation> + <yield/> + </citations> + </xml> + <xml name="sl-citations-clm"> + <citation type="bibtex"> + @unpublished{galaxyTools, + author = {C. Maughmer}, + title = {CPT Galaxy Tools}, + year = {2017-2020}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } + </citation> + <yield/> + </xml> +</macros> |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 cpt_fix_sixpack/cpt-macros.xml --- a/cpt_fix_sixpack/cpt-macros.xml Fri May 20 08:48:25 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,115 +0,0 @@ -<?xml version="1.0"?> -<macros> - <xml name="gff_requirements"> - <requirements> - <requirement type="package" version="2.7">python</requirement> - <requirement type="package" version="1.65">biopython</requirement> - <requirement type="package" version="2.12.1">requests</requirement> - <yield/> - </requirements> - <version_command> - <![CDATA[ - cd $__tool_directory__ && git rev-parse HEAD - ]]> - </version_command> - </xml> - <xml name="citation/mijalisrasche"> - <citation type="doi">10.1371/journal.pcbi.1008214</citation> - <citation type="bibtex">@unpublished{galaxyTools, - author = {E. Mijalis, H. Rasche}, - title = {CPT Galaxy Tools}, - year = {2013-2017}, - note = {https://github.com/tamu-cpt/galaxy-tools/} - } - </citation> - </xml> - <xml name="citations"> - <citations> - <citation type="doi">10.1371/journal.pcbi.1008214</citation> - <citation type="bibtex"> - @unpublished{galaxyTools, - author = {E. Mijalis, H. Rasche}, - title = {CPT Galaxy Tools}, - year = {2013-2017}, - note = {https://github.com/tamu-cpt/galaxy-tools/} - } - </citation> - <yield/> - </citations> - </xml> - <xml name="citations-crr"> - <citations> - <citation type="doi">10.1371/journal.pcbi.1008214</citation> - <citation type="bibtex"> - @unpublished{galaxyTools, - author = {C. Ross}, - title = {CPT Galaxy Tools}, - year = {2020-}, - note = {https://github.com/tamu-cpt/galaxy-tools/} - } - </citation> - <yield/> - </citations> - </xml> - <xml name="citations-2020"> - <citations> - <citation type="doi">10.1371/journal.pcbi.1008214</citation> - <citation type="bibtex"> - @unpublished{galaxyTools, - author = {E. Mijalis, H. Rasche}, - title = {CPT Galaxy Tools}, - year = {2013-2017}, - note = {https://github.com/tamu-cpt/galaxy-tools/} - } - </citation> - <citation type="bibtex"> - @unpublished{galaxyTools, - author = {A. Criscione}, - title = {CPT Galaxy Tools}, - year = {2019-2021}, - note = {https://github.com/tamu-cpt/galaxy-tools/} - } - </citation> - <yield/> - </citations> - </xml> - <xml name="citations-2020-AJC-solo"> - <citations> - <citation type="doi">10.1371/journal.pcbi.1008214</citation> - <citation type="bibtex"> - @unpublished{galaxyTools, - author = {A. Criscione}, - title = {CPT Galaxy Tools}, - year = {2019-2021}, - note = {https://github.com/tamu-cpt/galaxy-tools/} - } - </citation> - <yield/> - </citations> - </xml> - <xml name="citations-clm"> - <citations> - <citation type="doi">10.1371/journal.pcbi.1008214</citation> - <citation type="bibtex"> - @unpublished{galaxyTools, - author = {C. Maughmer}, - title = {CPT Galaxy Tools}, - year = {2017-2020}, - note = {https://github.com/tamu-cpt/galaxy-tools/} - } - </citation> - <yield/> - </citations> - </xml> - <xml name="sl-citations-clm"> - <citation type="bibtex"> - @unpublished{galaxyTools, - author = {C. Maughmer}, - title = {CPT Galaxy Tools}, - year = {2017-2020}, - note = {https://github.com/tamu-cpt/galaxy-tools/} - } - </citation> - <yield/> - </xml> -</macros> |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 cpt_fix_sixpack/gff3.py --- a/cpt_fix_sixpack/gff3.py Fri May 20 08:48:25 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,346 +0,0 @@\n-import copy\n-import logging\n-\n-log = logging.getLogger()\n-log.setLevel(logging.WARN)\n-\n-\n-def feature_lambda(\n- feature_list,\n- test,\n- test_kwargs,\n- subfeatures=True,\n- parent=None,\n- invert=False,\n- recurse=True,\n-):\n- """Recursively search through features, testing each with a test function, yielding matches.\n-\n- GFF3 is a hierachical data structure, so we need to be able to recursively\n- search through features. E.g. if you\'re looking for a feature with\n- ID=\'bob.42\', you can\'t just do a simple list comprehension with a test\n- case. You don\'t know how deeply burried bob.42 will be in the feature tree. This is where feature_lambda steps in.\n-\n- :type feature_list: list\n- :param feature_list: an iterable of features\n-\n- :type test: function reference\n- :param test: a closure with the method signature (feature, **kwargs) where\n- the kwargs are those passed in the next argument. This\n- function should return True or False, True if the feature is\n- to be yielded as part of the main feature_lambda function, or\n- False if it is to be ignored. This function CAN mutate the\n- features passed to it (think "apply").\n-\n- :type test_kwargs: dictionary\n- :param test_kwargs: kwargs to pass to your closure when it is called.\n-\n- :type subfeatures: boolean\n- :param subfeatures: when a feature is matched, should just that feature be\n- yielded to the caller, or should the entire sub_feature\n- tree for that feature be included? subfeatures=True is\n- useful in cases such as searching for a gene feature,\n- and wanting to know what RBS/Shine_Dalgarno_sequences\n- are in the sub_feature tree (which can be accomplished\n- with two feature_lambda calls). subfeatures=False is\n- useful in cases when you want to process (and possibly\n- return) the entire feature tree, such as applying a\n- qualifier to every single feature.\n-\n- :type invert: boolean\n- :param invert: Negate/invert the result of the filter.\n-\n- :rtype: yielded list\n- :return: Yields a list of matching features.\n- """\n- # Either the top level set of [features] or the subfeature attribute\n- for feature in feature_list:\n- feature._parent = parent\n- if not parent:\n- # Set to self so we cannot go above root.\n- feature._parent = feature\n- test_result = test(feature, **test_kwargs)\n- # if (not invert and test_result) or (invert and not test_result):\n- if invert ^ test_result:\n- if not subfeatures:\n- feature_copy = copy.deepcopy(feature)\n- feature_copy.sub_features = list()\n- yield feature_copy\n- else:\n- yield feature\n-\n- if recurse and hasattr(feature, "sub_features"):\n- for x in feature_lambda(\n- feature.sub_features,\n- test,\n- test_kwargs,\n- subfeatures=subfeatures,\n- parent=feature,\n- invert=invert,\n- recurse=recurse,\n- ):\n- yield x\n-\n-\n-def fetchParent(feature):\n- if not hasattr(feature, "_parent") or feature._parent is None:\n- return feature\n- else:\n- return fetchParent(feature._parent)\n-\n-\n-def feature_test_true(feature, **kwargs):\n- return True\n-\n-\n-def feature_test_type(feature, **kwargs):\n- if "type" in kwargs:\n- return str(feature.type).upper() == str(kwargs["type"]).upper()\n- elif "types" in kwargs:\n- for x in kwargs["types"]:\n- if str(feature.type).upper() == str(x).upper():\n- return True\n- return False\n- raise Exception("Incorrect feature_test_type call, ne'..b'feature.location.start,\n- # feature.location.end,\n- # feature.location.strand\n- # )\n- return result\n-\n-\n-def get_gff3_id(gene):\n- return gene.qualifiers.get("Name", [gene.id])[0]\n-\n-\n-def ensure_location_in_bounds(start=0, end=0, parent_length=0):\n- # This prevents frameshift errors\n- while start < 0:\n- start += 3\n- while end < 0:\n- end += 3\n- while start > parent_length:\n- start -= 3\n- while end > parent_length:\n- end -= 3\n- return (start, end)\n-\n-\n-def coding_genes(feature_list):\n- for x in genes(feature_list):\n- if (\n- len(\n- list(\n- feature_lambda(\n- x.sub_features,\n- feature_test_type,\n- {"type": "CDS"},\n- subfeatures=False,\n- )\n- )\n- )\n- > 0\n- ):\n- yield x\n-\n-\n-def genes(feature_list, feature_type="gene", sort=False):\n- """\n- Simple filter to extract gene features from the feature set.\n- """\n-\n- if not sort:\n- for x in feature_lambda(\n- feature_list, feature_test_type, {"type": feature_type}, subfeatures=True\n- ):\n- yield x\n- else:\n- data = list(genes(feature_list, feature_type=feature_type, sort=False))\n- data = sorted(data, key=lambda feature: feature.location.start)\n- for x in data:\n- yield x\n-\n-\n-def wa_unified_product_name(feature):\n- """\n- Try and figure out a name. We gave conflicting instructions, so\n- this isn\'t as trivial as it should be. Sometimes it will be in\n- \'product\' or \'Product\', othertimes in \'Name\'\n- """\n- # Manually applied tags.\n- protein_product = feature.qualifiers.get(\n- "product", feature.qualifiers.get("Product", [None])\n- )[0]\n-\n- # If neither of those are available ...\n- if protein_product is None:\n- # And there\'s a name...\n- if "Name" in feature.qualifiers:\n- if not is_uuid(feature.qualifiers["Name"][0]):\n- protein_product = feature.qualifiers["Name"][0]\n-\n- return protein_product\n-\n-\n-def is_uuid(name):\n- return name.count("-") == 4 and len(name) == 36\n-\n-\n-def get_rbs_from(gene):\n- # Normal RBS annotation types\n- rbs_rbs = list(\n- feature_lambda(\n- gene.sub_features, feature_test_type, {"type": "RBS"}, subfeatures=False\n- )\n- )\n- rbs_sds = list(\n- feature_lambda(\n- gene.sub_features,\n- feature_test_type,\n- {"type": "Shine_Dalgarno_sequence"},\n- subfeatures=False,\n- )\n- )\n- # Fraking apollo\n- apollo_exons = list(\n- feature_lambda(\n- gene.sub_features, feature_test_type, {"type": "exon"}, subfeatures=False\n- )\n- )\n- apollo_exons = [x for x in apollo_exons if len(x) < 10]\n- # These are more NCBI\'s style\n- regulatory_elements = list(\n- feature_lambda(\n- gene.sub_features,\n- feature_test_type,\n- {"type": "regulatory"},\n- subfeatures=False,\n- )\n- )\n- rbs_regulatory = list(\n- feature_lambda(\n- regulatory_elements,\n- feature_test_quals,\n- {"regulatory_class": ["ribosome_binding_site"]},\n- subfeatures=False,\n- )\n- )\n- # Here\'s hoping you find just one ;)\n- return rbs_rbs + rbs_sds + rbs_regulatory + apollo_exons\n-\n-\n-def nice_name(record):\n- """\n- get the real name rather than NCBI IDs and so on. If fails, will return record.id\n- """\n- name = record.id\n- likely_parental_contig = list(genes(record.features, feature_type="contig"))\n- if len(likely_parental_contig) == 1:\n- name = likely_parental_contig[0].qualifiers.get("organism", [name])[0]\n- return name\n-\n-\n-def fsort(it):\n- for i in sorted(it, key=lambda x: int(x.location.start)):\n- yield i\n' |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 cpt_fix_sixpack/gff3_fix_sixpack.py --- a/cpt_fix_sixpack/gff3_fix_sixpack.py Fri May 20 08:48:25 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,46 +0,0 @@ -#!