Mercurial > repos > iuc > proteinortho
changeset 6:fca464c2e8df draft
planemo upload for repository https://gitlab.com/paulklemm_PHD/proteinortho commit e151cf96893602bf011c27a2d91df1ef594b774d
| author | iuc |
|---|---|
| date | Fri, 13 Dec 2024 10:18:38 +0000 |
| parents | f26be779340a |
| children | 3cf3bab1562c |
| files | proteinortho.xml proteinortho_macros.xml |
| diffstat | 2 files changed, 100 insertions(+), 58 deletions(-) [+] |
line wrap: on
line diff
--- a/proteinortho.xml Fri Jun 16 20:52:09 2023 +0000 +++ b/proteinortho.xml Fri Dec 13 10:18:38 2024 +0000 @@ -2,24 +2,24 @@ <description>detects orthologous proteins/genes within different species</description> <macros> <import>proteinortho_macros.xml</import> - <xml name="test_output_proteinortho" tokens="nlines"> + <xml name="test_output_proteinortho" tokens="nlines" token_nlines_delta="0"> <output name="proteinortho"> <metadata name="column_names" value="species,genes,alg.-conn.,L.fasta,C.fasta,E.fasta,M.fasta"/> <assert_contents> <has_n_columns n="7"/> - <has_n_lines n="@NLINES@"/> + <has_n_lines n="@NLINES@" delta="@NLINES_DELTA@"/> <has_line_matching expression="# Species\tGenes\tAlg\.-Conn\.\t.*"/> <has_line_matching expression="[0-9]+\t[0-9]+\t.*"/> <has_line_matching expression=".*(C|C2|E|L|M)_[0-9]+.*"/> </assert_contents> </output> </xml> - <xml name="test_output_blastgraph" tokens="nlines"> + <xml name="test_output_blastgraph" tokens="nlines" token_nlines_delta="0"> <output name="blastgraph"> <metadata name="column_names" value="seqidA,seqidB,evalue_ab,bitscore_ab,evalue_ba,bitscore_ba"/> <assert_contents> <has_n_columns n="6" comment="#"/> - <has_n_lines n="@NLINES@"/> + <has_n_lines n="@NLINES@" delta="@NLINES_DELTA@"/> <has_line_matching expression="# file_a\tfile_b"/> <has_line_matching expression="# a\tb\tevalue_ab\tbitscore_ab\tevalue_ba\tbitscore_ba"/> <has_line_matching expression="# (C|C2|E|L|M)\.fasta\t(C|C2|E|L|M)\.fasta"/> @@ -41,6 +41,7 @@ </output> </xml> </macros> + <expand macro="biotools"/> <expand macro="requirements"/> <expand macro="version_command"/> <command detect_errors="exit_code"><![CDATA[ @@ -96,11 +97,15 @@ #end for# #end if 2> >(sed -E "s/.\[([0-9]{1,2}(;[0-9]{1,2})?)?[mGK]//g" 1>&2) + #if $more_options.selfblast: + && + mv result.blast-graph_clean result.blast-graph + #end if #if $synteny.synteny_options == "specified": && mv result.poff-graph result.proteinortho-graph && mv result.poff.tsv result.proteinortho.tsv && - mv result.poff.html result.proteinortho.html ; + mv result.poff.html result.proteinortho.html #end if ]]></command> <inputs> @@ -110,6 +115,8 @@ <option value="autoblast">auto detect NCBI-BLAST (protein and nucleotide sequences)</option> <option value="blastp">NCBI-BLASTP+ (protein sequences)</option> <option value="blastn">NCBI-BLASTN+ (nucleotide sequences)</option> + <option value="mmseqsp">MMseqs2 (aminoacid sequences)</option> + <option value="mmseqsn">MMseqs2 (nucleotide sequences)</option> <option value="lastp">Last (aminoacid sequences)</option> <option value="lastn">Last (nucleotide sequences)</option> <option value="blatp">BLAT (aminoacid sequences)</option> @@ -121,7 +128,7 @@ <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)."/> <param argument="--cov" type="integer" value="50" min="0" max="100" label="Minimal coverage of best blast alignments in %"/> <param argument="--identity" type="integer" value="25" min="0" max="100" label="Minimal percent identity of best blast hits in %"/> - <param argument="--selfblast" type="boolean" checked="false" truevalue="--selfblast" falsevalue="" label="Apply selfblast, detects paralogs without orthologs "/> + <param argument="--selfblast" type="boolean" checked="false" truevalue="--selfblast" falsevalue="" label="Apply selfblast, detects paralogs without orthologs (not compatible with synteny) "/> <param argument="--singles" type="boolean" checked="false" truevalue="--singles" falsevalue="" label="Report singleton genes without any hit "/> <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."