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
@@ -1,148 +1,346 @@
1
- source("{{biopipen_dir}}/utils/misc.R")
2
- source("{{biopipen_dir}}/utils/gsea.R")
3
- source("{{biopipen_dir}}/utils/mutate_helpers.R")
4
1
  library(rlang)
5
2
  library(Seurat)
6
3
  library(tidyseurat)
4
+ library(biopipen.utils)
7
5
 
8
6
  srtfile <- {{in.srtobj | r}} # nolint
9
7
  outdir <- {{out.outdir | r}} # nolint
8
+ joboutdir <- {{job.outdir | r}} # nolint
10
9
  mutaters <- {{envs.mutaters | r}} # nolint
11
- group.by <- {{envs["group-by"] | r}} # nolint
12
- ident.1 <- {{envs["ident-1"] | r}} # nolint
13
- ident.2 <- {{envs["ident-2"] | r}} # nolint
10
+ group_by <- {{envs.group_by | default: envs["group-by"] | default: None | r}} # nolint
11
+ ident_1 <- {{envs.ident_1 | default: envs["ident-1"] | default: None | r}} # nolint
12
+ ident_2 <- {{envs.ident_2 | default: envs["ident-2"] | default: None | r}} # nolint
13
+ assay <- {{envs.assay | r}} # nolint
14
14
  each <- {{envs.each | r}} # nolint
15
- section <- {{envs.section | r}} # nolint
15
+ subset <- {{envs.subset | r}} # nolint
16
16
  gmtfile <- {{envs.gmtfile | r}} # nolint
17
17
  method <- {{envs.method | r}} # nolint
18
18
  top <- {{envs.top | r}} # nolint
19
- minsize <- {{envs.minsize | r}} # nolint
20
- maxsize <- {{envs.maxsize | r}} # nolint
19
+ minsize <- {{envs.minSize | default: envs.minsize | r}} # nolint
20
+ maxsize <- {{envs.maxSize | default: envs.maxsize | r}} # nolint
21
21
  eps <- {{envs.eps | r}} # nolint
22
+ alleach_plots_defaults <- {{envs.alleach_plots_defaults | r}} # nolint
23
+ alleach_plots <- {{envs.alleach_plots | r}} #
22
24
  ncores <- {{envs.ncores | r}} # nolint
23
25
  rest <- {{envs.rest | r: todot="-"}} # nolint
24
26
  cases <- {{envs.cases | r: todot="-"}} # nolint
25
27
 
26
- srtobj <- readRDS(srtfile)
28
+ log <- get_logger()
29
+ reporter <- get_reporter()
30
+
31
+ alleach_plots <- lapply(alleach_plots, function(x) {
32
+ list_update(alleach_plots_defaults, x)
33
+ })
34
+
35
+ log$info("Reading Seurat object ...")
36
+ srtobj <- read_obj(srtfile)
37
+
27
38
  if (!is.null(mutaters) && length(mutaters) > 0) {
39
+ log$info("Mutating metadata columns ...")
28
40
  srtobj@meta.data <- srtobj@meta.data %>% mutate(!!!lapply(mutaters, parse_expr))
29
41
  }
30
42
 
