Mercurial > repos > iuc > spaln
changeset 1:37b5e1f0b544 draft
"planemo upload for repository https://github.com/ogotoh/spaln commit 4cfc21ef8456ca8b8da0a8a8c045b8a472858608"
| author | iuc |
|---|---|
| date | Thu, 16 Jul 2020 07:57:10 -0400 |
| parents | 95ea8d97abb4 |
| children | dd0cd2319ae5 |
| files | list_spaln_tables.py list_spaln_tables.xml macros.xml spaln.xml test-data/gnm2tab test-data/ncbi_taxonomy_sqlite.loc test-data/output1.bed12 test-data/output1.tabular test-data/output1_gff_genes.gff3 test-data/output1_gff_matches.gff3 test-data/output2.tabular test-data/sqlite_taxdb/tax.ncbitaxonomy.sqlite tool-data/ncbi_taxonomy_sqlite.loc.sample tool_data_table_conf.xml.sample tool_data_table_conf.xml.test |
| diffstat | 15 files changed, 1070 insertions(+), 140 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/list_spaln_tables.py Thu Jul 16 07:57:10 2020 -0400 @@ -0,0 +1,61 @@ +#!/usr/bin/env python3 + +import argparse +import shlex +import sys +from subprocess import run +from typing import TextIO + + +def find_common_ancestor_distance( + taxon: str, other_taxon: str, taxonomy_db_path: str, only_canonical: bool +): + canonical = "--only_canonical" if only_canonical else "" + cmd_str = f"taxonomy_util -d {taxonomy_db_path} common_ancestor_distance {canonical} '{other_taxon}' '{taxon}'" + cmd = shlex.split(cmd_str) + proc = run(cmd, encoding="utf8", capture_output=True) + return proc + + +def find_distances(gnm2tab_file: TextIO, taxon: str, taxonomy_db_path: str): + cmd = ["taxonomy_util", "-d", taxonomy_db_path, "get_id", taxon] + proc = run(cmd, capture_output=True, encoding="utf8") + if "not found in" in proc.stderr: + exit("Error: " + proc.stderr.strip()) + for line in gnm2tab_file: + fields = line.split("\t") + (species_code, settings, other_taxon) = map(lambda el: el.strip(), fields[:3]) + proc = find_common_ancestor_distance(taxon, other_taxon, taxonomy_db_path, True) + ancestor_info = proc.stdout.rstrip() + if proc.stderr != "": + print("Warning:", other_taxon, proc.stderr.rstrip(), file=sys.stderr) + else: + proc = find_common_ancestor_distance( + taxon, other_taxon, taxonomy_db_path, False + ) + non_canonical_distance = proc.stdout.split("\t")[0] + print( + non_canonical_distance, + ancestor_info, + species_code, + settings, + other_taxon, + sep="\t", + ) + + +if __name__ == "__main__": + parser = argparse.ArgumentParser(description="Find distance to common ancestor") + parser.add_argument( + "--taxonomy_db", required=True, help="NCBI Taxonomy database (SQLite format)" + ) + parser.add_argument( + "--gnm2tab_file", + required=True, + type=argparse.FileType(), + help="gnm2tab file from spal", + ) + parser.add_argument("taxon") + args = parser.parse_args() + + find_distances(args.gnm2tab_file, args.taxon, args.taxonomy_db)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/list_spaln_tables.xml Thu Jul 16 07:57:10 2020 -0400 @@ -0,0 +1,132 @@ +<tool id="list_spaln_tables" name="List spaln parameter tables" version="@TOOL_VERSION@+galaxy0"> + <description>Given a query species, list the spaln settings tables that exist, from closest related species to most different</description> + <macros> + <import>macros.xml</import> + </macros> + <requirements> + <requirement type="package" version="3.8">python</requirement> + <requirement type="package" version="@TOOL_VERSION@">spaln</requirement> + <requirement type="package" version="1.0.7">rust-ncbitaxonomy</requirement> + </requirements> + <command detect_errors="aggressive"><![CDATA[ + #if $gnm2tab.gnm2tab_source == "spaln_tool" + SPALN_LOCATION=\$(dirname \$(dirname \$(which spaln))) && + GNM2TAB_PATH="\$SPALN_LOCATION/share/spaln/table/gnm2tab" && + if [[ -f "\$GNM2TAB_PATH" ]] ; then + ln -s "\$GNM2TAB_PATH" gnm2tab ; + else + echo "Cannot find builtin gnm2tab file \$SPALN_LOCATION : \$GNM2TAB_PATH" >&2 ; exit 1 ; + fi && + #else + ln -s '${gnm2tab.gnm2tab_file}' gnm2tab && + #end if + #if $taxonomy.taxonomy_source == "cached" + ln -s '${taxonomy.taxonomy_sqlite_table.fields.path}/tax.ncbitaxonomy.sqlite' tax.ncbitaxonomy.sqlite && + #else + ln -s '${taxonomy.taxonomy_sqlite_file}' tax.ncbitaxonomy.sqlite && + #end if + python '${__tool_directory__}/list_spaln_tables.py' --taxonomy_db tax.ncbitaxonomy.sqlite --gnm2tab_file gnm2tab '$taxon' | sort -k1n > '${output}' + ]]></command> + <inputs> + <param name="taxon" label="Scientific name" type="text" /> + <conditional name="gnm2tab"> + <param name="gnm2tab_source" type="select" label="Choose source of gnm2tab file"> + <option value="spaln_tool" selected="true">From the spaln tool installation</option> + <option value="history">From dataset in history</option> + </param> + <when value="spaln_tool" /> + <when value="history"> + <param name="gnm2tab_file" type="data" format="tabular" label="gnm2tab file from spaln" help="The gnm2tab file should be from the table directory of spaln v. @TOOL_VERSION@" /> + </when> + </conditional> + <conditional name="taxonomy"> + <param type="select" name="taxonomy_source"> + <option value="cached" selected="true">Use built-in NCBI Taxonomy SQLite database</option> + <option value="history">Use NCBI Taxonomy SQLite database from history</option> + </param> + <when value="cached"> + <param type="select" name="taxonomy_sqlite_table" label="NCBI Taxonomy SQLite database"> + <options from_data_table="ncbi_taxonomy_sqlite"> + <filter type="sort_by" column="1" /> + <validator type="no_options" message="No NCBI Taxonomy SQLite database is available" /> + </options> + </param> + </when> + <when value="history"> + <param name="taxonomy_sqlite_file" type="data" format="sqlite" label="NCBI Taxonomy SQLite database" /> + </when> + </conditional> + </inputs> + <outputs> + <data name="output" format="tabular"> + <actions> + <action name="column_names" type="metadata" default="dist_all,dist_canonical,common_ancestor,species_code,settings_group,scientific_name" /> + </actions> + </data> + </outputs> + + <tests> + <test> + <param name="taxon" value="Lates calcarifer" /> + <conditional name="gnm2tab"> + <param name="gnm2tab_source" value="spaln_tool" /> + </conditional> + <conditional name="taxonomy"> + <param name="taxonomy_source" value="history" /> + <param name="taxonomy_sqlite_file" ftype="sqlite" value="sqlite_taxdb/tax.ncbitaxonomy.sqlite" /> + </conditional> + <output name="output"> + <assert_contents> + <has_line_matching expression="5\t4\tActinopteri\tcynosemi\tFish_mdl\tCynoglossus semilaevis" /> + <has_line_matching expression="30\t7\tEukaryota\tzea_mays\tMagnolio\tZea mays" /> + </assert_contents> + </output> + </test> + <test> + <param name="taxon" value="Lates calcarifer" /> + <conditional name="gnm2tab"> + <param name="gnm2tab_source" value="spaln_tool" /> + </conditional> + <conditional name="taxonomy"> + <param name="taxonomy_source" value="cached" /> + <param name="taxonomy_sqlite_table" value="sample" /> + </conditional> + <output name="output"> + <assert_contents> + <has_line_matching expression="5\t4\tActinopteri\tcynosemi\tFish_mdl\tCynoglossus semilaevis" /> + <has_line_matching expression="30\t7\tEukaryota\tzea_mays\tMagnolio\tZea mays" /> + </assert_contents> + </output> + </test> + <test> + <param name="taxon" value="Lates calcarifer" /> + <conditional name="gnm2tab"> + <param name="gnm2tab_source" value="history" /> + <param name="gnm2tab_file" ftype="tabular" value="gnm2tab" /> + </conditional> + <conditional name="taxonomy"> + <param name="taxonomy_source" value="cached" /> + <param name="taxonomy_sqlite_table" value="sample" /> + </conditional> + <output name="output"> + <assert_contents> + <has_line_matching expression="5\t4\tActinopteri\tcynosemi\tFish_mdl\tCynoglossus semilaevis" /> + <has_line_matching expression="30\t7\tEukaryota\tzea_mays\tMagnolio\tZea mays" /> + </assert_contents> + </output> + </test> + </tests> + <help><![CDATA[ + Spaln has a number of pre-computed settings files to tune its predictions for different species. These + are listed in a file named gnm2tab_ in the package. This tool uses the NCBI Taxonomy database to search + that able for a suitable (i.e. taxonomically close) set of settings for optimising spaln's alignment + predictions. + + Input is the scientific name of a species (as reflected in the NCBI Taxonomy DB), output is + information from the gnm2tab file sorted by taxonomic distance from the query species. + + .. _gnm2tab: https://github.com/ogotoh/spaln/blob/master/table/gnm2tab + ]]></help> + <citations> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Thu Jul 16 07:57:10 2020 -0400 @@ -0,0 +1,3 @@ +<macros> + <token name="@TOOL_VERSION@">2.4.03</token> +</macros> \ No newline at end of file
