biopipen 0.21.0__py3-none-any.whl → 0.34.26__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (290) hide show
  1. biopipen/__init__.py +1 -1
  2. biopipen/core/config.toml +28 -0
  3. biopipen/core/filters.py +79 -4
  4. biopipen/core/proc.py +12 -3
  5. biopipen/core/testing.py +75 -3
  6. biopipen/ns/bam.py +148 -6
  7. biopipen/ns/bed.py +75 -0
  8. biopipen/ns/cellranger.py +186 -0
  9. biopipen/ns/cellranger_pipeline.py +126 -0
  10. biopipen/ns/cnv.py +19 -3
  11. biopipen/ns/cnvkit.py +1 -1
  12. biopipen/ns/cnvkit_pipeline.py +20 -12
  13. biopipen/ns/delim.py +34 -35
  14. biopipen/ns/gene.py +68 -23
  15. biopipen/ns/gsea.py +63 -37
  16. biopipen/ns/misc.py +39 -14
  17. biopipen/ns/plot.py +304 -1
  18. biopipen/ns/protein.py +183 -0
  19. biopipen/ns/regulatory.py +290 -0
  20. biopipen/ns/rnaseq.py +142 -5
  21. biopipen/ns/scrna.py +2053 -473
  22. biopipen/ns/scrna_metabolic_landscape.py +228 -382
  23. biopipen/ns/snp.py +659 -0
  24. biopipen/ns/stats.py +484 -0
  25. biopipen/ns/tcr.py +683 -98
  26. biopipen/ns/vcf.py +236 -2
  27. biopipen/ns/web.py +97 -6
  28. biopipen/reports/bam/CNVpytor.svelte +4 -9
  29. biopipen/reports/cellranger/CellRangerCount.svelte +18 -0
  30. biopipen/reports/cellranger/CellRangerSummary.svelte +16 -0
  31. biopipen/reports/cellranger/CellRangerVdj.svelte +18 -0
  32. biopipen/reports/cnvkit/CNVkitDiagram.svelte +1 -1
  33. biopipen/reports/cnvkit/CNVkitHeatmap.svelte +1 -1
  34. biopipen/reports/cnvkit/CNVkitScatter.svelte +1 -1
  35. biopipen/reports/common.svelte +15 -0
  36. biopipen/reports/protein/ProdigySummary.svelte +16 -0
  37. biopipen/reports/scrna/CellsDistribution.svelte +4 -39
  38. biopipen/reports/scrna/DimPlots.svelte +1 -1
  39. biopipen/reports/scrna/MarkersFinder.svelte +6 -126
  40. biopipen/reports/scrna/MetaMarkers.svelte +3 -75
  41. biopipen/reports/scrna/RadarPlots.svelte +4 -20
  42. biopipen/reports/scrna_metabolic_landscape/MetabolicFeatures.svelte +61 -22
  43. biopipen/reports/scrna_metabolic_landscape/MetabolicPathwayActivity.svelte +88 -82
  44. biopipen/reports/scrna_metabolic_landscape/MetabolicPathwayHeterogeneity.svelte +70 -10
  45. biopipen/reports/snp/PlinkCallRate.svelte +24 -0
  46. biopipen/reports/snp/PlinkFreq.svelte +18 -0
  47. biopipen/reports/snp/PlinkHWE.svelte +18 -0
  48. biopipen/reports/snp/PlinkHet.svelte +18 -0
  49. biopipen/reports/snp/PlinkIBD.svelte +18 -0
  50. biopipen/reports/tcr/CDR3AAPhyschem.svelte +19 -66
  51. biopipen/reports/tcr/ClonalStats.svelte +16 -0
  52. biopipen/reports/tcr/CloneResidency.svelte +3 -93
  53. biopipen/reports/tcr/Immunarch.svelte +4 -155
  54. biopipen/reports/tcr/TCRClusterStats.svelte +3 -45
  55. biopipen/reports/tcr/TESSA.svelte +11 -28
  56. biopipen/reports/utils/misc.liq +22 -7
  57. biopipen/scripts/bam/BamMerge.py +11 -15
  58. biopipen/scripts/bam/BamSampling.py +90 -0
  59. biopipen/scripts/bam/BamSort.py +141 -0
  60. biopipen/scripts/bam/BamSplitChroms.py +10 -10
  61. biopipen/scripts/bam/BamSubsetByBed.py +38 -0
  62. biopipen/scripts/bam/CNAClinic.R +41 -5
  63. biopipen/scripts/bam/CNVpytor.py +153 -54
  64. biopipen/scripts/bam/ControlFREEC.py +13 -14
  65. biopipen/scripts/bam/SamtoolsView.py +33 -0
  66. biopipen/scripts/bed/Bed2Vcf.py +5 -5
  67. biopipen/scripts/bed/BedConsensus.py +5 -5
  68. biopipen/scripts/bed/BedLiftOver.sh +6 -4
  69. biopipen/scripts/bed/BedtoolsIntersect.py +54 -0
  70. biopipen/scripts/bed/BedtoolsMakeWindows.py +47 -0
  71. biopipen/scripts/bed/BedtoolsMerge.py +4 -4
  72. biopipen/scripts/cellranger/CellRangerCount.py +138 -0
  73. biopipen/scripts/cellranger/CellRangerSummary.R +181 -0
  74. biopipen/scripts/cellranger/CellRangerVdj.py +112 -0
  75. biopipen/scripts/cnv/AneuploidyScore.R +55 -20
  76. biopipen/scripts/cnv/AneuploidyScoreSummary.R +221 -163
  77. biopipen/scripts/cnv/TMADScore.R +25 -9
  78. biopipen/scripts/cnv/TMADScoreSummary.R +57 -86
  79. biopipen/scripts/cnvkit/CNVkitAccess.py +7 -6
