Next changeset 1:b46f0c9a4679 (2022-05-20) |
Commit message:
Uploaded |
added:
cpt_rem_annotes/cpt-macros.xml cpt_rem_annotes/macros.xml cpt_rem_annotes/remove_annotations.py cpt_rem_annotes/remove_annotations.xml cpt_rem_annotes/test-data/RemoveAnnote_In.gff3 cpt_rem_annotes/test-data/RemoveAnnote_Out.gff3 |
b |
diff -r 000000000000 -r 03d27abd1dfd cpt_rem_annotes/cpt-macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cpt_rem_annotes/cpt-macros.xml Fri May 13 05:26:10 2022 +0000 |
[ |
@@ -0,0 +1,115 @@ +<?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@unpublished{galaxyTools, + author = {E. Mijalis, H. Rasche}, + title = {CPT Galaxy Tools}, + year = {2013-2017}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } +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 + @unpublished{galaxyTools, + author = {E. Mijalis, H. Rasche}, + title = {CPT Galaxy Tools}, + year = {2013-2017}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } +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 + @unpublished{galaxyTools, + author = {C. Ross}, + title = {CPT Galaxy Tools}, + year = {2020-}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } + 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 + @unpublished{galaxyTools, + author = {E. Mijalis, H. Rasche}, + title = {CPT Galaxy Tools}, + year = {2013-2017}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } +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 + @unpublished{galaxyTools, + author = {A. Criscione}, + title = {CPT Galaxy Tools}, + year = {2019-2021}, + note = {https://github.com/tamu-cpt/galaxy-tools/} + } + 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 000000000000 -r 03d27abd1dfd cpt_rem_annotes/macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cpt_rem_annotes/macros.xml Fri May 13 05:26:10 2022 +0000 |
b |
@@ -0,0 +1,85 @@ +<?xml version="1.0"?> +<macros> + <xml name="requirements"> + <requirements> + <requirement type="package" version="3.6">python</requirement> + <requirement type="package" version="1.77">biopython</requirement> + <requirement type="package" version="1.1.3">cpt_gffparser</requirement> + <yield/> + </requirements> + </xml> + <token name="@BLAST_TSV@"> + "$blast_tsv" + </token> + <xml name="blast_tsv"> + <param label="Blast Results" help="TSV/tabular (25 Column)" + name="blast_tsv" type="data" format="tabular" /> + </xml> + + <token name="@BLAST_XML@"> + "$blast_xml" + </token> + <xml name="blast_xml"> + <param label="Blast Results" help="XML format" + name="blast_xml" type="data" format="blastxml" /> + </xml> + <xml name="gff3_with_fasta"> + <param label="Genome Sequences" name="fasta" type="data" format="fasta" /> + <param label="Genome Annotations" name="gff3" type="data" format="gff3" /> + </xml> + <xml name="genome_selector"> + <conditional name="reference_genome"> + <param name="reference_genome_source" type="select" label="Reference Genome"> + <option value="history" selected="True">From History</option> + <option value="cached">Locally Cached</option> + </param> + <when