/usr/bin/env python -import sys -import logging -import argparse -from CPT_GFFParser import gffParse, gffWrite -from Bio.SeqFeature import SeqFeature -from gff3 import feature_lambda, feature_test_type - -logging.basicConfig(level=logging.INFO) -log = logging.getLogger(__name__) - - -def fixed_feature(rec): - # Get all gene features to remove the mRNAs from - for feature in feature_lambda( - rec.features, feature_test_type, {"type": "gene"}, subfeatures=True - ): - gene = feature - sub_features = [] - # Filter out mRNA subfeatures, save other ones to new gene object. - for sf in feature_lambda( - feature.sub_features, - feature_test_type, - {"type": "mRNA"}, - subfeatures=True, - invert=True, - ): - sf.qualifiers["Parent"] = gene.qualifiers["ID"] - sub_features.append(sf) - # override original subfeatures with our filtered list - gene.sub_features = sub_features - yield gene - - -def gff_filter(gff3): - for rec in gffParse(gff3): - rec.features = sorted(list(fixed_feature(rec)), key=lambda x: x.location.start) - rec.annotations = {} - gffWrite([rec], sys.stdout) - - -if __name__ == "__main__": - parser = argparse.ArgumentParser(description="Fix gene model from naive ORF caller") - parser.add_argument("gff3", type=argparse.FileType("r"), help="GFF3 annotations") - args = parser.parse_args() - gff_filter(**vars(args)) |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 cpt_fix_sixpack/gff3_fix_sixpack.xml --- a/cpt_fix_sixpack/gff3_fix_sixpack.xml Fri May 20 08:48:25 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| @@ -1,38 +0,0 @@ -<?xml version="1.0"?> -<tool id="edu.tamu.cpt.gff3.fixsixpack" name="GFF3 Add Gene to CDS for Sixpack" version="19.1.0.0"> - <description>Properly formats naive ORF caller output for Apollo</description> - <macros> - <import>macros.xml</import> - <import>cpt-macros.xml</import> - </macros> - <expand macro="requirements"/> - <command detect_errors="aggressive"><![CDATA[ -$__tool_directory__/gff3_fix_sixpack.py -@INPUT_GFF@ -> $output]]></command> - <inputs> - <expand macro="gff3_input" /> - </inputs> - <outputs> - <data format="gff3" name="output"/> - </outputs> - <tests> - <test> - <param name="gff3_data" value="miro.gff3" /> - <output name="output" file="miro.6pfix.gff3" /> - </test> - <test> - <param name="gff3_data" value="miro.cds.gff3" /> - <output name="output" file="miro.cds6pfix.gff3" /> - </test> - </tests> - <help><![CDATA[ -**What it does** - -This tool **strips ALL the mRNA features** in a GFF3 file. It specifically formats -the output of the naïve ORF call Sixpack such that it will be compatible with -Apollo via JBrowse. - - ]]></help> - <expand macro="citations" /> -</tool> |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 cpt_fix_sixpack/macros.xml --- a/cpt_fix_sixpack/macros.xml Fri May 20 08:48:25 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,66 +0,0 @@ -<?xml version="1.0"?> -<macros> - <xml name="requirements"> - <requirements> - <requirement type="package" version="3.8.13">python</requirement> - <requirement type="package" version="1.79">biopython</requirement> - <requirement type="package" version="1.2.2">cpt_gffparser</requirement> - <yield/> - </requirements> - </xml> - <xml name="genome_selector"> - <conditional name="reference_genome"> - <param name="reference_genome_source" type="select" label="Reference Genome"> - <option value="history" selected="True">From History</option> - <option value="cached">Locally Cached</option> - </param> - <when value="cached"> - <param name="fasta_indexes" type="select" label="Source FASTA Sequence"> - <options from_data_table="all_fasta"/> - </param> - </when> - <when value="history"> - <param name="genome_fasta" type="data" format="fasta" label="Source FASTA Sequence"/> - </when> - </conditional> - </xml> - <xml name="gff3_input"> - <param label="GFF3 Annotations" name="gff3_data" type="data" format="gff3"/> - </xml> - <xml name="input/gff3+fasta"> - <expand macro="gff3_input" /> - <expand macro="genome_selector" /> - </xml> - <token name="@INPUT_GFF@"> - "$gff3_data" - </token> - <token name="@INPUT_FASTA@"> -#if str($reference_genome.reference_genome_source) == 'cached': - "${reference_genome.fasta_indexes.fields.path}" -#else if str($reference_genome.reference_genome_source) == 'history': - genomeref.fa -#end if - </token> - <token name="@GENOME_SELECTOR_PRE@"> -#if $reference_genome.reference_genome_source == 'history': - ln -s $reference_genome.genome_fasta genomeref.fa; -#end if - </token> - <token name="@GENOME_SELECTOR@"> -#if str($reference_genome.reference_genome_source) == 'cached': - "${reference_genome.fasta_indexes.fields.path}" -#else if str($reference_genome.reference_genome_source) == 'history': - genomeref.fa -#end if - </token> - <xml name="input/fasta"> - <param label="Fasta file" name="sequences" type="data" format="fasta"/> - </xml> - - <token name="@SEQUENCE@"> - "$sequences" - </token> - <xml name="input/fasta/protein"> - <param label="Protein fasta file" name="sequences" type="data" format="fasta"/> - </xml> -</macros> |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 cpt_fix_sixpack/test-data/miro.6pfix.gff3 --- a/cpt_fix_sixpack/test-data/miro.6pfix.gff3 Fri May 20 08:48:25 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| b'@@ -1,820 +0,0 @@\n-##gff-version 3\n-Miro\tfeature\tgene\t1\t910\t.\t-\t.\tID=Miro_1;\n-Miro\tGenBank\tCDS\t1\t900\t.\t-\t1\tID=Miro_1.CDS;Name=Miro_1;Parent=Miro_1;obsolete_name=Miro_163;product=rIIb;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t908\t910\t.\t-\t1\tAlias=Miro_1;ID=Miro_1.RBS;Name=Miro_1;Parent=Miro_1;\n-Miro\tfeature\tgene\t900\t3173\t.\t-\t.\tID=Miro_2;\n-Miro\tGenBank\tCDS\t900\t3161\t.\t-\t1\tID=Miro_2.CDS;Name=Miro_2;Parent=Miro_2;obsolete_name=Miro_162;product=rIIa;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t3171\t3173\t.\t-\t1\tAlias=Miro_2;ID=Miro_2.RBS;Name=Miro_2;Parent=Miro_2;\n-Miro\tfeature\tgene\t3172\t3417\t.\t-\t.\tID=Miro_3;\n-Miro\tGenBank\tCDS\t3172\t3408\t.\t-\t1\tID=Miro_3.CDS;Name=Miro_3;Parent=Miro_3;obsolete_name=Miro_161;product=hypothetical conserved;tmhelix=1 TMD (12-34) N in%2C C out;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t3414\t3417\t.\t-\t1\tAlias=Miro_3;ID=Miro_3.RBS;Name=Miro_3;Parent=Miro_3;\n-Miro\tfeature\tgene\t3412\t3979\t.\t-\t.\tID=Miro_4;\n-Miro\tGenBank\tCDS\t3412\t3966\t.\t-\t1\tID=Miro_4.CDS;Name=Miro_4;Note=contains SprT domain;Parent=Miro_4;obsolete_name=Miro_160;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t3975\t3979\t.\t-\t1\tAlias=Miro_4;ID=Miro_4.RBS;Name=Miro_4;Parent=Miro_4;\n-Miro\tfeature\tgene\t4038\t5334\t.\t-\t.\tID=Miro_5;\n-Miro\tGenBank\tCDS\t4038\t5324\t.\t-\t1\tID=Miro_5.CDS;Name=Miro_5;Note=T4 gp52-like;Parent=Miro_5;obsolete_name=Miro_159;product=DNA topoisomerase II medium subunit;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t5331\t5334\t.\t-\t1\tAlias=Miro_5;ID=Miro_5.RBS;Name=Miro_5;Parent=Miro_5;\n-Miro\tfeature\tgene\t5324\t7231\t.\t-\t.\tID=Miro_6;\n-Miro\tGenBank\tCDS\t5324\t7222\t.\t-\t1\tID=Miro_6.CDS;Name=Miro_6;Note=T4 gp39-like;Parent=Miro_6;obsolete_name=Miro_158;product=DNA topoisomerase II%2C large subunit;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t7228\t7231\t.\t-\t1\tAlias=Miro_6;ID=Miro_6.RBS;Name=Miro_6;Parent=Miro_6;\n-Miro\tfeature\tgene\t7290\t7465\t.\t-\t.\tID=Miro_7;\n-Miro\tGenBank\tCDS\t7290\t7454\t.\t-\t1\tID=Miro_7.CDS;Name=Miro_7;Note=contains zinc ribbon domain;Parent=Miro_7;obsolete_name=Miro_157;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t7463\t7465\t.\t-\t1\tAlias=Miro_7;ID=Miro_7.RBS;Name=Miro_7;Parent=Miro_7;\n-Miro\tfeature\tgene\t7454\t7906\t.\t-\t.\tID=Miro_8;\n-Miro\tGenBank\tCDS\t7454\t7894\t.\t-\t1\tID=Miro_8.CDS;Name=Miro_8;Parent=Miro_8;obsolete_name=Miro_156;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t7903\t7906\t.\t-\t1\tAlias=Miro_8;ID=Miro_8.RBS;Name=Miro_8;Parent=Miro_8;\n-Miro\tfeature\tgene\t7917\t8512\t.\t-\t.\tID=Miro_9;\n-Miro\tGenBank\tCDS\t7917\t8501\t.\t-\t1\tID=Miro_9.CDS;Name=Miro_9;Parent=Miro_9;obsolete_name=Miro_155;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t8509\t8512\t.\t-\t1\tAlias=Miro_9;ID=Miro_9.RBS;Name=Miro_9;Parent=Miro_9;\n-Miro\tfeature\tgene\t8488\t8779\t.\t-\t.\tID=Miro_10;\n-Miro\tGenBank\tCDS\t8488\t8766\t.\t-\t1\tID=Miro_10.CDS;Name=Miro_10;Parent=Miro_10;obsolete_name=Miro_154;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t8776\t8779\t.\t-\t1\tAlias=Miro_10;ID=Miro_10.RBS;Name=Miro_10;Parent=Miro_10;\n-Miro\tfeature\tgene\t8763\t9370\t.\t-\t.\tID=Miro_11;\n-Miro\tGenBank\tCDS\t8763\t9359\t.\t-\t1\tID=Miro_11.CDS;Name=Miro_11;Parent=Miro_11;obsolete_name=Miro_153;product=hypothetical conserved;tmhelix=1 TMD (10-29) N out%2C C in;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t9367\t9370\t.\t-\t1\tAlias=Miro_11;ID=Miro_11.RBS;Name=Miro_11;Parent=Miro_11;\n-Miro\tfeature\tgene\t9399\t9740\t.\t-\t.\tID=Miro_12;\n-Miro\tGenBank\tCDS\t9399\t9728\t.\t-\t1\tID=Miro_12.CDS;Name=Miro_12;Parent=Miro_12;obsolete_name=Miro_152;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t9736\t9740\t.\t-\t1\tAlias=Miro_12;ID=Miro_12.RBS;Name=Miro_12;Parent=Miro_12;\n-Miro\tfeature\tgene\t9788\t10025\t.\t-\t.\tID=Miro_13;\n-Miro\tGenBank\tCDS\t9788\t10012\t.\t-\t1\tID=Miro_13.CDS;Name=Miro_13;Parent=Miro_13;obsolete_name=Miro_151;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t10021\t10025\t.\t-\t1\tAlias=Miro_13;ID=Miro_13.RBS;Name=Miro_13;Parent=Miro_13;\n-Miro\tfeature\tgene\t10086\t10361\t.\t-\t.\tID=Miro_14;\n-Miro\tGenBank\tCDS\t10086\t10349\t.