/> <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."> @@ -132,7 +139,7 @@ </param> </section> <conditional name="synteny"> - <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."> + <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)"> <option value="no" selected="true">no</option> <option value="specified">yes</option> </param> @@ -172,16 +179,26 @@ </data> </outputs> <tests> - <test expect_num_outputs="3"> <!-- test normal --> + <test expect_num_outputs="3"> <!-- test normal / default params --> <param name="input_files" value="L.fasta,C.fasta,E.fasta,M.fasta"/> <param name="p" value="diamond"/> - <expand macro="test_output_proteinortho" nlines="34"/> - <expand macro="test_output_blastgraph" nlines="157"/> - <expand macro="test_output_proteinorthograph" nlines="134"/> + <expand macro="test_output_proteinortho" nlines="33" nlines_delta="5"/> + <expand macro="test_output_blastgraph" nlines="156" nlines_delta="20"/> + <expand macro="test_output_proteinorthograph" nlines="139" nlines_delta="20"/> <assert_command> <has_text text="--p=diamond"/> </assert_command> </test> + <test expect_num_outputs="3"> <!-- test normal mmseqs --> + <param name="input_files" value="L.fasta,C.fasta,E.fasta,M.fasta"/> + <param name="p" value="mmseqsp"/> + <expand macro="test_output_proteinortho" nlines="33" nlines_delta="5"/> + <expand macro="test_output_blastgraph" nlines="156" nlines_delta="20"/> + <expand macro="test_output_proteinorthograph" nlines="139" nlines_delta="20"/> + <assert_command> + <has_text text="--p=mmseqsp"/> + </assert_command> + </test> <test expect_num_outputs="3"> <!-- various parameter --> <param name="input_files" value="L.fasta,C.fasta,E.fasta,M.fasta"/> <param name="p" value="diamond"/> @@ -190,13 +207,12 @@ <section name="more_options"> <param name="cov" value="42"/> <param name="identity" value="42"/> - <param name="selfblast" value="true"/> <param name="singles" value="true"/> <param name="core" value="true"/> </section> - <expand macro="test_output_proteinortho" nlines="177"/> - <expand macro="test_output_blastgraph" nlines="2720"/> - <expand macro="test_output_proteinorthograph" nlines="384"/> + <expand macro="test_output_proteinortho" nlines="151" nlines_delta="50"/> + <expand macro="test_output_blastgraph" nlines="1403" nlines_delta="300"/> + <expand macro="test_output_proteinorthograph" nlines="239" nlines_delta="150"/> <assert_command> <has_text text="--p=diamond"/> </assert_command> @@ -208,8 +224,8 @@ <conditional name="synteny"> <param name="synteny_options" value="specified"/> </conditional> - <expand macro="test_output_proteinortho" nlines="38"/> - <expand macro="test_output_blastgraph" nlines="157"/> + <expand macro="test_output_proteinortho" nlines="38" nlines_delta="20"/> + <expand macro="test_output_blastgraph" nlines="300" nlines_delta="150"/> <expand macro="test_output_proteinorthograph" nlines="119" nlines_delta="10" ncolumns="8" add_columns=",same_strand,simscore"/> <assert_command> <has_text text="--p=diamond"/> @@ -218,9 +234,9 @@ <test expect_num_outputs="3"> <!