value="cached"> + <param name="fasta_indexes" type="select" label="Source FASTA Sequence"> + <options from_data_table="all_fasta"/> + </param> + </when> + <when value="history"> + <param name="genome_fasta" type="data" format="fasta" label="Source FASTA Sequence"/> + </when> + </conditional> + </xml> + <xml name="gff3_input"> + <param label="GFF3 Annotations" name="gff3_data" type="data" format="gff3"/> + </xml> + <xml name="input/gff3+fasta"> + <expand macro="gff3_input" /> + <expand macro="genome_selector" /> + </xml> + <token name="@INPUT_GFF@"> + "$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 000000000000 -r 03d27abd1dfd cpt_rem_annotes/remove_annotations.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cpt_rem_annotes/remove_annotations.py Fri May 13 05:26:10 2022 +0000 |
[ |
@@ -0,0 +1,19 @@ +#!/usr/bin/env python +import sys +import argparse +from CPT_GFFParser import gffParse, gffWrite + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument("gff3", type=argparse.FileType("r"), help="GFF3 annotations") + parser.add_argument("--remark", action="store_true", help="Remove remark features") + parser.add_argument("--region", action="store_true", help="Remove region features") + args = parser.parse_args() + + for rec in gffParse(args.gff3): + rec.annotations = {} + if args.remark: + rec.features = [x for x in rec.features if x.type != "remark"] + if args.region: + rec.features = [x for x in rec.features if x.type != "region"] + gffWrite([rec], sys.stdout) |
b |
diff -r 000000000000 -r 03d27abd1dfd cpt_rem_annotes/remove_annotations.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cpt_rem_annotes/remove_annotations.xml Fri May 13 05:26:10 2022 +0000 |
[ |
@@ -0,0 +1,48 @@ +<?xml version="1.0"?> +<tool id="edu.tamu.cpt.gff3.remove_annots" name="Remove Annotation Feature" version="19.1.0.1" profile="16.04"> + <description>that's unused in our GFF tools</description> + <macros> + <import>macros.xml</import> + <import>cpt-macros.xml</import> + </macros> + <expand macro="requirements"/> + <command detect_errors="aggressive"><![CDATA[ +python $__tool_directory__/remove_annotations.py +$gff3_data +$remark +$region +> $default]]></command> + <inputs> + <expand macro="gff3_input" /> + <param checked="true" label="Remove 'remark' features" name="remark" type="boolean" truevalue="--remark" falsevalue="" /> + <param checked="true" label="Remove 'region' features" name="region" type="boolean" truevalue="--region" falsevalue="" /> + </inputs> + <outputs> + <data format="gff3" name="default"/> + </outputs> + <tests> + <test> + <param name="gff3_data" value="RemoveAnnote_In.gff3" /> + <param name="remark" value="--remark" /> + <param name="region" value= "--region" /> + <output name="default" file="RemoveAnnote_Out.gff3" /> + </test> + </tests> + <help><![CDATA[ +**What it does** + +For an input GFF3, this tool specifically removes the feature entry with remark and/or region type (column 3) as needed for compatibility +with certain tools. These feature typically encompasses the entire length of the sequence upon which the GFF3 is based. + +Example input: + Miro annotation remark 1 167935 . . . gff-version=3;sequence-region=%28%27Miro%27%2C 0%2C 172788%29 + + Miro cpt gene 1231 5436 . . . ID=CDS1; + +Example output: + Miro cpt gene 1231 5436 . . . ID=CDS1; + + + ]]></help> + <expand macro="citations" /> +</tool> |