  80. biopipen/scripts/cnvkit/CNVkitAutobin.py +26 -18
  81. biopipen/scripts/cnvkit/CNVkitBatch.py +6 -6
  82. biopipen/scripts/cnvkit/CNVkitCall.py +3 -3
  83. biopipen/scripts/cnvkit/CNVkitCoverage.py +4 -3
  84. biopipen/scripts/cnvkit/CNVkitDiagram.py +5 -5
  85. biopipen/scripts/cnvkit/CNVkitFix.py +3 -3
  86. biopipen/scripts/cnvkit/CNVkitGuessBaits.py +12 -8
  87. biopipen/scripts/cnvkit/CNVkitHeatmap.py +5 -5
  88. biopipen/scripts/cnvkit/CNVkitReference.py +6 -5
  89. biopipen/scripts/cnvkit/CNVkitScatter.py +5 -5
  90. biopipen/scripts/cnvkit/CNVkitSegment.py +5 -5
  91. biopipen/scripts/cnvkit/guess_baits.py +166 -93
  92. biopipen/scripts/delim/RowsBinder.R +1 -1
  93. biopipen/scripts/delim/SampleInfo.R +116 -118
  94. biopipen/scripts/gene/GeneNameConversion.R +67 -0
  95. biopipen/scripts/gene/GenePromoters.R +61 -0
  96. biopipen/scripts/gsea/Enrichr.R +5 -5
  97. biopipen/scripts/gsea/FGSEA.R +184 -50
  98. biopipen/scripts/gsea/GSEA.R +2 -2
  99. biopipen/scripts/gsea/PreRank.R +5 -5
  100. biopipen/scripts/misc/Config2File.py +2 -2
  101. biopipen/scripts/misc/Plot.R +80 -0
  102. biopipen/scripts/misc/Shell.sh +15 -0
  103. biopipen/scripts/misc/Str2File.py +2 -2
  104. biopipen/scripts/plot/Heatmap.R +3 -3
  105. biopipen/scripts/plot/Manhattan.R +147 -0
  106. biopipen/scripts/plot/QQPlot.R +146 -0
  107. biopipen/scripts/plot/ROC.R +88 -0
  108. biopipen/scripts/plot/Scatter.R +112 -0
  109. biopipen/scripts/plot/VennDiagram.R +5 -9
  110. biopipen/scripts/protein/MMCIF2PDB.py +33 -0
  111. biopipen/scripts/protein/PDB2Fasta.py +60 -0
  112. biopipen/scripts/protein/Prodigy.py +119 -0
  113. biopipen/scripts/protein/ProdigySummary.R +140 -0
  114. biopipen/scripts/protein/RMSD.py +178 -0
  115. biopipen/scripts/regulatory/MotifAffinityTest.R +102 -0
  116. biopipen/scripts/regulatory/MotifAffinityTest_AtSNP.R +127 -0
  117. biopipen/scripts/regulatory/MotifAffinityTest_MotifBreakR.R +104 -0
  118. biopipen/scripts/regulatory/MotifScan.py +159 -0
  119. biopipen/scripts/regulatory/VariantMotifPlot.R +78 -0
  120. biopipen/scripts/regulatory/motifs-common.R +324 -0
  121. biopipen/scripts/rnaseq/Simulation-ESCO.R +180 -0
  122. biopipen/scripts/rnaseq/Simulation-RUVcorr.R +45 -0
  123. biopipen/scripts/rnaseq/Simulation.R +21 -0
  124. biopipen/scripts/rnaseq/UnitConversion.R +325 -54
  125. biopipen/scripts/scrna/AnnData2Seurat.R +40 -0
  126. biopipen/scripts/scrna/CCPlotR-patch.R +161 -0
  127. biopipen/scripts/scrna/CellCellCommunication.py +150 -0
  128. biopipen/scripts/scrna/CellCellCommunicationPlots.R +93 -0
  129. biopipen/scripts/scrna/CellSNPLite.py +30 -0
  130. biopipen/scripts/scrna/CellTypeAnnotation-celltypist.R +185 -0
  131. biopipen/scripts/scrna/CellTypeAnnotation-direct.R +68 -31
  132. biopipen/scripts/scrna/CellTypeAnnotation-hitype.R +27 -22
  133. biopipen/scripts/scrna/CellTypeAnnotation-sccatch.R +28 -20
  134. biopipen/scripts/scrna/CellTypeAnnotation-sctype.R +48 -25
  135. biopipen/scripts/scrna/CellTypeAnnotation.R +37 -1
  136. biopipen/scripts/scrna/CellsDistribution.R +456 -167
  137. biopipen/scripts/scrna/DimPlots.R +1 -1
  138. biopipen/scripts/scrna/ExprImputation-alra.R +109 -0
  139. biopipen/scripts/scrna/ExprImputation-rmagic.R +256 -0
  140. biopipen/scripts/scrna/{ExprImpution-scimpute.R → ExprImputation-scimpute.R} +8 -5
  141. biopipen/scripts/scrna/ExprImputation.R +7 -0
  142. biopipen/scripts/scrna/LoomTo10X.R +51 -0
  143. biopipen/scripts/scrna/MQuad.py +25 -0
  144. biopipen/scripts/scrna/MarkersFinder.R +679 -400
  145. biopipen/scripts/scrna/MetaMarkers.R +265 -161
  146. biopipen/scripts/scrna/ModuleScoreCalculator.R +66 -11
  147. biopipen/scripts/scrna/PseudoBulkDEG.R +678 -0
  148. biopipen/scripts/scrna/RadarPlots.R +355 -134
  149. biopipen/scripts/scrna/ScFGSEA.R +298 -100
  150. biopipen/scripts/scrna/ScSimulation.R +65 -0
  151. biopipen/scripts/scrna/ScVelo.py +617 -0
  152. biopipen/scripts/scrna/Seurat2AnnData.R +7 -0