31
- expand_cases <- function() {
32
- # fill up cases with missing parameters
33
- if (is.null(cases) || length(cases) == 0) {
34
- filled_cases <- list(
35
- DEFAULT = list(
36
- group.by = group.by,
37
- ident.1 = ident.1,
38
- ident.2 = ident.2,
39
- each = each,
40
- section = section,
41
- gmtfile = gmtfile,
42
- method = method,
43
- top = top,
44
- minsize = minsize,
45
- maxsize = maxsize,
46
- eps = eps,
47
- ncores = ncores,
48
- rest = rest
49
- )
50
- )
43
+ defaults <- list(
44
+ group_by = group_by,
45
+ ident_1 = ident_1,
46
+ ident_2 = ident_2,
47
+ assay = assay,
48
+ each = each,
49
+ subset = subset,
50
+ gmtfile = gmtfile,
51
+ method = method,
52
+ top = top,
53
+ minsize = minsize,
54
+ maxsize = maxsize,
55
+ eps = eps,
56
+ alleach_plots_defaults = alleach_plots_defaults,
57
+ alleach_plots = alleach_plots,
58
+ ncores = ncores,
59
+ rest = rest
60
+ )
61
+
62
+ expand_each <- function(name, case) {
63
+ outcases <- list()
64
+
65
+ case$group_by <- case$group_by %||% GetIdentityColumn(srtobj)
66
+
67
+ if (is.null(case$each) || is.na(case$each) || nchar(case$each) == 0 || isFALSE(each)) {
68
+ if (length(case$alleach_plots) > 0) {
69
+ stop("Cannot perform `alleach_plots` without `each` defined.")
70
+ }
71
+
72
+ outcases[[name]] <- case
51
73
  } else {
52
- filled_cases <- list()
53
- for (name in names(cases)) {
54
- case <- list_setdefault(
55
- cases[[name]],
56
- group.by = group.by,
57
- ident.1 = ident.1,
58
- ident.2 = ident.2,
59
- each = each,
60
- section = section,
61
- gmtfile = gmtfile,
62
- method = method,
63
- top = top,
64
- minsize = minsize,
65
- maxsize = maxsize,
66
- eps = eps,
67
- ncores = ncores,
68
- rest = rest
69
- )
70
- case$rest <- list_setdefault(case$rest, rest)
71
- filled_cases[[name]] <- case
74
+ eachs <- if (!is.null(case$subset)) {
75
+ srtobj@meta.data %>%
76
+ filter(!!parse_expr(case$subset)) %>%
77
+ pull(case$each) %>% na.omit() %>% unique() %>% as.vector()
78
+ } else {
79
+ srtobj@meta.data %>%
80
+ pull(case$each) %>% na.omit() %>% unique() %>% as.vector()
72
81
  }
73
- }
74
82
 
75
- outcases <- list()
76
- # expand each
77
- for (name in names(filled_cases)) {
78
- case <- filled_cases[[name]]
79
- if (is.null(case$each) || nchar(case$each) == 0) {
80
- outcases[[paste0(case$section, ":", name)]] <- case
83
+ if (length(cases) == 0 && name == "GSEA") {
84
+ prefix <- case$each
81
85
  } else {
82
- eachs <- srtobj@meta.data %>% pull(case$each) %>% na.omit() %>% unique() %>% as.vector()
83
- for (each in eachs) {
84
- by <- make.names(paste0(".", name, "_", case$each,"_", each))
85
- srtobj@meta.data <<- srtobj@meta.data %>%
86
- mutate(!!sym(by) := if_else(
87
- !!sym(case$each) == each,
88
- !!sym(case$group.by),
89
- NA
90
- ))
91
-
92
- key <- paste0(case$each, ":", each)
93
- if (name != "DEFAULT") {
94
- key <- paste0(key, " - ", name)
95
- }
96
- outcases[[key]] <- case
97
- outcases[[key]]$group.by <- by
86
+ prefix <- paste0(name, " (", case$each, ")")
87
+ }
88
+
89
+ for (each in eachs) {
90
+ newname <- paste0(prefix, "::", each)
91
+ newcase <- case
92
+
93
+ newcase$original_case <- paste0(name, " (all ", case$each,")")
94
+ newcase$each_name <- case$each
95
+ newcase$each <- each
96
+
97
+ newcase$alleach_plots_defaults <- NULL
98
+ newcase$alleach_plots <- NULL
99
+
100
+ if (!is.null(case$subset)) {
101
+ newcase$subset <- paste0(case$subset, " & ", bQuote(case$each), " == '", each, "'")
102
+ } else {
103
+ newcase$subset <- paste0(bQuote(case$each), " == '", each, "'")
98
104
  }
105
+
106
+ outcases[[newname]] <- newcase
107
+ }
108
+
109
+ if (length(case$alleach_plots) > 0) {
110
+ newcase <- case
111
+
112
+ newcase$gseas <- list()
113
+ newcase$alleach_plots <- lapply(
114
+ newcase$alleach_plots,
115
+ function(x) { list_update(newcase$alleach_plots_defaults, x) }
116
+ )
117
+
118
+ outcases[[paste0(name, " (all ", case$each,")")]] <- newcase
99
119
  }
100
120
  }
101
121
  outcases
102
122
  }
103
123
 