-- blast --> <param name="input_files" value="L.fasta,C.fasta,E.fasta,M.fasta"/> <param name="p" value="blastp"/> - <expand macro="test_output_proteinortho" nlines="32"/> - <expand macro="test_output_blastgraph" nlines="158"/> - <expand macro="test_output_proteinorthograph" nlines="142"/> + <expand macro="test_output_proteinortho" nlines="33" nlines_delta="20"/> + <expand macro="test_output_blastgraph" nlines="155" nlines_delta="50"/> + <expand macro="test_output_proteinorthograph" nlines="139" nlines_delta="50"/> <assert_command> <has_text text="--p=blastp"/> </assert_command> @@ -228,9 +244,9 @@ <test expect_num_outputs="3"> <!-- auto blast --> <param name="input_files" value="L.fasta,C.fasta,E.fasta,M.fasta"/> <param name="p" value="autoblast"/> - <expand macro="test_output_proteinortho" nlines="32"/> - <expand macro="test_output_blastgraph" nlines="158"/> - <expand macro="test_output_proteinorthograph" nlines="142"/> + <expand macro="test_output_proteinortho" nlines="33" nlines_delta="20"/> + <expand macro="test_output_blastgraph" nlines="157" nlines_delta="50"/> + <expand macro="test_output_proteinorthograph" nlines="136" nlines_delta="50"/> <assert_command> <has_text text="--p=autoblast"/> </assert_command> @@ -238,21 +254,21 @@ <test expect_num_outputs="3"> <!-- last --> <param name="input_files" value="L.fasta,C.fasta,E.fasta,M.fasta"/> <param name="p" value="lastp"/> - <expand macro="test_output_proteinortho" nlines="34"/> - <expand macro="test_output_blastgraph" nlines="148"/> - <expand macro="test_output_proteinorthograph" nlines="133"/> + <expand macro="test_output_proteinortho" nlines="34" nlines_delta="20"/> + <expand macro="test_output_blastgraph" nlines="148" nlines_delta="50"/> + <expand macro="test_output_proteinorthograph" nlines="134" nlines_delta="50"/> <assert_command> <has_text text="--p=lastp"/> </assert_command> </test> <test expect_num_outputs="3"> <!-- blat --> <param name="input_files" value="L.fasta,C.fasta,E.fasta,M.fasta"/> - <param name="p" value="blastp"/> - <expand macro="test_output_proteinortho" nlines="32"/> - <expand macro="test_output_blastgraph" nlines="158"/> - <expand macro="test_output_proteinorthograph" nlines="142"/> + <param name="p" value="blatp"/> + <expand macro="test_output_proteinortho" nlines="33" nlines_delta="20"/> + <expand macro="test_output_blastgraph" nlines="56" nlines_delta="50"/> + <expand macro="test_output_proteinorthograph" nlines="56" nlines_delta="50"/> <assert_command> - <has_text text="--p=blastp"/> + <has_text text="--p=blatp"/> </assert_command> </test> </tests> @@ -264,7 +280,7 @@ | It compares similarities of given gene/protein sequences and clusters them to find significant groups. | The algorithm was designed to handle large-scale data and can be applied to hundreds of species at once. - | Details can be found in (doi:10.1186/1471-2105-12-124). + | Details can be found in (doi:10.1186/1471-2105-12-124 and doi:10.3389/fbinf.2023.1322477). | To enhance the prediction accuracy, the relative order of genes (synteny) can be used as an additional feature for the discrimination of orthologs. The corresponding extension, namely PoFF (details see doi:10.1371/journal.pone.0105015), is already built in Proteinortho. ---- @@ -281,8 +297,8 @@ * **(ii) Cluster the RBH** - | Using two clustering algorithms, edges are removed that weakly connect two connected components to reduce false positive hits. - | The resulting connected components are outputted in orthology-groups / -pairs + | A spectral clustering algorithm is used to remove weak connections, reducing false positives. + | The connected components from this process are output as orthology groups or pairs. ---- @@ -318,14 +334,14 @@ | The result of the (ii) step, the clustered reciprocal best hit graph or the orthology groups. | Every line corresponds to an orthology group. - | 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. + | 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. | Then a column for each species follows containing the proteins of these species. | If a species contributes with more than one protein to a group of orthologs, then they are ordered by descending connectivity. | The '*' represents that this species does not contribute to the group. .. csv-table:: - Species,Genes,alg.