  153. biopipen/scripts/scrna/SeuratClusterStats-clustree.R +87 -0
  154. biopipen/scripts/scrna/SeuratClusterStats-dimplots.R +36 -30
  155. biopipen/scripts/scrna/SeuratClusterStats-features.R +138 -187
  156. biopipen/scripts/scrna/SeuratClusterStats-ngenes.R +81 -0
  157. biopipen/scripts/scrna/SeuratClusterStats-stats.R +78 -89
  158. biopipen/scripts/scrna/SeuratClusterStats.R +47 -10
  159. biopipen/scripts/scrna/SeuratClustering.R +36 -233
  160. biopipen/scripts/scrna/SeuratLoading.R +2 -2
  161. biopipen/scripts/scrna/SeuratMap2Ref.R +84 -113
  162. biopipen/scripts/scrna/SeuratMetadataMutater.R +16 -6
  163. biopipen/scripts/scrna/SeuratPreparing.R +223 -173
  164. biopipen/scripts/scrna/SeuratSubClustering.R +64 -0
  165. biopipen/scripts/scrna/SeuratTo10X.R +27 -0
  166. biopipen/scripts/scrna/Slingshot.R +65 -0
  167. biopipen/scripts/scrna/Subset10X.R +2 -2
  168. biopipen/scripts/scrna/TopExpressingGenes.R +169 -135
  169. biopipen/scripts/scrna/celltypist-wrapper.py +195 -0
  170. biopipen/scripts/scrna/scvelo_paga.py +313 -0
  171. biopipen/scripts/scrna/seurat_anndata_conversion.py +98 -0
  172. biopipen/scripts/scrna_metabolic_landscape/MetabolicFeatures.R +447 -82
  173. biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayActivity.R +348 -241
  174. biopipen/scripts/scrna_metabolic_landscape/MetabolicPathwayHeterogeneity.R +188 -166
  175. biopipen/scripts/snp/MatrixEQTL.R +217 -0
  176. biopipen/scripts/snp/Plink2GTMat.py +148 -0
  177. biopipen/scripts/snp/PlinkCallRate.R +199 -0
  178. biopipen/scripts/snp/PlinkFilter.py +100 -0
  179. biopipen/scripts/snp/PlinkFreq.R +291 -0
  180. biopipen/scripts/snp/PlinkFromVcf.py +81 -0
  181. biopipen/scripts/snp/PlinkHWE.R +85 -0
  182. biopipen/scripts/snp/PlinkHet.R +96 -0
  183. biopipen/scripts/snp/PlinkIBD.R +196 -0
  184. biopipen/scripts/snp/PlinkSimulation.py +124 -0
  185. biopipen/scripts/snp/PlinkUpdateName.py +124 -0
  186. biopipen/scripts/stats/ChowTest.R +146 -0
  187. biopipen/scripts/stats/DiffCoexpr.R +152 -0
  188. biopipen/scripts/stats/LiquidAssoc.R +135 -0
  189. biopipen/scripts/stats/Mediation.R +108 -0
  190. biopipen/scripts/stats/MetaPvalue.R +130 -0
  191. biopipen/scripts/stats/MetaPvalue1.R +74 -0
  192. biopipen/scripts/tcgamaf/Maf2Vcf.py +2 -2
  193. biopipen/scripts/tcgamaf/MafAddChr.py +2 -2
  194. biopipen/scripts/tcr/Attach2Seurat.R +3 -2
  195. biopipen/scripts/tcr/CDR3AAPhyschem.R +211 -143
  196. biopipen/scripts/tcr/CDR3Clustering.R +343 -0
  197. biopipen/scripts/tcr/ClonalStats.R +526 -0
  198. biopipen/scripts/tcr/CloneResidency.R +255 -131
  199. biopipen/scripts/tcr/CloneSizeQQPlot.R +4 -4
  200. biopipen/scripts/tcr/GIANA/GIANA.py +1356 -797
  201. biopipen/scripts/tcr/GIANA/GIANA4.py +1362 -789
  202. biopipen/scripts/tcr/GIANA/query.py +164 -162
  203. biopipen/scripts/tcr/Immunarch-basic.R +31 -9
  204. biopipen/scripts/tcr/Immunarch-clonality.R +25 -5
  205. biopipen/scripts/tcr/Immunarch-diversity.R +352 -134
  206. biopipen/scripts/tcr/Immunarch-geneusage.R +45 -5
  207. biopipen/scripts/tcr/Immunarch-kmer.R +68 -8
  208. biopipen/scripts/tcr/Immunarch-overlap.R +84 -4
  209. biopipen/scripts/tcr/Immunarch-spectratyping.R +35 -6
  210. biopipen/scripts/tcr/Immunarch-tracking.R +38 -6
  211. biopipen/scripts/tcr/Immunarch-vjjunc.R +165 -0
  212. biopipen/scripts/tcr/Immunarch.R +63 -11
  213. biopipen/scripts/tcr/Immunarch2VDJtools.R +2 -2
  214. biopipen/scripts/tcr/ImmunarchFilter.R +4 -4
  215. biopipen/scripts/tcr/ImmunarchLoading.R +38 -29
  216. biopipen/scripts/tcr/SampleDiversity.R +1 -1
  217. biopipen/scripts/tcr/ScRepCombiningExpression.R +40 -0
  218. biopipen/scripts/tcr/ScRepLoading.R +166 -0
  219. biopipen/scripts/tcr/TCRClusterStats.R +176 -22
  220. biopipen/scripts/tcr/TCRDock.py +110 -0
  221. biopipen/scripts/tcr/TESSA.R +102 -118
  222. biopipen/scripts/tcr/VJUsage.R +5 -5
  223. biopipen/scripts/tcr/immunarch-patched.R +142 -0
  224. biopipen/scripts/tcr/vdjtools-patch.sh +1 -1
  225. biopipen/scripts/vcf/BcftoolsAnnotate.py +91 -0