--- a/spaln.xml Fri Jan 11 18:15:21 2019 -0500 +++ b/spaln.xml Thu Jul 16 07:57:10 2020 -0400 @@ -1,7 +1,7 @@ <tool id="spaln" name="Spaln: align cDNA or Protein to genome" version="@TOOL_VERSION@+galaxy0"> <description>Maps and aligns a set of cDNA or protein sequences onto a whole genomic sequence.</description> <macros> - <token name="@TOOL_VERSION@">2.3.2</token> + <import>macros.xml</import> </macros> <edam_topics> <edam_topic>topic_3512</edam_topic> @@ -10,7 +10,36 @@ <requirement type="package" version="@TOOL_VERSION@">spaln</requirement> </requirements> <command detect_errors="aggressive"><![CDATA[ - spaln -t\${GALAXY_SLOTS:-1} -O$format -o '$output1' '$genome' '$query' + spaln -t\${GALAXY_SLOTS:-1} -O$format + #if str($species_params).strip() != '' + -T'${species_params}' + #end if + #if $adv.use == "yes" + -S'${adv.query_orientation}' + -V'${adv.hirschberg_threshold}' + -pa'${adv.polya_trim}' + ${adv.all_results} + -yu'${adv.gap_extension_penalty}' + -yv'${adv.gap_open_penalty}' + -yw'${adv.dp_matrix_scan_width}' + -ya'${adv.splice_stringency}' + -yj'${adv.gap_penalty_incline}' + -yk'${adv.gap_penalty_flex}' + '${adv.double_affine_gap}' + -ym'${adv.match_score}' + -yn'${adv.mismatch_score}' + -yo'${adv.stop_codon_penalty}' + -yx'${adv.frameshift_penalty}' + -yy'${adv.splice_site_weight} + -yz'${adv.coding_potential_weight}' + -yB'${adv.branch_point_weight} + -yL'${adv.min_intron_len}' + -yZ'${adv.intron_potential_weight}' + #if str($adv.max_gene_length).strip() != '' + -XG'${adv.max_gene_length}' + #end if + #end if + '$genome' '$query' >'$output1' ]]></command> <inputs> <param type="data" name="genome" format="fasta" label="Genome sequence to search (FASTA format)" /> @@ -20,7 +49,49 @@ <option value="2">GFF3 format matches</option> <option value="3">BED format</option> <option value="4">Tabular format exon information</option> + </param> + <param argument="-T" name="species_params" type="text" optional="true" label="Species to use for parameter setting" help="Choose a species table (e.g. cynosemi) from which to read parameters to optimise spaln" /> + <conditional name="adv"> + <param type="select" name="use" label="Advanced settings"> + <option selected="true" value="no">No</option> + <option value="yes">Yes</option> </param> + <when value="no"> + </when> + <when value="yes"> + <param argument="-S" name="query_orientation" type="select" label="DNA query orientation" help="Determines how to treat orientation of query sequence when searching"> + <option value="0">Infer orientation from sequence header (no poly-A/poly-T trimming)</option> + <option value="1">Forward orientation only. Poly-A tail might be trimmed off</option> + <option value="2">Reverse orientation only. Leading poly-T might be trimmed off</option> + <option selected="true" value="3">Examine both orientations. Poly-A / Poly-T might be trimmed off</option> + </param> + <param argument="-V" name="hirschberg_threshold" type="integer" value="16777216" label="Minimum space to induce Hirschberg's algorithm" help="Default is 16M (16x1024x1024 bytes)" /> + <param argument="-pa" name="polya_trim" type="integer" value="12" label="Limit 3' poly-As to this number of bases" help="poly-A/poly-T trimming is only done if -S (orientation) option is 0 or 3" /> + <param argument="-pw" name="all_results" type="boolean" checked="false" truevalue="-pw" falsevalue="" label="Report results even if the score is below the threshold" /> + <param argument="-yu" name="gap_extension_penalty" type="integer" value="3" label="Gap-extension penalty" /> + <param argument="-yv" name="gap_open_penalty" type="integer" value="8" label="Gap-open penalty" /> + <param argument="-yw" name="dp_matrix_scan_width" type="integer" value="100" label="Band width for DP matrix scan" /> + <param argument="-ya" name="splice_stringency" type="select" label="Stringency of splice site selection" help="Which dinucleotide pairs to accept at the ends of an intron"> + <option value="0" selected="true">accept only the canonical pairs (GT..AG,GC..AG,AT..AC)</option> + <option value="1">accept also AT..AN</option> + <option value="2">allow up to one mismatch from GT..AG</option> + <option value="3">accept any pairs</option> + </param> + <param argument="-yj" name="gap_penalty_incline" type="float" value="0.6" label="Incline of long gap penalty" /> + <param argument="-yk" name="gap_penalty_flex" type="integer" value="7" label="Flex point where the incline of gap penalty changes" /> + <param argument="-yl3" name="double_affine_gap" type="boolean" checked="false" truevalue="-yl3" falsevalue="" label="Use double affine gap penalty" help="Use the double affine gap rathr than single affine gap penalty calculation" /> + <param argument="-ym" name="match_score" type="integer" value="2" label="Nucleotide match score" /> + <param argument="-yn" name="mismatch_score" type="integer" value="-6" label="Nucleotide mismatch score" /> + <param argument="-yo" name="stop_codon_penalty" type="integer" value="100" label="Penalty for a premature termination codon" /> + <param argument="-yx" name="frameshift_penalty" type="integer" value="100" label="Penalty for a frame shift error" /> + <param argument="-yy" name="splice_site_weight" type="integer" value="8" label="Weight for splice site signal" /> + <param argument="-yz" name="coding_potential_weight" type="integer" value="2" label="Weight for coding potential" /> + <param argument="-yB" name="branch_point_weight" type="integer" value="0" label="Weight for branch point signal" /> + <param argument="-yL" name="min_intron_len" type="integer" value="30" label="Minimum expected length of intron" /> + <param argument="-yZ" name="intron_potential_weight" type="integer" value="0" label="Weight for intron potential" /> + <param argument="-XG" name="max_gene_length" type="text" label="Reset maximum expected gene size, suffix k or M is effective" /> + </when> + </conditional> </inputs> <outputs> <data name="output1" format="tabular"> @@ -49,32 +120,61 @@ <param name="genome" ftype="fasta" value="genome.fasta" /> <param name="query" ftype="fasta" value="query.fasta" /> <param name="format" value="0"/> - <output name="output1" value="output1_gff_genes.gff3" /> + <conditional name="adv"> + <param name="use" value="no" /> + </conditional> + <output name="output1" ftype="gff3" value="output1_gff_genes.gff3" /> </test> <test> <param name="genome" ftype="fasta" value="genome.fasta" /> <param name="query" ftype="fasta" value="query.fasta" /> <param name="format" value="2"/> - <output name="output1" value="output1_gff_matches.gff3" /> + <conditional name="adv"> + <param name="use" value="no" /> + </conditional> + <output name="output1" ftype="gff3" value="output1_gff_matches.gff3" /> </test> <test> <param name="genome" ftype="fasta" value="genome.fasta" /> <param name="query" ftype="fasta" value="query.fasta" /> <param name="format" value="3"/> - <output name="output1" value="output1.bed12" /> + <conditional name="adv"> + <param name="use" value="no" /> + </conditional> + <output name="output1" ftype="bed12" value="output1.bed12" /> </test> <test> <param name="genome" ftype="fasta" value="genome.fasta" /> <param name="query" ftype="fasta" value="query.fasta" /> <param name="format" value="4"/> - <output name="output1" value="output1.tabular" /> + <conditional name="adv"> + <param name="use" value="no" /> + </conditional> + <output name="output1" ftype="tabular" value="output1.tabular" /> + </test> + <test> + <param name="genome" ftype="fasta" value="genome.fasta" /> + <param name="query" ftype="fasta" value="query.fasta" /> + <param name="format" value="4"/> + <param name="species_params" value="cynosemi" /> + <conditional name="adv"> + <param name="use" value="no" /> + </conditional> + <output name="output1" ftype="tabular" value="output2.tabular" /> </test> </tests> <help><![CDATA[ Spaln_ (space-efficient spliced alignment) is a stand-alone program that maps and aligns a set of cDNA or protein sequences onto a whole genomic sequence in a single job. - This Galaxy wrapper currently only supports the default (i.e. *-O3*) algorithm for Spaln with default parameters. + This Galaxy wrapper currently only supports the default (i.e. *-O3*) algorithm for Spaln. This algorithm + takes FASTA format query and genome sequence and finds an alignment of the query (either cDNA or protein) + against the genome. + + Spaln optionally takes a species name to use for parameter setting (the "-T" parameter). The + "List spaln parameter tables" (list_spaln_tables) can be used to find a parameter file that is + close (in terms of taxonomic distance) to your species of interest. Use of this setting is recommended. + .. _Spaln: http://www.genome.ist.i.kyoto-u.ac.jp/~aln_user/spaln/ ]]></help>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/gnm2tab Thu Jul 16 07:57:10 2020 -0400 @@ -0,0 +1,688 @@ +aaosarxi Dothide2 Aaosphaeria arxii F +acidrich Dothide1 Acidomyces richmondensis F +acrealca Sordari1 Acremonium alcalophilum F +acyrpisu InsectDm Acyrthosiphon pisum A_I +aedeaegy InsectDm Aedes aegypti