| Previous changeset 26:5b8e15b2a67c (2022-10-26) Next changeset 28:896eb8ae1c8c (2022-10-27) |
|
Commit message:
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit be6750cb1d7ae18e71b60ae6f2c55e5331105c4f |
|
modified:
macros.xml |
|
added:
elm_networkin_psp_uniprot_lut.tabular kinase_metadata.sql kseaapp_demo.R phosphoelm_kinase_upid_desc.lut run_planemo_test.sh run_r_linter.R shed.yml |
| b |
| diff -r 5b8e15b2a67c -r 2e35f925c469 elm_networkin_psp_uniprot_lut.tabular --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/elm_networkin_psp_uniprot_lut.tabular Thu Oct 27 18:54:25 2022 +0000 |
| b |
| b"@@ -0,0 +1,446 @@\n+UniProtID\tAccessions\tkinase\tnetworkin_id\tpsp_id\tnetphorest_group\tECs\tgene_names\tDescriptions\n+A9UF07_HUMAN\tA9UF07\tBCR-ABL1 (PSP)\t\tBCR-ABL1\t\t\tBCR/ABL fusion\t2.7.10.2;Non-specific protein-tyrosine kinase\n+AAK1_HUMAN\tQ2M2I8\tAAK1\tAAK1\tAAK1\t\t2.7.11.1\tAAK1;KIAA1048\t2.7.11.1;AP2-associated protein kinase 1;Adaptor-associated kinase 1\n+AAKB1_HUMAN\tQ9Y478\tAMPKB1 (PSP)\t\tAMPKB1\t\t\tPRKAB1;AMPK\t5'-AMP-activated protein kinase subunit beta-1;AMPK subunit beta-1;AMPKb\n+AAKG2_HUMAN\tQ9UGJ0\tAMPKG2 (PSP)\t\tAMPKG2\t\t\tPRKAG2\t5'-AMP-activated protein kinase subunit gamma-2;AMPK gamma2;AMPK subunit gamma-2;H91620p;Isoform C of 5'-AMP-activated protein kinase subunit gamma-2\n+AAPK1_HUMAN\tQ13131\tAMPK_group\tAMPKa1\tAMPKA1\tAMPK_group\t2.7.11.1;2.7.11.26;2.7.11.27;2.7.11.31\tPRKAA1;AMPK1\t2.7.11.1;2.7.11.26;5'-AMP-activated protein kinase catalytic subunit alpha-1;AMPK subunit alpha-1;Acetyl-CoA carboxylase kinase;ACACA kinase;2.7.11.27;Hydroxymethylglutaryl-CoA reductase kinase;HMGCR kinase;2.7.11.31;Tau-protein kinase PRKAA1;Isoform 2 of 5'-AMP-activated protein kinase catalytic subunit alpha-1\n+AAPK2_HUMAN\tP54646\tAMPK_group\tAMPKa2\tAMPKA2\tAMPK_group\t2.7.11.1;2.7.11.27;2.7.11.31\tAMPK;PRKAA2;AMPK2\t2.7.11.1;Acetyl-CoA carboxylase kinase;ACACA kinase;2.7.11.27;Hydroxymethylglutaryl-CoA reductase kinase;HMGCR kinase;2.7.11.31;5'-AMP-activated protein kinase catalytic subunit alpha-2;AMPK subunit alpha-2\n+ABL1_HUMAN\tP00519\tAbl\tAbl\tAbl\tAbl_group\t2.7.10.2\tABL1;ABL;JTK7\t2.7.10.2;Tyrosine-protein kinase ABL1;Abelson murine leukemia viral oncogene homolog 1;Abelson tyrosine-protein kinase 1;Proto-oncogene c-Abl;p150\n+ABL2_HUMAN\tP42684\tAbl2\tAbl2\tArg\tAbl_group\t2.7.10.2\tARG;ABL2;ABLL\tEC 2.7.10.2;Tyrosine-protein kinase ABL2;Abelson murine leukemia viral oncogene homolog 2;Abelson tyrosine-protein kinase 2;Abelson-related gene protein;Tyrosine-protein kinase ARG\n+ACK1_HUMAN\tQ07912\tTNK2\tTNK2\tAck\t\t2.7.10.2;2.7.11.1\tTNK2;ACK1\t2.7.11.1;2.7.10.2;Activated CDC42 kinase 1;ACK-1;Tyrosine kinase non-receptor protein 2\n+ACV1B_HUMAN\tP36896\tALK4 (PSP)\t\tALK4\t\t2.7.11.30\tACVR1B;ACVRLK4;ALK4\tEC 2.7.11.30;Activin receptor type-1B;Activin receptor type IB;ACTR-IB;Activin receptor-like kinase 4;ALK-4;Serine/threonine-protein kinase receptor R2;SKR2;Isoform 5 of Activin receptor type-1B\n+ACVL1_HUMAN\tP37023\tALK1 (PSP)\t\tALK1\t\t2.7.11.30\tACVRL1;ACVRLK1;ALK1\tEC 2.7.11.30;TGF-B superfamily receptor type I;TSR-I;Serine/threonine-protein kinase receptor R3;SKR3;Activin receptor-like kinase 1;ALK-1\n+ADCK5_HUMAN\tQ3MIX3\tADCK5 (PSP)\t\tADCK5\t\t\tADCK5\tUncharacterized aarF domain-containing protein kinase 5;2.7.11.-\n+AKT1_HUMAN\tP31749\tPKBalpha (NetworKIN)\tPKBalpha\tAkt1\tPKB_group\t2.7.11.1\tAKT1;PKB;RAC\t2.7.11.1;PKB;RAC-alpha serine/threonine-protein kinase;Protein kinase B;Protein kinase B alpha;PKB alpha;Proto-oncogene c-Akt;RAC-PK-alpha;Isoform 2 of RAC-alpha serine/threonine-protein kinase\n+AKT2_HUMAN\tP31751\tPKB_beta\tPKBbeta\tAkt2\tPKB_group\t2.7.11.1\tAKT2\tEC 2.7.11.1;RAC-beta serine/threonine-protein kinase;Protein kinase Akt-2;Protein kinase B beta;PKB beta;RAC-PK-beta;Isoform 2 of RAC-beta serine/threonine-protein kinase\n+AKT3_HUMAN\tQ9Y243\tPKB_group\tPKBgamma\tAkt3\tPKB_group\t2.7.11.1\tAKT3;PKBG\tEC 2.7.11.1;RAC-gamma serine/threonine-protein kinase;Protein kinase Akt-3;Protein kinase B gamma;PKB gamma;RAC-PK-gamma;STK-2;Isoform 2 of RAC-gamma serine/threonine-protein