  226. biopipen/scripts/vcf/BcftoolsFilter.py +90 -0
  227. biopipen/scripts/vcf/BcftoolsMerge.py +31 -0
  228. biopipen/scripts/vcf/BcftoolsSort.py +113 -0
  229. biopipen/scripts/vcf/BcftoolsView.py +73 -0
  230. biopipen/scripts/vcf/TruvariBench.sh +14 -7
  231. biopipen/scripts/vcf/TruvariBenchSummary.R +16 -13
  232. biopipen/scripts/vcf/TruvariConsistency.R +1 -1
  233. biopipen/scripts/vcf/Vcf2Bed.py +2 -2
  234. biopipen/scripts/vcf/VcfAnno.py +11 -11
  235. biopipen/scripts/vcf/VcfDownSample.sh +22 -10
  236. biopipen/scripts/vcf/VcfFilter.py +5 -5
  237. biopipen/scripts/vcf/VcfFix.py +7 -7
  238. biopipen/scripts/vcf/VcfFix_utils.py +13 -4
  239. biopipen/scripts/vcf/VcfIndex.py +3 -3
  240. biopipen/scripts/vcf/VcfIntersect.py +3 -3
  241. biopipen/scripts/vcf/VcfLiftOver.sh +5 -0
  242. biopipen/scripts/vcf/VcfSplitSamples.py +4 -4
  243. biopipen/scripts/vcf/bcftools_utils.py +52 -0
  244. biopipen/scripts/web/Download.py +8 -4
  245. biopipen/scripts/web/DownloadList.py +5 -5
  246. biopipen/scripts/web/GCloudStorageDownloadBucket.py +82 -0
  247. biopipen/scripts/web/GCloudStorageDownloadFile.py +23 -0
  248. biopipen/scripts/web/gcloud_common.py +49 -0
  249. biopipen/utils/gene.py +108 -60
  250. biopipen/utils/misc.py +146 -20
  251. biopipen/utils/reference.py +64 -20
  252. biopipen/utils/reporter.py +177 -0
  253. biopipen/utils/vcf.py +1 -1
  254. biopipen-0.34.26.dist-info/METADATA +27 -0
  255. biopipen-0.34.26.dist-info/RECORD +292 -0
  256. {biopipen-0.21.0.dist-info → biopipen-0.34.26.dist-info}/WHEEL +1 -1
  257. {biopipen-0.21.0.dist-info → biopipen-0.34.26.dist-info}/entry_points.txt +6 -2
  258. biopipen/ns/bcftools.py +0 -111
  259. biopipen/ns/scrna_basic.py +0 -255
  260. biopipen/reports/delim/SampleInfo.svelte +0 -36
  261. biopipen/reports/scrna/GeneExpressionInvistigation.svelte +0 -32
  262. biopipen/reports/scrna/ScFGSEA.svelte +0 -35
  263. biopipen/reports/scrna/SeuratClusterStats.svelte +0 -82
  264. biopipen/reports/scrna/SeuratMap2Ref.svelte +0 -20
  265. biopipen/reports/scrna/SeuratPreparing.svelte +0 -38
  266. biopipen/reports/scrna/TopExpressingGenes.svelte +0 -55
  267. biopipen/reports/scrna_metabolic_landscape/MetabolicFeaturesIntraSubset.svelte +0 -31
  268. biopipen/reports/utils/gsea.liq +0 -110
  269. biopipen/scripts/bcftools/BcftoolsAnnotate.py +0 -42
  270. biopipen/scripts/bcftools/BcftoolsFilter.py +0 -79
  271. biopipen/scripts/bcftools/BcftoolsSort.py +0 -19
  272. biopipen/scripts/gene/GeneNameConversion.py +0 -66
  273. biopipen/scripts/scrna/ExprImpution-alra.R +0 -32
  274. biopipen/scripts/scrna/ExprImpution-rmagic.R +0 -29
  275. biopipen/scripts/scrna/ExprImpution.R +0 -7
  276. biopipen/scripts/scrna/GeneExpressionInvistigation.R +0 -132
  277. biopipen/scripts/scrna/Write10X.R +0 -11
  278. biopipen/scripts/scrna_metabolic_landscape/MetabolicFeaturesIntraSubset.R +0 -150
  279. biopipen/scripts/tcr/TCRClustering.R +0 -280
  280. biopipen/utils/common_docstrs.py +0 -61
  281. biopipen/utils/gene.R +0 -49
  282. biopipen/utils/gsea.R +0 -193
  283. biopipen/utils/io.R +0 -20
  284. biopipen/utils/misc.R +0 -114
  285. biopipen/utils/mutate_helpers.R +0 -433
  286. biopipen/utils/plot.R +0 -173
  287. biopipen/utils/rnaseq.R +0 -48
  288. biopipen/utils/single_cell.R +0 -115
  289. biopipen-0.21.0.dist-info/METADATA +0 -22
  290. biopipen-0.21.0.dist-info/RECORD +0 -218
@@ -0,0 +1,291 @@
1
+ library(rlang)
2
+ library(plotthis)
3
+ library(biopipen.utils)
4
+
5
+ indir <- {{in.indir | r}}
6
+ outdir <- {{out.outdir | r}}
7
+ plink <- {{envs.plink | r}}
8
+ ncores <- {{envs.ncores | r}}
9
+ modifier <- {{envs.modifier | r}}
10
+ gz <- {{envs.gz | r}}
11
+ cutoffs <- {{envs.cutoff | r}}
12
+ filters <- {{envs.filter | r}}
13
+ doplot <- {{envs.plot | r}}
14
+ devpars <- {{envs.devpars | r}}
15
+
16
+ bedfile = Sys.glob(file.path(indir, '*.bed'))
17
+ if (length(bedfile) == 0)
18
+ stop("No bed files found in the input directory.")