b |
diff -r 000000000000 -r 03d27abd1dfd cpt_rem_annotes/test-data/RemoveAnnote_In.gff3 --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cpt_rem_annotes/test-data/RemoveAnnote_In.gff3 Fri May 13 05:26:10 2022 +0000 |
b |
b'@@ -0,0 +1,292 @@\n+##gff-version 3\n+##sequence-region Pipo 1 41839\n+Pipo\tannotation\tremark\t1\t41839\t.\t.\t.\tgff-version=3;sequence-region=%28%27NODE_1_length_42045_cov_96%27%2C 0%2C 41956%29\n+Pipo\tGenBank\tgene\t258\t566\t.\t+\t1\tID=CPT_Pipo_001;Name=CPT_Pipo_001\n+Pipo\tGenBank\tmRNA\t273\t566\t.\t+\t1\tID=CPT_Pipo_001.t01;Parent=CPT_Pipo_001\n+Pipo\tGenBank\tCDS\t273\t566\t.\t+\t1\tID=CPT_Pipo_001.p01;Name=CPT_Pipo_001;Note=detected two transmembrane domains,8782901 HHPR;Parent=CPT_Pipo_001.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t273\t566\t.\t+\t1\tParent=CPT_Pipo_001.t01\n+Pipo\tGenBank\tRBS\t258\t261\t.\t+\t1\tName=CPT_Pipo_001;Parent=CPT_Pipo_001\n+Pipo\tGenBank\tgene\t841\t1031\t.\t+\t1\tID=CPT_Pipo_002;Name=CPT_Pipo_002\n+Pipo\tGenBank\tmRNA\t852\t1031\t.\t+\t1\tID=CPT_Pipo_002.t01;Parent=CPT_Pipo_002\n+Pipo\tGenBank\tCDS\t852\t1031\t.\t+\t1\tID=CPT_Pipo_002.p01;Name=CPT_Pipo_002;Note=4.9466e-34 %5BAcinetobacter phage vB_ApiP_P1%5D;Parent=CPT_Pipo_002.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t852\t1031\t.\t+\t1\tParent=CPT_Pipo_002.t01\n+Pipo\tGenBank\tRBS\t841\t844\t.\t+\t1\tName=CPT_Pipo_002;Parent=CPT_Pipo_002\n+Pipo\tGenBank\tgene\t1090\t1303\t.\t+\t1\tID=CPT_Pipo_003;Name=CPT_Pipo_003\n+Pipo\tGenBank\tmRNA\t1100\t1303\t.\t+\t1\tID=CPT_Pipo_003.t01;Parent=CPT_Pipo_003\n+Pipo\tGenBank\tCDS\t1100\t1303\t.\t+\t1\tID=CPT_Pipo_003.p01;Name=CPT_Pipo_003;Note=1.1538e-41%5BAcinetobacter phage vB_AbaP_B09_Aci08%5D;Parent=CPT_Pipo_003.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t1100\t1303\t.\t+\t1\tParent=CPT_Pipo_003.t01\n+Pipo\tGenBank\tRBS\t1090\t1092\t.\t+\t1\tName=CPT_Pipo_003;Parent=CPT_Pipo_003\n+Pipo\tGenBank\tgene\t1732\t1992\t.\t+\t1\tID=CPT_Pipo_004;Name=CPT_Pipo_004\n+Pipo\tGenBank\tmRNA\t1744\t1992\t.\t+\t1\tID=CPT_Pipo_004.t01;Parent=CPT_Pipo_004\n+Pipo\tGenBank\tCDS\t1744\t1992\t.\t+\t1\tID=CPT_Pipo_004.p01;Name=CPT_Pipo_004;Note=8.14463e-44 %5BAcinetobacter phage vB_AbaP_46-62_Aci07%5D;Parent=CPT_Pipo_004.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t1744\t1992\t.\t+\t1\tParent=CPT_Pipo_004.t01\n+Pipo\tGenBank\tRBS\t1732\t1736\t.\t+\t1\tName=CPT_Pipo_004;Parent=CPT_Pipo_004\n+Pipo\tGenBank\tgene\t2008\t2572\t.\t+\t1\tID=CPT_Pipo_005;Name=CPT_Pipo_005\n+Pipo\tGenBank\tmRNA\t2021\t2572\t.\t+\t1\tID=CPT_Pipo_005.t01;Parent=CPT_Pipo_005\n+Pipo\tGenBank\tCDS\t2021\t2572\t.\t+\t1\tID=CPT_Pipo_005.p01;Name=CPT_Pipo_005;Note=3.57359e-23 phiKMV NP_877442.1;Parent=CPT_Pipo_005.