def analyze_fabaceae_genome(fasta_path, ref):
seqs = parse_fasta(fasta_path)
alns = minimap2_align(seqs, ref, preset="map-ont")
numts = detect_numts(alns)
nupts = detect_nupts(alns)
return summarize(numts, nupts)
# NUMTs & NUPTs in Fabaceae Pipeline
results = analyze_fabaceae_genome(
"fabaceae_combined.fa",
"chloroplast_reference.fa"
)
# DESeq2 differential expression
dds <- DESeqDataSetFromMatrix(
countData = counts,
colData = col_data,
design = ~ condition
)
dds <- DESeq(dds)
res <- results(dds)
plotMA(res, ylim=c(-5,5))
# BLAST sequence annotation
blastn -query numt_candidates.fa \
-db nt -out results.xml \
-outfmt 5 -evalue 1e-5
# samtools BAM processing
samtools sort -o sorted.bam aln.bam
samtools index sorted.bam
samtools flagstat sorted.bam
# HTCondor job submission
condor_submit genome_assembly.sub
condor_q -format "%s\n" JobStatus
def analyze_fabaceae_genome(fasta_path, ref):
seqs = parse_fasta(fasta_path)
alns = minimap2_align(seqs, ref)
numts = detect_numts(alns)
nupts = detect_nupts(alns)
return summarize(numts, nupts)
Shakil Ahmed
PhD Student · Molecular Biology
Bailey Lab, NMSU
