| Previous changeset 8:54fb02338510 (2024-03-06) Next changeset 10:8a701e0754a1 (2025-04-08) |
|
Commit message:
planemo upload for repository https://gitlab.com/paulklemm_PHD/proteinortho commit e151cf96893602bf011c27a2d91df1ef594b774d |
|
modified:
proteinortho.xml proteinortho_macros.xml |
| b |
| diff -r 54fb02338510 -r 6140163233a5 proteinortho.xml --- a/proteinortho.xml Wed Mar 06 20:44:45 2024 +0000 +++ b/proteinortho.xml Fri Dec 13 10:19:09 2024 +0000 |
| [ |
| b'@@ -99,13 +99,13 @@\n 2> >(sed -E "s/.\\[([0-9]{1,2}(;[0-9]{1,2})?)?[mGK]//g" 1>&2)\n #if $more_options.selfblast:\n &&\n- mv result.blast-graph_clean result.blast-graph;\n+ mv result.blast-graph_clean result.blast-graph\n #end if\n #if $synteny.synteny_options == "specified":\n &&\n mv result.poff-graph result.proteinortho-graph &&\n mv result.poff.tsv result.proteinortho.tsv &&\n- mv result.poff.html result.proteinortho.html ;\n+ mv result.poff.html result.proteinortho.html\n #end if\n ]]></command>\n <inputs>\n@@ -115,6 +115,8 @@\n <option value="autoblast">auto detect NCBI-BLAST (protein and nucleotide sequences)</option>\n <option value="blastp">NCBI-BLASTP+ (protein sequences)</option>\n <option value="blastn">NCBI-BLASTN+ (nucleotide sequences)</option>\n+ <option value="mmseqsp">MMseqs2 (aminoacid sequences)</option>\n+ <option value="mmseqsn">MMseqs2 (nucleotide sequences)</option>\n <option value="lastp">Last (aminoacid sequences)</option>\n <option value="lastn">Last (nucleotide sequences)</option>\n <option value="blatp">BLAT (aminoacid sequences)</option>\n@@ -126,7 +128,7 @@\n <param argument="--evalue" type="float" value="0.001" min="0" label="E-value threshold of the blast algorithm" help="Larger values results in more false positives (connections between proteins)."/>\n <param argument="--cov" type="integer" value="50" min="0" max="100" label="Minimal coverage of best blast alignments in %"/>\n <param argument="--identity" type="integer" value="25" min="0" max="100" label="Minimal percent identity of best blast hits in %"/>\n- <param argument="--selfblast" type="boolean" checked="false" truevalue="--selfblast" falsevalue="" label="Apply selfblast, detects paralogs without orthologs "/>\n+ <param argument="--selfblast" type="boolean" checked="false" truevalue="--selfblast" falsevalue="" label="Apply selfblast, detects paralogs without orthologs (not compatible with synteny) "/>\n <param argument="--singles" type="boolean" checked="false" truevalue="--singles" falsevalue="" label="Report singleton genes without any hit "/>\n <param argument="--core" type="boolean" checked="false" truevalue="--core" falsevalue="" label="Stop clustering if a split would result in groups that do not span across all species of the inital connected component." help="Overrules the -conn threshold."/>\n <param argument="--isoform" type="select" label="Use isoform information" help="The reciprocal best hit graph is built using isoform information (isoforms are treated equivalent). For ncbi : simply add the additional files to the input (file names need to match). For Uniprot : the isoforms need to contain the word isoform and the corresponding identifier. For trinity simply use the trinity output format.">\n@@ -137,7 +139,7 @@\n </param>\n </section>\n <conditional name="synteny">\n- <param name="synteny_options" type="select" label="Activate synteny feature (POFF)" help="To enhance the prediction accuracy, the relative order of genes (synteny) can be used as an additional feature for the discrimination of orthologs. For more details see doi:10.1371/journal.pone.0105015.">\n+ <param name="synteny_options" type="select" label="Activate synteny feature (POFF)" help="To enhance the prediction accuracy, the relative order of genes (synteny) can be used as an additional feature for the discrimination of orthologs. For more details see doi:10.1371/journal.pone.0105015. (Not compatible with selfblast)">\n <option value="no" selected="true">no</option>\n <option value="specified">yes</option>\n </param>\n@@ -177,7 +179,7 @@\n </data>\n </outputs>\n <tests>'..b'itself in general. \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. \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.,ecoli.faa,human.faa,snail.faa,wale.faa,ebola.faa\n+ Species,Genes,alg.