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t2021\t2572\t.\t+\t1\tParent=CPT_Pipo_005.t01\n+Pipo\tGenBank\tRBS\t2008\t2010\t.\t+\t1\tName=CPT_Pipo_005;Parent=CPT_Pipo_005\n+Pipo\tGenBank\tgene\t2564\t2948\t.\t+\t1\tID=CPT_Pipo_006;Name=CPT_Pipo_006\n+Pipo\tGenBank\tmRNA\t2574\t2948\t.\t+\t1\tID=CPT_Pipo_006.t01;Parent=CPT_Pipo_006\n+Pipo\tGenBank\tCDS\t2574\t2948\t.\t+\t1\tID=CPT_Pipo_006.p01;Name=CPT_Pipo_006;Note=1.39987e-77 %5BAcinetobacter phage IME200%5D,detected coil fragment;Parent=CPT_Pipo_006.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t2574\t2948\t.\t+\t1\tParent=CPT_Pipo_006.t01\n+Pipo\tGenBank\tRBS\t2564\t2567\t.\t+\t1\tName=CPT_Pipo_006;Parent=CPT_Pipo_006\n+Pipo\tGenBank\tgene\t2930\t3052\t.\t+\t1\tID=CPT_Pipo_007;Name=CPT_Pipo_007\n+Pipo\tGenBank\tmRNA\t2939\t3052\t.\t+\t1\tID=CPT_Pipo_007.t01;Parent=CPT_Pipo_007\n+Pipo\tGenBank\tCDS\t2939\t3052\t.\t+\t1\tID=CPT_Pipo_007.p01;Name=CPT_Pipo_007;Parent=CPT_Pipo_007.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t2939\t3052\t.\t+\t1\tParent=CPT_Pipo_007.t01\n+Pipo\tGenBank\tRBS\t2930\t2933\t.\t+\t1\tName=CPT_Pipo_007;Parent=CPT_Pipo_007\n+Pipo\tGenBank\tgene\t3027\t3263\t.\t+\t1\tID=CPT_Pipo_008;Name=CPT_Pipo_008\n+Pipo\tGenBank\tmRNA\t3039\t3263\t.\t+\t1\tID=CPT_Pipo_008.t01;Parent=CPT_Pipo_008\n+Pipo\tGenBank\tCDS\t3039\t3263\t.\t+\t1\tID=CPT_Pipo_008.p01;Name=CPT_Pipo_008;Note=2.88488e-44 %5BAcinetobacter phage Fri1%5D;Parent=CPT_Pipo_008.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t3039\t3263\t.\t+\t1\tParent=CPT_Pipo_008.t01\n+Pipo\tGenBank\tRBS\t3027\t3030\t.\t+\t1\tName=CPT_Pipo_008;Parent=CPT_Pipo_008\n+Pipo\tGenBank\tgene\t3336\t3944\t.\t+\t1\tID=CPT_Pipo_009;Name=CPT_Pipo_009\n+Pipo\tGenBank\tmRNA\t3348\t3944\t.\t+\t1\tID=CPT_Pipo_009.t01;Parent=CPT_Pipo_009\n+Pipo\tGenBank\tCDS\t3348\t3944\t.\t+\t1\tID=CPT_Pipo_009.p01;Name=CPT_Pipo_009;Note=2.06752e-145 %5BAcine'..b'o_050.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t30356\t33241\t.\t+\t1\tParent=CPT_Pipo_050.t01\n+Pipo\tGenBank\tRBS\t30347\t30351\t.\t+\t1\tName=CPT_Pipo_050;Parent=CPT_Pipo_050\n+Pipo\tGenBank\tgene\t33240\t36349\t.\t+\t1\tID=CPT_Pipo_051;Name=CPT_Pipo_051\n+Pipo\tGenBank\tmRNA\t33251\t36349\t.\t+\t1\tID=CPT_Pipo_051.t01;Parent=CPT_Pipo_051\n+Pipo\tGenBank\tCDS\t33251\t36349\t.\t+\t1\tID=CPT_Pipo_051.p01;Name=CPT_Pipo_051;Note=putative membrane protein,blast to phiKMV with score %3D7.0935e-9;Parent=CPT_Pipo_051.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t33251\t36349\t.\t+\t1\tParent=CPT_Pipo_051.t01\n+Pipo\tGenBank\tRBS\t33240\t33245\t.\t+\t1\tName=CPT_Pipo_051;Parent=CPT_Pipo_051\n+Pipo\tGenBank\tgene\t36341\t38392\t.\t+\t1\tID=CPT_Pipo_052;Name=CPT_Pipo_052\n+Pipo\tGenBank\tmRNA\t36356\t38392\t.\t+\t1\tID=CPT_Pipo_052.t01;Parent=CPT_Pipo_052\n+Pipo\tGenBank\tCDS\t36356\t38392\t.\t+\t1\tID=CPT_Pipo_052.p01;Name=CPT_Pipo_052;Note=potential tail fiber/tail spike,5924656 HHPR hit 5JS4_C%3B 6EU4_C%3B 5W5P %28To be published by Leiman%29,PMID: 28209973;Parent=CPT_Pipo_052.t01;product=tailspike protein\n+Pipo\tGenBank\texon\t36356\t38392\t.