kinase\n+ALK_HUMAN\tQ9UM73\tALK\tALK\tALK\t\t2.7.10.1\tALK\t2.7.10.1;ALK tyrosine kinase receptor;Anaplastic lymphoma kinase;CD246\n+ALPK1_HUMAN\tQ96QP1\tAlphaK3 (PSP)\t\tAlphaK3\t\t2.7.11.1\tALPK1;KIAA1527;LAK\t2.7.11.1;Alpha-protein kinase 1;Chromosome 4 kinase;Lymphocyte alpha-protein kinase;Isoform 2 of Alpha-protein kinase 1\n+ALPK3_HUMAN\tQ96L96\tMAK (NetworKIN)\tMAK\t\tRCK_group\t2.7.11.1\tALPK3;KIAA1330;MAK\t2.7.11.1;Alpha-protein kinase 3;Muscle alpha-protein kinase\n+ARAF_HUMAN\tP10398\tARAF (NetworKIN)\tARAF\tARAF\tARAF_BRAF_RAF1_group\t2.7.11.1\tARAF;ARAF1;PKS;PKS2\tEC 2.7.11.1;Serine/threonine-protein kinase A-Raf;Proto-oncogene A-Raf;Proto-oncogene A-R"..b'n kinase;PYT;Isoform 2 of Dual specificity protein kinase TTK\n+TXK_HUMAN\tP42681\tTXK\tTXK\tTXK\tTec_group\t2.7.10.2\tTXK;PTK4;RLK\t2.7.10.2;Tyrosine-protein kinase TXK;Protein-tyrosine kinase 4;Resting lymphocyte kinase\n+TYK2_HUMAN\tP29597\tTyk2\tTyk2\tTyk2\tTyk2\t2.7.10.2\tTYK2\t2.7.10.2;Non-receptor tyrosine-protein kinase TYK2\n+TYRO3_HUMAN\tQ06418\tTyro3 (PSP)\t\tTyro3\t\t2.7.10.1\tTYRO3;BYK;DTK;RSE;SKY;TIF\tEC 2.7.10.1;Tyrosine-protein kinase receptor TYRO3;Tyrosine-protein kinase BYK;Tyrosine-protein kinase DTK;Tyrosine-protein kinase RSE;Tyrosine-protein kinase SKY;Tyrosine-protein kinase TIF\n+UFO_HUMAN\tP30530\tAxl\tAxl\tAXL\t\t2.7.10.1\tAXL;UFO\t2.7.10.1;Tyrosine-protein kinase receptor UFO;AXL oncogene\n+UHMK1_HUMAN\tQ8TAS1\tKIS\tKIS\tKIS\t\t2.7.11.1\tUHMK1;KIS;KIST\tEC 2.7.11.1;Serine/threonine-protein kinase Kist;Kinase interacting with stathmin;PAM COOH-terminal interactor protein 2;P-CIP2;U2AF homology motif kinase 1\n+ULK1_HUMAN\tO75385\tULK1 (PSP)\t\tULK1\t\t2.7.11.1\tULK1;KIAA0722\t2.7.11.1;Serine/threonine-protein kinase ULK1;Autophagy-related protein 1 homolog;ATG1;hATG1;Unc-51-like kinase 1\n+ULK2_HUMAN\tQ8IYT8\tULK2 (PSP)\t\tULK2\t\t2.7.11.1\tULK2;KIAA0623\tEC 2.7.11.1;Serine/threonine-protein kinase ULK2;Unc-51-like kinase 2\n+ULK3_HUMAN\tQ6PHR2\tULK3 (PSP)\t\tULK3\t\t2.7.11.1\tULK3\tEC 2.7.11.1;Serine/threonine-protein kinase ULK3;Unc-51-like kinase 3;Isoform 4 of Serine/threonine-protein kinase ULK3\n+VGFR1_HUMAN\tP17948\tFLT1\tFLT1\tVEGFR1\tKDR_FLT1_group\t2.7.10.1\tFLT1;FLT;FRT;VEGFR1\tEC 2.7.10.1;FLT;Vascular endothelial growth factor receptor 1;VEGFR-1;Fms-like tyrosine kinase 1;FLT-1;Tyrosine-protein kinase FRT;Tyrosine-protein kinase receptor FLT;Vascular permeability factor receptor\n+VGFR2_HUMAN\tP35968\tKDR\tKDR\tVEGFR2\tKDR_FLT1_group\t2.7.10.1\tKDR;FLK1;VEGFR2\t2.7.10.1;Vascular endothelial growth factor receptor 2;VEGFR-2;Fetal liver kinase 1;FLK-1;Kinase insert domain receptor;KDR;Protein-tyrosine kinase receptor flk-1;CD309;Isoform 2 of Vascular endothelial growth factor receptor 2\n+VGFR3_HUMAN\tP35916\tFLT4\tFLT4\t\t\t2.7.10.1\tFLT4;VEGFR3\tEC 2.7.10.1;Vascular endothelial growth factor receptor 3;VEGFR-3;Fms-like tyrosine kinase 4;FLT-4;Tyrosine-protein kinase receptor FLT4\n+VRK1_HUMAN\tQ99986\tVRK1\tVRK1\tVRK1\t\t2.7.11.1\tVRK1\t2.7.11.1;Serine/threonine-protein kinase VRK1;Vaccinia-related kinase 1\n+VRK2_HUMAN\tQ86Y07\tVRK2 (PSP)\t\tVRK2\t\t2.7.11.1\tVRK2\t2.7.11.1;Serine/threonine-protein kinase VRK2;Vaccinia-related kinase 2\n+VRK3_HUMAN\tQ8IV63\tVRK3 (PSP)\t\tVRK3\t\t\tVRK3\tInactive serine/threonine-protein kinase VRK3;Serine/threonine-protein pseudokinase VRK3;Vaccinia-related kinase 3\n+WEE1_HUMAN\tP30291\tWEE1\tWEE1\tWee1\t\t2.7.10.2\tWEE1\tEC 2.7.10.2;Wee1-like protein kinase;WEE1hu;Wee1A kinase\n+WNK1_HUMAN\tQ9H4A3\tWNK1\tWNK1\tWNK1\t\t2.7.11.1\tWNK1;HSN2;KDP;KIAA0344;PRKWNK1\t2.7.11.1;p65;Serine/threonine-protein kinase WNK1;Erythrocyte 65 kDa protein;Kinase deficient protein;Protein kinase lysine-deficient 1;Protein kinase with no lysine 1;hWNK1;Isoform 6 of Serine/threonine-protein kinase WNK1\n+WNK2_HUMAN\tQ9Y3S1\tWNK2 (PSP)\t\tWNK2\t\t2.7.11.1\tWNK2;KIAA1760;P/OKcl.13\t2.7.11.1;Serine/threonine-protein kinase WNK2;Antigen NY-CO-43;Protein kinase lysine-deficient 2;Protein kinase with no lysine 2;Serologically defined colon cancer antigen 43;Isoform 2 of Serine/threonine-protein kinase WNK2\n+WNK3_HUMAN\tQ9BYP7\tWNK3 (PSP)\t\tWNK3\t\t2.7.11.1\tWNK3;KIAA1566;PRKWNK3\t2.7.11.1;Serine/threonine-protein