From 028e4fd899acaa653ac596f2692f7b24e19616e6 Mon Sep 17 00:00:00 2001 From: Gregor Rot Date: Thu, 4 Apr 2024 08:34:54 +0200 Subject: [PATCH 1/2] skip comments at beginning of samples.tab --- splicekit/core/annotation.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/splicekit/core/annotation.py b/splicekit/core/annotation.py index d995db9..e20b637 100644 --- a/splicekit/core/annotation.py +++ b/splicekit/core/annotation.py @@ -74,7 +74,10 @@ def make_comparisons(): annotation.treatments = {} samples = set() f = open("samples.tab") - header = f.readline().replace("\r", "").replace("\n", "").split("\t") + r = f.readline() + while r.startswith("#"): + r = f.readline() + header = r.replace("\r", "").replace("\n", "").split("\t") r = f.readline() separates = set() while r: From df49b7ca2d10202d7fdac4d3e298ecac490c950e Mon Sep 17 00:00:00 2001 From: Gregor Rot Date: Fri, 5 Apr 2024 10:29:42 +0200 Subject: [PATCH 2/2] removed underscore from samples.tab dataset --- datasets/GSE182150/samples.tab | 72 +++++++++++++++++----------------- splicekit/__init__.py | 1 + splicekit/core/report.py | 5 ++- 3 files changed, 41 insertions(+), 37 deletions(-) diff --git a/datasets/GSE182150/samples.tab b/datasets/GSE182150/samples.tab index 339ac76..2602e9d 100644 --- a/datasets/GSE182150/samples.tab +++ b/datasets/GSE182150/samples.tab @@ -1,38 +1,38 @@ # note that this is a TAB delimited file (use TAB characters to separate values) sample_id readout_id treatment_id individual -GSM5519243 SRR15462283 DMSO Kasumi-1 -GSM5519244 SRR15462284 DMSO Kasumi-1 -GSM5519245 SRR15462285 DMSO Kasumi-1 -GSM5519246 SRR15462286 DMSO Kasumi-1 -GSM5519247 SRR15462287 DMSO Kasumi-1 -GSM5519248 SRR15462288 DMSO Kasumi-1 -GSM5519249 SRR15462289 Ava_12nM Kasumi-1 -GSM5519250 SRR15462290 Ava_12nM Kasumi-1 -GSM5519251 SRR15462291 GSK_12nM Kasumi-1 -GSM5519252 SRR15462292 GSK_12nM Kasumi-1 -GSM5519253 SRR15462293 Ava_12nM_AND_GSK_12nM Kasumi-1 -GSM5519254 SRR15462294 Ava_12nM_AND_GSK_12nM Kasumi-1 -GSM5519315 SRR15462355 DMSO Kasumi-1 -GSM5519316 SRR15462356 DMSO Kasumi-1 -GSM5519317 SRR15462357 DMSO Kasumi-1 -GSM5519318 SRR15462358 Ava_50nM Kasumi-1 -GSM5519319 SRR15462359 Ava_50nM Kasumi-1 -GSM5519320 SRR15462360 Ava_50nM Kasumi-1 -GSM5519321 SRR15462361 Dox_1ugml Kasumi-1 -GSM5519322 SRR15462362 Dox_1ugml Kasumi-1 -GSM5519323 SRR15462363 Dox_1ugml Kasumi-1 -GSM5519324 SRR15462364 Ava_50nM_AND_Dox_1ugml Kasumi-1 -GSM5519325 SRR15462365 Ava_50nM_AND_Dox_1ugml Kasumi-1 -GSM5519326 SRR15462366 Ava_50nM_AND_Dox_1ugml Kasumi-1 -GSM5519343 SRR15462383 DMSO 14-00613 -GSM5519344 SRR15462384 DMSO 14-00613 -GSM5519345 SRR15462385 DMSO 14-00613 -GSM5519346 SRR15462386 Ava_350nM 14-00613 -GSM5519347 SRR15462387 Ava_350nM 14-00613 -GSM5519348 SRR15462388 Ava_350nM 