\t-\t1\tID=Miro_14.CDS;Na'..b'product=tail fiber;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t166968\t166971\t.\t+\t1\tID=Miro_264.RBS;Name=Miro_264;Parent=Miro_264;\n-Miro\tfeature\tgene\t167645\t171466\t.\t+\t.\tID=Miro_265;\n-Miro\tGenBank\tCDS\t167654\t171466\t.\t+\t1\tAlias=Miro_265;ID=Miro_265.CDS;Name=Miro_265;Parent=Miro_265;obsolete_name=Miro_175;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t167645\t167648\t.\t+\t1\tID=Miro_265.RBS;Name=Miro_265;Parent=Miro_265;\n-Miro\tfeature\tgene\t171490\t172030\t.\t+\t.\tID=Miro_266;\n-Miro\tGenBank\tCDS\t171503\t172030\t.\t+\t1\tAlias=Miro_266;ID=Miro_266.CDS;Name=Miro_266;Note=T2 gp38-like;Parent=Miro_266;obsolete_name=Miro_174;product=receptor-recognizing protein;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t171490\t171494\t.\t+\t1\tID=Miro_266.RBS;Name=Miro_266;Parent=Miro_266;\n-Miro\tfeature\tgene\t172135\t172794\t.\t+\t.\tID=Miro_267;\n-Miro\tGenBank\tCDS\t172147\t172794\t.\t+\t1\tAlias=Miro_267;ID=Miro_267.CDS;Name=Miro_267;Note=T4 gpT-like;Parent=Miro_267;obsolete_name=Miro_173;product=holin;tmhelix=1 TMD (29-47) N in%2C C out;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t172135\t172137\t.\t+\t1\tID=Miro_267.RBS;Name=Miro_267;Parent=Miro_267;\n-Miro\tfeature\tgene\t172795\t173074\t.\t-\t.\tID=Miro_268;\n-Miro\tGenBank\tCDS\t172795\t173064\t.\t-\t1\tID=Miro_268.CDS;Name=Miro_268;Parent=Miro_268;obsolete_name=Miro_172;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t173071\t173074\t.\t-\t1\tAlias=Miro_268;ID=Miro_268.RBS;Name=Miro_268;Parent=Miro_268;\n-Miro\tfeature\tgene\t173061\t173361\t.\t-\t.\tID=Miro_269;\n-Miro\tGenBank\tCDS\t173061\t173351\t.\t-\t1\tID=Miro_269.CDS;Name=Miro_269;Parent=Miro_269;obsolete_name=Miro_171;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t173358\t173361\t.\t-\t1\tAlias=Miro_269;ID=Miro_269.RBS;Name=Miro_269;Parent=Miro_269;\n-Miro\tfeature\tgene\t173351\t174160\t.\t-\t.\tID=Miro_270;\n-Miro\tGenBank\tCDS\t173351\t174148\t.\t-\t1\tID=Miro_270.CDS;Name=Miro_270;Parent=Miro_270;obsolete_name=Miro_170;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t174156\t174160\t.\t-\t1\tAlias=Miro_270;ID=Miro_270.RBS;Name=Miro_270;Parent=Miro_270;\n-Miro\tfeature\tgene\t174229\t174467\t.\t-\t.\tID=Miro_271;\n-Miro\tGenBank\tCDS\t174229\t174456\t.\t-\t1\tID=Miro_271.CDS;Name=Miro_271;Parent=Miro_271;obsolete_name=Miro_169;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t174464\t174467\t.\t-\t1\tAlias=Miro_271;ID=Miro_271.RBS;Name=Miro_271;Parent=Miro_271;\n-Miro\tfeature\tgene\t174453\t174796\t.\t-\t.\tID=Miro_272;\n-Miro\tGenBank\tCDS\t174453\t174785\t.\t-\t1\tID=Miro_272.CDS;Name=Miro_272;Parent=Miro_272;obsolete_name=Miro_168;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t174793\t174796\t.\t-\t1\tAlias=Miro_272;ID=Miro_272.RBS;Name=Miro_272;Parent=Miro_272;\n-Miro\tfeature\tgene\t174760\t174903\t.\t-\t.\tID=Miro_273;\n-Miro\tGenBank\tCDS\t174760\t174894\t.\t-\t1\tID=Miro_273.CDS;Name=Miro_273;Parent=Miro_273;obsolete_name=Miro_167;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t174900\t174903\t.\t-\t1\tAlias=Miro_273;ID=Miro_273.RBS;Name=Miro_273;Parent=Miro_273;\n-Miro\tfeature\tgene\t174939\t175197\t.\t-\t.\tID=Miro_274;\n-Miro\tGenBank\tCDS\t174939\t175187\t.\t-\t1\tID=Miro_274.CDS;Name=Miro_274;Note=contains FCH and colicin domains;Parent=Miro_274;obsolete_name=Miro_166;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t175195\t175197\t.\t-\t1\tAlias=Miro_274;ID=Miro_274.RBS;Name=Miro_274;Parent=Miro_274;\n-Miro\tfeature\tgene\t175224\t175675\t.\t-\t.\tID=Miro_275;\n-Miro\tGenBank\tCDS\t175224\t175661\t.\t-\t1\tID=Miro_275.CDS;Name=Miro_275;Parent=Miro_275;obsolete_name=Miro_165;product=hypothetical conserved;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t175673\t175675\t.\t-\t1\tAlias=Miro_275;ID=Miro_275.RBS;Name=Miro_275;Parent=Miro_275;\n-Miro\tfeature\tgene\t175636\t176021\t.\t-\t.\tID=Miro_276;\n-Miro\tGenBank\tCDS\t175636\t176010\t.\t-\t1\tID=Miro_276.CDS;Name=Miro_276;Parent=Miro_276;obsolete_name=Miro_164;product=hypothetical conserved;tmhelix=2TMDs (44-66%2C 76-98) N in%2C C in;\n-Miro\tGenBank\tShine_Dalgarno_sequence\t176017\t176021\t.\t-\t1\tAlias=Miro_276;ID=Miro_276.RBS;Name=Miro_276;Parent=Miro_276;\n' |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 cpt_fix_sixpack/test-data/miro.cds.gff3 --- a/cpt_fix_sixpack/test-data/miro.cds.gff3 Fri May 20 08:48:25 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| b'@@ -1,278 +0,0 @@\n-##gff-version 3\n-##sequence-region Miro 1 176055\n-Miro\tGenBank\tCDS\t7454\t7894\t.\t-\t1\tID=Miro_8.CDS;Name=Miro_8;obsolete_name=Miro_156;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t7917\t8501\t.\t-\t1\tID=Miro_9.CDS;Name=Miro_9;obsolete_name=Miro_155;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t123286\t124212\t.\t+\t1\tAlias=Miro_206;ID=Miro_206.CDS;Name=Miro_206;obsolete_name=Miro_234;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t68490\t70706\t.\t-\t1\tID=Miro_117.CDS;Name=Miro_117;Note=contains von Willebrand factor%2C type A;obsolete_name=Miro_047;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t115743\t116735\t.\t+\t1\tAlias=Miro_200;ID=Miro_200.CDS;Name=Miro_200;Note=T4 gp6-like;obsolete_name=Miro_240;product=baseplate structural protein;\n-Miro\tGenBank\tCDS\t116745\t117608\t.\t+\t1\tAlias=Miro_201;ID=Miro_201.CDS;Name=Miro_201;Note=T4 gp9/gp10-like;obsolete_name=Miro_239;product=baseplate structural protein;\n-Miro\tGenBank\tCDS\t117605\t119422\t.\t+\t1\tAlias=Miro_202;ID=Miro_202.CDS;Name=Miro_202;Note=T4 gp9/gp10-like;obsolete_name=Miro_238;product=baseplate structural protein;\n-Miro\tGenBank\tCDS\t119422\t120090\t.\t+\t1\tAlias=Miro_203;ID=Miro_203.CDS;Name=Miro_203;Note=T4 gp11-like;obsolete_name=Miro_237;product=baseplate to short tail fiber connector protein;\n-Miro\tGenBank\tCDS\t81829\t81927\t.\t-\t1\tID=Miro_142.CDS;Name=Miro_142;obsolete_name=Miro_022;product=hypothetical conserved;tmhelix=1 TMD (4-26) N out%2C C in;\n-Miro\tGenBank\tCDS\t1\t900\t.\t-\t1\tID=Miro_1.CDS;Name=Miro_1;obsolete_name=Miro_163;product=rIIb;\n-Miro\tGenBank\tCDS\t900\t3161\t.\t-\t1\tID=Miro_2.CDS;Name=Miro_2;obsolete_name=Miro_162;product=rIIa;\n-Miro\tGenBank\tCDS\t3172\t3408\t.\t-\t1\tID=Miro_3.CDS;Name=Miro_3;obsolete_name=Miro_161;product=hypothetical conserved;tmhelix=1 TMD (12-34) N in%2C C out;\n-Miro\tGenBank\tCDS\t3412\t3966\t.\t-\t1\tID=Miro_4.CDS;Name=Miro_4;Note=contains SprT domain;obsolete_name=Miro_160;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t4038\t5324\t.\t-\t1\tID=Miro_5.CDS;Name=Miro_5;Note=T4 gp52-like;obsolete_name=Miro_159;product=DNA topoisomerase II medium subunit;\n-Miro\tGenBank\tCDS\t5324\t7222\t.\t-\t1\tID=Miro_6.CDS;Name=Miro_6;Note=T4 gp39-like;obsolete_name=Miro_158;product=DNA topoisomerase II%2C large subunit;\n-Miro\tGenBank\tCDS\t7290\t7454\t.\t-\t1\tID=Miro_7.CDS;Name=Miro_7;Note=contains zinc ribbon domain;obsolete_name=Miro_157;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t124222\t124968\t.\t+\t1\tAlias=Miro_207;ID=Miro_207.CDS;Name=Miro_207;Note=T4 gp14-like;obsolete_name=Miro_233;product=neck protein;\n-Miro\tGenBank\tCDS\t173061\t173351\t.\t-\t1\tID=Miro_269.CDS;Name=Miro_269;obsolete_name=Miro_171;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t66523\t66807\t.\t-\t1\tID=Miro_112.CDS;Name=Miro_112;obsolete_name=Miro_052;product=hypothetical conserved;signal=signal peptidase I cleavage site 17-18;\n-Miro\tGenBank\tCDS\t66879\t67163\t.\t-\t1\tID=Miro_113.CDS;Name=Miro_113;obsolete_name=Miro_051;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t44575\t45732\t.\t+\t1\tAlias=Miro_69;ID=Miro_69.CDS;Name=Miro_69;Note=T4 RNA ligase 1-like;obsolete_name=Miro_095;product=RNA ligase;\n-Miro\tGenBank\tCDS\t44229\t44594\t.\t+\t1\tAlias=Miro_68;ID=Miro_68.CDS;Name=Miro_68;Note=contains GIY-YIG domain;obsolete_name=Miro_096;product=homing endonuclease;\n-Miro\tGenBank\tCDS\t43905\t44225\t.\t+\t1\tID=Miro_67;Name=Miro_67;obsolete_name=Miro_097;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t42758\t43933\t.\t+\t1\tAlias=Miro_66;ID=Miro_66.CDS;Name=Miro_66;Note=T4 NrdB-like;obsolete_name=Miro_098;product=ribonucleotide reductase%2C small subunit;\n-Miro\tGenBank\tCDS\t40469\t42721\t.\t+\t1\tAlias=Miro_65;ID=Miro_65.CDS;Name=Miro_65;Note=T4 NrdA-like%3B E-val 0;obsolete_name=Miro_099;product=ribonucleotide reductase%2C large subunit;\n-Miro\tGenBank\tCDS\t39554\t40429\t.\t+\t1\tAlias=Miro_64;ID=Miro_64.CDS;Name=Miro_64;Note=T4-like;obsolete_name=Miro_100;product=thymidylate synthase;\n-Miro\tGenBank\tCDS\t38974\t39552\t.\t+\t1\tAlias=Miro_63;ID=Miro_63.CDS;Name=Miro_63;Note=T4-like;obsolete_name=Miro_101;product=dihydrofolate reductase;\n-Miro\tGenBank\tCDS\t38720'..b'ed;\n-Miro\tGenBank\tCDS\t9399\t9728\t.\t-\t1\tID=Miro_12.CDS;Name=Miro_12;obsolete_name=Miro_152;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t9788\t10012\t.\t-\t1\tID=Miro_13.CDS;Name=Miro_13;obsolete_name=Miro_151;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t8488\t8766\t.\t-\t1\tID=Miro_10.CDS;Name=Miro_10;obsolete_name=Miro_154;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t8763\t9359\t.\t-\t1\tID=Miro_11.CDS;Name=Miro_11;obsolete_name=Miro_153;product=hypothetical conserved;tmhelix=1 TMD (10-29) N out%2C C in;\n-Miro\tGenBank\tCDS\t10737\t10961\t.\t-\t1\tID=Miro_16.CDS;Name=Miro_16;obsolete_name=Miro_148;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t10965\t11114\t.\t-\t1\tID=Miro_17.CDS;Name=Miro_17;obsolete_name=Miro_147;product=hypothetical conserved;tmhelix=1 TMD (10-32) N out%2C C in;\n-Miro\tGenBank\tCDS\t10086\t10349\t.\t-\t1\tID=Miro_14.CDS;Name=Miro_14;obsolete_name=Miro_150;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t10438\t10737\t.\t-\t1\tID=Miro_15.CDS;Name=Miro_15;obsolete_name=Miro_149;product=hypothetical conserved;tmhelix=1 TMD (4-21) N out%2C C in;\n-Miro\tGenBank\tCDS\t53923\t54144\t.\t+\t1\tAlias=Miro_92;ID=Miro_92.CDS;Name=Miro_92;obsolete_name=Miro_072;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t54141\t54755\t.\t+\t1\tAlias=Miro_93;ID=Miro_93.CDS;Name=Miro_93;Note=contains haloacid dehydrogenase (HAD)-like domain;obsolete_name=Miro_071;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t53221\t53661\t.