From ecc421f79899487ab8fd86e82d18f6026fc54ee8 Mon Sep 17 00:00:00 2001 From: sepro Date: Fri, 7 Apr 2017 13:20:02 +0200 Subject: [PATCH 1/2] fixed small issue with spaces in gene names. --- README.md | 2 +- pipeline/check/quality.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 0d33c7c..8455810 100644 --- a/README.md +++ b/README.md @@ -94,7 +94,7 @@ for LSTrAP can be generated. ## Adapting LSTrAP to other cluster managers -LSTrAP is designed and tested on an Oracle Grid Engine, though with minimal effort it can be adopted to run on PBS and Torque +LSTrAP is designed and tested on a cluster running the Oracle Grid Engine, though with minimal effort it can be adopted to run on PBS and Torque based systems (and likely others). First, in the configuration file, check the qsub parameters (e.g. jobs that require multiple CPUs to run *-pe cores 4*), that differ between systems are set up properly (the nodes and cores on Torque and PBS need to be set using *-l nodes=4:ppn=2* to request 4 nodes with 2 processes per node). diff --git a/pipeline/check/quality.py b/pipeline/check/quality.py index d5422a6..3f6eff8 100644 --- a/pipeline/check/quality.py +++ b/pipeline/check/quality.py @@ -46,7 +46,7 @@ def check_htseq(filename, cutoff=0, log=None): with open(filename) as fin: mapped_reads = 0 for line in fin: - gene, value = line.strip().split() + gene, value = line.strip().rsplit(maxsplit=1) if gene not in quality_fields: mapped_reads += int(value) From 0c3a84d831e89732c8ae9edc29b9439db240018f Mon Sep 17 00:00:00 2001 From: sepro Date: Fri, 7 Apr 2017 14:08:06 +0200 Subject: [PATCH 2/2] fixed small issue with spaces in gene names. (in helper script this time) --- helper/htseq_count_stats.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/helper/htseq_count_stats.py b/helper/htseq_count_stats.py index 52eb5d4..3071102 100644 --- a/helper/htseq_count_stats.py +++ b/helper/htseq_count_stats.py @@ -23,7 +23,7 @@ mapped_reads = 0 for line in fin: - gene, value = line.strip().split() + gene, value = line.strip().rsplit(maxsplit=1) if gene not in quality_fields: mapped_reads += int(value)