kinase WNK3;Protein kinase lysine-deficient 3;Protein kinase with no lysine 3\n+WNK4_HUMAN\tQ96J92\tWNK4 (PSP)\t\tWNK4\t\t2.7.11.1\tWNK4;PRKWNK4\t2.7.11.1;Serine/threonine-protein kinase WNK4;Protein kinase lysine-deficient 4;Protein kinase with no lysine 4;Isoform 2 of Serine/threonine-protein kinase WNK4\n+YES_HUMAN\tP07947\tYes\tYes\tYes\tSrc_group\t2.7.10.2\tYES1;YES\tEC 2.7.10.2;Tyrosine-protein kinase Yes;Proto-oncogene c-Yes;p61-Yes\n+ZAP70_HUMAN\tP43403\tZAP70\tZAP70\tZAP70\t\t2.7.10.2\tZAP70;SRK\tEC 2.7.10.2;Tyrosine-protein kinase ZAP-70;70 kDa zeta-chain associated protein;Syk-related tyrosine kinase;Isoform 3 of Tyrosine-protein kinase ZAP-70\n' |
| b |
| diff -r 5b8e15b2a67c -r 2e35f925c469 kinase_metadata.sql --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/kinase_metadata.sql Thu Oct 27 18:54:25 2022 +0000 |
| b |
| @@ -0,0 +1,209 @@ +-- add the 'Phosida' site-type name, probably with id 4 +INSERT INTO site_type(type_name) VALUES ('Phosida') +; +-- eliminate the table that's about to be defined +DROP TABLE IF EXISTS site_metadata +; +-- define the site_metadata table +CREATE TABLE site_metadata( + id INTEGER PRIMARY KEY +, site_type_id INTEGER REFERENCES site_type(id) +, full TEXT UNIQUE ON CONFLICT IGNORE +, abbrev TEXT +, pattern TEXT +, motif TEXT +) +; +-- populate the table with initial values +INSERT INTO site_metadata(full, abbrev, site_type_id) + SELECT DISTINCT kinase_map, kinase_map, site_type_id + FROM ppep_gene_site + ORDER BY kinase_map + ; +-- change site_type_id to Phosida where appropriate +WITH phoo(id) AS ( + SELECT id + FROM site_type + WHERE type_name = 'Phosida' +) +UPDATE site_metadata + SET site_type_id = (SELECT id FROM phoo) + WHERE abbrev LIKE '%_Phosida%' + ; +-- fix messy prefixes due to compound HPRD/Phosida +WITH src(id, abbrev) AS ( + WITH RECURSIVE split(id, content, last, rest) AS ( + SELECT id, '', '', full + FROM site_metadata + WHERE site_type_id = ( + SELECT id + FROM site_type + WHERE type_name = 'Phosida' + ) + AND abbrev LIKE '%(HPRD)%' + UNION ALL + SELECT + id, + CASE + WHEN last = '&' + THEN + substr(rest, 1, 1) + ELSE + content || substr(rest, 1, 1) + END, + substr(rest, 1, 1), + substr(rest, 2) + FROM split + WHERE rest <> '' + ) + SELECT + id, substr(rest, 2) + FROM + split + WHERE last = '&' + AND rest NOT LIKE '%&%' +) +UPDATE site_metadata + SET abbrev = src.abbrev + FROM src + WHERE src.id = site_metadata.id + AND site_metadata.abbrev LIKE '%_Phosida%' + ; +-- parse out abbreviation and pattern for Phosida +WITH phoo(id) AS ( + SELECT id + FROM site_type + WHERE type_name = 'Phosida' +) +UPDATE site_metadata + SET abbrev = substr(abbrev, 1, instr(abbrev,'_Phosida ') - 1), + pattern = substr(abbrev, instr(abbrev,'_Phosida ') + 9) + FROM phoo + WHERE site_type_id = phoo.id + AND abbrev LIKE '%_Phosida%' + ; +-- parse out abbreviation and pattern for PhosphoSitePlus +WITH psp(id) AS ( + SELECT id + FROM site_type + WHERE type_name = 'PhosphoSite' +) +UPDATE site_metadata + SET abbrev = substr(abbrev, 1, instr(abbrev,'_PhosphoSite') - 1), + pattern = '' + FROM psp + WHERE site_type_id = psp.id + AND abbrev LIKE '%_PhosphoSite%' + ; +-- parse out abbreviation and pattern for NetworKIN +WITH ntwrk(id) AS ( + SELECT id + FROM site_type + WHERE type_name = 'NetworKIN' +) +UPDATE site_metadata + SET abbrev = substr(abbrev, 1, instr(abbrev,'_NetworKIN') - 1), + pattern = '' + FROM ntwrk + WHERE site_type_id = ntwrk.id + AND abbrev LIKE '%_NetworKIN%' + ; +-- fix messy prefixes due to compound HPRD/HPRD +WITH src(id, abbrev) AS ( + WITH RECURSIVE split(id, content, last, rest) AS ( + SELECT id, '', '', full + FROM site_metadata + WHERE site_type_id = ( + SELECT id + FROM site_type + WHERE type_name = 'motif' + ) + AND abbrev LIKE '%(HPRD)%' + UNION ALL + SELECT + id, + CASE + WHEN last = '&' + THEN + substr(rest, 1, 1) + ELSE + content || substr(rest, 1, 1) + END, + substr(rest, 1, 1), + substr(rest, 2) + FROM split + WHERE rest <> '' + ) + SELECT + id, substr(rest, 2) + FROM + split + WHERE + last = '&' AND rest NOT LIKE '%&%' +) +-- SELECT src.abbrev, site_metadata.