19
+ if (length(bedfile) > 1) {
20
+ log_warn("Multiple bed files found in the input directory. Using the first one.")
21
+ bedfile <- bedfile[1]
22
+ }
23
+ input <- tools::file_path_sans_ext(bedfile)
24
+ output <- file.path(outdir, basename(input))
25
+
26
+ modifier <- match.arg(modifier, c("none", "counts", "x"))
27
+
28
+ cmd <- c(
29
+ plink,
30
+ "--threads", ncores,
31
+ "--bfile", input,
32
+ "--out", output
33
+ )
34
+ if (modifier == "counts") {
35
+ cmd <- c(cmd, "--freq", "counts")
36
+ if (!is.list(cutoffs)) { cutoffs <- list(ALT1_CT = cutoffs) }
37
+ # } else if (modifier == "case-control") {
38
+ # cmd <- c(cmd, "--freq", "case-control")
39
+ # if (!is.list(cutoffs)) { cutoffs <- list(MAF_A = cutoffs) }
40
+ } else if (modifier == "x") {
41
+ cmd <- c(cmd, "--geno-counts")
42
+ if (!is.list(cutoffs)) { cutoffs <- list("HOM_ALT1_CT" = cutoffs) }
43
+ } else {
44
+ cmd <- c(cmd, "--freq")
45
+ if (!is.list(cutoffs)) { cutoffs <- list(MAF = cutoffs) }
46
+ }
47
+ if (isTRUE(gz)) { cmd <- c(cmd, "gz") }
48
+
49
+ if (!is.list(filters)) {
50
+ filters <- as.list(rep(filters, length(cutoffs)))
51
+ names(filters) <- names(cutoffs)
52
+ } else {
53
+ for (name in names(filters)) {
54
+ if (is.null(cutoffs[[name]])) {
55
+ stop(paste0("Cutoff for filter ", name, " is not provided."))
56
+ }
57
+ }
58
+ }
59
+
60
+ run_command(cmd, fg = TRUE)
61
+
62
+ post_process <- function(suffix, snp_col = "ID", sep = "\t", modifier = NULL) {
63
+ freq <- read.table(
64
+ paste0(output, suffix),
65
+ header=TRUE,
66
+ check.names=FALSE,
67
+ row.names = NULL,
68
+ sep = sep,
69
+ comment = ""
70
+ )
71
+ colnames(freq)[1] <- sub("#", "", colnames(freq)[1])
72
+ if (!is.null(modifier)) { freq <- modifier(freq) }
73
+ iter_in <- input
74
+ n <- 0
75
+ for (metric_col in names(cutoffs)) {
76
+ if (is.null(cutoffs[[metric_col]])) {
77
+ stop(paste0(
78
+ "Cutoff for metric ",
79
+ metric_col,
80
+ " is not provided in ",
81
+ suffix, "(x) file."))
82
+ }
83
+
84
+ freq[[metric_col]] <- as.numeric(freq[[metric_col]])
85
+ cutoff <- cutoffs[[metric_col]]
86
+ filter <- filters[[metric_col]] %||% "no"
87
+
88
+ if (filter == "no") {
89
+ ge_flag <- paste0(metric_col, " >= ", cutoff)
90
+ lt_flag <- paste0(metric_col, " < ", cutoff)
91
+ freq$GE <- freq[[metric_col]] >= cutoff
92
+ freq$Flag <- ifelse(freq$GE, ge_flag, lt_flag)
93
+ freq$Flag <- factor(freq$Flag, levels = c(lt_flag, ge_flag))
94
+ write.table(
95
+ freq[[snp_col]][freq$GE],
96
+ file = paste0(output, suffix, ".", metric_col, ".ge"),
97
+ col.names=FALSE,
98
+ row.names=FALSE,
99
+ quote=FALSE
100
+ )
101
+ write.table(
102
+ freq[[snp_col]][!freq$GE],
103
+ file = paste0(output, suffix, ".", metric_col, ".lt"),
104
+ col.names=FALSE,
105
+ row.names=FALSE,
106
+ quote=FALSE
107
+ )
108
+
109
+ if (doplot) {
110
+ p <- Histogram(
111
+ freq,
112
+ x = metric_col,
113
+ group_by = "Flag",
114
+ alpha = 0.8,
115
+ bins = 50,
116
+ xlab = metric_col,
117
+ ylab = "Count",
118
+ palette = "Set1"
119
+ )
120
+ res <- 70
121
+ height <- attr(p, "height") * res
122
+ width <- attr(p, "width") * res
123
+ png(paste0(output, suffix, ".", metric_col, ".png"), width = width, height = height, res = res)
124
+ print(p)
125
+ dev.off()
126
+ }
127
+ } else {
128
+ iter_dir <- file.path(outdir, paste0(metric_col, "_filtered"))
129
+ dir.create(iter_dir, showWarnings = FALSE)
130
+ iter_out <- file.path(iter_dir, basename(output))
131
+
132
+ filter <- match.arg(filter, c("gt", "lt", "ge", "le"))
133
+ indicate <- function(metric){
134
+ if (filter == "gt") {
135
+ return(freq[[metric_col]] > cutoff)
136
+ } else if (filter == "lt") {
137
+ return(freq[[metric_col]] < cutoff)
138
+ } else if (filter == "ge") {
139
+ return(freq[[metric_col]] >= cutoff)
140
