Merge pull request #2 from IGDRion/dev

Merge with dev to main for TFK updates, lncRNAs noORF, bambu memory
IGDRion · Mar 22, 2023 · 88df06e · 88df06e
2 parents 9738240 + 89329e3
commit 88df06e
Show file tree

Hide file tree

Showing 8 changed files with 17 additions and 11 deletions.
diff --git a/ANNEXA b/ANNEXA
diff --git a/README.md b/README.md
@@ -2,7 +2,7 @@
 
 ## Introduction
 
-**ANNEXA** is an all-in-one reproductible pipeline, written in the [Nextflow](https://nextflow.io), which allows users to analyze LR-RNAseq sequences from Oxford Nanopore Technologies (ONT), and to reconstruct and quantify known and novel genes and isoforms.
+**ANNEXA** is an all-in-one reproductible pipeline, written in the [Nextflow](https://nextflow.io), which allows users to analyze LR-RNAseq data (Long-Read RNASeq), and to reconstruct and quantify known and novel genes and isoforms.
 
 ## Pipeline summary
 
@@ -41,7 +41,7 @@ nextflow run IGDRion/ANNEXA \
     --fa /path/to/ref.fa
 ```
 
-The input parameter takes a file listing the bams to analyze (see example below)
+The input parameter takes a file listing the `bam` path files to analyze (see example below)
 
 ```
 /path/to/1.bam

diff --git a/bin/filter_gtf_ndr.py b/bin/filter_gtf_ndr.py
@@ -9,7 +9,7 @@ def parse_bambu(line):
 
 def parse_tfkmers(line):
     ids = line[0].split("::")
-    return ids[0], ids[1], line[2]
+    return ids[0], ids[1], line[1]
 
 
 def parse_ndr(csv, origin, th) -> Set[str]:

diff --git a/bin/qc.R b/bin/qc.R
@@ -230,8 +230,7 @@ gene_ext_dist = gene %>%
 # TRANSCRIPT
 #############################################################################
 transcript = read.csv(paste0(prefix,".transcript.stats"), header = T)
-lncRNA_biotypes = c("retained_intron",
-                    "lncRNA",
+lncRNA_biotypes = c("lncRNA",
                     "antisense",
                     "non-coding",
                     "lnc_RNA")

diff --git a/environment.yml b/environment.yml
@@ -8,7 +8,8 @@ dependencies:
 
   - conda-forge::r-base=4.1
   - conda-forge::r-rcolorbrewer
-  - conda-forge::r-tidyverse
+  - conda-forge::r-tidyverse=1.3.2
+  - conda-forge::r-dplyr=1.0.10
   - conda-forge::r-reshape2
   - conda-forge::r-ggpubr
   - conda-forge::r-ggridges

diff --git a/modules/feelnc/codpot.nf b/modules/feelnc/codpot.nf
@@ -30,6 +30,11 @@ process FEELNC_CODPOT {
       -l known_lncRNA.gtf \
       --numtx=3000,3000 \
       -o new
+  
+  # consider new noORF transcripts as new lncRNA
+  if [ -e feelnc_codpot_out/new.noORF.gtf ]; then
+    cat feelnc_codpot_out/new.noORF.gtf >> feelnc_codpot_out/new.lncRNA.gtf
+  fi
   """
 }
 
diff --git a/modules/index_bam.nf b/modules/index_bam.nf
@@ -1,8 +1,8 @@
 process INDEX_BAM {
-  conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
+  conda (params.enable_conda ? "bioconda::samtools=1.16.1" : null)
   container "${ workflow.containerEngine == 'singularity' ? 
-                'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' : 
-                'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }"
+                'https://depot.galaxyproject.org/singularity/samtools%3A1.16.1--h6899075_0' : 
+                'quay.io/biocontainers/samtools:1.16.1--h1170115_0' }"
 
   input:
   file bam

diff --git a/nextflow.config b/nextflow.config
@@ -3,7 +3,7 @@ params {
   outdir            = "results"
   withGeneCoverage  = false
   maxCpu            = 8
-  maxMemory         = "40GB"
+  maxMemory         = "80GB"
   enable_conda      = false
   filter            = false
   tfkmers_threshold = 0.2
@@ -14,7 +14,7 @@ params {
 }
 
 process {
-  memory = '8GB'
+  memory = '16GB'
 }
 
 profiles {