-conn.,ecoli.faa,human.faa,snail.faa,wale.faa,ebola.faa + Species,Genes,alg.-conn.,ecoli.faa,human.faa,snail.faa,wale.faa,mouse.faa 5,5,0.715,C_10,C_10;test,E_10,L_10,M_10 4,6,0.115,*,C_12,E_315,L_313,M_313 4,5,0.167,*,C_63,E_19,L_19,M_19 @@ -333,16 +349,43 @@ ---- -* **orthology-pairs** - - | 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: + | 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. + | 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). + | 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). .. csv-table:: - seqidA,seqidB,evalue_ab,bitscore_ab,evalue_ba,bitscore_ba + seqidA,seqidB,evalue_ab,bitscore_ab,evalue_ba,bitscore_ba + # ecoli.faa,human.faa + # 1.91e-112,357.5,1.825e-113,360 + L_10,C_10;test,4.32e-151,447,4.30e-151,446 + L_11,C_11,1.17e-68,209,3.00e-69,210 + L_14,C_14,3.64e-139,422,1.19e-142,431 + L_15,C_15,3.51e-100,303,2.12e-102,308 + L_16,C_16,3.75e-49,157,7.06e-50,159 + L_17,C_17,2.96e-195,578,5.50e-196,579 ---- +* **orthology-pairs** + + | Similar to orthology groups, but each edge is printed individually. + | The output is formatted the same as the RBH graph. + | 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: + +.. csv-table:: + + seqidA,seqidB,evalue_ab,bitscore_ab,evalue_ba,bitscore_ba + M_313,C_12,1.18e-115,407,6.12e-116,407 + C_12,E_315,4.50e-127,445,4.09e-127,445 + L_313,M_313,0.00e+00,1368,0.00e+00,1368 + L_313,C_12,3.76e-114,402,1.94e-114,402 + +---- + + | Especially L_313 and M_313 are very similar, probably identical. + | 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. + **Proteinortho-Tools for downstream analysis** * `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). @@ -350,12 +393,11 @@ More information can be found on github https://gitlab.com/paulklemm_PHD/proteinortho -**Citations:** - -- 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) -- 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) - ]]> </help> - <expand macro="citations" /> <!--- TODO: citations are not working in usegalxy, therefore they are added manually at the above. --> + <citations> + <citation type="doi">10.3389/fbinf.2023.1322477</citation> + <citation type="doi">10.1186/1471-2105-12-124</citation> + <citation type="doi">10.1371/journal.pone.0105015</citation> + </citations> </tool>
--- a/proteinortho_macros.xml Fri Jun 16 20:52:09 2023 +0000 +++ b/proteinortho_macros.xml Fri Dec 13 10:18:38 2024 +0000 @@ -1,21 +1,21 @@ <?xml version="1.0"?> <macros> - <token name="@TOOL_VERSION@">6.2.3</token> - <token name="@WRAPPER_VERSION@">1</token> - <token name="@PROFILE@">20.09</token> - <xml name="citations"> - <citations> - <citation type="doi">10.1186/1471-2105-12-124</citation> - <citation type="doi">10.1371/journal.pone.0105015</citation> - </citations> + <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> + </xrefs> </xml> <xml name="requirements"> <requirements> <requirement type="package" version="@TOOL_VERSION@">proteinortho</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="1422">last</requirement> + <requirement type="package" version="2.1.8">diamond</requirement> + <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">