Star Rna Seq Aligner

# Install with conda (recommended)
conda install -c bioconda star

# Verify
STAR --version
# STAR_2.7.11a

# Or compile from source
git clone https://github.com/alexdobin/STAR
cd STAR/source && make STAR

decisions:
  - id: D1
    param: reference_bundle
    kind: required
    source: user
    ask: "Which species, genome assembly, and matching GTF annotation release should be used?"
    default: null

  - id: D2
    param: --sjdbOverhang
    kind: derived
    source: data
    ask: "What is the longest trimmed read length observed in the FASTQ files?"
    default: "maximum trimmed read length minus 1"

  - id: D3
    param: --quantMode
    kind: derived
    source: upstream
    ask: "Does the downstream workflow require STAR gene counts, transcriptome BAM for RSEM, or only the genomic BAM?"
    default: "no quantMode; emit a coordinate-sorted genomic BAM"

  - id: D4
    param: --twopassMode
    kind: optional
    source: user
    ask: "Should alignment prioritize sensitive discovery of novel splice junctions?"
    default: "None"

  - id: D5
    param: --outFilterMultimapNmax
    kind: optional
    source: user
    ask: "How many genomic loci may a read match before it is treated as too ambiguous to align?"
    default: 10

  - id: D6
    param: --outFilterMismatchNmax
    kind: optional
    source: user
    ask: "Does this assay require a non-default maximum number of alignment mismatches?"
    default: 10

  - id: D7
    param: --alignIntronMax
    kind: optional_conditional
    source: literature
    ask: "Does the organism or assay require an intron-length limit different from the reference bundle's standard setting?"
    default: 1000000

  - id: D8
    param: --genomeSAindexNbases
    kind: never_ask
    source: data
    reason: "Calculated from genome length to size the index; it affects memory use, not the biological result."
    default: "min(14, floor(log2(genome_length) / 2 - 1))"

  - id: D9
    param: --runThreadN
    kind: never_ask
    source: data
    reason: "Affects runtime only, not the alignments"
    default: "min(8, available_cores)"

# 1. Generate genome index (~30 min, run once)
STAR --runMode genomeGenerate \
     --runThreadN 8 \
     --genomeDir genome/star_index \
     --genomeFastaFiles genome/GRCh38.fa \
     --sjdbGTFfile genome/gencode.v47.gtf \
     --sjdbOverhang 100    # ReadLength - 1

# 2. Align paired-end reads (~10-20 min)
STAR --runThreadN 8 \
     --genomeDir genome/star_index \
     --readFilesIn sample_R1.fastq.gz sample_R2.fastq.gz \
     --readFilesCommand zcat \
     --outSAMtype BAM SortedByCoordinate \
     --outFileNamePrefix results/sample/

# 3. Index the BAM
samtools index results/sample/Aligned.sortedByCoord.out.bam

# Download GRCh38 genome and GENCODE annotation
wget https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_47/GRCh38.primary_assembly.genome.fa.gz
wget https://ftp.ebi.ac.uk/pub/databases/gencode/Gencode_human/release_47/gencode.v47.primary_assembly.annotation.gtf.gz

gunzip GRCh38.primary_assembly.genome.fa.gz gencode.v47.primary_assembly.annotation.gtf.gz
mkdir -p genome/star_index

echo "Genome and GTF ready."
ls -lh GRCh38.primary_assembly.genome.fa gencode.v47.primary_assembly.annotation.gtf

# Standard human genome index (requires ~32 GB RAM)
STAR --runMode genomeGenerate \
     --runThreadN 16 \
     --genomeDir genome/star_index/ \
     --genomeFastaFiles GRCh38.primary_assembly.genome.fa \
     --sjdbGTFfile gencode.v47.primary_assembly.annotation.gtf \
     --sjdbOverhang 100

# For small genomes (e.g., E. coli ~4.6 Mb), reduce genomeSAindexNbases
# STAR --runMode genomeGenerate \
#      --genomeSAindexNbases 11 \
#      --genomeDir genome/ecoli_index/ ...