A_I +agarbisp Agarico1 Agaricus bisporus F +agarhyph Agarico2 Agaricostilbum hyphaenes F +ailumela Tetrapod Ailuropoda melanoleuca A_M +albulaib albulaib Albugo laibachii O +allomacr Blastocl Allomyces macrogynus F +altebras Dothide2 Alternaria brassicicola F +amanmusc Agaricom Amanita muscaria F +amanthie Agarico2 Amanita thiersii F +ambotric ambotric Amborella trichopoda P +amnilign Dothide2 Amniculicola lignicola F +amorresi Leotiom1 Amorphotheca resinae F +amphquee amphquee Amphimedon queenslandica A_O +anasplat Tetrapod Anas platyrhynchos A_B +anolcaro Tetrapod Anolis carolinensis A_R +anopdarl InsectAg Anopheles darlingi A_I +anopgamb InsectAg Anopheles gambiae A_I +anthavoc Sordari1 Anthostoma avocetta F +antolocu FungiAll Antonospora locustae F +antrsinu Agarico2 Antrodia sinuosa F +apiomont Sordari1 Apiospora montagnei F +apisflor InsectAg Apis florea A_I +apismell InsectAg Apis mellifera A_I +aplakerg Labyrint Aplanochytrium kerguelense O +aploprun Dothide2 Aplosporella prunicola F +aplycali ChordatU Aplysia californica A_mo +aquicoer Eudicoty Aquilegia coerulea P +arablyra Eudicoty Arabidopsis lyrata P +arabthal Eudicoty Arabidopsis thaliana P +armimell Agaricom Armillaria mellea F +arthbenh Eurotio1 Arthroderma benhamiae F +artholig Sordari1 Arthrobotrys oligospora F +ascoimme Pezizomy Ascobolus immersus F +ascorube Saccharo Ascoidea rubescens F +ascosarc Leotiom1 Ascocoryne sarcoides F +ashbgoss Saccharo Ashbya gossypii F +aspeacid Eurotio2 Aspergillus acidus F +aspeacul Eurotio2 Aspergillus aculeatus F +aspebras Eurotio2 Aspergillus brasiliensis F +aspecarb Eurotio2 Aspergillus carbonarius F +aspeclav Eurotio2 Aspergillus clavatus F +aspeflav Eurotio2 Aspergillus flavus F +aspefumi Eurotio2 Aspergillus fumigatus F +aspeglau Eurotio2 Aspergillus glaucus F +aspekawa Eurotio2 Aspergillus kawachii F +aspenidu Eurotio2 Aspergillus nidulans F +aspenige Eurotio2 Aspergillus niger F +aspeoryz Eurotio2 Aspergillus oryzae F +aspesydo Eurotio2 Aspergillus sydowii F +aspeterr Eurotio2 Aspergillus terreus F +aspetubi Eurotio2 Aspergillus tubingensis F +aspevers Eurotio2 Aspergillus versicolor F +aspewent Eurotio2 Aspergillus wentii F +aspezona Eurotio2 Aspergillus zonatus F +astespec astespec Asterochloris spec_Cgr/DA1pho P +astymexi Fish_lng Astyanax mexicanus A_F +atraspec atraspec Atractiellales spec F +attaceph InsectAc Atta cephalotes A_I +aulohede Dothide2 Aulographum hederae F +auralima Labyrint Aurantiochytrium limacinum O +aureanop Pelagoph Aureococcus anophagefferens O +aurepull Dothide2 Aureobasidium pulm_lulans F +aurepulm Dothide2 Aureobasidium pulm_lulans F +aurepuln Dothide2 Aureobasidium puln_lulans F +aurepulp Dothide2 Aureobasidium pulp_lulans F +aurepuls Dothide2 Aureobasidium puls_lulans F +aurideli Agarico1 Auricularia delicata F +aurisubg Agarico1 Auricularia subglabra F +babjinos Saccharo Babjeviella inositovor F +backcirc Mucorale Backusella circina F +batrdend Puccinia Batrachochytrium dendrobatidis F +baudcomp Dothide2 Baudoinia compniacensis F +beaubass Sordario Beauveria bassiana F +bigenata Pelagoph Bigelowiella natans O +bjeradus Agarico1 Bjerkandera adusta F +blasderm Eurotio3 Blastomyces dermatitidis F +blumgram Leotiomy Blumeria graminis F +boecstri Eudicoty Boechera stricta P +boleedul Agarico2 Boletus edulis F +bombimpa InsectAg Bombus impatiens A_I +bombmori InsectBm Bombyx mori A_I +bombterr InsectAg Bombus terrestris A_I +bos_taur Tetrapod Bos taurus A_M +botrbotr Agarico4 Botryobasidium botryosum F +botrcinb Leotiom2 Botrytis cinb0510 F +botrcine Leotiom2 Botrytis cinerea F +botrcint Leotiom2 Botrytis cint4 F +botrdoth Dothide2 Botryosphaeria dothidea F +botrfuck Leotiom2 Botryotinia fuckeliana F +bracdist Magnolio Brachypodium distachyon P +branflor ChordatC Branchiostoma floridae A_C +brasrapa brasrapa Brassica rapa P +brugmala NematodO Brugia malayi A_N +cadospec Leotiom1 Cadophora spec F +caenbren NematodC Caenorhabditis brenneri A_N +caenbrig NematodC Caenorhabditis briggsae A_N +caeneleg NematodC Caenorhabditis elegans A_N +caenjapo NematodC Caenorhabditis japonica A_N +caenrema NematodC Caenorhabditis remanei A_N +cajacaja Eudicoty Cajanus cajan P +calljacc Tetrapod Callithrix jacchus A_M +calocorn Dacrymyc Calocera cornea F +calovisc Dacrymyc Calocera viscosa F +camesine Eudicoty Camellia sinensis P +candalbi Saccharo Candida albicans F +candarab Saccharo Candida arabinofermentans F +candcase Saccharo Candida caseinolytica F +canddubl Saccharo Candida dubliniensis F +candglab Saccharo Candida glabrata F +candguil Saccharo Candida guilliermondii F +candlusi Saccharo Candida lusitaniae F +candtanz Saccharo Candida tanzawaensis F +candtenu Saccharo Candida tenuis F +candtrop Saccharo Candida tropicalis F +canifami Tetrapod Canis familiaris A_M +cannsati Eudicoty Cannabis sativa P +capitele capitele Capitella teleta A_O +caprhirc Tetrapod Capra hircus A_M +capsannu Eudicoty Capsicum annuum P +capsgran Eudicoty Capsella grandiflora P +capsowcz Ichthyos Capsaspora owczarzaki O +capsrube Eudicoty Capsella rubella P +caripapa Eudicoty Carica papaya P +cateangu Blastocl Catenaria anguillulae F +caviporc Tetrapod Cavia porcellus A_M +cenogeop Dothide2 Cenococcum geophilum F +ceracapi InsectDm Ceratitis capitata A_I +cerasimu Tetrapod Ceratotherium simum A_M +cerczeae Dothide2 Cercospora zeaemaydis F +cerisubv Agarico2 Ceriporiopsis subvermispora F +cerrunic Agarico2 Cerrena unicolor F +chaeglob Sordari1 Chaetomium globosum F +challong Leotiom1 Chalara longipes F +chinlani Tetrapod Chinchilla lanigera A_M +chlarein Chlospec Chlamydomonas reinhardtii P +chlovari Chlospec Chlorella variabilis_NC64A P +chlovulg Chlospec Chlorella vulgaris P +choiveno Pezizomy Choiromyces venosus F +cholfoff Tetrapod Choloepus hoffmanni A_M +chrypict Tetrapod Chrysemys picta bellii A_R +cicearie Eudicoty Cicer arietinum P +cioninte ChordatC Ciona intestinalis A_C +cionsavi ChordatC Ciona savignyi A_C +citrclem Eudicoty Citrus clementina P +citrlana Eudicoty Citrullus lanatus P +citrsine Eudicoty Citrus sinensis P +cladfulv Dothide2 Cladosporium fulvum F +cladgray cladgray Cladonia grayi F +clavpyxi Agarico2 Clavicorona pyxidata F +coccimmi Eurotio3 Coccidioides immitis F +coccporm Eurotio1 Coccidioides pormscc F +coccposa Eurotio1 Coccidioides posadasii F +coccposi Eurotio1 Coccidioides posilveira F +coccsube Chlospec Coccomyxa subellipsoidea P +cochcarb Dothide2 Cochliobolus carbonum F +cochhet4 Dothide2 Cochliobolus het4 F +cochhete Dothide2 Cochliobolus heterostrophus F +cochluna Dothide2 Cochliobolus lunatus F +cochmiya Dothide2 Cochliobolus miyabeanus F +cochsati Dothide2 Cochliobolus sativus F +cochvict Dothide2 Cochliobolus victoriae F +coemreve Mortiere Coemansia reversa F +collgram Sordario Colletotrichum graminicola F +collhigg Sordario Colletotrichum higginsianum F +colulivi Tetrapod Columba livia A_B +condcris Tetrapod Condylura cristata A_M +conicoro conicoro Conidiobolus coronatus F +conipute Agarico2 Coniophora puteana F +coprcine Agarico2 Coprinopsis cinerea F +cordmili Sordario Cordyceps militaris F +cortglau Agarico2 Cortinarius glaucopus F +corycass Dothideo Corynespora cassicola F +crasgiga Mollusca Crassostrea gigas A_mo +cricgris Tetrapod Cricetulus griseus A_M +cronquer Puccinia Cronartium quercuum F +crypgatt Tremell1 Cryptococcus gattii F +crypneof Tremell1 Cryptococcus neoformans F +cryppara Sordari3 Cryphonectria parasitica F +crypparv Conoidas Cryptosporidium parvum O +crypvish Tremell1 Cryptococcus vishniacii F +cucuberb Dothide2 Cucurbitaria berberidis F +cucusati Eudicoty Cucumis sativus P +culequin InsectDm Culex quinquefasciatus A_I +cybejadi Saccharo Cyberlindnera jadinii F +cylitorr cylitorr Cylindrobasidium torrendii F +cynosemi Fish_mdl Cynoglossus semilaevis A_F +dacrspec Dacrymyc Dacryopinax species F +daedquer Agarico2 Daedalea quercina F +daldesch Sordari1 Daldinia eschscholzii F +danaplex InsectAc Danaus plexippus A_I +danireri Fish_lng Danio rerio A_F +daphpule InsectDm Daphnia pulex A_I +dasynove Tetrapod Dasypus novemcinctus A_M +debahans Saccharo Debaryomyces hansenii F +dekkbrux Saccharo Dekkera bruxellensis F +deliconf Agaricom Delitschia confertaspora F +dendbisp Agarico2 Dendrothele bispora F +dendpond InsectAc Dendroctonus ponderosae A_I +dichsqua Agarico2 Dichomitus squalens F +dictdisc dictdisc Dictyostelium discoideum O +dictpurp dictpurp Dictyostelium purpureum O +didyexig Dothide4 Didymella exigua F +dioscryo Tremell2 Dioszegia cryoxerica F +dipoordi Tetrapod Dipodomys ordii A_M +dissacic Dothide1 Dissoconium aciculare F +dothsept Dothide2 Dothistroma septosporum F +dothsymp Dothide2 Dothidotthia symphoricarpi F +drosanan InsectDm Drosophila ananassae A_I +droserec InsectDm Drosophila erecta A_I +drosgrim InsectDm Drosophila grimshawi A_I +drosmela InsectDm Drosophila melanogaster A_I +drosmoja InsectDm Drosophila mojavensis