-conn.,ecoli.faa,human.faa,snail.faa,wale.faa,mouse.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@@ -337,16 +349,43 @@\n \n ----\n \n-* **orthology-pairs**\n-\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+ | The first group is comprised of 5 proteins of 5 species: \'C_10\' of ecoli.faa, \'C_10;test\' of human.faa, \'E_10\' of snail.faa, \'L_10\' of wale.faa, and \'M_10\' of mouse.faa.\n+ | The alg.-conn. (algebraic connectivity) of 0.715 indicates the connectivity of this group, the higher the more edges are connecting these 5 proteins (at most there can be 10 and at least there need to be 4).\n+ | The second group contains 6 proteins distributed over 4 species. The star indicates the species where no protein was found (in this case ecoli.faa).\n \n .. csv-table::\n \n- seqidA,seqidB,evalue_ab,bitscore_ab,evalue_ba,bitscore_ba \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-pairs**\n+\n+ | Similar to orthology groups, but each edge is printed individually.\n+ | The output is formatted the same as the RBH graph.\n+ | For example extracting all hits of the second group of the example orthology-group output (\'4,6,0.115,*,C_12,E_315,L_313,M_313\') using grep (-E, regular expression="(C_12|E_315|L_313|M_313).*(C_12|E_315|L_313|M_313)", input file=proteinortho-graph) would reveal all edges of this groups:\n+\n+.. csv-table::\n+\n+ seqidA,seqidB,evalue_ab,bitscore_ab,evalue_ba,bitscore_ba \n+ M_313,C_12,1.18e-115,407,6.12e-116,407\n+ C_12,E_315,4.50e-127,445,4.09e-127,445\n+ L_313,M_313,0.00e+00,1368,0.00e+00,1368\n+ L_313,C_12,3.76e-114,402,1.94e-114,402\n+\n+----\n+\n+ | Especially L_313 and M_313 are very similar, probably identical.\n+ | The group cotnains 4 edges out of the 6 possible edges for a group of 4 proteins. The missing edges are M_313-E_315 as well as L_313-E_315. This means that E_315 is only connected to the other 3 proteins via C_12 and thus could be considered as a weak link in the group.\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 or a subset (e.g. filter by Species>10).\n@@ -354,9 +393,11 @@\n \n More information can be found on github https://gitlab.com/paulklemm_PHD/proteinortho\n \n-**Citations:**\n-\n ]]>\n </help>\n- <expand macro="citations" /> <!--- TODO: citations are not working in usegalxy, therefore they are added manually at the above. -->\n+ <citations>\n+ <citation type="doi">10.3389/fbinf.2023.1322477</citation>\n+ <citation type="doi">10.1186/1471-2105-12-124</citation>\n+ <citation type="doi">10.1371/journal.pone.0105015</citation>\n+ </citations>\n </tool>\n' |
| b |
| diff -r 54fb02338510 -r 6140163233a5 proteinortho_macros.xml --- a/proteinortho_macros.xml Wed Mar 06 20:44:45 2024 +0000 +++ b/proteinortho_macros.xml Fri Dec 13 10:19:09 2024 +0000 |
| b |
| @@ -1,15 +1,8 @@ <?xml version="1.0"?> <macros> - <token name="@TOOL_VERSION@">6.3.1</token> - <token name="@WRAPPER_VERSION@">0</token> - <token name="@PROFILE@">22.05</token> - <xml name="citations"> - <citations> - <citation type="doi">10.1186/1471-2105-12-124</citation> - <citation type="doi">10.1371/journal.pone.0105015</citation> - <citation type="doi">10.3389/fbinf.2023.1322477</citation> - </citations> - </xml> + <token name="@TOOL_VERSION@">6.3.4</token> + <token name="@WRAPPER_VERSION@">0</token> + <token name="@PROFILE@">22.05</token> <xml name="biotools"> <xrefs> <xref type="bio.tools">proteinortho</xref> @@ -22,6 +15,7 @@ <requirement type="package" version="2.15.0">blast</requirement> <requirement type="package" version="445">ucsc-blat</requirement> <requirement type="package" version="1519">last</requirement> + <requirement type="package" version="16.747c6">mmseqs2</requirement> </requirements> </xml> <xml name="version_command"> |