---
title: "13-Peve-lncRNA-matrix"
format: html
editor: visual
---

```{bash}
mkdir -p ../output/13-Peve-lncRNA-matrix
```

```{bash}
/home/shared/subread-2.0.5-Linux-x86_64/bin/featureCounts \
  -T 42 \
  -O \
  --fraction \
  -a ../output/12-Peve-lncRNA-discovery/lncRNA.gtf \
  -o ../output/13-Peve-lncRNA-matrix/Peve_lncRNA_counts.txt \
  -t lncRNA \
  -g gene_id \
  -p \
../output/12-Peve-lncRNA-discovery/*sorted.bam
```

```{bash}
head ../output/13-Peve-lncRNA-matrix/Peve_lncRNA_counts.txt
```

# Alternative approach: If the -F flag doesn't work as expected,

# you can post-process the output file to rename columns

# This script extracts just the filename without the path

```{bash}
awk -v FS='\t' -v OFS='\t' '
  /^Geneid(\t|$)/ {
    for (i=7; i<=NF; i++) {
      gsub(/^.*\//, "", $i);          # drop path
      sub(/\.sorted\.bam$/, "", $i);  # drop suffix
    }
  }
  { print }
' ../output/13-Peve-lncRNA-matrix/Peve_lncRNA_counts.txt > ../output/13-Peve-lncRNA-matrix/Peve_lncRNA_counts.clean.txt
```

```{bash}
head ../output/13-Peve-lncRNA-matrix/Peve_lncRNA_counts.clean.txt
```

```{bash}
python 13.1-filter_count_matrix.py ../output/13-Peve-lncRNA-matrix/Peve_lncRNA_counts.clean.txt ../output/13-Peve-lncRNA-matrix/Peve_lncRNA_counts_filtered.txt
```