A_I +drospers InsectDm Drosophila persimilis A_I +drospseu InsectDm Drosophila pseudoobscura A_I +drossech InsectDm Drosophila sechellia A_I +drossimu InsectDm Drosophila simulans A_I +drosviri InsectDm Drosophila virilis A_I +droswill InsectDm Drosophila willistoni A_I +drosyaku InsectDm Drosophila yakuba A_I +echitelf Tetrapod Echinops telfairi A_M +emilhuxl emilhuxl Emiliania huxleyi O +encecuni FungiAll Encephalitozoon cuniculi F +encehell FungiAll Encephalitozoon hellem F +enceinte FungiAll Encephalitozoon intestinalis F +enceroma FungiAll Encephalitozoon romaleae F +entahist Archamoe Entamoeba histolytica O +entebien FungiAll Enterocytozoon bieneusi F +equucaba Tetrapod Equus caballus A_M +eremcymb Saccharo Eremothecium cymbalariae F +eremgoss Saccharo Eremothecium gossypii F +erineuro Tetrapod Erinaceus europaeus A_M +eucacama Eudicoty Eucalyptus camaldulensis P +eucagran Eudicoty Eucalyptus grandis P +euroherb Eurotio1 Eurotium herbariorum F +eutrsals Eudicoty Eutrema salsugineum P +eutylata Sordari1 Eutypa lata F +exidglan Agarico1 Exidia glandulosa F +exobvacc exobvacc Exobasidium vaccinii F +falccher Tetrapod Falco cherrug A_B +falcpere Tetrapod Falco peregrinus A_B +felicatu Tetrapod Felis catus A_M +fibrradi Agarico2 Fibroporia radiculosa F +fibuspec Agarico2 Fibulorhizoctonia spec F +ficealbi Tetrapod Ficedula albicollis A_B +fisthepa Agaricom Fistulina hepatica F +fomimedi Agarico2 Fomitiporia mediterranea F +fomipini Agarico2 Fomitopsis pinicola F +fraganan Eudicoty Fragariax ananassa P +fragcyli Heterolo Fragilariopsis cylindrus O +fragvesc Eudicoty Fragaria vesca P +fusafuji fusagram Fusarium fujikuroi F +fusagram fusagram Fusarium graminearum F +fusaoxys fusagram Fusarium oxysporum F +fusavert fusagram Fusarium verticillioides F +gadumorh Fish_mdl Gadus morhua A_F +gaeugram Agarico2 Gaeumannomyces graminis F +galemarg Agarico2 Galerina marginata F +gallgall Tetrapod Gallus gallus A_B +ganospec Agarico2 Ganoderma species F +gastacul Fish_mdl Gasterosteus aculeatus A_F +giarlamb Archamoe Giardia lamblia O +gibbmoni Sordario Gibberella moniliformis F +gibbzeae Sordari5 Gibberella zeae F +glarlozo Leotiom1 Glarea lozoyensis F +gloetrab Agarico2 Gloeophyllum trabeum F +glomacut Sordari1 Glomerella acutata F +glomcing Sordari5 Glomerella cingulata F +glomgram Sordari5 Glomerella graminicola F +glycmax_ Eudicoty Glycine max P +gonaprol gonaprol Gonapodya prolifera F +gorigori Tetrapod Gorilla gorilla A_M +gossraim Eudicoty Gossypium raimondii P +grosclav Sordario Grosmannia clavigera F +guilthet guilthet Guillardia theta O +gymnaura Eurotio2 Gymnascella aurantiaca F +gymnchry Agarico2 Gymnopilus chrysopellus F +gymncitr Eurotio2 Gymnascella citrina F +gymnluxu Agarico2 Gymnopus luxurians F +gyrolivi Agarico2 Gyrodon lividus F +hanspoly Saccharo Hansenula polymorpha F +hansvalb Saccharo Hanseniaspora valbyensis F +hebecyli Agarico2 Hebeloma cylindrosporum F +helimelp InsectAc Heliconius melpomene A_I +helorobu Echinode Helobdella robusta A_O +heteanno Agarico2 Heterobasidion annosum F +heteglab Tetrapod Heterocephalus glaber A_M +hetepycn hetepycn Heterogastridium pycnidioideum F +histcag1 Eurotio3 Histoplasma cag186ar F +histcah1 Eurotio3 Histoplasma cah143 F +histcah8 Eurotio3 Histoplasma cah88 F +histcana Eurotio3 Histoplasma canam1 F +histcaps Eurotio3 Histoplasma capsulatum F +homosapi Tetrapod Homo sapiens A_M +hyalarab Oomycet1 Hyaloperonospora arabidopsidis O +hydnpina Agarico2 Hydnomerulius pinastri F +hydrmagn Echinode Hydra magnipapillata A_O +hyphburt Saccharo Hyphopichia burtonii F +hyphsubl Agarico2 Hypholoma sublateritium F +hypospco Sordari1 Hypoxylon spCO275 F +hypospec Sordari1 Hypoxylon species F +hystpuli Dothideo Hysterium pulicare F +ictitrid Tetrapod Ictidomys tridecemlineatus A_M +ilyoradi Sordari5 Ilyonectria radicola F +ixodscap InsectBm Ixodes scapularis A_I +jaapargi Agarico2 Jaapia argillacea F +jacujacu Tetrapod Jaculus jaculus A_M +jatrcurc Eudicoty Jatropha curcas P +karsrhod Dothide4 Karstenula rhodostom F +kazaafri Saccharo Kazachstania africana F +kluylact Saccharo Kluyveromyces lactis F +komapast Saccharo Komagataella pastoris F +laccamet Agarico2 Laccaria amethystina F +laccbico Agarico1 Laccaria bicolor F +lachkluy Saccharo Lachancea Lachancea F +lachther Saccharo Lachancea thermotolerans F +laetsulp Agarico2 Laetiporus sulphureus F +latichal Tetrapod Latimeria chalumnae A_A +leisbraz Archamoe Leishmania braziliensis O +leisdono Archamoe Leishmania donovani O +leisinfa Archamoe Leishmania infantum O +leismajo Archamoe Leishmania major O +lentfluv Dothide2 Lentithecium fluviatile F +lenttigr Agarico2 Lentinus tigrinus F +lepiocul Fish_lng Lepisosteus oculatus A_F +lepipalu Dothide2 Lepidopterella palustri F +leptmacu Dothideo Leptosphaeria maculans F +leucgong Agarico2 Leucoagaricus gongylophorus F +leucmoll Agarico2 Leucogyrophana mollusca F +lichhyal Mucorale Lichtheimia hyalospora F +linuusit Eudicoty Linum usitatissimum P +lipostar Saccharo Lipomyces starkeyi F +loa_loa_ NematodO Loa loa A_N +loddelon Saccharo Lodderomyces elongisporus F +lophmacr Dothide2 Lophiostoma macrostomum F +lophmyti Dothide2 Lophium mytilinum F +lottgiga Mollusca Lottia gigantea A_mo +lotujapo Eudicoty Lotus japonicus P +loxoafri Tetrapod Loxodonta africana A_M +macafasc Tetrapod Macaca fascicularis A_M +macamula Tetrapod Macaca mulatta A_M +macranom Dothide4 Macroventuria anomochaeta F +macreuge Tetrapod Macropus eugenii A_M +macrfuli Agarico1 Macrolepiota fuliginosa F +macrphas Dothide2 Macrophomina phaseolina F +magngris Sordari3 Magnaporthe grisea F +magnoryz Sordari3 Magnaporthe oryzae F +magnpoae Sordari3 Magnaporthe poae F +malaglob Schizosa Malassezia globosa F +malasymp FungiAll Malassezia sympodialis F +maludome Eudicoty Malus domesticas P +maniescu Eudicoty Manihot esculenta P +maylzebr Fish_mdl Maylandia　zebra A_B +meditrun Eudicoty Medicago truncatula P +megarotu InsectAg Megachile rotundata A_I +megascal InsectDm Megaselia scalaris A_I +melalari Puccinia Melampsora laricispopulina F +melapulv Dothide2 Melanomma pulvis-pyrius F +melaspnr melaspnr Melanconium spNRRL F +melegall Tetrapod Meleagris gallopavo A_B +melibico Leotiom1 Meliniomyces bicolor F +melicinx melicinx Melitaea cinxia A_I +melivari Leotiom1 Meliniomyces variabilis F +meloundu Tetrapod Melopsittacus undulatus A_B +mesoaura Tetrapod Mesocricetus auratus A_M +metaacri Sordario Metarhizium acridum F +metaanis Sordario Metarhizium anisopliae F +metaocci metaocci Metaseiulus occidentalis A_I +metarobe Sordario Metarhizium robertsii F +metsbicu Saccharo Metschnikowia bicuspidata F +micrcani Eurotio1 Microsporum canis F +micrgyps Eurotio1 Microsporum gypseum F +micrmuri Tetrapod Microcebus murinus A_M +microchr Tetrapod Microtus ochrogaster A_M +micrpusi Micrspec Micromonas pusilla P +micrrcc2 Micrspec Micromonas rcc299 P +mimugutt Eudicoty Mimulus guttatus P +mixiosmu mixiosmu Mixia osmundae F +monahapt Sordari1 Monacrosporium haptotylum F +monapurp Eurotio1 Monascus purpureus F +monarube Eurotio1 Monascus ruber F +monipern Agaricom Moniliophthora perniciosa F +monobrev monobrev Monosiga brevicollis O +monodome Tetrapod Monodelphis domestica A_M +morcconi Pezizomy Morchella conica F +mortelon Mortiere Mortierella elongata F +mortvert Mortiere Mortierella verticillata F +mucocirc Mucorale Mucor circinelloides F +mus_musc Tetrapod Mus musculus A_M +musaacum Magnolio Musa acuminata P +mustputo Tetrapod Mustela putorius A_M +mycether Sordari1 Myceliophthora thermophila F +mycofiji Dothide2 Mycosphaerella fijiensis F +mycogram Dothide2 Mycosphaerella graminicola F +myotluci Tetrapod Myotis lucifugus A_M +myriduri Dothide2 Myriangium duriaei F +nadsfulv Saccharo Nadsonia fulvescens F +naeggrub Heterolo Naegleria gruberi O +naiaflui naiaflui Naiadella fluitansa F +nasovitr InsectAg Nasonia vitripennis A_I +necthaem Sordari5 Nectria haematococca F +nemapari FungiAll Nematocida parisii F +nemavect Echinode Nematostella vectensis A_O +neofparv Dothide2 Neofusicoccum parvum F +neollepi Agarico2 Neolentinus lepideus F +neosfisc Eurotio2 Neosartorya fischeri F +neurcras Sordari1 Neurospora crassa F +neurdisc Sordari1 Neurospora discreta F +neurtetr Sordari1 Neurospora tetrasperma F +nicobent Eudicoty Nicotiana benthamiana P +nomaleuc Tetrapod Nomascus leucogenys A_M +nosecera FungiAll Nosema ceranae F +obbarivu Agarico2 Obba rivulosa F +ochoprin Tetrapod Ochotona princeps A_M +octodegu Tetrapod Octodon degus A_M +odobrosm Tetrapod Odobenus rosmarus A_M +oidimaiu Leotiom1 Oidiodendron maius F +ompholea Agaricom Omphalotus olearius F +onchvolv onchvolv Onchocerca volvulus A_N +ophidiss Dothide4 Ophiostoma piceae F +ophipice Sordario Ophiostoma piceae F +orciorca Tetrapod Orcinus orca A_M +oreonilo Fish_mdl Oreochromis niloticus A_F +ornianat Tetrapod Ornithorhynchus anatinus A_M +orpispec Ichthyos Orpinomyces