* +-- FROM src, site_metadata +-- WHERE src.id = site_metadata.id +-- AND site_metadata.abbrev LIKE '%(HPRD)%(HPRD)%' +-- ; +UPDATE site_metadata + SET abbrev = src.abbrev + FROM src + WHERE src.id = site_metadata.id + AND site_metadata.abbrev LIKE '%(HPRD)%(HPRD)%' + ; +-- parse out abbreviation and pattern for motif +WITH mtf(id) AS ( + SELECT id + FROM site_type + WHERE type_name = 'motif' +) +UPDATE site_metadata + SET abbrev = substr(abbrev, 1, instr(abbrev,'(HPRD) ') - 1), + pattern = substr(abbrev, instr(abbrev,'(HPRD) ') + 7) + FROM mtf + WHERE site_type_id = mtf.id + AND abbrev LIKE '%(HPRD)%' + ; +-- trim off verbosities for motif +WITH mtf(id) AS ( + SELECT id + FROM site_type + WHERE type_name = 'motif' +) +UPDATE site_metadata + SET abbrev = substr(abbrev, 1, instr(abbrev,'substrate') - 1), + motif = 'substrate' + FROM mtf + WHERE site_type_id = mtf.id + AND abbrev LIKE '%substrate%' + ; +-- trim off verbosities for motif +WITH mtf(id) AS ( + SELECT id + FROM site_type + WHERE type_name = 'motif' +) +UPDATE site_metadata + SET abbrev = substr(abbrev, 1, instr(abbrev,'domain binding motif') - 1), + motif = 'binding' + FROM mtf + WHERE site_type_id = mtf.id + AND abbrev LIKE '%domain binding motif%' + ; + + + + +-- DROP TABLE IF EXISTS ppep_gene_siteref +-- ; +-- +-- CREATE TABLE ppep_gene_siteref( +-- ppep_id INTEGER REFERENCES ppep(id) +-- , gene_names TEXT +-- , site_type_id INTEGER REFERENCES site_type(id) +-- , site_metadata_id INTEGER REFERENCES site_metadata(id) +-- , PRIMARY KEY (ppep_id, site_metadata_id) ON CONFLICT IGNORE +-- ); +-- + |
| b |
| diff -r 5b8e15b2a67c -r 2e35f925c469 kseaapp_demo.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/kseaapp_demo.R Thu Oct 27 18:54:25 2022 +0000 |
| [ |
| b'@@ -0,0 +1,481 @@\n+# KSEAapp demo using SQLite data source\n+library(sqldf) # implies that package RSQLite will be available\n+library(KSEAapp) # implies that package gplots will be available\n+\n+# ref: http://adv-r.had.co.nz/Environments.html\n+# "When creating your own environment, note that you should set its parent\n+# environment to be the empty environment. This ensures you don\'t\n+# accidentally inherit objects from somewhere else."\n+# Caution: this prevents `with(my_env, expr)` from working when `expr`\n+# contains anything from the global environment, even operators!\n+# Hence, `x <- 1; get("x", new_env())` fails by design.\n+new_env <- function() {\n+ new.env(parent = emptyenv())\n+}\n+\n+# Adapted from KSEAapp::KSEA.Heatmap to allow specification of output file\n+ksea_heatmap <-\n+function(\n+ # the data frame outputs from the KSEA.Scores() function, in list format\n+ score_list,\n+ # a character vector of all the sample names for heatmap annotation:\n+ # - the names must be in the same order as the data in score_list\n+ # - please avoid long names, as they may get cropped in the final image\n+ sample_labels,\n+ # character string of either "p.value" or "FDR" indicating the data column\n+ # to use for marking statistically significant scores\n+ stats,\n+ # a numeric value between 0 and infinity indicating the min. number of\n+ # substrates a kinase must have to be included in the heatmap\n+ m_cutoff,\n+ # a numeric value between 0 and 1 indicating the p-value/FDR cutoff\n+ # for indicating significant kinases in the heatmap\n+ p_cutoff,\n+ # a binary input of TRUE or FALSE, indicating whether or not to perform\n+ # hierarchical clustering of the sample columns\n+ sample_cluster,\n+ # a binary input of TRUE or FALSE, indicating whether or not to export\n+ # the bar plot as a .tiff image into the working directory\n+ export = FALSE\n+) {\n+ filter_m <- function(dataset, m_cutoff) {\n+ filtered <- dataset[(dataset$m >= m_cutoff), ]\n+ return(filtered)\n+ }\n+ score_list_m <- lapply(score_list, function(...)\n+ filter_m(...,\n+ m_cutoff))\n+ for (i in seq_len(length(score_list_m))) {\n+ names <- colnames(score_list_m[[i]])[c(2:7)]\n+ colnames(score_list_m[[i]])[c(2:7)] <-\n+ paste(names, i, sep = ".")\n+ }\n+ master <-\n+ Reduce(function(...)