14-00613 -GSM5519349 SRR15462389 ORY_12nM 14-00613 -GSM5519350 SRR15462390 ORY_12nM 14-00613 -GSM5519351 SRR15462391 ORY_12nM 14-00613 -GSM5519352 SRR15462392 Ava_350nM_AND_ORY_12nM 14-00613 -GSM5519353 SRR15462393 Ava_350nM_AND_ORY_12nM 14-00613 -GSM5519354 SRR15462394 Ava_350nM_AND_ORY_12nM 14-00613 +GSM5519243 SRR15462283 DMSO Kasumi_1 +GSM5519244 SRR15462284 DMSO Kasumi_1 +GSM5519245 SRR15462285 DMSO Kasumi_1 +GSM5519246 SRR15462286 DMSO Kasumi_1 +GSM5519247 SRR15462287 DMSO Kasumi_1 +GSM5519248 SRR15462288 DMSO Kasumi_1 +GSM5519249 SRR15462289 Ava_12nM Kasumi_1 +GSM5519250 SRR15462290 Ava_12nM Kasumi_1 +GSM5519251 SRR15462291 GSK_12nM Kasumi_1 +GSM5519252 SRR15462292 GSK_12nM Kasumi_1 +GSM5519253 SRR15462293 Ava_12nM_AND_GSK_12nM Kasumi_1 +GSM5519254 SRR15462294 Ava_12nM_AND_GSK_12nM Kasumi_1 +GSM5519315 SRR15462355 DMSO Kasumi_1 +GSM5519316 SRR15462356 DMSO Kasumi_1 +GSM5519317 SRR15462357 DMSO Kasumi_1 +GSM5519318 SRR15462358 Ava_50nM Kasumi_1 +GSM5519319 SRR15462359 Ava_50nM Kasumi_1 +GSM5519320 SRR15462360 Ava_50nM Kasumi_1 +GSM5519321 SRR15462361 Dox_1ugml Kasumi_1 +GSM5519322 SRR15462362 Dox_1ugml Kasumi_1 +GSM5519323 SRR15462363 Dox_1ugml Kasumi_1 +GSM5519324 SRR15462364 Ava_50nM_AND_Dox_1ugml Kasumi_1 +GSM5519325 SRR15462365 Ava_50nM_AND_Dox_1ugml Kasumi_1 +GSM5519326 SRR15462366 Ava_50nM_AND_Dox_1ugml Kasumi_1 +GSM5519343 SRR15462383 DMSO 14_00613 +GSM5519344 SRR15462384 DMSO 14_00613 +GSM5519345 SRR15462385 DMSO 14_00613 +GSM5519346 SRR15462386 Ava_350nM 14_00613 +GSM5519347 SRR15462387 Ava_350nM 14_00613 +GSM5519348 SRR15462388 Ava_350nM 14_00613 +GSM5519349 SRR15462389 ORY_12nM 14_00613 +GSM5519350 SRR15462390 ORY_12nM 14_00613 +GSM5519351 SRR15462391 ORY_12nM 14_00613 +GSM5519352 SRR15462392 Ava_350nM_AND_ORY_12nM 14_00613 +GSM5519353 SRR15462393 Ava_350nM_AND_ORY_12nM 14_00613 +GSM5519354 SRR15462394 Ava_350nM_AND_ORY_12nM 14_00613 diff --git a/splicekit/__init__.py b/splicekit/__init__.py index c88f8f6..545bffa 100644 --- a/splicekit/__init__.py +++ b/splicekit/__init__.py @@ -280,5 +280,6 @@ def process(force=False): motifs() promisc() clusterlogfc_process() + june_process() splicekit.report.process() jbrowse2_process(force_samples=force, force_annotation=force) diff --git a/splicekit/core/report.py b/splicekit/core/report.py index 84efc1e..a2e72eb 100644 --- a/splicekit/core/report.py +++ b/splicekit/core/report.py @@ -45,7 +45,10 @@ def edgeR_feature(feature_name, version=""): samples = [] f = open("samples.tab", "rt") - header = f.readline().replace("\r", "").replace("\n", "").split("\t") + r = f.readline() + while r.startswith("#"): + r = f.readline() + header = r.replace("\r", "").replace("\n", "").split("\t") r = f.readline() while r: r = r.replace("\r", "").replace("\n", "").split("\t")