\t+\t1\tAlias=Miro_90;ID=Miro_90.CDS;Name=Miro_90;Note=T4 Y12G-like;obsolete_name=Miro_074;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t53658\t53921\t.\t+\t1\tAlias=Miro_91;ID=Miro_91.CDS;Name=Miro_91;obsolete_name=Miro_073;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t57000\t57203\t.\t+\t1\tAlias=Miro_96;ID=Miro_96.CDS;Name=Miro_96;obsolete_name=Miro_068;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t57206\t57382\t.\t+\t1\tAlias=Miro_97;ID=Miro_97.CDS;Name=Miro_97;obsolete_name=Miro_067;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t54736\t56265\t.\t+\t1\tAlias=Miro_94;ID=Miro_94.CDS;Name=Miro_94;Note=T4-like;obsolete_name=Miro_070;product=DNA ligase;\n-Miro\tGenBank\tCDS\t56342\t56911\t.\t+\t1\tAlias=Miro_95;ID=Miro_95.CDS;Name=Miro_95;obsolete_name=Miro_069;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t57379\t57543\t.\t+\t1\tAlias=Miro_98;ID=Miro_98.CDS;Name=Miro_98;obsolete_name=Miro_066;product=hypothetical conserved;tmhelix=2TMDs (7-26%2C 31-53) N in%2C C in;\n-Miro\tGenBank\tCDS\t57624\t57914\t.\t+\t1\tAlias=Miro_99;ID=Miro_99.CDS;Name=Miro_99;obsolete_name=Miro_065;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t81924\t82079\t.\t-\t1\tID=Miro_143.CDS;Name=Miro_143;obsolete_name=Miro_021;product=hypothetical conserved;tmhelix=1 TMD (15-37) N out%2C C in;\n-Miro\tGenBank\tCDS\t67179\t67649\t.\t-\t1\tID=Miro_114.CDS;Name=Miro_114;obsolete_name=Miro_050;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t81366\t81839\t.\t-\t1\tID=Miro_141.CDS;Name=Miro_141;Note=contains macro domain;obsolete_name=Miro_023;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t81076\t81363\t.\t-\t1\tID=Miro_140.CDS;Name=Miro_140;obsolete_name=Miro_024;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t83223\t83618\t.\t-\t1\tID=Miro_147.CDS;Name=Miro_147;obsolete_name=Miro_017;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t83066\t83212\t.\t-\t1\tID=Miro_146.CDS;Name=Miro_146;obsolete_name=Miro_018;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t82479\t83069\t.\t-\t1\tID=Miro_145.CDS;Name=Miro_145;obsolete_name=Miro_019;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t67646\t67804\t.\t-\t1\tID=Miro_115.CDS;Name=Miro_115;obsolete_name=Miro_049;product=hypothetical conserved;tmhelix=2TMDs (2-21%2C 31-50) N in%2C C in;\n-Miro\tGenBank\tCDS\t84392\t84946\t.\t-\t1\tID=Miro_149.CDS;Name=Miro_149;obsolete_name=Miro_015;product=hypothetical conserved;\n-Miro\tGenBank\tCDS\t83686\t84327\t.\t-\t1\tID=Miro_148.CDS;Name=Miro_148;Note=T4 RegB-like;obsolete_name=Miro_016;product=endoribonuclease;signal=signal peptidase II cleavage site 12-13;\n-Miro\tGenBank\tCDS\t67801\t68451\t.\t-\t1\tID=Miro_116.CDS;Name=Miro_116;obsolete_name=Miro_048;product=hypothetical conserved;\n' |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 cpt_fix_sixpack/test-data/miro.cds6pfix.gff3 --- a/cpt_fix_sixpack/test-data/miro.cds6pfix.gff3 Fri May 20 08:48:25 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| @@ -1,1 +0,0 @@ -##gff-version 3 |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 cpt_fix_sixpack/test-data/miro.gff3 --- a/cpt_fix_sixpack/test-data/miro.gff3 Fri May 20 08:48:25 2022 +0000 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| b |
| b'@@ -1,827 +0,0 @@\n-##gff-version 3\n-##sequence-region Miro 1 176055\n-Miro\tfeature\tgene\t7454\t7906\t.\t-\t.\tID=Miro_8\n-Miro\tGenBank\tCDS\t7454\t7894\t.\t-\t1\tID=Miro_8.CDS;Name=Miro_8;Parent=Miro_8;obsolete_name=Miro_156;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t7903\t7906\t.\t-\t1\tAlias=Miro_8;ID=Miro_8.RBS;Name=Miro_8;Parent=Miro_8\n-Miro\tfeature\tgene\t7917\t8512\t.\t-\t.\tID=Miro_9\n-Miro\tGenBank\tCDS\t7917\t8501\t.\t-\t1\tID=Miro_9.CDS;Name=Miro_9;Parent=Miro_9;obsolete_name=Miro_155;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t8509\t8512\t.\t-\t1\tAlias=Miro_9;ID=Miro_9.RBS;Name=Miro_9;Parent=Miro_9\n-Miro\tfeature\tgene\t123276\t124212\t.\t+\t.\tID=Miro_206\n-Miro\tGenBank\tCDS\t123286\t124212\t.\t+\t1\tAlias=Miro_206;ID=Miro_206.CDS;Name=Miro_206;Parent=Miro_206;obsolete_name=Miro_234;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t123276\t123279\t.\t+\t1\tID=Miro_206.rbs;Name=Miro_206;Parent=Miro_206\n-Miro\tfeature\tgene\t68490\t70715\t.\t-\t.\tID=Miro_117\n-Miro\tGenBank\tCDS\t68490\t70706\t.\t-\t1\tID=Miro_117.CDS;Name=Miro_117;Note=contains von Willebrand factor%2C type A;Parent=Miro_117;obsolete_name=Miro_047;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t70713\t70715\t.\t-\t1\tAlias=Miro_117;ID=Miro_117.RBS;Name=Miro_117;Parent=Miro_117\n-Miro\tfeature\tgene\t115729\t116735\t.\t+\t.\tID=Miro_200\n-Miro\tGenBank\tCDS\t115743\t116735\t.\t+\t1\tAlias=Miro_200;ID=Miro_200.CDS;Name=Miro_200;Note=T4 gp6-like;Parent=Miro_200;obsolete_name=Miro_240;product=baseplate structural protein\n-Miro\tGenBank\tShine_Dalgarno_sequence\t115729\t115732\t.\t+\t1\tID=Miro_200.RBS;Name=Miro_200;Parent=Miro_200\n-Miro\tfeature\tgene\t116735\t117608\t.\t+\t.\tID=Miro_201\n-Miro\tGenBank\tCDS\t116745\t117608\t.\t+\t1\tAlias=Miro_201;ID=Miro_201.CDS;Name=Miro_201;Note=T4 gp9/gp10-like;Parent=Miro_201;obsolete_name=Miro_239;product=baseplate structural protein\n-Miro\tGenBank\tShine_Dalgarno_sequence\t116735\t116738\t.\t+\t1\tID=Miro_201.RBS;Name=Miro_201;Parent=Miro_201\n-Miro\tfeature\tgene\t117595\t119422\t.\t+\t.\tID=Miro_202\n-Miro\tGenBank\tCDS\t117605\t119422\t.\t+\t1\tAlias=Miro_202;ID=Miro_202.CDS;Name=Miro_202;Note=T4 gp9/gp10-like;Parent=Miro_202;obsolete_name=Miro_238;product=baseplate structural protein\n-Miro\tGenBank\tShine_Dalgarno_sequence\t117595\t117597\t.\t+\t1\tID=Miro_202.RBS;Name=Miro_202;Parent=Miro_202\n-Miro\tfeature\tgene\t119412\t120090\t.\t+\t.\tID=Miro_203\n-Miro\tGenBank\tCDS\t119422\t120090\t.\t+\t1\tAlias=Miro_203;ID=Miro_203.CDS;Name=Miro_203;Note=T4 gp11-like;Parent=Miro_203;obsolete_name=Miro_237;product=baseplate to short tail fiber connector protein\n-Miro\tGenBank\tShine_Dalgarno_sequence\t119412\t119415\t.\t+\t1\tID=Miro_203.RBS;Name=Miro_203;Parent=Miro_203\n-Miro\tfeature\tgene\t81829\t81940\t.\t-\t.\tID=Miro_142\n-Miro\tGenBank\tCDS\t81829\t81927\t.\t-\t1\tID=Miro_142.CDS;Name=Miro_142;Parent=Miro_142;obsolete_name=Miro_022;product=hypothetical conserved;tmhelix=1 TMD %284-26%29 N out%2C C in\n-Miro\tGenBank\tShine_Dalgarno_sequence\t81938\t81940\t.\t-\t1\tAlias=Miro_142;ID=Miro_142.RBS;Name=Miro_142;Parent=Miro_142\n-Miro\tfeature\tgene\t1\t910\t.\t-\t.\tID=Miro_1\n-Miro\tGenBank\tCDS\t1\t900\t.\t-\t1\tID=Miro_1.CDS;Name=Miro_1;Parent=Miro_1;obsolete_name=Miro_163;product=rIIb\n-Miro\tGenBank\tShine_Dalgarno_sequence\t908\t910\t.\t-\t1\tAlias=Miro_1;ID=Miro_1.RBS;Name=Miro_1;Parent=Miro_1\n-Miro\tfeature\tgene\t900\t3173\t.\t-\t.\tID=Miro_2\n-Miro\tGenBank\tCDS\t900\t3161\t.\t-\t1\tID=Miro_2.CDS;Name=Miro_2;Parent=Miro_2;obsolete_name=Miro_162;product=rIIa\n-Miro\tGenBank\tShine_Dalgarno_sequence\t3171\t3173\t.\t-\t1\tAlias=Miro_2;ID=Miro_2.RBS;Name=Miro_2;Parent=Miro_2\n-Miro\tfeature\tgene\t3172\t3417\t.\t-\t.\tID=Miro_3\n-Miro\tGenBank\tCDS\t3172\t3408\t.\t-\t1\tID=Miro_3.CDS;Name=Miro_3;Parent=Miro_3;obsolete_name=Miro_161;product=hypothetical conserved;tmhelix=1 TMD %2812-34%29 N in%2C C out\n-Miro\tGenBank\tShine_Dalgarno_sequence\t3414\t3417\t.\t-\t1\tAlias=Miro_3;ID=Miro_3.RBS;Name=Miro_3;Parent=Miro_3\n-Miro\tfeature\tgene\t3412\t3979\t.\t-\t.\tID=Miro_4\n-Miro\tGenBank\tCDS\t3412\t3966\t.\t-\t1\tID=Miro_4.CDS;Name=Miro_4;Note=contains SprT domain;Parent=Miro_4;obsolete_name=Miro_160;product=hypothetical'..b't=Miro_98;obsolete_name=Miro_066;product=hypothetical conserved;tmhelix=2TMDs %287-26%2C 31-53%29 N in%2C C in\n-Miro\tGenBank\tShine_Dalgarno_sequence\t57368\t57372\t.\t+\t1\tID=Miro_98.RBS;Name=Miro_98;Parent=Miro_98\n-Miro\tfeature\tgene\t57613\t57914\t.\t+\t.\tID=Miro_99\n-Miro\tGenBank\tCDS\t57624\t57914\t.\t+\t1\tAlias=Miro_99;ID=Miro_99.CDS;Name=Miro_99;Parent=Miro_99;obsolete_name=Miro_065;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t57613\t57616\t.\t+\t1\tID=Miro_99.RBS;Name=Miro_99;Parent=Miro_99\n-Miro\tfeature\tgene\t81924\t82086\t.\t-\t.\tID=Miro_143\n-Miro\tGenBank\tCDS\t81924\t82079\t.\t-\t1\tID=Miro_143.CDS;Name=Miro_143;Parent=Miro_143;obsolete_name=Miro_021;product=hypothetical conserved;tmhelix=1 TMD %2815-37%29 N out%2C C in\n-Miro\tGenBank\tShine_Dalgarno_sequence\t82084\t82086\t.\t-\t1\tAlias=Miro_143;ID=Miro_143.RBS;Name=Miro_143;Parent=Miro_143\n-Miro\tfeature\tgene\t67179\t67658\t.\t-\t.\tID=Miro_114\n-Miro\tGenBank\tCDS\t67179\t67649\t.\t-\t1\tID=Miro_114.CDS;Name=Miro_114;Parent=Miro_114;obsolete_name=Miro_050;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t67656\t67658\t.\t-\t1\tAlias=Miro_114;ID=Miro_114.RBS;Name=Miro_114;Parent=Miro_114\n-Miro\tfeature\tgene\t81366\t81851\t.\t-\t.\tID=Miro_141\n-Miro\tGenBank\tCDS\t81366\t81839\t.\t-\t1\tID=Miro_141.CDS;Name=Miro_141;Note=contains macro domain;Parent=Miro_141;obsolete_name=Miro_023;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t81849\t81851\t.\t-\t1\tAlias=Miro_141;ID=Miro_141.RBS;Name=Miro_141;Parent=Miro_141\n-Miro\tfeature\tgene\t81076\t81376\t.\t-\t.\tID=Miro_140\n-Miro\tGenBank\tCDS\t81076\t81363\t.\t-\t1\tID=Miro_140.CDS;Name=Miro_140;Parent=Miro_140;obsolete_name=Miro_024;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t81374\t81376\t.\t-\t1\tAlias=Miro_140;ID=Miro_140.RBS;Name=Miro_140;Parent=Miro_140\n-Miro\tfeature\tgene\t83223\t83630\t.\t-\t.\tID=Miro_147\n-Miro\tGenBank\tCDS\t83223\t83618\t.\t-\t1\tID=Miro_147.CDS;Name=Miro_147;Parent=Miro_147;obsolete_name=Miro_017;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t83627\t83630\t.\t-\t1\tAlias=Miro_147;ID=Miro_147.RBS;Name=Miro_147;Parent=Miro_147\n-Miro\tfeature\tgene\t83066\t83224\t.\t-\t.\tID=Miro_146\n-Miro\tGenBank\tCDS\t83066\t83212\t.\t-\t1\tID=Miro_146.CDS;Name=Miro_146;Parent=Miro_146;obsolete_name=Miro_018;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t83221\t83224\t.\t-\t1\tAlias=Miro_146;ID=Miro_146.RBS;Name=Miro_146;Parent=Miro_146\n-Miro\tfeature\tgene\t82479\t83083\t.\t-\t.\tID=Miro_145\n-Miro\tGenBank\tCDS\t82479\t83069\t.