\n+ merge(..., by = "Kinase.Gene", all = F), score_list_m)\n+ #ACE if (is.null(master)) return ("No significant kinase genes found") \n+ row.names(master) <- master$Kinase.Gene\n+ columns <- as.character(colnames(master))\n+ merged_scores <- as.matrix(master[, grep("z.score", columns)])\n+ colnames(merged_scores) <- sample_labels\n+ merged_stats <- as.matrix(master[, grep(stats, columns)])\n+ asterisk <- function(matrix) {\n+ new <- data.frame()\n+ for (i in seq_len(nrow(matrix))) {\n+ for (j in seq_len(ncol(matrix))) {\n+ if (matrix[i, j] < p_cutoff) {\n+ new[i, j] <- "*"\n+ }\n+ else {\n+ new[i, j] <- ""\n+ }\n+ }\n+ }\n+ return(new)\n+ }\n+ merged_asterisk <- as.matrix(asterisk(merged_stats))\n+ create_breaks <- function(merged_scores) {\n+ if (min(merged_scores) < -1.6) {\n+ breaks_neg <- seq(-1.6, 0, length.out = 30)\n+ breaks_neg <-\n+ append(seq(min(merged_scores), -1.6, length.out = 10), breaks_neg)\n+ breaks_neg <- sort(unique(breaks_neg))\n+ }\n+ else {\n+ breaks_neg <- seq(-1.6, 0, length.out = 30)\n+ }\n+ if (max(merged_scores) > 1.6) {\n+ breaks_pos <- seq(0, 1.6, length.out = 30)\n+ breaks_pos <-\n+ append(breaks_pos, seq(1.6, max(merged_scores), length.out = 10))\n+ breaks_pos <- sort(unique(breaks_pos))\n+ }\n+ else {\n+ breaks_pos <- seq(0, 1.6, length.out = 30)\n+ }\n+ breaks_all <- unique(append(breaks_neg, breaks_pos))\n+ mycol_neg <-\n+ gplots::colorpanel(n = length(breaks_neg),\n+ low = "blue",\n+ high = "white")\n+ mycol_pos <-\n+ gplots::colorpanel(n = length(break'..b' WHERE contrast = %d\n+ ", i_cntrst\n+ ),\n+ connection = db\n+ )\n+ #ACE K_S_links <-\n+ #ACE KSEA.KS_table(\n+ #ACE KSEAapp::KSData,\n+ #ACE kseaapp_input,\n+ #ACE networkin = TRUE,\n+ #ACE networkin_cutoff = 2\n+ #ACE )\n+ #ACE print(sprintf("contrast = %d", i_cntrst))\n+ tryCatch(\n+ expr = {\n+ main_title <- (\n+ sprintf(\n+ "Change from treatment %s to treatment %s",\n+ contrast_metadata_df[i_cntrst, "b_level"],\n+ contrast_metadata_df[i_cntrst, "a_level"]\n+ )\n+ )\n+ sub_title <- (\n+ sprintf(\n+ "Trt %s = {%s}. Trt %s = {%s}.",\n+ contrast_metadata_df[i_cntrst, "b_level"],\n+ gsub(\n+ pattern = ";",\n+ replacement = ", ",\n+ x = contrast_metadata_df[i_cntrst, "b_samples"],\n+ fixed = TRUE\n+ ),\n+ contrast_metadata_df[i_cntrst, "a_level"],\n+ gsub(\n+ pattern = ";",\n+ replacement = "",\n+ x = contrast_metadata_df[i_cntrst, "a_samples"],\n+ fixed = TRUE\n+ )\n+ )\n+ )\n+ ksea_barplot(\n+ KSEAapp::KSData,\n+ kseaapp_input,\n+ networkin = TRUE,\n+ networkin_cutoff = 2,\n+ m_cutoff = 2,\n+ p_cutoff = 0.05,\n+ export = FALSE,\n+ main = main_title,\n+ sub = sub_title\n+ )\n+ },\n+ error = function(e) {\n+ if (tolower(e$message) == err_na_subscr_df_const) {\n+ cat(\n+ sprintf("\\nNo scores or plot for contrast \'%s\' because:\\n \'%s\'\\n",\n+ contrast_label,\n+ "There are too many missing or invalid values."\n+ ),\n+ file = stdout()\n+ )\n+ } else {\n+ cat(\n+ sprintf("\\nNo scores or plot for contrast \'%s\' because:\\n \'%s\'\\n",\n+ contrast_label,\n+ e$message\n+ ),\n+ file = stdout()\n+ )\n+ }\n+ }\n+ )\n+ tryCatch(\n+ expr = {\n+ ksea_scores <-\n+ KSEA.Scores(\n+ KSEAapp::KSData,\n+ kseaapp_input,\n+ NetworKIN = TRUE,\n+ NetworKIN.cutoff = 2\n+ )\n+\n+ if (0 < sum(!is.nan(ksea_scores$FDR))) {\n+ next_index <- 1 + next_index\n+ rslt$score_list[[next_index]] <- ksea_scores\n+ #ACE rslt$usable_contrast_list[[next_index]] <- i_cntrst\n+ rslt$name_list[[next_index]] <- contrast_label\n+ cat("\\n", rslt$name_list[[next_index]], "\\n")\n+ low_fdr_print(next_index)\n+ }\n+ },\n+ error = function(e) str(e)\n+ )\n+}\n+if (length(rslt$score_list) > 0) {\n+ ksea_heatmap(\n+ # the data frame outputs from the KSEA.Scores() function, in list format\n+ score_list = rslt$score_list,\n+ # a character vector of all the sample names for heatmap annotation:\n+ # - the names must be in the same order as the data in score_list\n+ # - please avoid long names, as they may get cropped in the final image\n+ sample_labels = rslt$name_list,\n+ # character string of either "p.value" or "FDR" indicating the data column\n+ # to use for marking statistically significant scores\n+ stats = c("p.value", "FDR")[2],\n+ # a numeric value between 0 and infinity indicating the min. number of\n+ # substrates a kinase must have to be included in the heatmap\n+ m_cutoff = 1,\n+ # a numeric value between 0 and 1 indicating the p-value/FDR cutoff\n+ # for indicating significant kinases in the heatmap\n+ p_cutoff = 0.05,\n+ # a binary input of TRUE or FALSE, indicating whether or not to perform\n+ # hierarchical clustering of the sample columns\n+ sample_cluster = TRUE,\n+ # a binary input of TRUE or FALSE, indicating whether or not to export\n+ # the bar plot as a .tiff image into the working directory\n+ export = FALSE\n+ )\n+}\n+dbDisconnect(db)\n' |