spec F +oryccuni Tetrapod Oryctolagus cuniculus A_M +oryzbrac Magnolio Oryza brachyantha P +oryzlati Fish_mdl Oryzias latipes A_F +oryzsati Magnolio Oryza sativa P +oryzsatj Magnolio Oryza sativa P +ostrluci Ostrspec Ostreococcus lucimarinus P +ostrrcc8 Ostrspec Ostreococcus rcc809 P +ostrtaur Ostrspec Ostreococcus tauri P +otolgarn Tetrapod Otolemur garnettii A_M +ovisarie Tetrapod Ovis aries A_M +pachtann Saccharo Pachysolen tannophilus F +pan_pani Tetrapod Pan paniscus A_M +pan_trog Tetrapod Pan troglodytes A_M +panivirg Magnolio Panicum virgatum P +papianub Tetrapod Papio anubis A_M +parabra1 Eurotio3 Paracoccidioides bra1 F +parabras Eurotio3 Paracoccidioides brasiliensis F +paratetr paratetr Paramecium tetraurelia O +pateatra Dothide2 Patellaria atrata F +paxiinvo Agarico2 Paxillus involutus F +paxirubi Agarico2 Paxillus rubicundulus F +pedihuma InsectAg Pediculus humanus A_I +pelosine Tetrapod Pelodiscus sinensis A_R +penibila Eurotio1 Penicillium bilaiae F +penibrev Eurotio2 Penicillium brevicompactum F +penicane Eurotio2 Penicillium canescens F +penichry Eurotio2 Penicillium chrysogenum F +penidigi Eurotio2 Penicillium digitatum F +peniexpa Eurotio2 Penicillium expansum F +penifell Eurotio2 Penicillium fellutanum F +peniglab Eurotio2 Penicillium glabrum F +penijant Eurotio1 Penicillium janthinellum F +penilano Eurotio2 Penicillium lanosocoeruleum F +penioxal Eurotiom Penicillium oxalicum F +penirais Eurotio2 Penicillium raistrickii F +petrmari ChordatU Petromyzon marinus A_C +phaealeo Sordario Phaeoacremonium aleophilum F +phaenodo phaenodo Phaeosphaeria nodorum F +phaetric Bacillar Phaeodactylum tricornutum O +phancarn Agarico1 Phanerochaete carnosa F +phanchry Agarico1 Phanerochaete chrysosporium F +phasvulg Eudicoty Phaseolus vulgaris P +phlebrev Agarico2 Phlebia brevispora F +phlegiga Agarico1 Phlebiopsis gigantea F +phoedact Magnolio Phoenix dactylifera P +phomtrac Dothide2 Phoma tracheiphila F +phycblak Mucorale Phycomyces blakesleeanus F +phylhete Magnolio Phyllostachys heterocycla P +physpate physpate Physcomitrella patens P +physpoly Sordario Physarum polycephalum F +phytcaps Oomycet2 Phytophthora capsici O +phytcinn Oomycet2 Phytophthora cinnamomi O +phytinfe Oomycet1 Phytophthora infestans O +phytramo Oomycet1 Phytophthora ramorum O +phytsoja Oomycet1 Phytophthora sojae O +pichmemb Saccharo Pichia membranifaciens F +pichpast Saccharo Pichia pastoris F +pichstip Saccharo Pichia stipitis F +piedhort Dothide4 Piedraia hortae F +pilocroc Agarico2 Piloderma croceum F +piriindi Agarico1 Piriformospora indica F +pirospec Ichthyos Piromyces species F +pisomicr Agarico2 Pisolithus microcarpus F +pisotinc Agarico2 Pisolithus tinctorius F +plasberg Aconoida Plasmodium berghei O +plaschab Aconoida Plasmodium chabaudi O +plasfalc Aconoida Plasmodium falciparum O +plasknow Aconoida Plasmodium knowlesi O +plasviva Aconoida Plasmodium vivax O +pleosipa Dothide2 Pleomassaria siparia F +pleuostr Agarico1 Pleurotus ostreatus F +pliccris Agarico2 Plicaturopsis crispa F +pneujiro FungiAll Pneumocystis jirovecii F +podoanse Sordari1 Podospora anserina F +poecform Fish_lng Poecilia formosa A_F +polyarcu Agarico2 Polyporus arcularius F +polycitr Dothide1 Polychaeton citri F +pongabel Tetrapod Pongo abelii A_M +poputric Eudicoty Populus trichocarpa P +postplac Agarico2 Postia placenta F +prispaci prispaci Pristionchus pacificus A_N +proccape Tetrapod Procavia capensis A_M +prunmume Eudicoty Prunus mume P +prunpers Eudicoty Prunus persica P +pseuanta Sordari3 Pseudozyma antarctica F +pseuhube Ichthyos Pseudozyma hubeiensis F +pseuhumi Tetrapod Pseudopodoces humilis A_B +pseumult Bacillar Pseudo-nitzschia multiseries O +ptervamp Tetrapod Pteropus vampyrus A_M +puccgram Puccinia Puccinia graminis F +puccstri Puccinia Puccinia striiformis F +pucctrit Puccinia Puccinia triticina F +puncstri Agarico2 Punctularia strigosozonata F +pycncinn FungiAll Pycnoporus cinnabarinus F +pycncocc Agarico2 Pycnoporus coccineus F +pycnsang Agarico2 Pycnoporus sanguineus F +pyretere Dothide2 Pyrenophora teres F +pyretrit Dothide2 Pyrenophora tritici F +pyroconf Pezizomy Pyronema confluens F +pythulti Oomycet2 Pythium ultimum O +pythvexa pythvexa Pythium vexans O +rattnorv Tetrapod Rattus norvegicus A_M +rhizirre Blastocl Rhizophagus irregularis F +rhizmicr Mucorale Rhizopus microsporus F +rhizoryz Mucorale Rhizopus oryzae F +rhizsola Agarico4 Rhizoctonia solani F +rhizvini Agarico1 Rhizopus microsporus F +rhodgram rhodgram Rhodotorula graminis F +rhodminu rhodminu Rhodotorula minuta F +rhodprol InsectAc Rhodnius prolixus A_I +rhytrufu Dothideo Rhytidhysteron rufulum F +ricicomm Eudicoty Ricinus communis P +rickmell Agarico1 Rickenella mellea F +rozeallo Tremell2 Rozella allomycis F +saccbaya Saccharo Saccharomyces bayanus F +sacccast Saccharo Saccharomyces castellii F +sacccere Saccharo Saccharomyces cerevisiae F +sacckluy Saccharo Saccharomyces kluyveri F +sacckowa Tetrapod Saccoglossus kowalevskii A_C +sacckudr Saccharo Saccharomyces kudriavzevii F +saccmika Saccharo Saccharomyces mikatae F +saccpara Saccharo Saccharomyces paradoxus F +saccpast Saccharo Saccharomyces pastorianus F +saccprot Saccharo Saccharata proteae F +saimboli Tetrapod Saimiri boliviensis A_M +saitcomp Agarico1 Saitoella complicata F +salprose salprose Salpingoeca rosetta O +sarcharr Tetrapod Sarcophilus harrisii A_M +schiaggr Labyrint Schizochytrium aggregatum O +schicom3 Agarico1 Schizophyllum com3 F +schicoml Agarico1 Schizophyllum comL F +schicomm Agarico1 Schizophyllum commune F +schicomt Agarico1 Schizophyllum comT F +schicryo Schizosa Schizosaccharomyces cryophilus F +schijapo Schizosa Schizosaccharomyces japonicus F +schimans schimans Schistosoma mansoni A_O +schiocto Schizosa Schizosaccharomyces octosporus F +schipara Agarico2 Schizopora paradoxa F +schipomb Schizosa Schizosaccharomyces pombe F +sclecitr Agarico2 Scleroderma citrinum F +sclescle Leotiom2 Sclerotinia sclerotiorum F +sebaverm Agarico1 Sebacina vermifera F +selamoel selamoel Selaginella moellendorffii P +septmusi Dothide1 Septoria musiva F +septpopu Dothide1 Septoria populicola F +serplacr Agarico2 Serpula lacrymans F +setaital Magnolio Setaria italica P +setoturc Dothide2 Setosphaeria turcica F +sistbrin Agarico2 Sistotrema brinkmannii F +sistnive Agarico1 Sistotremastrum niveocremeu F +sistsuec Agarico1 Sistotremastrum suecicum F +sodialka Sordari3 Sodiomyces alkalinus F +solalyco Eudicoty Solanum lycopersicum P +solatube Eudicoty Solanum tuberosum P +soleinvi InsectDm Solenopsis invicta A_I +sorearan Tetrapod Sorex araneus A_M +sorgbico Magnolio Sorghum bicolor P +spatpass Saccharo Spathaspora passalidarum F +sphaarct Ichthyos Sphaeroforma arctica F +sphastel Agarico1 Sphaerobolus stellatus F +spizpunc FungiAll Spizellomyces punctatus F +sporfime Dothide4 Sporormia fimetaria F +sporlind Agaricom Sporobolomyces linderae F +sporreil Puccinia Sporisorium reilianum F +sporrose Puccinia Sporobolomyces roseus F +sporther Sordari1 Sporotrichum thermophile F +stagnodo Dothideo Stagonospora nodorum F +sterhirs Agarico4 Stereum hirsutum F +strimari InsectDm Strigamia maritima A_I +stropurp ChordatU Strongylocentrotus purpuratus A_C +suilbrev Agarico1 Suillus brevipes F +suillute Agarico2 Suillus luteus F +sus_scro Tetrapod Sus scrofa A_M +symbkoch symbkoch Symbiotaphrina kochii F +taengutt Tetrapod Taeniopygia guttata A_B +takirubr Fish_sht Takifugu rubripes A_F +talaacul Eurotio2 Talaromyces aculeatus F +talamarn Eurotio2 Talaromyces marneffei F +talastip Eurotio2 Talaromyces stipitatus F +taphdefo Dothide4 Taphrina deformans F +tarssyri Tetrapod Tarsius syrichta A_M +terfboud Pezizomy Terfezia boudieri F +tetrnigr Fish_sht Tetraodon nigroviridis A_F +tetrphaf Saccharo Tetrapisispora phaffii F +tetrther tetrther Tetrahymena thermophila O +tetrurti InsectAg Tetranychus urticae A_I +thalpseu thalpseu Thalassiosira pseudonana O +thectrah FungiAll Thecamonas trahens O +theiannu Theileri Theileria annulata A_O +theiparv Theileri Theileria parva A_O +thelhalo Eudicoty Thellungiella halophila P +thelparv Eudicoty Thellungiella parvula P +theocaca Eudicoty Theobroma cacao P +theraura Eurotio2 Thermoascus aurantiacus F +thieanta FungiAll Thielavia antarctica F +thieappe Sordari1 Thielavia appendiculata F +thiearen Sordari1 Thielavia arenaria F +thiehyrc Sordari1 Thielavia hyrcaniae F +thieterr Sordari1 Thielavia terrestris F +tillanom tillanom Tilletiaria anomala F +torudelb Saccharo Torulaspora delbrueckii F +toxogond Conoidas Toxoplasma gondii O +tramvers Agarico2 Trametes versicolor F +tremmese Tremell2 Tremella mesenterica F +trempert trempert Trematosphaeria pertusa F +tremspec Tremell2 Tremella species F +tribcast tribcast Tribolium castaneum A_I +tricabie Agarico2 Trichaptum abietinum F +tricadha tricadha Trichoplax adhaerens A_O +tricaspe Sordari1 Trichoderma asperellum F +tricatro