\t-\t1\tID=Miro_145.CDS;Name=Miro_145;Parent=Miro_145;obsolete_name=Miro_019;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t83080\t83083\t.\t-\t1\tAlias=Miro_145;ID=Miro_145.RBS;Name=Miro_145;Parent=Miro_145\n-Miro\tfeature\tgene\t67646\t67816\t.\t-\t.\tID=Miro_115\n-Miro\tGenBank\tCDS\t67646\t67804\t.\t-\t1\tID=Miro_115.CDS;Name=Miro_115;Parent=Miro_115;obsolete_name=Miro_049;product=hypothetical conserved;tmhelix=2TMDs %282-21%2C 31-50%29 N in%2C C in\n-Miro\tGenBank\tShine_Dalgarno_sequence\t67814\t67816\t.\t-\t1\tAlias=Miro_115;ID=Miro_115.RBS;Name=Miro_115;Parent=Miro_115\n-Miro\tfeature\tgene\t84392\t84959\t.\t-\t.\tID=Miro_149\n-Miro\tGenBank\tCDS\t84392\t84946\t.\t-\t1\tID=Miro_149.CDS;Name=Miro_149;Parent=Miro_149;obsolete_name=Miro_015;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t84955\t84959\t.\t-\t1\tAlias=Miro_149;ID=Miro_149.RBS;Name=Miro_149;Parent=Miro_149\n-Miro\tfeature\tgene\t83686\t84337\t.\t-\t.\tID=Miro_148\n-Miro\tGenBank\tCDS\t83686\t84327\t.\t-\t1\tID=Miro_148.CDS;Name=Miro_148;Note=T4 RegB-like;Parent=Miro_148;obsolete_name=Miro_016;product=endoribonuclease;signal=signal peptidase II cleavage site 12-13\n-Miro\tGenBank\tShine_Dalgarno_sequence\t84334\t84337\t.\t-\t1\tAlias=Miro_148;ID=Miro_148.RBS;Name=Miro_148;Parent=Miro_148\n-Miro\tfeature\tgene\t67801\t68461\t.\t-\t.\tID=Miro_116\n-Miro\tGenBank\tCDS\t67801\t68451\t.\t-\t1\tID=Miro_116.CDS;Name=Miro_116;Parent=Miro_116;obsolete_name=Miro_048;product=hypothetical conserved\n-Miro\tGenBank\tShine_Dalgarno_sequence\t68457\t68461\t.\t-\t1\tAlias=Miro_116;ID=Miro_116.RBS;Name=Miro_116;Parent=Miro_116\n' |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 gff3.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gff3.py Mon Jun 05 02:42:28 2023 +0000 |
| [ |
| b'@@ -0,0 +1,346 @@\n+import copy\n+import logging\n+\n+log = logging.getLogger()\n+log.setLevel(logging.WARN)\n+\n+\n+def feature_lambda(\n+ feature_list,\n+ test,\n+ test_kwargs,\n+ subfeatures=True,\n+ parent=None,\n+ invert=False,\n+ recurse=True,\n+):\n+ """Recursively search through features, testing each with a test function, yielding matches.\n+\n+ GFF3 is a hierachical data structure, so we need to be able to recursively\n+ search through features. E.g. if you\'re looking for a feature with\n+ ID=\'bob.42\', you can\'t just do a simple list comprehension with a test\n+ case. You don\'t know how deeply burried bob.42 will be in the feature tree. This is where feature_lambda steps in.\n+\n+ :type feature_list: list\n+ :param feature_list: an iterable of features\n+\n+ :type test: function reference\n+ :param test: a closure with the method signature (feature, **kwargs) where\n+ the kwargs are those passed in the next argument. This\n+ function should return True or False, True if the feature is\n+ to be yielded as part of the main feature_lambda function, or\n+ False if it is to be ignored. This function CAN mutate the\n+ features passed to it (think "apply").\n+\n+ :type test_kwargs: dictionary\n+ :param test_kwargs: kwargs to pass to your closure when it is called.\n+\n+ :type subfeatures: boolean\n+ :param subfeatures: when a feature is matched, should just that feature be\n+ yielded to the caller, or should the entire sub_feature\n+ tree for that feature be included? subfeatures=True is\n+ useful in cases such as searching for a gene feature,\n+ and wanting to know what RBS/Shine_Dalgarno_sequences\n+ are in the sub_feature tree (which can be accomplished\n+ with two feature_lambda calls). subfeatures=False is\n+ useful in cases when you want to process (and possibly\n+ return) the entire feature tree, such as applying a\n+ qualifier to every single feature.\n+\n+ :type invert: boolean\n+ :param invert: Negate/invert the result of the filter.\n+\n+ :rtype: yielded list\n+ :return: Yields a list of matching features.\n+ """\n+ # Either the top level set of [features] or the subfeature attribute\n+ for feature in feature_list:\n+ feature._parent = parent\n+ if not parent:\n+ # Set to self so we cannot go above root.\n+ feature._parent = feature\n+ test_result = test(feature, **test_kwargs)\n+ # if (not invert and test_result) or (invert and not test_result):\n+ if invert ^ test_result:\n+ if not subfeatures:\n+ feature_copy = copy.deepcopy(feature)\n+ feature_copy.sub_features = list()\n+ yield feature_copy\n+ else:\n+ yield feature\n+\n+ if recurse and hasattr(feature, "sub_features"):\n+ for x in feature_lambda(\n+ feature.sub_features,\n+ test,\n+ test_kwargs,\n+ subfeatures=subfeatures,\n+ parent=feature,\n+ invert=invert,\n+ recurse=recurse,\n+ ):\n+ yield x\n+\n+\n+def fetchParent(feature):\n+ if not hasattr(feature, "_parent") or feature._parent is None:\n+ return feature\n+ else:\n+ return fetchParent(feature._parent)\n+\n+\n+def feature_test_true(feature, **kwargs):\n+ return True\n+\n+\n+def feature_test_type(feature, **kwargs):\n+ if "type" in kwargs:\n+ return str(feature.type).upper() == str(kwargs["type"]).upper()\n+ elif "types" in kwargs:\n+ for x in kwargs["types"]:\n+ if str(feature.type).upper() == str(x).upper():\n+ return True\n+ return False\n+ raise Exception("Incorrect feature_test'..b'feature.location.start,\n+ # feature.location.end,\n+ # feature.location.strand\n+ # )\n+ return result\n+\n+\n+def get_gff3_id(gene):\n+ return gene.qualifiers.get("Name", [gene.id])[0]\n+\n+\n+def ensure_location_in_bounds(start=0, end=0, parent_length=0):\n+ # This prevents frameshift errors\n+ while start < 0:\n+ start += 3\n+ while end < 0:\n+ end += 3\n+ while start > parent_length:\n+ start -= 3\n+ while end > parent_length:\n+ end -= 3\n+ return (start, end)\n+\n+\n+def coding_genes(feature_list):\n+ for x in genes(feature_list):\n+ if (\n+ len(\n+ list(\n+ feature_lambda(\n+ x.sub_features,\n+ feature_test_type,\n+ {"type": "CDS"},\n+ subfeatures=False,\n+ )\n+ )\n+ )\n+ > 0\n+ ):\n+ yield x\n+\n+\n+def genes(feature_list, feature_type="gene", sort=False):\n+ """\n+ Simple filter to extract gene features from the feature set.\n+ """\n+\n+ if not sort:\n+ for x in feature_lambda(\n+ feature_list, feature_test_type, {"type": feature_type}, subfeatures=True\n+ ):\n+ yield x\n+ else:\n+ data = list(genes(feature_list, feature_type=feature_type, sort=False))\n+ data = sorted(data, key=lambda feature: feature.location.start)\n+ for x in data:\n+ yield x\n+\n+\n+def wa_unified_product_name(feature):\n+ """\n+ Try and figure out a name. We gave conflicting instructions, so\n+ this isn\'t as trivial as it should be. Sometimes it will be in\n+ \'product\' or \'Product\', othertimes in \'Name\'\n+ """\n+ # Manually applied tags.\n+ protein_product = feature.qualifiers.get(\n+ "product", feature.qualifiers.get("Product", [None])\n+ )[0]\n+\n+ # If neither of those are available ...\n+ if protein_product is None:\n+ # And there\'s a name...\n+ if "Name" in feature.qualifiers:\n+ if not is_uuid(feature.qualifiers["Name"][0]):\n+ protein_product = feature.qualifiers["Name"][0]\n+\n+ return protein_product\n+\n+\n+def is_uuid(name):\n+ return name.count("-") == 4 and len(name) == 36\n+\n+\n+def get_rbs_from(gene):\n+ # Normal RBS annotation types\n+ rbs_rbs = list(\n+ feature_lambda(\n+ gene.sub_features, feature_test_type, {"type": "RBS"}, subfeatures=False\n+ )\n+ )\n+ rbs_sds = list(\n+ feature_lambda(\n+ gene.sub_features,\n+ feature_test_type,\n+ {"type": "Shine_Dalgarno_sequence"},\n+ subfeatures=False,\n+ )\n+ )\n+ # Fraking apollo\n+ apollo_exons = list(\n+ feature_lambda(\n+ gene.sub_features, feature_test_type, {"type": "exon"}, subfeatures=False\n+ )\n+ )\n+ apollo_exons = [x for x in apollo_exons if len(x) < 10]\n+ # These are more NCBI\'s style\n+ regulatory_elements = list(\n+ feature_lambda(\n+ gene.sub_features,\n+ feature_test_type,\n+ {"type": "regulatory"},\n+ subfeatures=False,\n+ )\n+ )\n+ rbs_regulatory = list(\n+ feature_lambda(\n+ regulatory_elements,\n+ feature_test_quals,\n+ {"regulatory_class": ["ribosome_binding_site"]},\n+ subfeatures=False,\n+ )\n+ )\n+ # Here\'s hoping you find just one ;)\n+ return rbs_rbs + rbs_sds + rbs_regulatory + apollo_exons\n+\n+\n+def nice_name(record):\n+ """\n+ get the real name rather than NCBI IDs and so on. If fails, will return record.id\n+ """\n+ name = record.id\n+ likely_parental_contig = list(genes(record.features, feature_type="contig"))\n+ if len(likely_parental_contig) == 1:\n+ name = likely_parental_contig[0].qualifiers.get("organism", [name])[0]\n+ return name\n+\n+\n+def fsort(it):\n+ for i in sorted(it, key=lambda x: int(x.location.start)):\n+ yield i\n' |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 gff3_fix_sixpack.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gff3_fix_sixpack.py Mon Jun 05 02:42:28 2023 +0000 |
| [ |
| @@ -0,0 +1,46 @@ +#!/usr/bin/env python +import sys +import logging +import argparse +from CPT_GFFParser import gffParse, gffWrite +from Bio.SeqFeature import SeqFeature +from gff3 import feature_lambda, feature_test_type + +logging.basicConfig(level=logging.INFO) +log = logging.getLogger(__name__) + + +def fixed_feature(rec): + # Get all gene features to remove the mRNAs from + for feature in feature_lambda( + rec.features, feature_test_type, {"type": "gene"}, subfeatures=True + ): + gene = feature + sub_features = [] + # Filter out mRNA subfeatures, save other ones to new gene object. + for sf in feature_lambda( + feature.sub_features, + feature_test_type, + {"type": "mRNA"}, + subfeatures=True, + invert=True, + ): + sf.qualifiers["Parent"] = gene.qualifiers["ID"] + sub_features.append(sf) + # override original subfeatures with our filtered list + gene.sub_features = sub_features + yield gene + + +def gff_filter(gff3): + for rec in gffParse(gff3): + rec.features = sorted(list(fixed_feature(rec)), key=lambda x: x.location.start) + rec.annotations = {} + gffWrite([rec], sys.stdout) + + +if __name__ == "__main__": + parser = argparse.ArgumentParser(description="Fix gene model from naive ORF caller") + parser.add_argument("gff3", type=argparse.FileType("r"), help="GFF3 annotations") + args = parser.parse_args() + gff_filter(**vars(args)) |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 gff3_fix_sixpack.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gff3_fix_sixpack.xml Mon Jun 05 02:42:28 2023 +0000 |