| b |
| diff -r 5b8e15b2a67c -r 2e35f925c469 macros.xml --- a/macros.xml Wed Oct 26 23:48:51 2022 +0000 +++ b/macros.xml Thu Oct 27 18:54:25 2022 +0000 |
| b |
| @@ -4,7 +4,7 @@ <xml name="requirements"> <requirements> <requirement type="package" version="1.56.0" >bioconductor-preprocesscore</requirement> - <requirement type="package" >gmp</requirement> + <requirement type="package" version="6.2.1" >gmp</requirement> <requirement type="package" version="1.23.4" >numpy</requirement> <requirement type="package" version="0.3.3" >openblas</requirement> <requirement type="package" version="1.5.1" >pandas</requirement> |
| b |
| diff -r 5b8e15b2a67c -r 2e35f925c469 phosphoelm_kinase_upid_desc.lut --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/phosphoelm_kinase_upid_desc.lut Thu Oct 27 18:54:25 2022 +0000 |
| b |
| b'@@ -0,0 +1,299 @@\n+kinase_name\tuniprot_id\tdescription\n+AAK1\tQ2M2I8\tAP2 associated kinase 1\n+Abl\tP00519\tProto-oncogene tyrosine-protein kinase ABL1\n+Abl2\tP42684\tv-abl Abelson murine leukemia viral oncogene homolog 2 (arg, Abelson-related gene)\n+Abl_drome\tP00522\tTyrosine-protein kinase Abl\n+Ack_drome\tQ9VZI2\tAck\n+AFK\tP80197\tActin-fragmin kinase (Physarum polycephalum)\n+Akt1_drome\tQ8INB9\tRAC serine/threonine-protein kinase\n+AKT_group_Caeel\t\tSerine/threonine-protein kinase akt group\n+ALK\tQ9UM73\tAnaplastic lymphoma kinase\n+AMPK_group\t\t\n+Atg1_drome\tQ9VU14\tAutophagy-specific gene 1\n+ATM\tQ13315\tAtaxia telangiectasia mutated\n+ATR\tQ13535\tAtaxia telangiectasia and Rad3-related protein (FRAP-related protein 1)\n+Aurora A\tO14965\tSerine/threonine-protein kinase 6 (STK6)\n+Aurora B\tQ96GD4\tSerine/threonine-protein kinase 12 (AURKB)\n+Axl\tP30530\tTyrosine-protein kinase receptor UFO\n+BCKDK\tO14874\tBranched-chain alpha-ketoacid dehydrogenase kinase\n+BLK\tP51451\tB lymphoid tyrosine kinase\n+BMPR1B\tO00238\tbone morphogenetic protein receptor, type IB\n+BMX\tP51813\tBMX non-receptor tyrosine kinase (Etk)\n+Brk\tQ13882\tBreast tumor kinase (PTK6)\n+BRSK1\tQ8TDC3\tBR serine/threonine kinase 1 (SAD1A)\n+BTK\tQ06187\tBruton`s tyrosine kinase (AGMX1) (ATK) (BPK)\n+Caki_drome\tQ24210\tCalcium/calmodulin-dependent protein kinase\n+CaM-KI_alpha\tQ14012\tcalcium/calmodulin-dependent protein kinase I\n+CaM-KI_group\t\t\n+CaM-KII_alpha\tQ9UQM7\tcalcium/calmodulin-dependent protein kinase (CaM kinase) II alpha\n+CaM-KII_delta\tQ13557\tcalcium/calmodulin-dependent protein kinase (CaM kinase) II delta\n+CaMKII_drome\tQ00168\tCalcium/calmodulin-dependent protein kinase type II alpha chain\n+CaM-KII_group\t\t\n+CaM-KIV\tQ16566\tcalcium/calmodulin-dependent protein kinase (CaM kinase) IV\n+CaM-KK_alpha\tQ8N5S9\tcalcium/calmodulin-dependent protein kinase kinase 1, alpha\n+CCDPK\tQ9U5L0\tCa2+/calmodulin-dependent protein kinase II (Suberites domuncula)\n+CDC2_drome\tP23572\tCell division protein kinase 1\n+CDK1\tP06493\tCell division control protein 2 homolog (p34 protein kinase) (Cyclin-dependent kinase 1) GENE=CDC2\n+CDK11\tQ9BWU1\tCell division cycle 2-like 6\n+CDK2\tP24941\tCell division protein kinase 2\n+CDK3\tQ00526\tcyclin-dependent kinase 3\n+CDK4\tP11802\tCell division protein kinase 4 (Cyclin-dependent kinase 4)\n+CDK5\tQ00535\tCell division protein kinase 5 \n+CDK6\tQ00534\tcyclin-dependent kinase 6\n+CDK7\tP50613\tCell division protein kinase 7 (CDK-activating kinase) (TFIIH basal transcription factor complex kinase subunit)\n+CDK9\tP50750\tcyclin-dependent kinase 9 (CDC2-related kinase)\n+CDK_group\t\t\n+CDPK\t\tCalcium-dependent protein kinase ( in plants)\n+Chak1\tQ96QT4\ttransient receptor potential cation channel, subfamily