104
- do_case <- function(name, case) {
105
- print(paste("- Processing case:", name, "..."))
106
- section_case <- unlist(strsplit(name, ":"))
107
- section <- section_case[1]
108
- casename <- paste(section_case[-1], collapse = ":")
109
- case_dir <- file.path(outdir, section, casename)
110
- dir.create(case_dir, showWarnings = FALSE, recursive = TRUE)
124
+ log$info("Expanding cases...")
125
+ cases <- expand_cases(cases, defaults, expand_each, default_case = "GSEA")
126
+
127
+
128
+ ensure_sobj <- function(expr, allow_empty) {
129
+ tryCatch({ expr }, error = function(e) {
130
+ if (allow_empty) {
131
+ log$warn(" Ignoring this case: {e$message}")
132
+ return(NULL)
133
+ } else {
134
+ stop(e)
135
+ }
136
+ })
137
+ }
138
+
139
+ do_case <- function(name) {
140
+ log$info("- Processing case: {name} ...")
141
+ case <- cases[[name]]
142
+ info <- case_info(name, outdir, create = TRUE)
143
+
144
+ if (!is.null(case$gseas)) {
145
+
146
+ if (length(case$gseas) == 0) {
147
+ log$warn(" No GSEA results found for case {name}. Skipping.")
148
+ return(invisible(NULL))
149
+ }
150
+
151
+ each_levels <- names(case$gseas)
152
+ gseas <- do_call(rbind, lapply(each_levels, function(x) {
153
+ gsea_df <- case$gseas[[x]]
154
+ if (nrow(gsea_df) > 0) {
155
+ gsea_df[[case$each]] <- x
156
+ } else {
157
+ gsea_df[[case$each]] <- character(0) # Empty case
158
+ }
159
+ gsea_df
160
+ }))
161
+ gseas[[case$each]] <- factor(gseas[[case$each]], levels = each_levels)
162
+
163
+ for (plotname in names(case$alleach_plots)) {
164
+ plotargs <- case$alleach_plots[[plotname]]
165
+ plotargs <- extract_vars(plotargs, "devpars")
166
+ plotargs$gsea_results <- gseas
167
+ plotargs$group_by <- case$each
168
+ if (plotargs$plot_type == "heatmap") {
169
+ plotargs$show_row_names <- plotargs$show_row_names %||% TRUE
170
+ plotargs$show_column_names <- plotargs$show_column_names %||% TRUE
171
+ }
172
+
173
+ p <- do_call(VizGSEA, plotargs)
174
+
175
+ outprefix <- file.path(info$prefix, paste0("all.", slugify(plotname)))
176
+ save_plot(p, outprefix, devpars, formats = "png")
177
+ reporter$add2(
178
+ list(kind = "descr", content = paste0("Pathways for all ", case$each, ".")),
179
+ list(kind = "image", src = paste0(outprefix, ".png")),
180
+ hs = c(info$section, info$name),
181
+ hs2 = plotname
182
+ )
183
+ }
184
+
185
+ return(invisible(NULL))
186
+ }
111
187
 
188
+ allow_empty = !is.null(case$each)
112
189
  # prepare expression matrix
113
- print(" Preparing expression matrix...")
114
- sobj <- srtobj %>% filter(!is.na(!!sym(case$group.by)))
115
- if (!is.null(case$ident.2)) {
116
- sobj <- sobj %>% filter(!!sym(case$group.by) %in% c(case$ident.1, case$ident.2))
190
+ log$info(" Preparing expression matrix...")
191
+ sobj <- ensure_sobj({ srtobj %>% filter(!is.na(!!sym(case$group_by))) }, allow_empty)
192
+ if (is.null(sobj)) {
193
+ reporter$add2(
194
+ list(
195
+ kind = "error",
196
+ content = paste0("No cells with non-NA `", case$group_by, "` in the Seurat object.")
197
+ ),
198
+ hs = c(info$section, info$name)
199
+ )
200
+ return(NULL)
201
+ }
202
+
203
+ if (!is.null(case$subset)) {
204
+ sobj <- ensure_sobj({ sobj %>% filter(!!!parse_exprs(case$subset)) }, allow_empty)
205
+ if (is.null(sobj)) {
206
+ reporter$add2(
207
+ list(
208
+ kind = "error",
209
+ content = paste0("No cells with non-NA `", case$group_by, "` in the Seurat object.")
210
+ ),
211
+ hs = c(info$section, info$name)
212
+ )
213
+ return(NULL)
214
+ }
215
+ }
216
+ if (!is.null(case$ident_2)) {
217
+ sobj <- ensure_sobj({ sobj %>% filter(!!sym(case$group_by) %in% c(case$ident_1, case$ident_2)) }, allow_empty)
218
+ if (is.null(sobj)) {
219
+ reporter$add2(
220
+ list(
221
+ kind = "error",
222
+ content = paste0("No cells with non-NA `", case$group_by, "` in the Seurat object.")
223
+ ),
224
+ hs = c(info$section, info$name)
225
+ )
226
+ return(NULL)
227
+ }
117
228
  }
118
229
 