| [ |
| @@ -0,0 +1,37 @@ +<tool id="edu.tamu.cpt.gff3.fixsixpack" name="GFF3 Add Gene to CDS for Sixpack" version="19.1.0.0"> + <description>Properly formats naive ORF caller output for Apollo</description> + <macros> + <import>macros.xml</import> + <import>cpt-macros.xml</import> + </macros> + <expand macro="requirements"/> + <command detect_errors="aggressive"><![CDATA[ +'$__tool_directory__/gff3_fix_sixpack.py' +@INPUT_GFF@ +> '$output']]></command> + <inputs> + <expand macro="gff3_input"/> + </inputs> + <outputs> + <data format="gff3" name="output"/> + </outputs> + <tests> + <test> + <param name="gff3_data" value="miro.gff3"/> + <output name="output" file="miro.6pfix.gff3"/> + </test> + <test> + <param name="gff3_data" value="miro.cds.gff3"/> + <output name="output" file="miro.cds6pfix.gff3"/> + </test> + </tests> + <help><![CDATA[ +**What it does** + +This tool **strips ALL the mRNA features** in a GFF3 file. It specifically formats +the output of the naïve ORF call Sixpack such that it will be compatible with +Apollo via JBrowse. + + ]]></help> + <expand macro="citations"/> +</tool> |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Mon Jun 05 02:42:28 2023 +0000 |
| b |
| @@ -0,0 +1,74 @@ +<macros> + <xml name="requirements"> + <requirements> + <requirement type="package">progressivemauve</requirement> + <!--<requirement type="package" version="2.7">python</requirement>--> + <requirement type="package" version="0.6.4">bcbiogff</requirement> + <yield/> + </requirements> + </xml> + <token name="@WRAPPER_VERSION@">2.4.0</token> + <xml name="citation/progressive_mauve"> + <citation type="doi">10.1371/journal.pone.0011147</citation> + </xml> + <xml name="citation/gepard"> + <citation type="doi">10.1093/bioinformatics/btm039</citation> + </xml> + <token name="@XMFA_INPUT@"> + '$xmfa' + </token> + <xml name="xmfa_input" token_formats="xmfa"> + <param type="data" format="@FORMATS@" name="xmfa" label="XMFA MSA"/> + </xml> + <token name="@XMFA_FA_INPUT@"> + '$sequences' + </token> + <xml name="xmfa_fa_input"> + <param type="data" format="fasta" name="sequences" label="Sequences in alignment" help="These sequences should be the SAME DATASET that was used in the progressiveMauve run. Failing that, they should be provided in the same order as in original progressiveMauve run"/> + </xml> + <xml name="genome_selector"> + <conditional name="reference_genome"> + <param name="reference_genome_source" type="select" label="Reference Genome"> + <option value="history" selected="True">From History</option> + <option value="cached">Locally Cached</option> + </param> + <when value="cached"> + <param name="fasta_indexes" type="select" label="Source FASTA Sequence"> + <options from_data_table="all_fasta"/> + </param> + </when> + <when value="history"> + <param name="genome_fasta" type="data" format="fasta" label="Source FASTA Sequence"/> + </when> + </conditional> + </xml> + <xml name="gff3_input"> + <param label="GFF3 Annotations" name="gff3_data" type="data" format="gff3"/> + </xml> + <xml name="input/gff3+fasta"> + <expand macro="gff3_input"/> + <expand macro="genome_selector"/> + </xml> + <token name="@INPUT_GFF@"> + '$gff3_data' + </token> + <token name="@INPUT_FASTA@"> + #if str($reference_genome.reference_genome_source) == 'cached': + '${reference_genome.fasta_indexes.fields.path}' + #else if str($reference_genome.reference_genome_source) == 'history': + genomeref.fa + #end if + </token> + <token name="@GENOME_SELECTOR_PRE@"> + #if $reference_genome.reference_genome_source == 'history': + ln -s '$reference_genome.genome_fasta' genomeref.fa; + #end if + </token> + <token name="@GENOME_SELECTOR@"> + #if str($reference_genome.reference_genome_source) == 'cached': + '${reference_genome.fasta_indexes.fields.path}' + #else if str($reference_genome.reference_genome_source) == 'history': + genomeref.fa + #end if + </token> +</macros> |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 test-data/miro.6pfix.gff3 --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/miro.6pfix.gff3 Mon Jun 05 02:42:28 2023 +0000 |
| b |
| b'@@ -0,0 +1,820 @@\n+##gff-version 3\n+Miro\tfeature\tgene\t1\t910\t.\t-\t.\tID=Miro_1;\n+Miro\tGenBank\tCDS\t1\t900\t.\t-\t1\tID=Miro_1.CDS;Name=Miro_1;Parent=Miro_1;obsolete_name=Miro_163;product=rIIb;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t908\t910\t.\t-\t1\tAlias=Miro_1;ID=Miro_1.RBS;Name=Miro_1;Parent=Miro_1;\n+Miro\tfeature\tgene\t900\t3173\t.\t-\t.\tID=Miro_2;\n+Miro\tGenBank\tCDS\t900\t3161\t.\t-\t1\tID=Miro_2.CDS;Name=Miro_2;Parent=Miro_2;obsolete_name=Miro_162;product=rIIa;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t3171\t3173\t.\t-\t1\tAlias=Miro_2;ID=Miro_2.RBS;Name=Miro_2;Parent=Miro_2;\n+Miro\tfeature\tgene\t3172\t3417\t.\t-\t.\tID=Miro_3;\n+Miro\tGenBank\tCDS\t3172\t3408\t.\t-\t1\tID=Miro_3.CDS;Name=Miro_3;Parent=Miro_3;obsolete_name=Miro_161;product=hypothetical conserved;tmhelix=1 TMD (12-34) N in%2C C out;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t3414\t3417\t.\t-\t1\tAlias=Miro_3;ID=Miro_3.RBS;Name=Miro_3;Parent=Miro_3;\n+Miro\tfeature\tgene\t3412\t3979\t.\t-\t.\tID=Miro_4;\n+Miro\tGenBank\tCDS\t3412\t3966\t.\t-\t1\tID=Miro_4.CDS;Name=Miro_4;Note=contains SprT domain;Parent=Miro_4;obsolete_name=Miro_160;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t3975\t3979\t.\t-\t1\tAlias=Miro_4;ID=Miro_4.RBS;Name=Miro_4;Parent=Miro_4;\n+Miro\tfeature\tgene\t4038\t5334\t.\t-\t.\tID=Miro_5;\n+Miro\tGenBank\tCDS\t4038\t5324\t.\t-\t1\tID=Miro_5.CDS;Name=Miro_5;Note=T4 gp52-like;Parent=Miro_5;obsolete_name=Miro_159;product=DNA topoisomerase II medium subunit;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t5331\t5334\t.\t-\t1\tAlias=Miro_5;ID=Miro_5.RBS;Name=Miro_5;Parent=Miro_5;\n+Miro\tfeature\tgene\t5324\t7231\t.\t-\t.\tID=Miro_6;\n+Miro\tGenBank\tCDS\t5324\t7222\t.\t-\t1\tID=Miro_6.CDS;Name=Miro_6;Note=T4 gp39-like;Parent=Miro_6;obsolete_name=Miro_158;product=DNA topoisomerase II%2C large subunit;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t7228\t7231\t.\t-\t1\tAlias=Miro_6;ID=Miro_6.RBS;Name=Miro_6;Parent=Miro_6;\n+Miro\tfeature\tgene\t7290\t7465\t.\t-\t.\tID=Miro_7;\n+Miro\tGenBank\tCDS\t7290\t7454\t.\t-\t1\tID=Miro_7.CDS;Name=Miro_7;Note=contains zinc ribbon domain;Parent=Miro_7;obsolete_name=Miro_157;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t7463\t7465\t.\t-\t1\tAlias=Miro_7;ID=Miro_7.RBS;Name=Miro_7;Parent=Miro_7;\n+Miro\tfeature\tgene\t7454\t7906\t.\t-\t.\tID=Miro_8;\n+Miro\tGenBank\tCDS\t7454\t7894\t.\t-\t1\tID=Miro_8.CDS;Name=Miro_8;Parent=Miro_8;obsolete_name=Miro_156;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t7903\t7906\t.\t-\t1\tAlias=Miro_8;ID=Miro_8.RBS;Name=Miro_8;Parent=Miro_8;\n+Miro\tfeature\tgene\t7917\t8512\t.\t-\t.\tID=Miro_9;\n+Miro\tGenBank\tCDS\t7917\t8501\t.\t-\t1\tID=Miro_9.CDS;Name=Miro_9;Parent=Miro_9;obsolete_name=Miro_155;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t8509\t8512\t.\t-\t1\tAlias=Miro_9;ID=Miro_9.RBS;Name=Miro_9;Parent=Miro_9;\n+Miro\tfeature\tgene\t8488\t8779\t.\t-\t.\tID=Miro_10;\n+Miro\tGenBank\tCDS\t8488\t8766\t.\t-\t1\tID=Miro_10.CDS;Name=Miro_10;Parent=Miro_10;obsolete_name=Miro_154;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t8776\t8779\t.\t-\t1\tAlias=Miro_10;ID=Miro_10.RBS;Name=Miro_10;Parent=Miro_10;\n+Miro\tfeature\tgene\t8763\t9370\t.\t-\t.\tID=Miro_11;\n+Miro\tGenBank\tCDS\t8763\t9359\t.\t-\t1\tID=Miro_11.CDS;Name=Miro_11;Parent=Miro_11;obsolete_name=Miro_153;product=hypothetical conserved;tmhelix=1 TMD (10-29) N out%2C C in;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t9367\t9370\t.\t-\t1\tAlias=Miro_11;ID=Miro_11.RBS;Name=Miro_11;Parent=Miro_11;\n+Miro\tfeature\tgene\t9399\t9740\t.\t-\t.\tID=Miro_12;\n+Miro\tGenBank\tCDS\t9399\t9728\t.\t-\t1\tID=Miro_12.CDS;Name=Miro_12;Parent=Miro_12;obsolete_name=Miro_152;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t9736\t9740\t.\t-\t1\tAlias=Miro_12;ID=Miro_12.RBS;Name=Miro_12;Parent=Miro_12;\n+Miro\tfeature\tgene\t9788\t10025\t.\t-\t.\tID=Miro_13;\n+Miro\tGenBank\tCDS\t9788\t10012\t.\t-\t1\tID=Miro_13.CDS;Name=Miro_13;Parent=Miro_13;obsolete_name=Miro_151;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t10021\t10025\t.\t-\t1\tAlias=Miro_13;ID=Miro_13.RBS;Name=Miro_13;Parent=Miro_13;\n+Miro\tfeature\tgene\t10086\t10361\t.\t-\t.\tID=Miro_14;\n+Miro\tGenBank\tCDS\t10086\t10349\t.\t-\t1\tID=Miro_14.CDS;Na'..b'product=tail fiber;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t166968\t166971\t.\t+\t1\tID=Miro_264.RBS;Name=Miro_264;Parent=Miro_264;\n+Miro\tfeature\tgene\t167645\t171466\t.\t+\t.\tID=Miro_265;\n+Miro\tGenBank\tCDS\t167654\t171466\t.\t+\t1\tAlias=Miro_265;ID=Miro_265.CDS;Name=Miro_265;Parent=Miro_265;obsolete_name=Miro_175;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t167645\t167648\t.\t+\t1\tID=Miro_265.RBS;Name=Miro_265;Parent=Miro_265;\n+Miro\tfeature\tgene\t171490\t172030\t.\t+\t.\tID=Miro_266;\n+Miro\tGenBank\tCDS\t171503\t172030\t.\t+\t1\tAlias=Miro_266;ID=Miro_266.CDS;Name=Miro_266;Note=T2 gp38-like;Parent=Miro_266;obsolete_name=Miro_174;product=receptor-recognizing protein;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t171490\t171494\t.\t+\t1\tID=Miro_266.RBS;Name=Miro_266;Parent=Miro_266;\n+Miro\tfeature\tgene\t172135\t172794\t.\t+\t.\tID=Miro_267;\n+Miro\tGenBank\tCDS\t172147\t172794\t.\t+\t1\tAlias=Miro_267;ID=Miro_267.CDS;Name=Miro_267;Note=T4 gpT-like;Parent=Miro_267;obsolete_name=Miro_173;product=holin;tmhelix=1 TMD (29-47) N in%2C C out;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t172135\t172137\t.\t+\t1\tID=Miro_267.RBS;Name=Miro_267;Parent=Miro_267;\n+Miro\tfeature\tgene\t172795\t173074\t.\t-\t.\tID=Miro_268;\n+Miro\tGenBank\tCDS\t172795\t173064\t.\t-\t1\tID=Miro_268.CDS;Name=Miro_268;Parent=Miro_268;obsolete_name=Miro_172;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t173071\t173074\t.\t-\t1\tAlias=Miro_268;ID=Miro_268.RBS;Name=Miro_268;Parent=Miro_268;\n+Miro\tfeature\tgene\t173061\t173361\t.