Sordari1 Trichoderma atroviride F +triccitr Sordario Trichoderma citrinoviride F +tricequi Eurotio2 Trichophyton equinum F +tricharz Sordari1 Trichoderma harzianum F +triclong Sordari1 Trichoderma longibrachiatum F +tricmana Tetrapod Trichechus manatus A_M +tricmats Agarico1 Tricholoma matsutake F +tricolea Tremell2 Trichosporon oleaginosus F +tricrees Sordari1 Trichoderma reesei F +tricrubr Eurotio1 Trichophyton rubrum F +tricspir tribcast Trichinella spiralis A_O +trictons Eurotio1 Trichophyton tonsurans F +tricverr Eurotio1 Trichophyton verrucosum F +tricvire Sordari1 Trichoderma virens F +tritaesa Magnolio Triticum aestivum P +tritaesb Magnolio Triticum aestivum P +tritaesd Magnolio Triticum aestivum P +tritspec tritspec Tritirachium species F +trypbruc Archamoe Trypanosoma brucei O +trypelut Dothide2 Trypethelium eluteriae F +tubemela Pezizomy Tuber melanosporum F +tulacalo Agarico4 Tulasnella calospora F +tupabela Tetrapod Tupaia belangeri A_M +turstrun Tetrapod Tursiops truncatus A_M +umberama Mucorale Umbelopsis ramanniana F +uncirees Eurotio1 Uncinocarpus reesii F +ustimayd Eurotio3 Ustilago maydis F +vertalbo Sordario Verticillium alboatrum F +vertalfa Sordario Verticillium alfalfae F +vertdahl Sordario Verticillium dahliae F +vicupaco Tetrapod Vicugna pacos A_ +vitivini Eudicoty Vitis vinifera P +volvcart Chlospec Volvox carteri P +volvvolv Agaricom Volvariella volvacea F +wallicht Dothide4 Wallemia ichthyophaga F +wallsebi wallsebi Wallemia sebi F +wickanom Saccharo Wickerhamomyces anomalus F +wilcmiko Pezizomy Wilcoxina mikolae F +wolfcoco Agarico2 Wolfiporia cocos F +xantpari Agarico2 Xanthoria parietina F +xenotrop Tetrapod Xenopus tropicalis A_A +xiphmacu Fish_mdl Xiphophorus maculatus A_F +xyloheve xyloheve Xylona heveae F +yarrlipo Saccharo Yarrowia lipolytica F +zasmcell Dothide2 Zasmidium cellare F +zea_mays Magnolio Zea mays P +zonoalbi Tetrapod Zonotrichia albicollis A_B +zopfrhiz Dothide2 Zopfia rhizophila F +zygoroux Saccharo Zygosaccharomyces rouxii F +zymotrit Dothide2 Zymoseptoria tritici F
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/ncbi_taxonomy_sqlite.loc Thu Jul 16 07:57:10 2020 -0400 @@ -0,0 +1,2 @@ +#value description path +sample sample database ${__HERE__}/sqlite_taxdb
--- a/test-data/output1.bed12 Fri Jan 11 18:15:21 2019 -0500 +++ b/test-data/output1.bed12 Thu Jul 16 07:57:10 2020 -0400 @@ -1,2 +1,2 @@ track name=Spaln description="NP_001121846.1" useScore=1 -scaffold_1 233 29800 NP_001121846.1 1000 + 233 29800 255,0,0 43 31,30,125,9,9,106,4,9,5,37,8,18,12,18,9,4,30,18,8,3,2,3,15,6,10,7,5,7,14,2,11,20,12,12,2,19,23,26,5,7,9,23,5, 0,71,184,1922,2587,6911,7425,7504,7626,8016,8114,8185,8347,8632,8746,9149,9725,15480,15549,15615,16511,16714,16848,17115,17191,18118,18504,19271,19365,19443,20377,22213,22440,25892,25951,26121,26227,26308,26406,28178,28715,28868,29562 +scaffold_1 16 10418 NP_001121846.1 530 + 16 10418 255,0,0 16 46,33,122,127,33,4,127,33,6,18,15,11,13,24,24,24, 0,111,401,7107,7546,7642,7721,7908,8278,8849,8963,9050,9959,10028,10212,10378
--- a/test-data/output1.tabular Fri Jan 11 18:15:21 2019 -0500 +++ b/test-data/output1.tabular Thu Jul 16 07:57:10 2020 -0400 @@ -1,45 +1,18 @@ # rID gID %id ExonL MisMch Unpair ref_l ref_r tgt_l tgt_r eScore IntrnL iScore Sig3/I Sig5/T # - X P DiNuc -NP_001121846.1 scaffold_1 30.00 31 7 0 1 10 234 264 71.9 0 0.0 67.90 -1.80 0 0 0 0 . -NP_001121846.1 scaffold_1 16.67 30 6 9 11 27 305 334 -9.0 40 -8.2 9.90 -2.20 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 64.29 125 15 0 28 69 418 542 226.4 83 8.4 22.20 16.00 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 66.67 9 1 0 70 72 2156 2164 37.9 1613 -6.6 4.40 21.90 0 0 0 0 GT.AG -NP_001121846.1 scaffold_1 66.67 9 1 0 73 75 2821 2829 32.3 656 7.5 7.20 12.10 0 0 0 0 GT.AG -NP_001121846.1 scaffold_1 62.86 106 13 0 76 110 7145 7250 176.6 4315 4.0 25.10 25.30 0 0 0 0 GT.AG -NP_001121846.1 scaffold_1 0.00 4 2 0 111 112 7659 7662 22.9 408 11.8 5.70 17.50 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 0.00 9 2 1 113 114 7738 7746 4.9 75 20.0 13.50 2.90 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 0.00 5 1 0 115 115 7860 7864 24.0 113 -3.9 7.30 16.20 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 30.00 37 7 0 116 125 8250 8286 15.8 385 9.7 12.50 11.50 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 100.00 8 0 0 126 127 8348 8355 28.3 61 18.0 16.20 -0.80 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 33.33 18 4 0 128 133 8419 8436 26.2 63 1.5 12.10 6.70 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 0.00 12 4 0 134 137 8581 8592 29.2 144 9.9 18.20 9.20 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 0.00 18 6 0 138 143 8866 8883 29.1 273 5.7 14.00 24.90 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 0.00 9 3 0 144 146 8980 8988 28.2 96 33.9 21.70 10.20 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 50.00 4 1 0 147 148 9383 9386 33.7 394 -5.5 3.40 14.10 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 10.00 30 5 4 149 154 9959 9988 21.1 572 3.1 10.30 20.60 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 16.67 18 5 0 155 160 15714 15731 43.6 5725 3.9 18.20 22.40 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 50.00 8 1 0 161 162 15783 15790 19.0 51 8.8 -3.20 17.10 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 0.00 3 1 0 163 163 15849 15851 17.0 58 20.8 13.40 3.40 0 0 0 1 GC.AG -NP_001121846.1 scaffold_1 0.00 2 1 0 164 164 16745 16746 20.9 893 -5.3 14.60 8.20 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 0.00 3 1 0 165 165 16948 16950 27.2 201 14.2 22.30 9.10 0 0 0 0 GT.AG -NP_001121846.1 scaffold_1 100.00 15 0 0 166 166 17082 17096 13.3 131 17.9 23.40 2.50 0 0 0 0 GT.AG -NP_001121846.1 scaffold_1 0.00 6 1 1 167 167 17349 17354 28.3 252 -9.3 5.30 22.50 0 0 0 0 GT.AG -NP_001121846.1 scaffold_1 33.33 10 2 0 168 170 17425 17434 15.0 70 22.3 10.10 2.30 0 0 0 0 GT.AG -NP_001121846.1 scaffold_1 33.33 7 2 0 171 173 18352 18358 24.7 917 -18.2 2.90 16.40 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 100.00 5 0 0 174 174 18738 18742 17.0 379 19.5 12.40 0.60 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 66.67 7 1 0 175 177 19505 19511 32.6 762 -14.2 7.60 16.10 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 0.00 14 4 0 178 181 19599 19612 16.1 87 15.0 1.90 18.00 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 0.00 2 1 0 182 182 19677 19678 17.1 64 18.2 10.00 3.60 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 50.00 11 1 0 183 184 20611 20621 30.0 932 -2.8 17.10 15.00 0 0 0 0 GT.AG -NP_001121846.1 scaffold_1 33.33 20 2 2 185 188 22447 22466 27.3 1825 -5.3 7.50 15.80 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 50.00 12 2 0 189 192 22674 22685 31.9 207 4.4 5.00 7.70 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 20.00 12 3 1 193 197 26126 26137 31.8 3440 -1.3 22.70 14.00 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 0.00 2 1 0 198 198 26185 26186 22.5 47 14.8 12.40 8.30 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 33.33 19 4 0 199 204 26355 26373 33.1 168 7.8 15.10 7.10 0 0 0 0 GT.AG -NP_001121846.1 scaffold_1 0.00 23 3 0 205 207 26461 26483 8.0 87 11.9 16.80 8.10 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 33.33 26 2 4 208 212 26542 26567 22.6 58 18.9 20.50 -0.50 0 0 0 0 GT.AG -NP_001121846.1 scaffold_1 0.00 5 1 0 213 213 26640 26644 24.6 72 3.9 14.90 11.30 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 33.33 7 2 0 214 216 28412 28418 28.0 1767 -4.5 11.80 12.30 0 0 0 1 GT.AG -NP_001121846.1 scaffold_1 100.00 9 0 0 217 217 28949 28957 26.9 530 17.1 25.30 10.30 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 28.57 23 2 3 218 221 29102 29124 36.1 144 16.5 21.20 10.60 0 0 0 2 GT.AG -NP_001121846.1 scaffold_1 0.00 5 1 1 222 222 29796 29800 24.4 671 8.0 19.10 10.60 0 0 0 1 GT.AG -@ scaffold_1 + ( 234 29800 ) NP_001121846.1 222 ( 1 222 ) S: 1357.3 =: 38.1 C: 110.8 T#: 122 T-: 26 B#: 0 B-: 0 X: 0 Pam: 0 +NP_001121846.1 scaffold_1 21.43 46 11 0 1 14 17 62 79.7 0 0.0 66.40 0.90 0 0 0 0 . +NP_001121846.1 scaffold_1 12.50 33 8 3 15 27 128 160 -4.3 65 -23.9 -5.20 10.70 0 0 0 1 GT.AG +NP_001121846.1 scaffold_1 68.29 122 13 0 28 68 418 539 210.5 257 -0.1 16.10 6.60 0 0 0 1 GT.AG +NP_001121846.1 scaffold_1 64.29 127 15 0 69 110 7124 7250 187.0 6584 -24.3 14.60 17.80 0 0 0 0 GT.AG +NP_001121846.1 scaffold_1 9.09 33 10 0 111 121 7563 7595 11.0 312 -4.2 5.70 5.20 0 0 0 1 GT.AG +NP_001121846.1 scaffold_1 0.00 4 2 0 122 123 7659 7662 21.2 63 -6.4 7.90 13.90 0 0 0 1 GT.AG +NP_001121846.1 scaffold_1 20.45 127 31 2 124 165 7738 7864 21.7 75 5.0 11.80 13.20 0 0 0 2 GT.AG +NP_001121846.1 scaffold_1 9.09 33 10 0 166 176 7925 7957 26.1 60 1.0 7.20 9.70 0 0 0 0 GT.AG +NP_001121846.1 scaffold_1 50.00 6 1 0 177 178 8295 8300 29.4 337 -9.5 8.90 10.80 0 0 0 0 GT.AG +NP_001121846.1 scaffold_1 16.67 18 5 0 179 184 8866 8883 31.0 565 -7.7 12.00 17.60 0 0 0 0 GT.AG +NP_001121846.1 scaffold_1 0.00 15 5 0 185 189 8980 8994 30.3 96 11.1 15.90 9.10 0 0 0 0 GT.AG +NP_001121846.1 scaffold_1 0.00 11 4 0 190 193 9067 9077 27.0 72 -4.0 7.10 7.60 0 0 0 0 GT.AG +NP_001121846.1 scaffold_1 25.00 13 3 0 194 197 9976 9988 28.5 898 -22.1 6.80 15.40 0 0 0 2 GT.AG +NP_001121846.1 scaffold_1 37.50 24 5 0 198 205 10045 10068 27.5 56 3.7 7.70 5.10 0 0 0 0 GT.AG +NP_001121846.1 scaffold_1 25.00 24 6 0 206 213 10229 10252 38.3 160 -6.9 13.10 12.60 0 0 0 0 GT.AG +NP_001121846.1 scaffold_1 20.00 24 6 1 214 222 10395 10418 23.3 142 0.3 12.40 12.60 0 0 0 0 GT.AG +@ scaffold_1 + ( 17 10418 ) NP_001121846.1 222 ( 1 222 ) S: 627.0 =: 36.5 C: 97.3 T#: 135 T-: 6 B#: 0 B-: 0 X: 0 Nexn: 16