119
- allclasses <- sobj@meta.data[, case$group.by, drop = TRUE]
120
- if (is.null(case$ident.2)) {
121
- case$ident.2 <- ".rest"
122
- allclasses[allclasses != case$ident.1] <- ".rest"
230
+ allclasses <- sobj@meta.data[, case$group_by, drop = TRUE]
231
+ if (is.null(case$ident_2)) {
232
+ case$ident_2 <- "Other"
233
+ allclasses[allclasses != case$ident_1] <- "Other"
123
234
  }
124
- exprs <- GetAssayData(sobj, slot = "data", assay = "RNA")
235
+ exprs <- GetAssayData(sobj, layer = "data", assay = case$assay)
125
236
 
126
237
  # get preranks
127
- print(" Getting preranks...")
128
- ranks <- prerank(exprs, case$ident.1, case$ident.2, allclasses, case$method)
238
+ log$info(" Getting preranks...")
239
+ ranks <- RunGSEAPreRank(exprs, allclasses, case$ident_1, case$ident_2, case$method)
129
240
  write.table(
130
- ranks,
131
- file.path(case_dir, "fgsea.rank"),
132
- row.names = FALSE,
241
+ as.data.frame(ranks),
242
+ file.path(info$prefix, "fgsea.rank.txt"),
243
+ row.names = TRUE,
133
244
  col.names = TRUE,
134
245
  sep = "\t",
135
246
  quote = FALSE
136
247
  )
248
+ if (all(is.na(ranks))) {
249
+ log$warn(" All gene ranks are NA. It's probably due to high missing rate in the data.")
250
+ log$warn(" Case ignored, you may also try a different ranking method.")
251
+ reporter$add2(
252
+ list(
253
+ kind = "error",
254
+ content = "All gene ranks are NA. It's probably due to high missing rate in the data."
255
+ ),
256
+ hs = c(info$section, info$name)
257
+ )
258
+ return(invisible(NULL))
259
+ }
137
260
 
138
261
  # run fgsea
139
- print(" Running fgsea...")
140
- case$rest$minSize <- case$minsize
141
- case$rest$maxSize <- case$maxsize
262
+ log$info(" Running fgsea...")
263
+ case$rest$ranks <- ranks
264
+ case$rest$genesets <- ParseGMT(case$gmtfile)
265
+ case$rest$minSize <- case$rest$minSize %||% case$rest$minsize %||% case$minsize
266
+ case$rest$maxSize <- case$rest$maxSize %||% case$rest$maxsize %||% case$maxsize
142
267
  case$rest$eps <- case$eps
143
268
  case$rest$nproc <- case$ncores
144
- runFGSEA(ranks, gmtfile, case$top, case_dir, case$rest)
269
+ case$rest$minsize <- NULL
270
+ case$rest$maxsize <- NULL
271
+ result <- do_call(RunGSEA, case$rest)
272
+ write.table(
273
+ result,
274
+ file.path(info$prefix, "fgsea.tsv"),
275
+ row.names = FALSE,
276
+ col.names = TRUE,
277
+ sep = "\t",
278
+ quote = FALSE
279
+ )
280
+
281
+ aspect.ratio <- sqrt(case$top) / sqrt(10)
282
+ p_summary <- VizGSEA(
283
+ result,
284
+ plot_type = "summary",
285
+ top_term = case$top,
286
+ aspect.ratio = aspect.ratio
287
+ )
288
+ save_plot(
289
+ p_summary,
290
+ file.path(info$prefix, "summary"),
291
+ devpars = list(res = 100, height = attr(p_summary, "height") * 100 / 1.5, width = attr(p_summary, "width") * 100),
292
+ formats = "png"
293
+ )
294
+
295
+ p_gsea <- VizGSEA(
296
+ result,
297
+ plot_type = "gsea",
298
+ gs = result$pathway[1:min(case$top, nrow(result))]
299
+ )
300
+ save_plot(
301
+ p_gsea,
302
+ file.path(info$prefix, "pathways"),
303
+ devpars = list(res = 100, height = attr(p_gsea, "height") * 100, width = attr(p_gsea, "width") * 100),
304
+ formats = "png"
305
+ )
306
+
307
+
308
+ reporter$add2(
309
+ list(
310
+ name = paste0("Table (", case$ident_1, " vs ", case$ident_2, ")"),
311
+ contents = list(
312
+ list(kind = "descr", content = paste0(
313
+ "Showing top 50 pathways by padj in descending order. ",
314
+ "Use 'Download the entire data' button to download all pathways."
315
+ )),
316
+ list(kind = "table", src = file.path(info$prefix, "fgsea.tsv"), data = list(nrows = 50))
317
+ )
318
+ ),
319
+ list(
320
+ name = "Summary Plot",
321
+ contents = list(
322
+ list(kind = "descr", content = paste0("Showing top ", case$top, " pathways.")),
323
+ list(kind = "image", src = file.path(info$prefix, "summary.png"))
324
+ )
325
+ ),
326
+ list(
327
+ name = "GSEA Plots",
328
+ contents = list(
329
+ list(kind = "descr", content = paste0("Showing top ", case$top, " pathways.")),
330
+ list(kind = "image", src = file.path(info$prefix, "pathways.png"))
331
+ )
332
+ ),
333
+ hs = c(info$section, info$name),
334
+ ui = "tabs"
335
+ )
336
+
337
+ if (!is.null(case$original_case) && !is.null(cases[[case$original_case]])) {
338
+ cases[[case$original_case]]$gseas[[case$each]] <<- result
339
+ }
340
+
341
+ invisible()
145
342
  }
146
343
 