\t-\t.\tID=Miro_269;\n+Miro\tGenBank\tCDS\t173061\t173351\t.\t-\t1\tID=Miro_269.CDS;Name=Miro_269;Parent=Miro_269;obsolete_name=Miro_171;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t173358\t173361\t.\t-\t1\tAlias=Miro_269;ID=Miro_269.RBS;Name=Miro_269;Parent=Miro_269;\n+Miro\tfeature\tgene\t173351\t174160\t.\t-\t.\tID=Miro_270;\n+Miro\tGenBank\tCDS\t173351\t174148\t.\t-\t1\tID=Miro_270.CDS;Name=Miro_270;Parent=Miro_270;obsolete_name=Miro_170;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t174156\t174160\t.\t-\t1\tAlias=Miro_270;ID=Miro_270.RBS;Name=Miro_270;Parent=Miro_270;\n+Miro\tfeature\tgene\t174229\t174467\t.\t-\t.\tID=Miro_271;\n+Miro\tGenBank\tCDS\t174229\t174456\t.\t-\t1\tID=Miro_271.CDS;Name=Miro_271;Parent=Miro_271;obsolete_name=Miro_169;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t174464\t174467\t.\t-\t1\tAlias=Miro_271;ID=Miro_271.RBS;Name=Miro_271;Parent=Miro_271;\n+Miro\tfeature\tgene\t174453\t174796\t.\t-\t.\tID=Miro_272;\n+Miro\tGenBank\tCDS\t174453\t174785\t.\t-\t1\tID=Miro_272.CDS;Name=Miro_272;Parent=Miro_272;obsolete_name=Miro_168;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t174793\t174796\t.\t-\t1\tAlias=Miro_272;ID=Miro_272.RBS;Name=Miro_272;Parent=Miro_272;\n+Miro\tfeature\tgene\t174760\t174903\t.\t-\t.\tID=Miro_273;\n+Miro\tGenBank\tCDS\t174760\t174894\t.\t-\t1\tID=Miro_273.CDS;Name=Miro_273;Parent=Miro_273;obsolete_name=Miro_167;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t174900\t174903\t.\t-\t1\tAlias=Miro_273;ID=Miro_273.RBS;Name=Miro_273;Parent=Miro_273;\n+Miro\tfeature\tgene\t174939\t175197\t.\t-\t.\tID=Miro_274;\n+Miro\tGenBank\tCDS\t174939\t175187\t.\t-\t1\tID=Miro_274.CDS;Name=Miro_274;Note=contains FCH and colicin domains;Parent=Miro_274;obsolete_name=Miro_166;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t175195\t175197\t.\t-\t1\tAlias=Miro_274;ID=Miro_274.RBS;Name=Miro_274;Parent=Miro_274;\n+Miro\tfeature\tgene\t175224\t175675\t.\t-\t.\tID=Miro_275;\n+Miro\tGenBank\tCDS\t175224\t175661\t.\t-\t1\tID=Miro_275.CDS;Name=Miro_275;Parent=Miro_275;obsolete_name=Miro_165;product=hypothetical conserved;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t175673\t175675\t.\t-\t1\tAlias=Miro_275;ID=Miro_275.RBS;Name=Miro_275;Parent=Miro_275;\n+Miro\tfeature\tgene\t175636\t176021\t.\t-\t.\tID=Miro_276;\n+Miro\tGenBank\tCDS\t175636\t176010\t.\t-\t1\tID=Miro_276.CDS;Name=Miro_276;Parent=Miro_276;obsolete_name=Miro_164;product=hypothetical conserved;tmhelix=2TMDs (44-66%2C 76-98) N in%2C C in;\n+Miro\tGenBank\tShine_Dalgarno_sequence\t176017\t176021\t.\t-\t1\tAlias=Miro_276;ID=Miro_276.RBS;Name=Miro_276;Parent=Miro_276;\n' |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 test-data/miro.cds.gff3 --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/miro.cds.gff3 Mon Jun 05 02:42:28 2023 +0000 |
| b |
| b'@@ -0,0 +1,278 @@\n+##gff-version 3\n+##sequence-region Miro 1 176055\n+Miro\tGenBank\tCDS\t7454\t7894\t.\t-\t1\tID=Miro_8.CDS;Name=Miro_8;obsolete_name=Miro_156;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t7917\t8501\t.\t-\t1\tID=Miro_9.CDS;Name=Miro_9;obsolete_name=Miro_155;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t123286\t124212\t.\t+\t1\tAlias=Miro_206;ID=Miro_206.CDS;Name=Miro_206;obsolete_name=Miro_234;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t68490\t70706\t.\t-\t1\tID=Miro_117.CDS;Name=Miro_117;Note=contains von Willebrand factor%2C type A;obsolete_name=Miro_047;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t115743\t116735\t.\t+\t1\tAlias=Miro_200;ID=Miro_200.CDS;Name=Miro_200;Note=T4 gp6-like;obsolete_name=Miro_240;product=baseplate structural protein;\n+Miro\tGenBank\tCDS\t116745\t117608\t.\t+\t1\tAlias=Miro_201;ID=Miro_201.CDS;Name=Miro_201;Note=T4 gp9/gp10-like;obsolete_name=Miro_239;product=baseplate structural protein;\n+Miro\tGenBank\tCDS\t117605\t119422\t.\t+\t1\tAlias=Miro_202;ID=Miro_202.CDS;Name=Miro_202;Note=T4 gp9/gp10-like;obsolete_name=Miro_238;product=baseplate structural protein;\n+Miro\tGenBank\tCDS\t119422\t120090\t.\t+\t1\tAlias=Miro_203;ID=Miro_203.CDS;Name=Miro_203;Note=T4 gp11-like;obsolete_name=Miro_237;product=baseplate to short tail fiber connector protein;\n+Miro\tGenBank\tCDS\t81829\t81927\t.\t-\t1\tID=Miro_142.CDS;Name=Miro_142;obsolete_name=Miro_022;product=hypothetical conserved;tmhelix=1 TMD (4-26) N out%2C C in;\n+Miro\tGenBank\tCDS\t1\t900\t.\t-\t1\tID=Miro_1.CDS;Name=Miro_1;obsolete_name=Miro_163;product=rIIb;\n+Miro\tGenBank\tCDS\t900\t3161\t.\t-\t1\tID=Miro_2.CDS;Name=Miro_2;obsolete_name=Miro_162;product=rIIa;\n+Miro\tGenBank\tCDS\t3172\t3408\t.\t-\t1\tID=Miro_3.CDS;Name=Miro_3;obsolete_name=Miro_161;product=hypothetical conserved;tmhelix=1 TMD (12-34) N in%2C C out;\n+Miro\tGenBank\tCDS\t3412\t3966\t.\t-\t1\tID=Miro_4.CDS;Name=Miro_4;Note=contains SprT domain;obsolete_name=Miro_160;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t4038\t5324\t.\t-\t1\tID=Miro_5.CDS;Name=Miro_5;Note=T4 gp52-like;obsolete_name=Miro_159;product=DNA topoisomerase II medium subunit;\n+Miro\tGenBank\tCDS\t5324\t7222\t.\t-\t1\tID=Miro_6.CDS;Name=Miro_6;Note=T4 gp39-like;obsolete_name=Miro_158;product=DNA topoisomerase II%2C large subunit;\n+Miro\tGenBank\tCDS\t7290\t7454\t.\t-\t1\tID=Miro_7.CDS;Name=Miro_7;Note=contains zinc ribbon domain;obsolete_name=Miro_157;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t124222\t124968\t.\t+\t1\tAlias=Miro_207;ID=Miro_207.CDS;Name=Miro_207;Note=T4 gp14-like;obsolete_name=Miro_233;product=neck protein;\n+Miro\tGenBank\tCDS\t173061\t173351\t.\t-\t1\tID=Miro_269.CDS;Name=Miro_269;obsolete_name=Miro_171;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t66523\t66807\t.\t-\t1\tID=Miro_112.CDS;Name=Miro_112;obsolete_name=Miro_052;product=hypothetical conserved;signal=signal peptidase I cleavage site 17-18;\n+Miro\tGenBank\tCDS\t66879\t67163\t.\t-\t1\tID=Miro_113.CDS;Name=Miro_113;obsolete_name=Miro_051;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t44575\t45732\t.\t+\t1\tAlias=Miro_69;ID=Miro_69.CDS;Name=Miro_69;Note=T4 RNA ligase 1-like;obsolete_name=Miro_095;product=RNA ligase;\n+Miro\tGenBank\tCDS\t44229\t44594\t.\t+\t1\tAlias=Miro_68;ID=Miro_68.CDS;Name=Miro_68;Note=contains GIY-YIG domain;obsolete_name=Miro_096;product=homing endonuclease;\n+Miro\tGenBank\tCDS\t43905\t44225\t.\t+\t1\tID=Miro_67;Name=Miro_67;obsolete_name=Miro_097;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t42758\t43933\t.\t+\t1\tAlias=Miro_66;ID=Miro_66.CDS;Name=Miro_66;Note=T4 NrdB-like;obsolete_name=Miro_098;product=ribonucleotide reductase%2C small subunit;\n+Miro\tGenBank\tCDS\t40469\t42721\t.\t+\t1\tAlias=Miro_65;ID=Miro_65.CDS;Name=Miro_65;Note=T4 NrdA-like%3B E-val 0;obsolete_name=Miro_099;product=ribonucleotide reductase%2C large subunit;\n+Miro\tGenBank\tCDS\t39554\t40429\t.\t+\t1\tAlias=Miro_64;ID=Miro_64.CDS;Name=Miro_64;Note=T4-like;obsolete_name=Miro_100;product=thymidylate synthase;\n+Miro\tGenBank\tCDS\t38974\t39552\t.\t+\t1\tAlias=Miro_63;ID=Miro_63.CDS;Name=Miro_63;Note=T4-like;obsolete_name=Miro_101;product=dihydrofolate reductase;\n+Miro\tGenBank\tCDS\t38720'..b'ed;\n+Miro\tGenBank\tCDS\t9399\t9728\t.\t-\t1\tID=Miro_12.CDS;Name=Miro_12;obsolete_name=Miro_152;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t9788\t10012\t.\t-\t1\tID=Miro_13.CDS;Name=Miro_13;obsolete_name=Miro_151;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t8488\t8766\t.\t-\t1\tID=Miro_10.CDS;Name=Miro_10;obsolete_name=Miro_154;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t8763\t9359\t.\t-\t1\tID=Miro_11.CDS;Name=Miro_11;obsolete_name=Miro_153;product=hypothetical conserved;tmhelix=1 TMD (10-29) N out%2C C in;\n+Miro\tGenBank\tCDS\t10737\t10961\t.\t-\t1\tID=Miro_16.CDS;Name=Miro_16;obsolete_name=Miro_148;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t10965\t11114\t.\t-\t1\tID=Miro_17.CDS;Name=Miro_17;obsolete_name=Miro_147;product=hypothetical conserved;tmhelix=1 TMD (10-32) N out%2C C in;\n+Miro\tGenBank\tCDS\t10086\t10349\t.\t-\t1\tID=Miro_14.CDS;Name=Miro_14;obsolete_name=Miro_150;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t10438\t10737\t.\t-\t1\tID=Miro_15.CDS;Name=Miro_15;obsolete_name=Miro_149;product=hypothetical conserved;tmhelix=1 TMD (4-21) N out%2C C in;\n+Miro\tGenBank\tCDS\t53923\t54144\t.\t+\t1\tAlias=Miro_92;ID=Miro_92.CDS;Name=Miro_92;obsolete_name=Miro_072;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t54141\t54755\t.\t+\t1\tAlias=Miro_93;ID=Miro_93.CDS;Name=Miro_93;Note=contains haloacid dehydrogenase (HAD)-like domain;obsolete_name=Miro_071;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t53221\t53661\t.\t+\t1\tAlias=Miro_90;ID=Miro_90.CDS;Name=Miro_90;Note=T4 Y12G-like;obsolete_name=Miro_074;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t53658\t53921\t.\t+\t1\tAlias=Miro_91;ID=Miro_91.CDS;Name=Miro_91;obsolete_name=Miro_073;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t57000\t57203\t.\t+\t1\tAlias=Miro_96;ID=Miro_96.CDS;Name=Miro_96;obsolete_name=Miro_068;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t57206\t57382\t.\t+\t1\tAlias=Miro_97;ID=Miro_97.CDS;Name=Miro_97;obsolete_name=Miro_067;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t54736\t56265\t.\t+\t1\tAlias=Miro_94;ID=Miro_94.CDS;Name=Miro_94;Note=T4-like;obsolete_name=Miro_070;product=DNA ligase;\n+Miro\tGenBank\tCDS\t56342\t56911\t.\t+\t1\tAlias=Miro_95;ID=Miro_95.CDS;Name=Miro_95;obsolete_name=Miro_069;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t57379\t57543\t.\t+\t1\tAlias=Miro_98;ID=Miro_98.CDS;Name=Miro_98;obsolete_name=Miro_066;product=hypothetical conserved;tmhelix=2TMDs (7-26%2C 31-53) N in%2C C in;\n+Miro\tGenBank\tCDS\t57624\t57914\t.\t+\t1\tAlias=Miro_99;ID=Miro_99.CDS;Name=Miro_99;obsolete_name=Miro_065;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t81924\t82079\t.\t-\t1\tID=Miro_143.CDS;Name=Miro_143;obsolete_name=Miro_021;product=hypothetical conserved;tmhelix=1 TMD (15-37) N out%2C C in;\n+Miro\tGenBank\tCDS\t67179\t67649\t.\t-\t1\tID=Miro_114.CDS;Name=Miro_114;obsolete_name=Miro_050;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t81366\t81839\t.\t-\t1\tID=Miro_141.CDS;Name=Miro_141;Note=contains macro domain;obsolete_name=Miro_023;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t81076\t81363\t.\t-\t1\tID=Miro_140.CDS;Name=Miro_140;obsolete_name=Miro_024;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t83223\t83618\t.\t-\t1\tID=Miro_147.CDS;Name=Miro_147;obsolete_name=Miro_017;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t83066\t83212\t.\t-\t1\tID=Miro_146.CDS;Name=Miro_146;obsolete_name=Miro_018;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t82479\t83069\t.\t-\t1\tID=Miro_145.CDS;Name=Miro_145;obsolete_name=Miro_019;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t67646\t67804\t.\t-\t1\tID=Miro_115.CDS;Name=Miro_115;obsolete_name=Miro_049;product=hypothetical conserved;tmhelix=2TMDs (2-21%2C 31-50) N in%2C C in;\n+Miro\tGenBank\tCDS\t84392\t84946\t.\t-\t1\tID=Miro_149.CDS;Name=Miro_149;obsolete_name=Miro_015;product=hypothetical conserved;\n+Miro\tGenBank\tCDS\t83686\t84327\t.\t-\t1\tID=Miro_148.CDS;Name=Miro_148;Note=T4 RegB-like;obsolete_name=Miro_016;product=endoribonuclease;signal=signal peptidase II cleavage site 12-13;\n+Miro\tGenBank\tCDS\t67801\t68451\t.\t-\t1\tID=Miro_116.CDS;Name=Miro_116;obsolete_name=Miro_048;product=hypothetical conserved;\n' |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 test-data/miro.cds6pfix.gff3 --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/miro.cds6pfix.gff3 Mon Jun 05 02:42:28 2023 +0000 |