\t+\t1\tParent=CPT_Pipo_052.t01\n+Pipo\tGenBank\tRBS\t36341\t36344\t.\t+\t1\tName=CPT_Pipo_052;Parent=CPT_Pipo_052\n+Pipo\tGenBank\tgene\t38392\t38737\t.\t+\t1\tID=CPT_Pipo_053;Name=CPT_Pipo_053\n+Pipo\tGenBank\tmRNA\t38402\t38737\t.\t+\t1\tID=CPT_Pipo_053.t01;Parent=CPT_Pipo_053\n+Pipo\tGenBank\tCDS\t38402\t38737\t.\t+\t1\tID=CPT_Pipo_053.p01;Name=CPT_Pipo_053;Note=7.76278e-74,IPR006481,detected three transmembrane domains;Parent=CPT_Pipo_053.t01;product=holin\n+Pipo\tGenBank\texon\t38402\t38737\t.\t+\t1\tParent=CPT_Pipo_053.t01\n+Pipo\tGenBank\tRBS\t38392\t38396\t.\t+\t1\tName=CPT_Pipo_053;Parent=CPT_Pipo_053\n+Pipo\tGenBank\tgene\t38715\t39281\t.\t+\t1\tID=CPT_Pipo_054;Name=CPT_Pipo_054\n+Pipo\tGenBank\tmRNA\t38724\t39281\t.\t+\t1\tID=CPT_Pipo_054.t01;Parent=CPT_Pipo_054\n+Pipo\tGenBank\tCDS\t38724\t39281\t.\t+\t1\tID=CPT_Pipo_054.p01;Name=CPT_Pipo_054;Note=IPR023346 1.63e-19,Random endo-hydrolysis of N-acetyl-beta-D-glucosaminide %281-%3E4%29-beta-linkages in chitin and chitodextrins.;Parent=CPT_Pipo_054.t01;product=endolysin\n+Pipo\tGenBank\texon\t38724\t39281\t.\t+\t1\tParent=CPT_Pipo_054.t01\n+Pipo\tGenBank\tRBS\t38715\t38718\t.\t+\t1\tName=CPT_Pipo_054;Parent=CPT_Pipo_054\n+Pipo\tGenBank\tgene\t39280\t39598\t.\t+\t1\tID=CPT_Pipo_055;Name=CPT_Pipo_055\n+Pipo\tGenBank\tmRNA\t39290\t39598\t.\t+\t1\tID=CPT_Pipo_055.t01;Parent=CPT_Pipo_055\n+Pipo\tGenBank\tCDS\t39290\t39598\t.\t+\t1\tID=CPT_Pipo_055.p01;Name=CPT_Pipo_055;Note=1.10536e-8 %5BphiKMV%5D;Parent=CPT_Pipo_055.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t39290\t39598\t.\t+\t1\tParent=CPT_Pipo_055.t01\n+Pipo\tGenBank\tRBS\t39280\t39284\t.\t+\t1\tName=CPT_Pipo_055;Parent=CPT_Pipo_055\n+Pipo\tGenBank\tgene\t39598\t41545\t.\t+\t1\tID=CPT_Pipo_056;Name=CPT_Pipo_056\n+Pipo\tGenBank\tmRNA\t39608\t41545\t.\t+\t1\tID=CPT_Pipo_056.t01;Parent=CPT_Pipo_056\n+Pipo\tGenBank\tCDS\t39608\t41545\t.\t+\t1\tID=CPT_Pipo_056.p01;Name=CPT_Pipo_056;Note=4.73143e-112,probably DNA maturase B phiKMV;Parent=CPT_Pipo_056.t01;product=large terminase subunit\n+Pipo\tGenBank\texon\t39608\t41545\t.\t+\t1\tParent=CPT_Pipo_056.t01\n+Pipo\tGenBank\tRBS\t39598\t39602\t.\t+\t1\tName=CPT_Pipo_056;Parent=CPT_Pipo_056\n+Pipo\tGenBank\tgene\t41528\t41676\t.\t+\t1\tID=CPT_Pipo_057;Name=CPT_Pipo_057\n+Pipo\tGenBank\tmRNA\t41542\t41676\t.\t+\t1\tID=CPT_Pipo_057.t01;Parent=CPT_Pipo_057\n+Pipo\tGenBank\tCDS\t41542\t41676\t.\t+\t1\tID=CPT_Pipo_057.p01;Name=CPT_Pipo_057;Note=1.21677e-21 Acinetobacter phage vB_AbaP_B3;Parent=CPT_Pipo_057.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t41542\t41676\t.\t+\t1\tParent=CPT_Pipo_057.t01\n+Pipo\tGenBank\tRBS\t41528\t41533\t.\t+\t1\tName=CPT_Pipo_057;Parent=CPT_Pipo_057\n+Pipo\tGenBank\tgene\t41624\t41839\t.\t+\t1\tID=CPT_Pipo_058;Name=CPT_Pipo_058\n+Pipo\tGenBank\tmRNA\t41636\t41839\t.\t+\t1\tID=CPT_Pipo_058.t01;Parent=CPT_Pipo_058\n+Pipo\tGenBank\tCDS\t41636\t41839\t.\t+\t1\tID=CPT_Pipo_058.p01;Name=CPT_Pipo_058;Note=1.12427e-36,Acinetobacter phage vB_AbaP_B5;Parent=CPT_Pipo_058.t01;product=hypothetical protein\n+Pipo\tGenBank\texon\t41636\t41839\t.\t+\t1\tParent=CPT_Pipo_058.t01\n+Pipo\tGenBank\tRBS\t41624\t41628\t.\t+\t1\tName=CPT_Pipo_058;Parent=CPT_Pipo_058\n' |