echo "Index complete: $(ls genome/star_index/ | wc -l) files"

# Single-end alignment
STAR --runThreadN 8 \
     --genomeDir genome/star_index/ \
     --readFilesIn sample1.fastq.gz \
     --readFilesCommand zcat \
     --outSAMtype BAM SortedByCoordinate \
     --outSAMattributes NH HI AS NM MD \
     --outFileNamePrefix results/sample1/

# Paired-end alignment
STAR --runThreadN 8 \
     --genomeDir genome/star_index/ \
     --readFilesIn sample1_R1.fastq.gz sample1_R2.fastq.gz \
     --readFilesCommand zcat \
     --outSAMtype BAM SortedByCoordinate \
     --outSAMattributes NH HI AS NM MD \
     --outFileNamePrefix results/sample1/

echo "BAM: results/sample1/Aligned.sortedByCoord.out.bam"

# First pass — collect splice junctions
STAR --runThreadN 8 \
     --genomeDir genome/star_index/ \
     --readFilesIn sample1_R1.fastq.gz sample1_R2.fastq.gz \
     --readFilesCommand zcat \
     --outSAMtype None \
     --outFileNamePrefix pass1/sample1/

# Second pass — realign with all junctions from pass 1
SJ_FILES=$(ls pass1/*/SJ.out.tab | tr '\n' ' ')

STAR --runThreadN 8 \
     --genomeDir genome/star_index/ \
     --readFilesIn sample1_R1.fastq.gz sample1_R2.fastq.gz \
     --readFilesCommand zcat \
     --sjdbFileChrStartEnd $SJ_FILES \
     --outSAMtype BAM SortedByCoordinate \
     --outFileNamePrefix results/sample1/

# Alternative: single-command 2-pass
STAR --runThreadN 8 \
     --genomeDir genome/star_index/ \
     --readFilesIn sample1_R1.fastq.gz sample1_R2.fastq.gz \
     --readFilesCommand zcat \
     --twopassMode Basic \
     --outSAMtype BAM SortedByCoordinate \
     --outFileNamePrefix results/sample1/

# View the alignment summary
cat results/sample1/Log.final.out

# Parse key metrics with python
python3 - << 'EOF'
import re, sys
from pathlib import Path

log = Path("results/sample1/Log.final.out").read_text()
metrics = {}
for line in log.splitlines():
    if "|" in line:
        key, _, val = line.partition("|")
        metrics[key.strip()] = val.strip()

print(f"Unique mapping:     {metrics.get('Uniquely mapped reads %', 'N/A')}")
print(f"Multi-mapping:      {metrics.get('% of reads mapped to multiple loci', 'N/A')}")
print(f"Too many mismatches:{metrics.get('% of reads unmapped: too many mismatches', 'N/A')}")
print(f"Total input reads:  {metrics.get('Number of input reads', 'N/A')}")
EOF

# Align and count simultaneously
STAR --runThreadN 8 \
     --genomeDir genome/star_index/ \
     --readFilesIn sample1_R1.fastq.gz sample1_R2.fastq.gz \
     --readFilesCommand zcat \
     --outSAMtype BAM SortedByCoordinate \
     --quantMode GeneCounts \
     --outFileNamePrefix results/sample1/

# ReadsPerGene.out.tab has 4 columns:
# gene_id  unstranded  stranded_fwd  stranded_rev
head results/sample1/ReadsPerGene.out.tab

# Load into pandas (select column based on library strandedness)
python3 - << 'EOF'
import pandas as pd

df = pd.read_csv("results/sample1/ReadsPerGene.out.tab",
                 sep="\t", header=None, skiprows=4,
                 names=["gene_id", "unstranded", "fwd", "rev"])
# For unstranded library: use column 2 (unstranded)
counts = df.set_index("gene_id")["unstranded"]
print(f"Genes with counts > 0: {(counts > 0).sum()}")
print(counts[counts > 0].sort_values(ascending=False).head())
EOF