| b |
| @@ -0,0 +1,1 @@ +##gff-version 3 |
| b |
| diff -r 6a9b026cb378 -r efa4dfc23549 test-data/miro.gff3 --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/miro.gff3 Mon Jun 05 02:42:28 2023 +0000 |
| b |
| b'@@ -0,0 +1,827 @@\n+##gff-version 3\n+##sequence-region Miro 1 176055\n+Miro\tfeature\tgene\t7454\t7906\t.\t-\t.\tID=Miro_8\n+Miro\tGenBank\tCDS\t7454\t7894\t.\t-\t1\tID=Miro_8.CDS;Name=Miro_8;Parent=Miro_8;obsolete_name=Miro_156;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t7903\t7906\t.\t-\t1\tAlias=Miro_8;ID=Miro_8.RBS;Name=Miro_8;Parent=Miro_8\n+Miro\tfeature\tgene\t7917\t8512\t.\t-\t.\tID=Miro_9\n+Miro\tGenBank\tCDS\t7917\t8501\t.\t-\t1\tID=Miro_9.CDS;Name=Miro_9;Parent=Miro_9;obsolete_name=Miro_155;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t8509\t8512\t.\t-\t1\tAlias=Miro_9;ID=Miro_9.RBS;Name=Miro_9;Parent=Miro_9\n+Miro\tfeature\tgene\t123276\t124212\t.\t+\t.\tID=Miro_206\n+Miro\tGenBank\tCDS\t123286\t124212\t.\t+\t1\tAlias=Miro_206;ID=Miro_206.CDS;Name=Miro_206;Parent=Miro_206;obsolete_name=Miro_234;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t123276\t123279\t.\t+\t1\tID=Miro_206.rbs;Name=Miro_206;Parent=Miro_206\n+Miro\tfeature\tgene\t68490\t70715\t.\t-\t.\tID=Miro_117\n+Miro\tGenBank\tCDS\t68490\t70706\t.\t-\t1\tID=Miro_117.CDS;Name=Miro_117;Note=contains von Willebrand factor%2C type A;Parent=Miro_117;obsolete_name=Miro_047;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t70713\t70715\t.\t-\t1\tAlias=Miro_117;ID=Miro_117.RBS;Name=Miro_117;Parent=Miro_117\n+Miro\tfeature\tgene\t115729\t116735\t.\t+\t.\tID=Miro_200\n+Miro\tGenBank\tCDS\t115743\t116735\t.\t+\t1\tAlias=Miro_200;ID=Miro_200.CDS;Name=Miro_200;Note=T4 gp6-like;Parent=Miro_200;obsolete_name=Miro_240;product=baseplate structural protein\n+Miro\tGenBank\tShine_Dalgarno_sequence\t115729\t115732\t.\t+\t1\tID=Miro_200.RBS;Name=Miro_200;Parent=Miro_200\n+Miro\tfeature\tgene\t116735\t117608\t.\t+\t.\tID=Miro_201\n+Miro\tGenBank\tCDS\t116745\t117608\t.\t+\t1\tAlias=Miro_201;ID=Miro_201.CDS;Name=Miro_201;Note=T4 gp9/gp10-like;Parent=Miro_201;obsolete_name=Miro_239;product=baseplate structural protein\n+Miro\tGenBank\tShine_Dalgarno_sequence\t116735\t116738\t.\t+\t1\tID=Miro_201.RBS;Name=Miro_201;Parent=Miro_201\n+Miro\tfeature\tgene\t117595\t119422\t.\t+\t.\tID=Miro_202\n+Miro\tGenBank\tCDS\t117605\t119422\t.\t+\t1\tAlias=Miro_202;ID=Miro_202.CDS;Name=Miro_202;Note=T4 gp9/gp10-like;Parent=Miro_202;obsolete_name=Miro_238;product=baseplate structural protein\n+Miro\tGenBank\tShine_Dalgarno_sequence\t117595\t117597\t.\t+\t1\tID=Miro_202.RBS;Name=Miro_202;Parent=Miro_202\n+Miro\tfeature\tgene\t119412\t120090\t.\t+\t.\tID=Miro_203\n+Miro\tGenBank\tCDS\t119422\t120090\t.\t+\t1\tAlias=Miro_203;ID=Miro_203.CDS;Name=Miro_203;Note=T4 gp11-like;Parent=Miro_203;obsolete_name=Miro_237;product=baseplate to short tail fiber connector protein\n+Miro\tGenBank\tShine_Dalgarno_sequence\t119412\t119415\t.\t+\t1\tID=Miro_203.RBS;Name=Miro_203;Parent=Miro_203\n+Miro\tfeature\tgene\t81829\t81940\t.\t-\t.\tID=Miro_142\n+Miro\tGenBank\tCDS\t81829\t81927\t.\t-\t1\tID=Miro_142.CDS;Name=Miro_142;Parent=Miro_142;obsolete_name=Miro_022;product=hypothetical conserved;tmhelix=1 TMD %284-26%29 N out%2C C in\n+Miro\tGenBank\tShine_Dalgarno_sequence\t81938\t81940\t.\t-\t1\tAlias=Miro_142;ID=Miro_142.RBS;Name=Miro_142;Parent=Miro_142\n+Miro\tfeature\tgene\t1\t910\t.\t-\t.\tID=Miro_1\n+Miro\tGenBank\tCDS\t1\t900\t.\t-\t1\tID=Miro_1.CDS;Name=Miro_1;Parent=Miro_1;obsolete_name=Miro_163;product=rIIb\n+Miro\tGenBank\tShine_Dalgarno_sequence\t908\t910\t.\t-\t1\tAlias=Miro_1;ID=Miro_1.RBS;Name=Miro_1;Parent=Miro_1\n+Miro\tfeature\tgene\t900\t3173\t.\t-\t.\tID=Miro_2\n+Miro\tGenBank\tCDS\t900\t3161\t.\t-\t1\tID=Miro_2.CDS;Name=Miro_2;Parent=Miro_2;obsolete_name=Miro_162;product=rIIa\n+Miro\tGenBank\tShine_Dalgarno_sequence\t3171\t3173\t.\t-\t1\tAlias=Miro_2;ID=Miro_2.RBS;Name=Miro_2;Parent=Miro_2\n+Miro\tfeature\tgene\t3172\t3417\t.\t-\t.\tID=Miro_3\n+Miro\tGenBank\tCDS\t3172\t3408\t.\t-\t1\tID=Miro_3.CDS;Name=Miro_3;Parent=Miro_3;obsolete_name=Miro_161;product=hypothetical conserved;tmhelix=1 TMD %2812-34%29 N in%2C C out\n+Miro\tGenBank\tShine_Dalgarno_sequence\t3414\t3417\t.\t-\t1\tAlias=Miro_3;ID=Miro_3.RBS;Name=Miro_3;Parent=Miro_3\n+Miro\tfeature\tgene\t3412\t3979\t.\t-\t.\tID=Miro_4\n+Miro\tGenBank\tCDS\t3412\t3966\t.\t-\t1\tID=Miro_4.CDS;Name=Miro_4;Note=contains SprT domain;Parent=Miro_4;obsolete_name=Miro_160;product=hypothetical'..b't=Miro_98;obsolete_name=Miro_066;product=hypothetical conserved;tmhelix=2TMDs %287-26%2C 31-53%29 N in%2C C in\n+Miro\tGenBank\tShine_Dalgarno_sequence\t57368\t57372\t.\t+\t1\tID=Miro_98.RBS;Name=Miro_98;Parent=Miro_98\n+Miro\tfeature\tgene\t57613\t57914\t.\t+\t.\tID=Miro_99\n+Miro\tGenBank\tCDS\t57624\t57914\t.\t+\t1\tAlias=Miro_99;ID=Miro_99.CDS;Name=Miro_99;Parent=Miro_99;obsolete_name=Miro_065;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t57613\t57616\t.\t+\t1\tID=Miro_99.RBS;Name=Miro_99;Parent=Miro_99\n+Miro\tfeature\tgene\t81924\t82086\t.\t-\t.\tID=Miro_143\n+Miro\tGenBank\tCDS\t81924\t82079\t.\t-\t1\tID=Miro_143.CDS;Name=Miro_143;Parent=Miro_143;obsolete_name=Miro_021;product=hypothetical conserved;tmhelix=1 TMD %2815-37%29 N out%2C C in\n+Miro\tGenBank\tShine_Dalgarno_sequence\t82084\t82086\t.\t-\t1\tAlias=Miro_143;ID=Miro_143.RBS;Name=Miro_143;Parent=Miro_143\n+Miro\tfeature\tgene\t67179\t67658\t.\t-\t.\tID=Miro_114\n+Miro\tGenBank\tCDS\t67179\t67649\t.\t-\t1\tID=Miro_114.CDS;Name=Miro_114;Parent=Miro_114;obsolete_name=Miro_050;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t67656\t67658\t.\t-\t1\tAlias=Miro_114;ID=Miro_114.RBS;Name=Miro_114;Parent=Miro_114\n+Miro\tfeature\tgene\t81366\t81851\t.\t-\t.\tID=Miro_141\n+Miro\tGenBank\tCDS\t81366\t81839\t.\t-\t1\tID=Miro_141.CDS;Name=Miro_141;Note=contains macro domain;Parent=Miro_141;obsolete_name=Miro_023;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t81849\t81851\t.\t-\t1\tAlias=Miro_141;ID=Miro_141.RBS;Name=Miro_141;Parent=Miro_141\n+Miro\tfeature\tgene\t81076\t81376\t.\t-\t.\tID=Miro_140\n+Miro\tGenBank\tCDS\t81076\t81363\t.\t-\t1\tID=Miro_140.CDS;Name=Miro_140;Parent=Miro_140;obsolete_name=Miro_024;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t81374\t81376\t.\t-\t1\tAlias=Miro_140;ID=Miro_140.RBS;Name=Miro_140;Parent=Miro_140\n+Miro\tfeature\tgene\t83223\t83630\t.\t-\t.\tID=Miro_147\n+Miro\tGenBank\tCDS\t83223\t83618\t.\t-\t1\tID=Miro_147.CDS;Name=Miro_147;Parent=Miro_147;obsolete_name=Miro_017;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t83627\t83630\t.\t-\t1\tAlias=Miro_147;ID=Miro_147.RBS;Name=Miro_147;Parent=Miro_147\n+Miro\tfeature\tgene\t83066\t83224\t.\t-\t.\tID=Miro_146\n+Miro\tGenBank\tCDS\t83066\t83212\t.\t-\t1\tID=Miro_146.CDS;Name=Miro_146;Parent=Miro_146;obsolete_name=Miro_018;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t83221\t83224\t.\t-\t1\tAlias=Miro_146;ID=Miro_146.RBS;Name=Miro_146;Parent=Miro_146\n+Miro\tfeature\tgene\t82479\t83083\t.\t-\t.\tID=Miro_145\n+Miro\tGenBank\tCDS\t82479\t83069\t.\t-\t1\tID=Miro_145.CDS;Name=Miro_145;Parent=Miro_145;obsolete_name=Miro_019;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t83080\t83083\t.\t-\t1\tAlias=Miro_145;ID=Miro_145.RBS;Name=Miro_145;Parent=Miro_145\n+Miro\tfeature\tgene\t67646\t67816\t.\t-\t.\tID=Miro_115\n+Miro\tGenBank\tCDS\t67646\t67804\t.\t-\t1\tID=Miro_115.CDS;Name=Miro_115;Parent=Miro_115;obsolete_name=Miro_049;product=hypothetical conserved;tmhelix=2TMDs %282-21%2C 31-50%29 N in%2C C in\n+Miro\tGenBank\tShine_Dalgarno_sequence\t67814\t67816\t.\t-\t1\tAlias=Miro_115;ID=Miro_115.RBS;Name=Miro_115;Parent=Miro_115\n+Miro\tfeature\tgene\t84392\t84959\t.\t-\t.\tID=Miro_149\n+Miro\tGenBank\tCDS\t84392\t84946\t.\t-\t1\tID=Miro_149.CDS;Name=Miro_149;Parent=Miro_149;obsolete_name=Miro_015;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t84955\t84959\t.\t-\t1\tAlias=Miro_149;ID=Miro_149.RBS;Name=Miro_149;Parent=Miro_149\n+Miro\tfeature\tgene\t83686\t84337\t.\t-\t.\tID=Miro_148\n+Miro\tGenBank\tCDS\t83686\t84327\t.\t-\t1\tID=Miro_148.CDS;Name=Miro_148;Note=T4 RegB-like;Parent=Miro_148;obsolete_name=Miro_016;product=endoribonuclease;signal=signal peptidase II cleavage site 12-13\n+Miro\tGenBank\tShine_Dalgarno_sequence\t84334\t84337\t.\t-\t1\tAlias=Miro_148;ID=Miro_148.RBS;Name=Miro_148;Parent=Miro_148\n+Miro\tfeature\tgene\t67801\t68461\t.\t-\t.\tID=Miro_116\n+Miro\tGenBank\tCDS\t67801\t68451\t.\t-\t1\tID=Miro_116.CDS;Name=Miro_116;Parent=Miro_116;obsolete_name=Miro_048;product=hypothetical conserved\n+Miro\tGenBank\tShine_Dalgarno_sequence\t68457\t68461\t.\t-\t1\tAlias=Miro_116;ID=Miro_116.RBS;Name=Miro_116;Parent=Miro_116\n' |