b |
diff -r 000000000000 -r 03d27abd1dfd cpt_rem_annotes/test-data/RemoveAnnote_Out.gff3 --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/cpt_rem_annotes/test-data/RemoveAnnote_Out.gff3 Fri May 13 05:26:10 2022 +0000 |
[ |
b'@@ -0,0 +1,290 @@\n+##gff-version 3\n+Pipo\tGenBank\tgene\t258\t566\t.\t+\t1\tID=CPT_Pipo_001;Name=CPT_Pipo_001;\n+Pipo\tGenBank\tmRNA\t273\t566\t.\t+\t1\tID=CPT_Pipo_001.t01;Parent=CPT_Pipo_001;\n+Pipo\tGenBank\tCDS\t273\t566\t.\t+\t1\tID=CPT_Pipo_001.p01;Name=CPT_Pipo_001;Note=detected two transmembrane domains,8782901 HHPR;Parent=CPT_Pipo_001.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t273\t566\t.\t+\t1\tParent=CPT_Pipo_001.t01;\n+Pipo\tGenBank\tRBS\t258\t261\t.\t+\t1\tName=CPT_Pipo_001;Parent=CPT_Pipo_001;\n+Pipo\tGenBank\tgene\t841\t1031\t.\t+\t1\tID=CPT_Pipo_002;Name=CPT_Pipo_002;\n+Pipo\tGenBank\tmRNA\t852\t1031\t.\t+\t1\tID=CPT_Pipo_002.t01;Parent=CPT_Pipo_002;\n+Pipo\tGenBank\tCDS\t852\t1031\t.\t+\t1\tID=CPT_Pipo_002.p01;Name=CPT_Pipo_002;Note=4.9466e-34 [Acinetobacter phage vB_ApiP_P1];Parent=CPT_Pipo_002.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t852\t1031\t.\t+\t1\tParent=CPT_Pipo_002.t01;\n+Pipo\tGenBank\tRBS\t841\t844\t.\t+\t1\tName=CPT_Pipo_002;Parent=CPT_Pipo_002;\n+Pipo\tGenBank\tgene\t1090\t1303\t.\t+\t1\tID=CPT_Pipo_003;Name=CPT_Pipo_003;\n+Pipo\tGenBank\tmRNA\t1100\t1303\t.\t+\t1\tID=CPT_Pipo_003.t01;Parent=CPT_Pipo_003;\n+Pipo\tGenBank\tCDS\t1100\t1303\t.\t+\t1\tID=CPT_Pipo_003.p01;Name=CPT_Pipo_003;Note=1.1538e-41[Acinetobacter phage vB_AbaP_B09_Aci08];Parent=CPT_Pipo_003.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t1100\t1303\t.\t+\t1\tParent=CPT_Pipo_003.t01;\n+Pipo\tGenBank\tRBS\t1090\t1092\t.\t+\t1\tName=CPT_Pipo_003;Parent=CPT_Pipo_003;\n+Pipo\tGenBank\tgene\t1732\t1992\t.\t+\t1\tID=CPT_Pipo_004;Name=CPT_Pipo_004;\n+Pipo\tGenBank\tmRNA\t1744\t1992\t.\t+\t1\tID=CPT_Pipo_004.t01;Parent=CPT_Pipo_004;\n+Pipo\tGenBank\tCDS\t1744\t1992\t.\t+\t1\tID=CPT_Pipo_004.p01;Name=CPT_Pipo_004;Note=8.14463e-44 [Acinetobacter phage vB_AbaP_46-62_Aci07];Parent=CPT_Pipo_004.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t1744\t1992\t.\t+\t1\tParent=CPT_Pipo_004.t01;\n+Pipo\tGenBank\tRBS\t1732\t1736\t.\t+\t1\tName=CPT_Pipo_004;Parent=CPT_Pipo_004;\n+Pipo\tGenBank\tgene\t2008\t2572\t.\t+\t1\tID=CPT_Pipo_005;Name=CPT_Pipo_005;\n+Pipo\tGenBank\tmRNA\t2021\t2572\t.\t+\t1\tID=CPT_Pipo_005.t01;Parent=CPT_Pipo_005;\n+Pipo\tGenBank\tCDS\t2021\t2572\t.\t+\t1\tID=CPT_Pipo_005.p01;Name=CPT_Pipo_005;Note=3.57359e-23 phiKMV NP_877442.1;Parent=CPT_Pipo_005.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t2021\t2572\t.\t+\t1\tParent=CPT_Pipo_005.t01;\n+Pipo\tGenBank\tRBS\t2008\t2010\t.\t+\t1\tName=CPT_Pipo_005;Parent=CPT_Pipo_005;\n+Pipo\tGenBank\tgene\t2564\t2948\t.\t+\t1\tID=CPT_Pipo_006;Name=CPT_Pipo_006;\n+Pipo\tGenBank\tmRNA\t2574\t2948\t.