+ } else if (filter == "le") {
141
+ return(freq[[metric_col]] <= cutoff)
142
+ }
143
+ }
144
+ freq$Flag <- ifelse(indicate(freq), "Fail", "Pass")
145
+ freq$Flag <- factor(freq$Flag, levels = c("Fail", "Pass"))
146
+ failfile <- paste0(output, suffix, ".", metric_col, ".fail")
147
+ write.table(
148
+ freq[[snp_col]][freq$Flag == "Fail"],
149
+ file = failfile,
150
+ col.names=FALSE,
151
+ row.names=FALSE,
152
+ quote=FALSE
153
+ )
154
+
155
+ if (doplot) {
156
+ p <- Histogram(
157
+ freq,
158
+ x = metric_col,
159
+ group_by = "Flag",
160
+ alpha = 0.8,
161
+ bins = 50,
162
+ xlab = metric_col,
163
+ ylab = "Count",
164
+ palette = "Set1"
165
+ )
166
+ res <- 70
167
+ height <- attr(p, "height") * res
168
+ width <- attr(p, "width") * res
169
+ png(paste0(output, suffix, ".", metric_col, ".png"), width = width, height = height, res = res)
170
+ print(p)
171
+ dev.off()
172
+ }
173
+
174
+ filter_cmd <- c(
175
+ plink,
176
+ "--threads", ncores,
177
+ "--bfile", shQuote(iter_in),
178
+ "--exclude", shQuote(failfile),
179
+ "--make-bed",
180
+ "--out", shQuote(iter_out)
181
+ )
182
+ run_command(filter_cmd, fg = TRUE)
183
+
184
+ iter_in <- iter_out
185
+ n <- n + 1
186
+
187
+ if (n == length(cutoffs)) {
188
+ # make symbolic links to output from input .bed, .bim and .fam files
189
+ file.symlink(paste0(iter_in, '.bed'), paste0(output, '.bed'))
190
+ file.symlink(paste0(iter_in, '.bim'), paste0(output, '.bim'))
191
+ file.symlink(paste0(iter_in, '.fam'), paste0(output, '.fam'))
192
+ }
193
+ }
194
+ }
195
+ }
196
+
197
+ splitup <- function(x, agg = NULL) {
198
+ sp <- strsplit(as.character(x), ",")
199
+ if (is.null(agg)) {
200
+ return(sp)
201
+ }
202
+ return(sapply(sp, agg))
203
+ }
204
+ if (modifier == "none") {
205
+ mod <- function(freq) {
206
+ # Add ALT1, ALT1_FREQ, REF_FREQ and MAF columns
207
+ writing = FALSE
208
+ if (is.null(freq$ALT1)) {
209
+ # should be the first allele of ALT
210
+ freq$ALT1 <- splitup(freq$ALT, agg = function(s) s[1])
211
+ writing = TRUE
212
+ }
213
+ if (is.null(freq$ALT1_FREQ)) {
214
+ freq$ALT1_FREQ <- as.double(splitup(freq$ALT_FREQS, agg = function(s) s[1]))
215
+ writing = TRUE
216
+ }
217
+ if (is.null(freq$REF_FREQ)) {
218
+ freq$REF_FREQ <- 1 - splitup(freq$ALT_FREQS, agg = function(s) sum(as.double(s)))
219
+ writing = TRUE
220
+ }
221
+ if (is.null(freq$MAF)) {
222
+ min_alt_freqs <- splitup(freq$ALT_FREQS, agg = function(s) min(as.double(s)))
223
+ freq$MAF <- pmin(freq$REF_FREQ, min_alt_freqs)
224
+ writing = TRUE
225
+ }
226
+ if (writing) {
227
+ write.table(
228
+ freq,
229
+ file = paste0(output, ".afreqx"),
230
+ col.names=TRUE,
231
+ row.names=FALSE,
232
+ quote=FALSE,
233
+ sep = "\t"
234
+ )
235
+ }
236
+ return(freq)
237
+ }
238
+ post_process(".afreq", modifier = mod)
239
+ } else if (modifier == "counts") {
240
+ mod <- function(freq) {
241
+ # Add ALT1, ALT1_CT, and REF_CT columns
242
+ writing = FALSE
243
+ if (is.null(freq$ALT1)) {
244
+ # should be the first allele of ALT
245
+ freq$ALT1 <- splitup(freq$ALT, agg = function(s) s[1])
246
+ writing = TRUE
247
+ }
248
+ if (is.null(freq$ALT1_CT)) {
249
+ freq$ALT1_CT <- as.integer(splitup(freq$ALT_CTS, agg = function(s) s[1]))
250
+ writing = TRUE
251
+ }
252
+ if (is.null(freq$REF_CT)) {
253
+ freq$REF_CT <- freq$OBS_CT - splitup(freq$ALT_CTS, agg = function(s) sum(as.integer(s)))
254
+ writing = TRUE
255
+ }
256
+ if (writing) {
257
+ write.table(
258
+ freq,
259
+ file = paste0(output, ".acountx"),
260
+ col.names=TRUE,
261
+ row.names=FALSE,
262
+ quote=FALSE,
263
+ sep = "\t"
264
+ )
265
+ }
266
+ return(freq)
267
+ }
268
+ post_process(".acount", modifier = mod)
269
+ # } else if (modifier == "case-control") {
270
+ # post_process(".frq.cc")
271
+ } else if (modifier == "x") {
272
+ mod <- function(freq) {
