cleaned up mutation colors and plotting

Author: mdiberna

.gitignore

@@ -11,9 +11,8 @@ data/genome_data/*.txt
 data/ribosome_profiling
 data/mutation_data
 
-# output folders
-notebooks/**/
-notebooks/*_test.ipynb
+# test notebooks
+notebooks/
 
 # script outputs
 scripts/out

notebooks/bed_cleanup.ipynb

@@ -390,7 +390,7 @@ async def process_gene(
                         alt_features=truncation_feature,
                         mutations_df=pair_mutations,
                         output_file=str(
-                            transcript_dir / f"{pair_base_filename}_filtered.png"
+                            transcript_dir / f"{pair_base_filename}_filtered.pdf"
                         ),
                     )
 
@@ -401,7 +401,7 @@ async def process_gene(
                         alt_features=truncation_feature,
                         mutations_df=pair_mutations,
                         output_file=str(
-                            transcript_dir / f"{pair_base_filename}_filtered_zoom.png"
+                            transcript_dir / f"{pair_base_filename}_filtered_zoom.pdf"
                         ),
                         padding=100,
                     )

scripts/analyze_truncations.py

@@ -5,15 +5,15 @@
 #SBATCH --ntasks=1                      # Run a single task
 #SBATCH --cpus-per-task=12              # Single CPU for the controller job
 #SBATCH --mem=24G                       # Memory for the controller job
-#SBATCH --time=1:00:00                  # Time limit (hrs:min:sec)
+#SBATCH --time=12:00:00                  # Time limit (hrs:min:sec)
 #SBATCH --output=out/truncations-%j.out # Standard output log
 
 # Activate conda environment (adjust path as needed)
 source ~/.bashrc
 conda activate swissisoform
 
 # Create output directory
-mkdir -p results_reduced
+mkdir -p results
 
 # Define paths for command-line arguments
 GENE_LIST="../data/ribosome_profiling/gene_list.txt"

scripts/analyze_truncations_full.sh

@@ -0,0 +1,51 @@
+#!/usr/bin/env python3
+
+"""Cleanup files for the ribosome profiling data.
+
+This script cleans up the GTF file and BED files for the ribosome profiling data.
+It updates the gene names in the GTF file to match the latest version of the GTF file.
+It also cleans up the BED files to update gene names and remove duplicates.
+"""
+
+from swissisoform.alternative_isoforms import AlternativeIsoform
+from swissisoform.utils import cleanup_bed, update_gencode_gene_names
+
+# GTF: update gene names 
+input_gtf = "../data/genome_data/gencode.v25.annotation.gtf"
+output_gtf = "../data/genome_data/gencode.v25.annotation.ensembl_cleaned.gtf"
+reference_gtf = "../data/genome_data/gencode.v47.annotation.gtf"
+
+update_gencode_gene_names(
+    input_gtf_path=input_gtf,
+    output_gtf_path=output_gtf,
+    reference_gtf_path=reference_gtf,
+    verbose=True,
+)
+
+# All truncations: bed cleanup
+input_bed = "../data/ribosome_profiling/full_truncations_JL.bed"
+output_bed = "../data/ribosome_profiling/full_truncations_JL_cleaned.bed"
+
+cleanup_bed(input_bed, output_bed, gtf_path=output_gtf, verbose=True)
+
+alt_isoforms = AlternativeIsoform()
+alt_isoforms.load_bed("../data/ribosome_profiling/full_truncations_JL_cleaned.bed")
+gene_list = alt_isoforms.get_gene_list()
+
+with open("../data/ribosome_profiling/gene_list.txt", "w") as f:
+    for gene in gene_list:
+        f.write(gene + "\n")
+
+# Selected truncations: bed cleanup
+input_bed = "../data/ribosome_profiling/selected_truncations_JL.bed"
+output_bed = "../data/ribosome_profiling/selected_truncations_JL_cleaned.bed"
+
+cleanup_bed(input_bed, output_bed, gtf_path=output_gtf, verbose=True)
+
+alt_isoforms = AlternativeIsoform()
+alt_isoforms.load_bed("../data/ribosome_profiling/selected_truncations_JL_cleaned.bed")
+gene_list = alt_isoforms.get_gene_list()
+
+with open("../data/ribosome_profiling/gene_list_reduced.txt", "w") as f:
+    for gene in gene_list:
+        f.write(gene + "\n")