M, member 7\n+CHK1\tO14757\tSerine/threonine-protein kinase Chk1\n+CHK2\tO96017\tCHK2 checkpoint homolog\n+CK1_alpha\tP48729\tcasein kinase 1, alpha 1\n+CK1_delta\tP48730\tcasein kinase 1, delta\n+CK1_epsilon\tP49674\tcasein kinase 1, epsilon\n+CK1_group\t\t\n+CK2_alpha\tP68400\tcasein kinase 2, alpha 1 polypeptide\n+CK2_beta\t\t\n+CK2_group\t\t\n+CK_group_Caeel\t\tCasein kinase group\n+CkI_alpha_drome\tP54367\tCasein kinase I isoform alpha\n+CkII_beta_drome\tP08182\tCasein kinase II subunit beta\n+CkII_group_drome\t\tCasein kinase II group\n+CLK1\tP49759\tCDC-like kinase 1\n+CSF1R\tP07333\tcolony stimulating factor 1 receptor, formerly McDonough feline sarcoma viral (v-fms) oncogene homolog\n+Csk\tP41240\tTyrosine-protein kinase CSK\n+DAPK1\tP53355\tdeath-associated protein kinase 1\n+DAPK2\tQ9UIK4\tdeath-associated protein kinase 2\n+DAPK3\tO43293\tdeath-associated protein kinase 3\n+DAPK_group\t\t\n+DCAMKL1\tO15075\tdoublecortin and CaM kinase-like 1\n+DMPK_group\t\t\n+DNA-PK\tP78527\tDNA-dependent protein kinase catalytic subunit\n+DYRK1A\tQ13627\tdual-specificity tyrosine-(Y)-phosphorylation regulated kinase 1A\n+DYRK1B\tQ9Y463\tDual specificity tyrosine-phosphorylation-regulated kinase 1B\n+DYRK2\tQ92630\tdual-specificity tyrosine-(Y)-phosphorylation regulated kinase 2\n+DYRK3\tO43781\tdual-specificity tyrosine-(Y)-phosphorylation regulated kinase 3\n+Eg3 kinase\t\tmember of the KIN1/PAR-1/M'..b'in kinase 1\n+PDGFR_alpha\tP16234\tplatelet-derived growth factor receptor, alpha polypeptide\n+PDGFR_beta\tP09619\tplatelet-derived growth factor receptor, beta polypeptide\n+PDGFR_group\t\t\n+PDHK1\tQ15118\tpyruvate dehydrogenase kinase, isozyme 1\n+PDHK2\tQ15119\tpyruvate dehydrogenase kinase, isozyme 2\n+PDHK3\tQ15120\tpyruvate dehydrogenase kinase, isozyme 3\n+PDHK4\tQ16654\tpyruvate dehydrogenase kinase, isozyme 4\n+PDK-1\tO15530\t3-phosphoinositide dependent protein kinase 1\n+PDK-2\t\t\n+PDKC\t\t\n+PHK_group\t\t\n+PIK3CA\t\t\n+PIK3CB\t\t\n+PIK3CD\t\t\n+PIK3CG\t\t\n+PIM-1\tP11309\tpim-1 oncogene\n+PKA_alpha\tP17612\tprotein kinase, cAMP-dependent, catalytic, alpha\n+Pka-C1_drome\tP12370\tcAMP-dependent protein kinase catalytic subunit\n+PKA_group\t\t\n+PKA_group_drome\t\tcAMP-dependent protein kinase catalytic subunit group\n+PKB_beta\tP31751\tv-akt murine thymoma viral oncogene homolog 2\n+PKB_group\t\t\n+PKC_alpha\tP17252\tProtein kinase C, alpha type\n+PKC_beta\tP05771\tprotein kinase C, beta 1\n+PKC_delta\tQ05655\tProtein kinase C, delta type\n+PKC_epsilon\tQ02156\tProtein kinase C, epsilon type\n+PKC_eta\tP24723\tProtein kinase C, eta\n+PKC_gamma\tP05129\tprotein kinase C, gamma\n+PKC_group\t\t\n+PKC_group_drome\t\tProtein kinase C group\n+PKC_iota\tP41743\tprotein kinase C, iota\n+PKC_theta\tQ04759\tProtein kinase C, theta type\n+PKC_zeta\tQ05513\tProtein kinase C, zeta type\n+PKD1\tQ15139\tprotein kinase D1\n+PKD2\tQ9BZL6\tprotein kinase D2\n+PKG1/cGK-I\tP14619\tcGMP-dependent protein kinase 1\n+PKG2/cGK-II\tQ13237\tcGMP-dependent protein kinase 2\n+PKG/cGK_group\t\t\n+PKN1\tQ16512\tprotein kinase N1\n+PLK1\tP53350\tPolo like kinase 1\n+PLK3\tQ9H4B4\tPolo like kinase 3\n+PRP4\tQ13523\tPRP4 pre-mRNA processing factor 4 homolog (yeast)\n+PYK2\tQ14289\tFocal adhesion kinase 2\n+RAF1\tP04049\tRAF proto-oncogene serine/threonine-protein kinase\n+RET\tP07949\tProto-oncogene tyrosine-protein kinase receptor ret\n+ROCK1\tQ13464\tRho-associated, coiled-coil containing protein kinase 1\n+ROCK2\tO75116\tRho-associated, coiled-coil containing protein kinase 2\n+ROCK_group\t\t\n+RON\tQ04912\tMacrophage-stimulating protein receptor ( Stem cell-derived tyrosine kinase) (Mst1r)\n+RSK-1\tQ15418\tRibosomal protein S6 kinase alpha 1\n+RSK-2\tQ15349\tRibosomal protein S6 kinase alpha 2\n+RSK-3\tP51812\tRibosomal protein S6 kinase alpha 3\n+RSK-5\tO75582\tribosomal protein S6 kinase, 90kDa, polypeptide 5 (MSK1)\n+RSK_group\t\t\n+sgg_drome\tP83101\tPutative glycogen synthase kinase-3 homolog\n+SGK_group\t\t\n+SIK\tP57059\tSNF1-like kinase\n+SRC\tP12931\tProto-oncogene tyrosine-protein kinase Src\n+SRC64B_drome\tP00528\tTyrosine-protein kinase Src64B\n+SRC_group\t\t\n+STLK3\tQ9UEW8\tKnown - Refseq /Serine/threonine-protein kinase 39\n+SYK\tP43405\tTyrosine-protein kinase SYK (Spleen tyrosine kinase).