273
+ # Add ALT1, HET_REF_ALT1_CT, HOM_ALT1_CT
274
+ writing = FALSE
275
+ if (is.null(freq$ALT1)) {
276
+ # should be the first allele of ALT
277
+ freq$ALT1 <- splitup(freq$ALT, agg = function(s) s[1])
278
+ writing = TRUE
279
+ }
280
+ if (is.null(freq$HET_REF_ALT1_CT)) {
281
+ freq$HET_REF_ALT1_CT <- as.integer(splitup(freq$HET_REF_ALT_CTS, agg = function(s) s[1]))
282
+ writing = TRUE
283
+ }
284
+ if (is.null(freq$HOM_ALT1_CT)) {
285
+ freq$HOM_ALT1_CT <- as.integer(splitup(freq$TWO_ALT_GENO_CTS, agg = function(s) s[1]))
286
+ writing = TRUE
287
+ }
288
+ return(freq)
289
+ }
290
+ post_process(".gcount", modifier = mod)
291
+ }
@@ -0,0 +1,81 @@
1
+ from __future__ import annotations
2
+
3
+ from os import path, PathLike
4
+ from biopipen.core.filters import dict_to_cli_args
5
+ from biopipen.utils.reference import tabix_index
6
+ from biopipen.utils.misc import run_command
7
+
8
+ invcf: str | PathLike = {{in.invcf | quote}} # noqa: E999 # pyright: ignore
9
+ outprefix: str = {{in.invcf | stem0 | quote}} # pyright: ignore
10
+ outdir: str = {{out.outdir | quote}} # pyright: ignore
11
+ args: dict = {{envs | dict}} # pyright: ignore
12
+
13
+ plink = args.pop("plink")
14
+ tabix = args.pop("tabix")
15
+ ncores = args.pop("ncores")
16
+
17
+ # normalize vcf-filter
18
+ args.setdefault("vcf_filter", True)
19
+ if isinstance(args["vcf_filter"], str):
20
+ args["vcf_filter"] = args["vcf_filter"].split()
21
+
22
+ # normalize biallelic-only
23
+ args.setdefault("max_alleles", 2)
24
+
25
+ # This makes it possible to keep the allele order in the output
26
+ # no need for plink2
27
+ # args["keep_allele_order"] = True
28
+ args.setdefault("keep_allele_order", True)
29
+
30
+ # resolve plink 1.x --set-missing-var-ids doesn't distinguish $1, $2,...
31
+ # for ref and alts
32
+ # if (
33
+ # "set_missing_var_ids" in args
34
+ # and args["set_missing_var_ids"]
35
+ # and ("$" in args["set_missing_var_ids"] or "%" in args["set_missing_var_ids"])
36
+ # ):
37
+ # tmpfile = path.join(outdir, 'with_var_ids.vcf')
38
+ # set_missing_var_ids = args.pop("set_missing_var_ids")
39
+ # set_missing_var_ids = (
40
+ # set_missing_var_ids
41
+ # .replace("@", "%CHROM")
42
+ # .replace("#", "%POS")
43
+ # .replace("$1", "%REF")
44
+ # .replace("$2", "%ALT{0}")
45
+ # .replace("$3", "%ALT{1}")
46
+ # .replace("$4", "%ALT{2}")
47
+ # .replace("$5", "%ALT{3}")
48
+ # .replace("$6", "%ALT{4}")
49
+ # .replace("%CHROM_", "%CHROM\\_")
50
+ # .replace("%POS_", "%POS\\_")
51
+ # .replace("%REF_", "%REF\\_")
52
+ # )
53
+ # set_vid_cmd = [
54
+ # bcftools,
55
+ # "annotate",
56
+ # "--set-id",
57
+ # f"+{set_missing_var_ids}",
58
+ # "--output-type",
59
+ # "z",
60
+ # "--output",
61
+ # tmpfile,
62
+ # "--threads",
63
+ # ncores,
64
+ # invcf,
65
+ # ]
66
+
67
+ # run_command(set_vid_cmd, fg=True, env={"cwd": outdir})
68
+ # invcf = tmpfile
69
+
70
+ invcf = tabix_index(invcf, "vcf", tabix=tabix)
71
+ args["vcf"] = invcf
72
+ args["out"] = path.join(outdir, outprefix)
73
+ args["threads"] = ncores
74
+
75
+ cmd = [
76
+ plink,
77
+ "--make-bed",
78
+ *dict_to_cli_args(args, dup_key=False, dashify = True),
79
+ ]
80
+
81
+ run_command(cmd, fg=True, env={"cwd": outdir})
@@ -0,0 +1,85 @@
1
+ library(plotthis)
2
+ library(biopipen.utils)
3
+
4
+ indir <- {{in.indir | r}}
5
+ outdir <- {{out.outdir | r}}
6
+ plink <- {{envs.plink | r}}
7
+ ncores <- {{envs.ncores | r}}
8
+ cutoff <- {{envs.cutoff | r}}
9
+ doplot <- {{envs.plot | r}}
10
+ devpars <- {{envs.devpars | r}}
11
+
12
+ bedfile = Sys.glob(file.path(indir, '*.bed'))
13
+ if (length(bedfile) == 0)
14
+ stop("No bed files found in the input directory.")
15
+ if (length(bedfile) > 1) {
16
+ log_warn("Multiple bed files found in the input directory. Using the first one.")
