From 1de53e5e6ecac74989f96a6da3926f21adb15a04 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Luc=C3=ADa=20Pe=C3=B1a-P=C3=A9rez?= Date: Thu, 10 Oct 2024 09:57:42 +0200 Subject: [PATCH] Apply suggestions from code review Co-authored-by: Felix Lenner <52530259+fellen31@users.noreply.github.com> --- bin/drop_sample_annot.py | 4 ---- docs/usage.md | 4 ++-- nextflow.config | 2 +- workflows/tomte.nf | 1 - 4 files changed, 3 insertions(+), 8 deletions(-) diff --git a/bin/drop_sample_annot.py b/bin/drop_sample_annot.py index e05b7d7..6dde5fb 100755 --- a/bin/drop_sample_annot.py +++ b/bin/drop_sample_annot.py @@ -67,8 +67,6 @@ def is_stranded(strandedness: str) -> str: def count_mode(sample_count_mode: str) -> str: """Logical funciton to determine if count mode is given or default "IntersectionStrict" should be used""" - print("Hello") - print(sample_count_mode) if isna(sample_count_mode) or sample_count_mode == "" or sample_count_mode == "NA": return "IntersectionStrict" else: @@ -77,8 +75,6 @@ def count_mode(sample_count_mode: str) -> str: def count_overlaps(sample_count_overlap: str) -> str: """Logical funciton to determine if count overlap is given or default "TRUE" should be used""" - print("Hello") - print(sample_count_overlap) if ( isna(sample_count_overlap) or sample_count_overlap == "" diff --git a/docs/usage.md b/docs/usage.md index bfdf092..ef53022 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -282,11 +282,11 @@ To build your own database you will need at least 50 for aberrant expression, if - `--skip_export_counts_drop false` this switch will ensure that a folder called export_counts is created - `--skip_drop_as false` if you want to get a database for aberrant splicing - `--skip_drop_ae false` if you want to get a database for aberrant expression -- `--skip_subsample_region false` if you have sequenced any material with overrrepresented regions (such as hemoglobin in whole blood) we recommend to remove it by setting this parameter to false and providing a bed with thet overrepresented region with `--subsample_bed` +- `--skip_subsample_region false` if you have sequenced any material with overrepresented regions (such as hemoglobin in whole blood) we recommend to remove it by setting this parameter to false and providing a bed with the overrepresented region with `--subsample_bed` - `--skip_downsample false` if you have very deeply sequenced samples, we recommend to downsample, the default is 60M read pairs - `--skip_build_tracks true`, `--skip_stringtie true`, `--skip_vep true` as most users will be interested in getting the database rather than other downstream results -Running DROP with many samples requires a lot of time and a lot of memory, that is why we recommend to subsample overrepresented regions and downsampled if you have deeply sequenced samples. If your run fails for either of this reasons, try to relaunched it from the work directory where DROP was run so that DROP continues from the point where it failed (if you restart the pipeline with `-resume` it will begin from the start and it will likely fail in the same way). +Running DROP with many samples requires a lot of time and a lot of memory, that is why we recommend to subsample overrepresented regions and downsample if you have deeply sequenced samples. If your run fails for either of this reasons, try to relaunch it from the work directory where DROP was run so that DROP continues from the point where it failed (if you restart the pipeline with `-resume` it will begin from the start and it will likely fail in the same way). To restart DROP, start by finding the work directory where it was run. You can do so by opening the execution trace file in the pipeline_info folder and looking at the hash of the processes with name `TOMTE:ANALYSE_TRANSCRIPTS:DROP_CONFIG_RUN_AE` and `TOMTE:ANALYSE_TRANSCRIPTS:DROP_CONFIG_RUN_AS`. The work directory used to run the pipeline followed by the hash should be enough information to find the folder where DROP was run. Tomte should have set everything up in that directory so go into it and restart the run by running from the container created by Tomte the script `.command.sh`. If you want to run it with slurm remember to add a header with number of cores, time... diff --git a/nextflow.config b/nextflow.config index f5497b9..99597ed 100644 --- a/nextflow.config +++ b/nextflow.config @@ -50,7 +50,7 @@ params { skip_stringtie = false skip_drop_ae = false skip_drop_as = false - skip_export_counts_drop = true + skip_export_counts_drop = true drop_group_samples_ae = 'outrider' drop_group_samples_as = 'fraser' drop_padjcutoff_ae = 0.05 diff --git a/workflows/tomte.nf b/workflows/tomte.nf index 19061de..ed2172b 100644 --- a/workflows/tomte.nf +++ b/workflows/tomte.nf @@ -22,7 +22,6 @@ include { CALL_VARIANTS } from '../subworkflows/local/call_variants' include { ALLELE_SPECIFIC_CALLING } from '../subworkflows/local/allele_specific_calling' include { ANNOTATE_SNV } from '../subworkflows/local/annotate_snv' include { IGV_TRACKS } from '../subworkflows/local/igv_tracks' -//include { BUILD_DROP_DATABASE } from '../subworkflows/local/drop_database' include { methodsDescriptionText } from '../subworkflows/local/utils_nfcore_tomte_pipeline' //