--- a/test-data/output1_gff_genes.gff3 Fri Jan 11 18:15:21 2019 -0500 +++ b/test-data/output1_gff_genes.gff3 Thu Jul 16 07:57:10 2020 -0400 @@ -1,47 +1,20 @@ ##gff-version 3 ##sequence-region scaffold_1 1 59940 -scaffold_1 ALN gene 234 29800 1357 + . ID=gene00001;Name=scaffold_1_15 -scaffold_1 ALN mRNA 234 29800 1357 + . ID=mRNA00001;Parent=gene00001;Name=scaffold_1_15 -scaffold_1 ALN cds 234 264 71 + 0 ID=cds00001;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 1 10 + -scaffold_1 ALN cds 305 334 -9 + 2 ID=cds00002;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 11 27 + -scaffold_1 ALN cds 418 542 226 + 2 ID=cds00003;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 28 69 + -scaffold_1 ALN cds 2156 2164 37 + 0 ID=cds00004;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 70 72 + -scaffold_1 ALN cds 2821 2829 32 + 0 ID=cds00005;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 73 75 + -scaffold_1 ALN cds 7145 7250 176 + 0 ID=cds00006;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 76 110 + -scaffold_1 ALN cds 7659 7662 22 + 2 ID=cds00007;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 111 112 + -scaffold_1 ALN cds 7738 7746 4 + 1 ID=cds00008;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 113 114 + -scaffold_1 ALN cds 7860 7864 24 + 1 ID=cds00009;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 115 115 + -scaffold_1 ALN cds 8250 8286 15 + 2 ID=cds00010;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 116 125 + -scaffold_1 ALN cds 8348 8355 28 + 1 ID=cds00011;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 126 127 + -scaffold_1 ALN cds 8419 8436 26 + 2 ID=cds00012;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 128 133 + -scaffold_1 ALN cds 8581 8592 29 + 2 ID=cds00013;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 134 137 + -scaffold_1 ALN cds 8866 8883 29 + 2 ID=cds00014;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 138 143 + -scaffold_1 ALN cds 8980 8988 28 + 2 ID=cds00015;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 144 146 + -scaffold_1 ALN cds 9383 9386 33 + 2 ID=cds00016;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 147 148 + -scaffold_1 ALN cds 9959 9988 21 + 1 ID=cds00017;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 149 154 + -scaffold_1 ALN cds 15714 15731 43 + 1 ID=cds00018;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 155 160 + -scaffold_1 ALN cds 15783 15790 19 + 1 ID=cds00019;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 161 162 + -scaffold_1 ALN cds 15849 15851 17 + 2 ID=cds00020;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 163 163 + -scaffold_1 ALN cds 16745 16746 20 + 2 ID=cds00021;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 164 164 + -scaffold_1 ALN cds 16948 16950 27 + 0 ID=cds00022;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 165 165 + -scaffold_1 ALN cds 17082 17096 13 + 0 ID=cds00023;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 166 166 + -scaffold_1 ALN cds 17349 17354 28 + 0 ID=cds00024;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 167 167 + -scaffold_1 ALN cds 17425 17434 15 + 0 ID=cds00025;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 168 170 + -scaffold_1 ALN cds 18352 18358 24 + 2 ID=cds00026;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 171 173 + -scaffold_1 ALN cds 18738 18742 17 + 1 ID=cds00027;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 174 174 + -scaffold_1 ALN cds 19505 19511 32 + 2 ID=cds00028;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 175 177 + -scaffold_1 ALN cds 19599 19612 16 + 1 ID=cds00029;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 178 181 + -scaffold_1 ALN cds 19677 19678 17 + 2 ID=cds00030;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 182 182 + -scaffold_1 ALN cds 20611 20621 30 + 0 ID=cds00031;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 183 184 + -scaffold_1 ALN cds 22447 22466 27 + 1 ID=cds00032;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 185 188 + -scaffold_1 ALN cds 22674 22685 31 + 2 ID=cds00033;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 189 192 + -scaffold_1 ALN cds 26126 26137 31 + 2 ID=cds00034;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 193 197 + -scaffold_1 ALN cds 26185 26186 22 + 2 ID=cds00035;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 198 198 + -scaffold_1 ALN cds 26355 26373 33 + 0 ID=cds00036;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 199 204 + -scaffold_1 ALN cds 26461 26483 8 + 2 ID=cds00037;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 205 207 + -scaffold_1 ALN cds 26542 26567 22 + 0 ID=cds00038;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 208 212 + -scaffold_1 ALN cds 26640 26644 24 + 1 ID=cds00039;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 213 213 + -scaffold_1 ALN cds 28412 28418 28 + 2 ID=cds00040;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 214 216 + -scaffold_1 ALN cds 28949 28957 26 + 1 ID=cds00041;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 217 217 + -scaffold_1 ALN cds 29102 29124 36 + 1 ID=cds00042;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 218 221 + -scaffold_1 ALN cds 29796 29800 24 + 2 ID=cds00043;Parent=mRNA00001;Name=scaffold_1_15;Target=NP_001121846.1 222 222 + +scaffold_1 ALN gene 17 10418 627 + . ID=gene00001;Name=scaffold_1_5 +scaffold_1 ALN mRNA 17 10418 627 + . ID=mRNA00001;Parent=gene00001;Name=scaffold_1_5 +scaffold_1 ALN cds 17 62 79 + 0 ID=cds00001;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 1 14 + +scaffold_1 ALN cds 128 160 -4 + 2 ID=cds00002;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 15 27 + +scaffold_1 ALN cds 418 539 210 + 2 ID=cds00003;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 28 68 + +scaffold_1 ALN cds 7124 7250 187 + 0 ID=cds00004;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 69 110 + +scaffold_1 ALN cds 7563 7595 11 + 2 ID=cds00005;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 111 121 + +scaffold_1 ALN cds 7659 7662 21 + 2 ID=cds00006;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 122 123 + +scaffold_1 ALN cds 7738 7864 21 + 1 ID=cds00007;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 124 165 + +scaffold_1 ALN cds 7925 7957 26 + 0 ID=cds00008;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 166 176 + +scaffold_1 ALN cds 8295 8300 29 + 0 ID=cds00009;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 177 178 + +scaffold_1 ALN cds 8866 8883 31 + 0 ID=cds00010;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 179 184 + +scaffold_1 ALN cds 8980 8994 30 + 0 ID=cds00011;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 185 189 + +scaffold_1 ALN cds 9067 9077 27 + 0 ID=cds00012;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 190 193 + +scaffold_1 ALN cds 9976 9988 28 + 1 ID=cds00013;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 194 197 + +scaffold_1 ALN cds 10045 10068 27 + 0 ID=cds00014;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 198 205 + +scaffold_1 ALN cds 10229 10252 38 + 0 ID=cds00015;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 206 213 + +scaffold_1 ALN cds 10395 10418 23 + 0 ID=cds00016;Parent=mRNA00001;Name=scaffold_1_5;Target=NP_001121846.1 214 222 +