\t+\t1\tID=CPT_Pipo_006.t01;Parent=CPT_Pipo_006;\n+Pipo\tGenBank\tCDS\t2574\t2948\t.\t+\t1\tID=CPT_Pipo_006.p01;Name=CPT_Pipo_006;Note=1.39987e-77 [Acinetobacter phage IME200],detected coil fragment;Parent=CPT_Pipo_006.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t2574\t2948\t.\t+\t1\tParent=CPT_Pipo_006.t01;\n+Pipo\tGenBank\tRBS\t2564\t2567\t.\t+\t1\tName=CPT_Pipo_006;Parent=CPT_Pipo_006;\n+Pipo\tGenBank\tgene\t2930\t3052\t.\t+\t1\tID=CPT_Pipo_007;Name=CPT_Pipo_007;\n+Pipo\tGenBank\tmRNA\t2939\t3052\t.\t+\t1\tID=CPT_Pipo_007.t01;Parent=CPT_Pipo_007;\n+Pipo\tGenBank\tCDS\t2939\t3052\t.\t+\t1\tID=CPT_Pipo_007.p01;Name=CPT_Pipo_007;Parent=CPT_Pipo_007.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t2939\t3052\t.\t+\t1\tParent=CPT_Pipo_007.t01;\n+Pipo\tGenBank\tRBS\t2930\t2933\t.\t+\t1\tName=CPT_Pipo_007;Parent=CPT_Pipo_007;\n+Pipo\tGenBank\tgene\t3027\t3263\t.\t+\t1\tID=CPT_Pipo_008;Name=CPT_Pipo_008;\n+Pipo\tGenBank\tmRNA\t3039\t3263\t.\t+\t1\tID=CPT_Pipo_008.t01;Parent=CPT_Pipo_008;\n+Pipo\tGenBank\tCDS\t3039\t3263\t.\t+\t1\tID=CPT_Pipo_008.p01;Name=CPT_Pipo_008;Note=2.88488e-44 [Acinetobacter phage Fri1];Parent=CPT_Pipo_008.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t3039\t3263\t.\t+\t1\tParent=CPT_Pipo_008.t01;\n+Pipo\tGenBank\tRBS\t3027\t3030\t.\t+\t1\tName=CPT_Pipo_008;Parent=CPT_Pipo_008;\n+Pipo\tGenBank\tgene\t3336\t3944\t.\t+\t1\tID=CPT_Pipo_009;Name=CPT_Pipo_009;\n+Pipo\tGenBank\tmRNA\t3348\t3944\t.\t+\t1\tID=CPT_Pipo_009.t01;Parent=CPT_Pipo_009;\n+Pipo\tGenBank\tCDS\t3348\t3944\t.\t+\t1\tID=CPT_Pipo_009.p01;Name=CPT_Pipo_009;Note=2.06752e-145 [Acinetobacter phage vB_AbaP_B1];Parent=CPT_Pipo_009.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t3348\t3944\t.\t+\t1\tParent=CPT_Pipo_0'..b'l protein;\n+Pipo\tGenBank\texon\t30356\t33241\t.\t+\t1\tParent=CPT_Pipo_050.t01;\n+Pipo\tGenBank\tRBS\t30347\t30351\t.\t+\t1\tName=CPT_Pipo_050;Parent=CPT_Pipo_050;\n+Pipo\tGenBank\tgene\t33240\t36349\t.\t+\t1\tID=CPT_Pipo_051;Name=CPT_Pipo_051;\n+Pipo\tGenBank\tmRNA\t33251\t36349\t.\t+\t1\tID=CPT_Pipo_051.t01;Parent=CPT_Pipo_051;\n+Pipo\tGenBank\tCDS\t33251\t36349\t.\t+\t1\tID=CPT_Pipo_051.p01;Name=CPT_Pipo_051;Note=putative membrane protein,blast to phiKMV with score %3D7.0935e-9;Parent=CPT_Pipo_051.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t33251\t36349\t.\t+\t1\tParent=CPT_Pipo_051.t01;\n+Pipo\tGenBank\tRBS\t33240\t33245\t.\t+\t1\tName=CPT_Pipo_051;Parent=CPT_Pipo_051;\n+Pipo\tGenBank\tgene\t36341\t38392\t.\t+\t1\tID=CPT_Pipo_052;Name=CPT_Pipo_052;\n+Pipo\tGenBank\tmRNA\t36356\t38392\t.\t+\t1\tID=CPT_Pipo_052.t01;Parent=CPT_Pipo_052;\n+Pipo\tGenBank\tCDS\t36356\t38392\t.\t+\t1\tID=CPT_Pipo_052.p01;Name=CPT_Pipo_052;Note=potential tail fiber/tail spike,5924656 HHPR hit 5JS4_C%3B 6EU4_C%3B 5W5P (To be published by Leiman),PMID: 28209973;Parent=CPT_Pipo_052.t01;product=tailspike protein;\n+Pipo\tGenBank\texon\t36356\t38392\t.\t+\t1\tParent=CPT_Pipo_052.t01;\n+Pipo\tGenBank\tRBS\t36341\t36344\t.\t+\t1\tName=CPT_Pipo_052;Parent=CPT_Pipo_052;\n+Pipo\tGenBank\tgene\t38392\t38737\t.