17
+ bedfile <- bedfile[1]
18
+ }
19
+ input <- tools::file_path_sans_ext(bedfile)
20
+ output <- file.path(outdir, basename(input))
21
+
22
+ cmd <- c(
23
+ plink,
24
+ "--threads", ncores,
25
+ "--bfile", input,
26
+ "--hardy",
27
+ "--out", output
28
+ )
29
+ run_command(cmd, fg = TRUE)
30
+
31
+ hardy <- read.table(
32
+ paste0(output, '.hardy'),
33
+ header = TRUE,
34
+ row.names = NULL,
35
+ check.names = FALSE,
36
+ comment.char = ""
37
+ )
38
+ hardy.fail <- hardy[which(hardy$P < cutoff), 'ID', drop = FALSE]
39
+ write.table(
40
+ hardy.fail,
41
+ paste0(output, '.hardy.fail'),
42
+ col.names = FALSE,
43
+ row.names = FALSE,
44
+ sep = "\t",
45
+ quote = FALSE
46
+ )
47
+
48
+ if (doplot) {
49
+ hardy$Pval <- -log10(hardy$P)
50
+ hardy$Status <- "Pass"
51
+ hardy[which(hardy$SNP %in% hardy.fail$SNP), "Status"] <- "Fail"
52
+ hardy$Status <- factor(hardy$Status, levels = c("Fail", "Pass"))
53
+
54
+ p <- Histogram(
55
+ hardy,
56
+ x = "Pval",
57
+ group_by = "Status",
58
+ alpha = 0.8,
59
+ bins = 50,
60
+ xlab = "-log10(HWE p-value)",
61
+ ylab = "Count",
62
+ palette = "Set1"
63
+ )
64
+ res <- 70
65
+ height <- attr(p, "height") * res
66
+ width <- attr(p, "width") * res
67
+ png(
68
+ filename = paste0(output, '.hardy.png'),
69
+ width = width,
70
+ height = height,
71
+ res = res
72
+ )
73
+ print(p)
74
+ dev.off()
75
+ }
76
+
77
+ cmd <- c(
78
+ plink,
79
+ "--threads", ncores,
80
+ "--bfile", input,
81
+ "--exclude", paste0(output, '.hardy.fail'),
82
+ "--make-bed",
83
+ "--out", output
84
+ )
85
+ run_command(cmd, fg = TRUE)
@@ -0,0 +1,96 @@
1
+ library(plotthis)
2
+ library(biopipen.utils)
3
+
4
+ indir <- {{in.indir | r}}
5
+ outdir <- {{out.outdir | r}}
6
+ plink <- {{envs.plink | r}}
7
+ ncores <- {{envs.ncores | r}}
8
+ cutoff <- {{envs.cutoff | r}}
9
+ doplot <- {{envs.plot | r}}
10
+ devpars <- {{envs.devpars | r}}
11
+
12
+ log <- get_logger()
13
+
14
+ bedfile = Sys.glob(file.path(indir, '*.bed'))
15
+ if (length(bedfile) == 0)
16
+ stop("No bed files found in the input directory.")
17
+ if (length(bedfile) > 1) {
18
+ log$warn("Multiple bed files found in the input directory. Using the first one.")
19
+ bedfile <- bedfile[1]
20
+ }
21
+ input <- tools::file_path_sans_ext(bedfile)
22
+ output <- file.path(outdir, basename(input))
23
+
24
+ # need .afreq for --het for plink2
25
+ freq_cmd <- cmd <- c(
26
+ plink,
27
+ "--threads", ncores,
28
+ "--bfile", input,
29
+ "--freq",
30
+ "--out", output
31
+ )
32
+ run_command(freq_cmd, fg = TRUE)
33
+
34
+ cmd <- c(
35
+ plink,
36
+ "--threads", ncores,
37
+ "--bfile", input,
38
+ "--het",
39
+ "--out", output,
40
+ "--read-freq", paste0(output, '.afreq')
41
+ )
42
+ run_command(cmd, fg = TRUE)
43
+
44
+ phet <- read.table(
45
+ paste0(output, '.het'),
46
+ header = TRUE,
47
+ row.names = NULL,
48
+ check.names = FALSE,
49
+ comment.char = ""
50
+ )
51
+ het <- data.frame(Het = 1 - phet[, "O(HOM)"]/phet[, "OBS_CT"])
52
+ rownames(het) <- paste(phet$FID, phet$IID, sep = "\t")
53
+ het.mean <- mean(het$Het, na.rm = TRUE)
54
+ het.sd <- sd(het$Het, na.rm = TRUE)
55
+ het.fail <- rownames(het[
56
+ !is.na(het$Het) & (het$Het < het.mean-cutoff*het.sd | het$Het > het.mean+cutoff*het.sd), , drop = FALSE
57
+ ])
58
+ writeLines(het.fail, con = file(paste0(output, '.het.fail')))
59
+
60
+ if (doplot) {
61
+ het$Status <- "Pass"
62
+ het[het.fail, "Status"] <- "Fail"
63
+ het$Status <- factor(het$Status, levels = c("Fail", "Pass"))
64
+
65
+ p <- Histogram(
66
+ het,
67
+ x = "Het",
68
+ group_by = "Status",
69
+ alpha = 0.8,
70
+ bins = 50,
71
+ xlab = "Sample Heterozygosity",
72
+ ylab = "Count",
73
+ palette = "Set1"
74
+ )
75
+ res <- 70
76
+ height <- attr(p, "height") * res
77
+ width <- attr(p, "width") * res
78
+ png(
79
+ filename = paste0(output, '.het.png'),
80
+ width = width,
81
+ height = height,
82
+ res = res
83
+ )
84
+ print(p)
85
+ dev.off()
86
+ }
87
+
88
+ cmd <- c(
89
+ plink,
90
+ "--threads", ncores,
91
+ "--bfile", input,
92
+ "--remove", paste0(output, '.het.fail'),
93
+ "--make-bed",
94
+ "--out", output
95
+ )
96
+ run_command(cmd, fg = TRUE)