\n+TBK1\tQ9UHD2\tTANK-binding kinase 1\n+TEC\tP42680\tTyrosine-protein kinase Tec\n+TESK1\tQ15569\tDual specificity testis-specific protein kinase 1\n+TESK2\tQ96S53\tDual specificity testis-specific protein kinase 2\n+TGFbR1\tP36897\tTGF-beta receptor type I\n+TGFbR2\tP37173\tTGF-beta receptor type II\n+TIE1\tP35590\ttyrosine kinase with immunoglobulin-like and EGF-like domains 1\n+TIE2\tQ02763\tAngiopoietin-1 receptor precursor (EC 2.7.1.112) (Tyrosine-protein kinase receptor TIE-2) (Tyrosine-protein kinase receptor TEK)\n+Titin kinase\t\t\n+TLK1\tQ9UKI8\ttousled-like kinase 1\n+TNK2\tQ07912\ttyrosine kinase, non-receptor, 2 (p21cdc42Hs, ACK)\n+Tor_drome\tP18475\tTarget of rapamycin\n+TRKA\tP04629\tHigh affinity nerve growth factor receptor\n+TRKB\tQ16620\tBDNF/NT-3 growth factors receptor\n+Tropomyosin kinase\t\tTropomyosin receptor kinase (Gallus gallus)\n+TSSK3\tQ96PN8\ttestis-specific serine kinase 3\n+TTK\tP33981\tTTK protein kinase\n+TXK\tP42681\tSyn= Rlk\n+Tyk2\tP29597\tNon-receptor tyrosine-protein kinase TYK2\n+unc-43_Caeel\tQ9NH60\tCalcium/calmodulin-dependent protein kinase II isoform B\n+VRK1\tQ99986\tvaccinia related kinase 1\n+WEE1\tP30291\tWEE1 homolog (S. pombe)\n+WNK1\tQ9H4A3\tWNK lysine deficient protein kinase 1\n+wts_drome\tQ24590\tSerine/threonine kinase PAK homolog DPAK\n+Yes\tP07947\tProto-oncogene tyrosine-protein kinase Yes\n+ZAP70\tP43403\tTyrosine-protein kinase ZAP-70\n' |
| b |
| diff -r 5b8e15b2a67c -r 2e35f925c469 run_planemo_test.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/run_planemo_test.sh Thu Oct 27 18:54:25 2022 +0000 |
| b |
| @@ -0,0 +1,8 @@ +#!/bin/env bash +WHATTOTEST=$1 + +old_path=$PATH +new_path=`echo $PATH | sed -e "s^/home/rstudio/bin/tinytex:^^"` +export PATH=$new_path + +planemo test --biocontainers --galaxy_root ~/galaxy/thor/planemo_galaxy/galaxyproject-galaxy ${WHATTOTEST:-.} |
| b |
| diff -r 5b8e15b2a67c -r 2e35f925c469 run_r_linter.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/run_r_linter.R Thu Oct 27 18:54:25 2022 +0000 |
| b |
| @@ -0,0 +1,15 @@ +#!/bin/env Rscript +library(lintr) +linters <- linters_with_defaults( + line_length_linter = NULL, + cyclocomp_linter = NULL, + object_usage_linter = NULL +) +cat("linting MaxQuantProcessingScript.R\n") +lint(filename = "MaxQuantProcessingScript.R", linters = linters) +cat("linting mqppep_anova.R\n") +lint(filename = "mqppep_anova.R", linters = linters) +cat("done linting R scripts\n") +cat("linting mqppep_anova_script.Rmd\n") +lint(filename = "mqppep_anova_script.Rmd", linters = linters) +cat("done linting Rmd scripts\n") |
| b |
| diff -r 5b8e15b2a67c -r 2e35f925c469 shed.yml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/shed.yml Thu Oct 27 18:54:25 2022 +0000 |
| b |
| @@ -0,0 +1,24 @@ +name: mqppep +owner: eschen42 +description: MaxQuant Phosphoproteomic Enrichment Pipeline - Preprocessing and ANOVA +homepage_url: 'https://github.com/galaxyproteomics/tools-galaxyp/' +long_description: | + Phosphoproteomic Enrichment Pipeline provides tools two tools for processing MaxQuant data for phosphoproteome-enriched samples. + + "MaxQuant Phosphopeptide Preprocessing" (mqppep_preproc) transforms the 'Phospho (STY)Sites.txt' output file that MaxQuant produces for for phosphoproteome-enriched samples to prepare it for ANOVA. + + "MaxQuant Phosphopeptide ANOVA" (mqppep_anova) performs ANOVA on the preprocessed data. +remote_repository_url: https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep +type: unrestricted +categories: +- Proteomics +auto_tool_repositories: + name_template: "{{ tool_id }}" + description_template: "Wrapper for the mqppep suite tool: {{ tool_name }}" +suite: + name: "suite_mqppep" + description: suite for preprocessing, ANOVA, and KSEA of MaxQuant results for phosphoproteomic enrichment + long_description: | + Phosphoproteomic Enrichment Pipeline provides tools for preprocessing + the 'Phospho (ST)Sites.txt' or 'Phospho (Y)Sites.txt' files produced + by MaxQuant and for ANOVA analysis of the preprocessed data. |