--- a/test-data/output1_gff_matches.gff3 Fri Jan 11 18:15:21 2019 -0500 +++ b/test-data/output1_gff_matches.gff3 Thu Jul 16 07:57:10 2020 -0400 @@ -1,45 +1,18 @@ ##gff-version 3 ##sequence-region scaffold_1 1 59940 -scaffold_1 ALN nucleotide_to_protein_match 234 264 71 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 1 10 +;Gap=M10 -scaffold_1 ALN nucleotide_to_protein_match 305 334 -9 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 11 27 +;Gap=M2 D1 M5 I8 M2 -scaffold_1 ALN nucleotide_to_protein_match 418 542 226 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 28 69 +;Gap=M42 -scaffold_1 ALN nucleotide_to_protein_match 2156 2164 37 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 70 72 +;Gap=M3 -scaffold_1 ALN nucleotide_to_protein_match 2821 2829 32 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 73 75 +;Gap=M3 -scaffold_1 ALN nucleotide_to_protein_match 7145 7250 176 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 76 110 +;Gap=M35 -scaffold_1 ALN nucleotide_to_protein_match 7659 7662 22 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 111 112 +;Gap=M2 -scaffold_1 ALN nucleotide_to_protein_match 7738 7746 4 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 113 114 +;Gap=D1 M2 -scaffold_1 ALN nucleotide_to_protein_match 7860 7864 24 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 115 115 +;Gap=M1 -scaffold_1 ALN nucleotide_to_protein_match 8250 8286 15 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 116 125 +;Gap=M10 D3 -scaffold_1 ALN nucleotide_to_protein_match 8348 8355 28 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 126 127 +;Gap=M2 -scaffold_1 ALN nucleotide_to_protein_match 8419 8436 26 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 128 133 +;Gap=M6 -scaffold_1 ALN nucleotide_to_protein_match 8581 8592 29 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 134 137 +;Gap=M4 -scaffold_1 ALN nucleotide_to_protein_match 8866 8883 29 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 138 143 +;Gap=M6 -scaffold_1 ALN nucleotide_to_protein_match 8980 8988 28 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 144 146 +;Gap=M3 -scaffold_1 ALN nucleotide_to_protein_match 9383 9386 33 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 147 148 +;Gap=M2 -scaffold_1 ALN nucleotide_to_protein_match 9959 9988 21 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 149 154 +;Gap=D4 M6 -scaffold_1 ALN nucleotide_to_protein_match 15714 15731 43 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 155 160 +;Gap=M6 -scaffold_1 ALN nucleotide_to_protein_match 15783 15790 19 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 161 162 +;Gap=M2 -scaffold_1 ALN nucleotide_to_protein_match 15849 15851 17 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 163 163 +;Gap=M1 -scaffold_1 ALN nucleotide_to_protein_match 16745 16746 20 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 164 164 +;Gap=M1 -scaffold_1 ALN nucleotide_to_protein_match 16948 16950 27 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 165 165 +;Gap=M1 -scaffold_1 ALN nucleotide_to_protein_match 17082 17096 13 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 166 166 +;Gap=M1 D4 -scaffold_1 ALN nucleotide_to_protein_match 17349 17354 28 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 167 167 +;Gap=D1 M1 -scaffold_1 ALN nucleotide_to_protein_match 17425 17434 15 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 168 170 +;Gap=M3 -scaffold_1 ALN nucleotide_to_protein_match 18352 18358 24 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 171 173 +;Gap=M3 -scaffold_1 ALN nucleotide_to_protein_match 18738 18742 17 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 174 174 +;Gap=M1 -scaffold_1 ALN nucleotide_to_protein_match 19505 19511 32 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 175 177 +;Gap=M3 -scaffold_1 ALN nucleotide_to_protein_match 19599 19612 16 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 178 181 +;Gap=M4 -scaffold_1 ALN nucleotide_to_protein_match 19677 19678 17 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 182 182 +;Gap=M1 -scaffold_1 ALN nucleotide_to_protein_match 20611 20621 30 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 183 184 +;Gap=M2 D2 -scaffold_1 ALN nucleotide_to_protein_match 22447 22466 27 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 185 188 +;Gap=D2 M4 -scaffold_1 ALN nucleotide_to_protein_match 22674 22685 31 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 189 192 +;Gap=M4 -scaffold_1 ALN nucleotide_to_protein_match 26126 26137 31 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 193 197 +;Gap=I1 M4 -scaffold_1 ALN nucleotide_to_protein_match 26185 26186 22 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 198 198 +;Gap=M1 -scaffold_1 ALN nucleotide_to_protein_match 26355 26373 33 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 199 204 +;Gap=M6 -scaffold_1 ALN nucleotide_to_protein_match 26461 26483 8 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 205 207 +;Gap=M3 D5 -scaffold_1 ALN nucleotide_to_protein_match 26542 26567 22 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 208 212 +;Gap=D4 M5 -scaffold_1 ALN nucleotide_to_protein_match 26640 26644 24 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 213 213 +;Gap=M1 -scaffold_1 ALN nucleotide_to_protein_match 28412 28418 28 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 214 216 +;Gap=M3 -scaffold_1 ALN nucleotide_to_protein_match 28949 28957 26 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 217 217 +;Gap=M1 D2 -scaffold_1 ALN nucleotide_to_protein_match 29102 29124 36 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 218 221 +;Gap=D3 M4 -scaffold_1 ALN nucleotide_to_protein_match 29796 29800 24 + . ID=match00001;Name=scaffold_1_15;Target=NP_001121846.1 222 222 +;Gap=M1 D1 +scaffold_1 ALN nucleotide_to_protein_match 17 62 79 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 1 14 +;Gap=D1 M14 +scaffold_1 ALN nucleotide_to_protein_match 128 160 -4 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 15 27 +;Gap=M5 I3 M1 D1 M4 +scaffold_1 ALN nucleotide_to_protein_match 418 539 210 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 28 68 +;Gap=M41 +scaffold_1 ALN nucleotide_to_protein_match 7124 7250 187 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 69 110 +;Gap=M42 +scaffold_1 ALN nucleotide_to_protein_match 7563 7595 11 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 111 121 +;Gap=M11 +scaffold_1 ALN nucleotide_to_protein_match 7659 7662 21 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 122 123 +;Gap=M2 +scaffold_1 ALN nucleotide_to_protein_match 7738 7864 21 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 124 165 +;Gap=M14 D1 M7 I2 M19 D1 +scaffold_1 ALN nucleotide_to_protein_match 7925 7957 26 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 166 176 +;Gap=M11 +scaffold_1 ALN nucleotide_to_protein_match 8295 8300 29 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 177 178 +;Gap=M2 +scaffold_1 ALN nucleotide_to_protein_match 8866 8883 31 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 179 184 +;Gap=M6 +scaffold_1 ALN nucleotide_to_protein_match 8980 8994 30 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 185 189 +;Gap=M5 +scaffold_1 ALN nucleotide_to_protein_match 9067 9077 27 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 190 193 +;Gap=M4 +scaffold_1 ALN nucleotide_to_protein_match 9976 9988 28 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 194 197 +;Gap=M4 +scaffold_1 ALN nucleotide_to_protein_match 10045 10068 27 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 198 205 +;Gap=M8 +scaffold_1 ALN nucleotide_to_protein_match 10229 10252 38 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 206 213 +;Gap=M8 +scaffold_1 ALN nucleotide_to_protein_match 10395 10418 23 + . ID=match00001;Name=scaffold_1_5;Target=NP_001121846.1 214 222 +;Gap=M5 I1 M3
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/output2.tabular Thu Jul 16 07:57:10 2020 -0400 @@ -0,0 +1,7 @@ +# rID gID %id ExonL MisMch Unpair ref_l ref_r tgt_l tgt_r eScore IntrnL iScore Sig3/I Sig5/T # - X P DiNuc +NP_001121846.1 scaffold_1 11.11 91 24 0 1 27 17 107 54.8 0 0.0 66.40 5.40 0 0 0 0 . +NP_001121846.1 scaffold_1 65.85 122 14 0 28 68 418 539 210.7 310 -20.3 17.40 8.60 0 0 0 1 GT.AG +NP_001121846.1 scaffold_1 64.29 127 15 0 69 110 7124 7250 188.0 6584 -33.9 16.50 16.90 0 0 0 0 GT.AG +NP_001121846.1 scaffold_1 28.57 147 30 0 111 152 44187 44333 28.7 36936 -44.6 10.00 9.60 0 0 0 1 GT.AG +NP_001121846.1 scaffold_1 20.55 221 52 3 153 222 44595 44815 23.4 261 -18.9 14.00 9.60 0 0 0 1 GT.AG +@ scaffold_1 + ( 17 44815 ) NP_001121846.1 222 ( 1 222 ) S: 349.5 =: 37.8 C: 98.6 T#: 135 T-: 3 B#: 0 B-: 0 X: 0 Nexn: 5
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/ncbi_taxonomy_sqlite.loc.sample Thu Jul 16 07:57:10 2020 -0400 @@ -0,0 +1,2 @@ +#This file describes the storage location for the NCBI Taxonomy SQLite database file +#<unique_name> <description> <file_path> \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Thu Jul 16 07:57:10 2020 -0400 @@ -0,0 +1,8 @@ +<?xml version="1.0"?> +<tables> + <!-- Locations of SQLite format NCBI Taxonomy database --> + <table name="ncbi_taxonomy_sqlite" comment_char="#"> + <columns>value, description, path</columns> + <file path="tool-data/ncbi_taxonomy_sqlite.loc" /> + </table> +</tables>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.test Thu Jul 16 07:57:10 2020 -0400 @@ -0,0 +1,8 @@ +<?xml version="1.0"?> +<tables> + <!-- Locations of SQLite format NCBI Taxonomy database --> + <table name="ncbi_taxonomy_sqlite" comment_char="#"> + <columns>value, description, path</columns> + <file path="${__HERE__}/test-data/ncbi_taxonomy_sqlite.loc" /> + </table> +</tables>