\t+\t1\tID=CPT_Pipo_053;Name=CPT_Pipo_053;\n+Pipo\tGenBank\tmRNA\t38402\t38737\t.\t+\t1\tID=CPT_Pipo_053.t01;Parent=CPT_Pipo_053;\n+Pipo\tGenBank\tCDS\t38402\t38737\t.\t+\t1\tID=CPT_Pipo_053.p01;Name=CPT_Pipo_053;Note=7.76278e-74,IPR006481,detected three transmembrane domains;Parent=CPT_Pipo_053.t01;product=holin;\n+Pipo\tGenBank\texon\t38402\t38737\t.\t+\t1\tParent=CPT_Pipo_053.t01;\n+Pipo\tGenBank\tRBS\t38392\t38396\t.\t+\t1\tName=CPT_Pipo_053;Parent=CPT_Pipo_053;\n+Pipo\tGenBank\tgene\t38715\t39281\t.\t+\t1\tID=CPT_Pipo_054;Name=CPT_Pipo_054;\n+Pipo\tGenBank\tmRNA\t38724\t39281\t.\t+\t1\tID=CPT_Pipo_054.t01;Parent=CPT_Pipo_054;\n+Pipo\tGenBank\tCDS\t38724\t39281\t.\t+\t1\tID=CPT_Pipo_054.p01;Name=CPT_Pipo_054;Note=IPR023346 1.63e-19,Random endo-hydrolysis of N-acetyl-beta-D-glucosaminide (1->4)-beta-linkages in chitin and chitodextrins.;Parent=CPT_Pipo_054.t01;product=endolysin;\n+Pipo\tGenBank\texon\t38724\t39281\t.\t+\t1\tParent=CPT_Pipo_054.t01;\n+Pipo\tGenBank\tRBS\t38715\t38718\t.\t+\t1\tName=CPT_Pipo_054;Parent=CPT_Pipo_054;\n+Pipo\tGenBank\tgene\t39280\t39598\t.\t+\t1\tID=CPT_Pipo_055;Name=CPT_Pipo_055;\n+Pipo\tGenBank\tmRNA\t39290\t39598\t.\t+\t1\tID=CPT_Pipo_055.t01;Parent=CPT_Pipo_055;\n+Pipo\tGenBank\tCDS\t39290\t39598\t.\t+\t1\tID=CPT_Pipo_055.p01;Name=CPT_Pipo_055;Note=1.10536e-8 [phiKMV];Parent=CPT_Pipo_055.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t39290\t39598\t.\t+\t1\tParent=CPT_Pipo_055.t01;\n+Pipo\tGenBank\tRBS\t39280\t39284\t.\t+\t1\tName=CPT_Pipo_055;Parent=CPT_Pipo_055;\n+Pipo\tGenBank\tgene\t39598\t41545\t.\t+\t1\tID=CPT_Pipo_056;Name=CPT_Pipo_056;\n+Pipo\tGenBank\tmRNA\t39608\t41545\t.\t+\t1\tID=CPT_Pipo_056.t01;Parent=CPT_Pipo_056;\n+Pipo\tGenBank\tCDS\t39608\t41545\t.\t+\t1\tID=CPT_Pipo_056.p01;Name=CPT_Pipo_056;Note=4.73143e-112,probably DNA maturase B phiKMV;Parent=CPT_Pipo_056.t01;product=large terminase subunit;\n+Pipo\tGenBank\texon\t39608\t41545\t.\t+\t1\tParent=CPT_Pipo_056.t01;\n+Pipo\tGenBank\tRBS\t39598\t39602\t.\t+\t1\tName=CPT_Pipo_056;Parent=CPT_Pipo_056;\n+Pipo\tGenBank\tgene\t41528\t41676\t.\t+\t1\tID=CPT_Pipo_057;Name=CPT_Pipo_057;\n+Pipo\tGenBank\tmRNA\t41542\t41676\t.\t+\t1\tID=CPT_Pipo_057.t01;Parent=CPT_Pipo_057;\n+Pipo\tGenBank\tCDS\t41542\t41676\t.\t+\t1\tID=CPT_Pipo_057.p01;Name=CPT_Pipo_057;Note=1.21677e-21 Acinetobacter phage vB_AbaP_B3;Parent=CPT_Pipo_057.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t41542\t41676\t.\t+\t1\tParent=CPT_Pipo_057.t01;\n+Pipo\tGenBank\tRBS\t41528\t41533\t.\t+\t1\tName=CPT_Pipo_057;Parent=CPT_Pipo_057;\n+Pipo\tGenBank\tgene\t41624\t41839\t.\t+\t1\tID=CPT_Pipo_058;Name=CPT_Pipo_058;\n+Pipo\tGenBank\tmRNA\t41636\t41839\t.\t+\t1\tID=CPT_Pipo_058.t01;Parent=CPT_Pipo_058;\n+Pipo\tGenBank\tCDS\t41636\t41839\t.\t+\t1\tID=CPT_Pipo_058.p01;Name=CPT_Pipo_058;Note=1.12427e-36,Acinetobacter phage vB_AbaP_B5;Parent=CPT_Pipo_058.t01;product=hypothetical protein;\n+Pipo\tGenBank\texon\t41636\t41839\t.\t+\t1\tParent=CPT_Pipo_058.t01;\n+Pipo\tGenBank\tRBS\t41624\t41628\t.\t+\t1\tName=CPT_Pipo_058;Parent=CPT_Pipo_058;\n' |