| Previous changeset 4:85c411546123 (2022-11-22) Next changeset 6:10112d9127af (2023-10-31) |
|
Commit message:
planemo upload for repository https://gitlab.com/paulklemm_PHD/proteinortho commit b4d8b8da2a259973c9ad90e4b9d1a3e22ae4348f |
|
modified:
proteinortho.xml proteinortho_macros.xml |
| b |
| diff -r 85c411546123 -r 5532c0e5d4a6 proteinortho.xml --- a/proteinortho.xml Tue Nov 22 16:49:50 2022 +0000 +++ b/proteinortho.xml Fri Jun 16 20:52:41 2023 +0000 |
| [ |
| b'@@ -2,24 +2,37 @@\n <description>detects orthologous proteins/genes within different species</description>\n <macros>\n <import>proteinortho_macros.xml</import>\n- <xml name="test_outputs">\n+ <xml name="test_output_proteinortho" tokens="nlines">\n <output name="proteinortho">\n+ <metadata name="column_names" value="species,genes,alg.-conn.,L.fasta,C.fasta,E.fasta,M.fasta"/>\n <assert_contents>\n+ <has_n_columns n="7"/>\n+ <has_n_lines n="@NLINES@"/>\n <has_line_matching expression="# Species\\tGenes\\tAlg\\.-Conn\\.\\t.*"/>\n <has_line_matching expression="[0-9]+\\t[0-9]+\\t.*"/>\n <has_line_matching expression=".*(C|C2|E|L|M)_[0-9]+.*"/>\n </assert_contents>\n </output>\n+ </xml>\n+ <xml name="test_output_blastgraph" tokens="nlines">\n <output name="blastgraph">\n+ <metadata name="column_names" value="seqidA,seqidB,evalue_ab,bitscore_ab,evalue_ba,bitscore_ba"/>\n <assert_contents>\n+ <has_n_columns n="6" comment="#"/>\n+ <has_n_lines n="@NLINES@"/>\n <has_line_matching expression="# file_a\\tfile_b"/>\n <has_line_matching expression="# a\\tb\\tevalue_ab\\tbitscore_ab\\tevalue_ba\\tbitscore_ba"/>\n <has_line_matching expression="# (C|C2|E|L|M)\\.fasta\\t(C|C2|E|L|M)\\.fasta"/>\n <has_line_matching expression=".*(C|C2|E|L|M)_[0-9]+\\t(C|C2|E|L|M)_[0-9]+.*"/>\n </assert_contents>\n </output>\n+ </xml>\n+ <xml name="test_output_proteinorthograph" tokens="nlines" token_nlines_delta="0" token_add_columns="" token_ncolumns="6">\n <output name="proteinorthograph">\n+ <metadata name="column_names" value="seqidA,seqidB,evalue_ab,bitscore_ab,evalue_ba,bitscore_ba@ADD_COLUMNS@"/>\n <assert_contents>\n+ <has_n_columns n="@NCOLUMNS@" comment="#"/>\n+ <has_n_lines n="@NLINES@" delta="@NLINES_DELTA@"/>\n <has_line_matching expression="# file_a\\tfile_b"/>\n <has_line_matching expression="# a\\tb\\tevalue_ab\\tbitscore_ab\\tevalue_ba\\tbitscore_ba(\\tsame_strand\\tsimscore)?"/>\n <has_line_matching expression="# (C|C2|E|L|M)\\.fasta\\t(C|C2|E|L|M)\\.fasta"/>\n@@ -44,21 +57,23 @@\n proteinortho \n --project=result\n --cpus="\\${GALAXY_SLOTS:-4}"\n- --ram="\\${GALAXY_MEMORY_MB:-16000}"\n #if $more_options.selfblast:\n $more_options.selfblast\n #end if\n #if $more_options.singles:\n $more_options.singles\n #end if\n+ #if $more_options.core:\n+ $more_options.core\n+ #end if\n --p=$p\n- --e=$evalue\n+ --e=$more_options.evalue\n --conn=$conn\n #if $more_options.cov:\n --cov=$more_options.cov\n #end if\n- #if $more_options.sim:\n- --sim=`LC_NUMERIC=C awk "BEGIN {printf \\"%.2f\\",$more_options.sim/100}"`\n+ #if $sim:\n+ --sim=`LC_NUMERIC=C awk "BEGIN {printf \\"%.2f\\",$sim/100}"`\n #end if\n #if $more_options.identity:\n --cov=$more_options.identity\n@@ -100,15 +115,16 @@\n <option value="blatp">BLAT (aminoacid sequences)</option>\n <option value="blatn">BLAT (nucleotide sequences)</option>\n </param>\n- <param argument="--evalue" type="float" value="0.001" min="0" label="E-value threshold of the blast algorithm" help="This is the main parameter for the generation of the reciprocal best hit graph. Larger values results in more false positives (connections between proteins)."/>\n- <param argument="--conn" type="float" value="0.1'..b'owing these header lines, each line corresponds to a reciprocal best hit of 2 proteins/genes (columns 1 and 2) of the announced species. The output format is shown below.\n | *seqidA*,*seqidB* = the 2 ids/names of the proteins involved \n | *evalue_ab* = evalue with seqidA as query and seqidB as part of the database \n | *bitscore_ab* = bitscore with seqidA as query ...\n | *evalue_ba* = evalue with seqidB as query ...\n- | ...\n \n .. csv-table::\n \n seqidA,seqidB,evalue_ab,bitscore_ab,evalue_ba,bitscore_ba \n+ # ecoli.faa,human.faa\n+ # 1.91e-112,357.5,1.825e-113,360\n+ L_10,C_10;test,4.32e-151,447,4.30e-151,446\n+ L_11,C_11,1.17e-68,209,3.00e-69,210\n+ L_14,C_14,3.64e-139,422,1.19e-142,431\n+ L_15,C_15,3.51e-100,303,2.12e-102,308\n+ L_16,C_16,3.75e-49,157,7.06e-50,159\n+ L_17,C_17,2.96e-195,578,5.50e-196,579\n \n ----\n \n * **orthology-groups**\n \n | The result of the (ii) step, the clustered reciprocal best hit graph or the orthology groups.