147
- cases <- expand_cases()
148
- sapply(sort(names(cases)), function(name) do_case(name, cases[[name]]))
344
+ sapply(names(cases), function(name) do_case(name))
345
+
346
+ reporter$save(joboutdir)
@@ -0,0 +1,65 @@
1
+ library(rlang)
2
+ library(splatter)
3
+ library(scater)
4
+ library(biopipen.utils)
5
+
6
+ # Load template variables
7
+ seed <- {{ in.seed | r }}
8
+ outfile <- {{ out.outfile | r }}
9
+ ngenes <- {{ envs.ngenes | r }}
10
+ ncells <- {{ envs.ncells | r }}
11
+ nspikes <- {{ envs.nspikes | r }}
12
+ outtype <- {{ envs.outtype | r }}
13
+ method <- {{ envs.method | r }}
14
+ user_params <- {{ envs.params | r: todot="-" }}
15
+
16
+ log <- get_logger()
17
+
18
+ log$info("Generating simulation parameters ...")
19
+
20
+ seed <- seed %||% 1
21
+ if (length(seed) > 1) {
22
+ log$warn("- multiple seeds provided, using the first one")
23
+ seed <- seed[1]
24
+ }
25
+ if (is.character(seed)) {
26
+ library(digest)
27
+ proj <- seed
28
+ seed <- digest2int(seed)
29
+ } else {
30
+ proj <- paste0("S", seed)
31
+ }
32
+
33
+ set.seed(seed)
34
+ mock_sce_params <- list()
35
+ if (!is.null(ngenes)) mock_sce_params$ngenes <- ngenes
36
+ if (!is.null(ncells)) mock_sce_params$ncells <- ncells
37
+ if (!is.null(nspikes)) mock_sce_params$nspikes <- nspikes
38
+ sce <- do.call(mockSCE, mock_sce_params)
39
+ params <- splatEstimate(sce)
40
+ user_params$seed <- seed
41
+ user_params$object = params
42
+ do_call(setParams, user_params)
43
+
44
+
45
+ log$info("Saving simulation parameters to file ...")
46
+
47
+ sim <- splatSimulate(params, method = method, verbose = TRUE)
48
+
49
+ outtype <- tolower(outtype)
50
+ if (outtype == "sce") outtype <- "singlecellexperiment"
51
+
52
+ if (outtype == "singlecellexperiment") {
53
+ log$info("Saving simulation to file ...")
54
+ save_obj(sim, file = outfile)
55
+ } else {
56
+ log$info("Converting simulation to Seurat object ...")
57
+ cnts <- SingleCellExperiment::counts(sim)
58
+ sobj <- Seurat::CreateSeuratObject(counts = cnts, project = proj)
59
+ rm(sim)
60
+ rm(cnts)
61
+ gc()
62
+
63
+ log$info("Saving simulation to file ...")
64
+ save_obj(sobj, file = outfile)
65
+ }