\n- | Every line corresponds to an orthology group of proteins/genes. \n- | The first 3 columns characterize general properties of that group: number of proteins, species and the algebraic connectivity. The higher the algebraic connectivity the more edges are there and the better the group is connected to itself in general. \n- | Then a column for each species follows containing the proteins of that species. If a species contributes with more than one protein to a group of orthologs, then they are ordered by connectivity.\n+ | Every line corresponds to an orthology group. \n+ | The first 3 columns characterize the general properties of that group: number of proteins, species, and algebraic connectivity. The higher the algebraic connectivity the more edges are there and the better the group is connected to itself in general. \n+ | Then a column for each species follows containing the proteins of these species. \n+ | If a species contributes with more than one protein to a group of orthologs, then they are ordered by descending connectivity.\n+ | The \'*\' represents that this species does not contribute to the group.\n \n .. csv-table::\n \n- Species,Genes,Alg.-Conn. \n+ Species,Genes,alg.-conn.,ecoli.faa,human.faa,snail.faa,wale.faa,ebola.faa\n+ 5,5,0.715,C_10,C_10;test,E_10,L_10,M_10\n+ 4,6,0.115,*,C_12,E_315,L_313,M_313\n+ 4,5,0.167,*,C_63,E_19,L_19,M_19\n+ 4,4,0.816,*,C_64,E_18,L_18,M_18\n \n ----\n \n * **orthology-pairs**\n \n- | The same as orthology-groups but every edge is printed one-by-one here. The output is formatted the same as the RBH graph:\n+ | The same as orthology-groups but every edge is printed one-by-one instead of the whole group. The output is formatted the same as the RBH graph:\n \n .. csv-table::\n \n@@ -273,11 +345,17 @@\n \n **Proteinortho-Tools for downstream analysis**\n \n-* `proteinortho grab proteins` : find gene(s)/protein(s) in a given fasta file and retrieve their sequence(s). You can also use a orthology-groups file.\n+* `proteinortho grab proteins` : find gene(s)/protein(s) in a given fasta file and retrieve their sequence(s). You can also use a orthology-groups file or a subset (e.g. filter by Species>10).\n * `proteinortho summary` : Summaries the orthology-pairs/RBH files to determine how the species are connected to each other.\n \n More information can be found on github https://gitlab.com/paulklemm_PHD/proteinortho\n+\n+**Citations:**\n+\n+- Lechner, Marcus, et al. "Proteinortho: detection of (co-) orthologs in large-scale analysis." BMC bioinformatics 12.1 (2011): 1-9. (10.1186/1471-2105-12-124) \n+- Lechner, Marcus, et al. "Orthology detection combining clustering and synteny for very large datasets." PLoS one 9.8 (2014): e105015. (10.1371/journal.pone.0105015)\n+\n ]]>\n </help>\n- <expand macro="citations"/>\n+ <expand macro="citations" /> <!--- TODO: citations are not working in usegalxy, therefore they are added manually at the above. -->\n </tool>\n' |
| b |
| diff -r 85c411546123 -r 5532c0e5d4a6 proteinortho_macros.xml --- a/proteinortho_macros.xml Tue Nov 22 16:49:50 2022 +0000 +++ b/proteinortho_macros.xml Fri Jun 16 20:52:41 2023 +0000 |
| b |
| @@ -1,6 +1,6 @@ <?xml version="1.0"?> <macros> - <token name="@TOOL_VERSION@">6.1.2</token> + <token name="@TOOL_VERSION@">6.2.3</token> <token name="@WRAPPER_VERSION@">1</token> <token name="@PROFILE@">20.09</token> <xml name="citations"> @@ -12,12 +12,10 @@ <xml name="requirements"> <requirements> <requirement type="package" version="@TOOL_VERSION@">proteinortho</requirement> - <!-- blast, blat, and last are not in the biopython requirements - diamond is, but latest version does not work: https://gitlab.com/paulklemm_PHD/proteinortho/-/issues/55 --> - <requirement type="package" version="2.0.15">diamond</requirement> + <requirement type="package" version="2.1.4">diamond</requirement> <requirement type="package" version="2.13.0">blast</requirement> <requirement type="package" version="377">ucsc-blat</requirement> - <requirement type="package" version="1418">last</requirement> + <requirement type="package" version="1422">last</requirement> </requirements> </xml> <xml name="version_command"> |