5 Paths · 122 Lessons
Learn Python for Bioinformatics.
Work through NumPy, Pandas, Biopython, and HGVS in a structured course. Every lesson is an interactive notebook, and the Python beside this sentence is running in your browser right now — nothing to install.
records = {}
name = None
with open("sample.fasta") as handle:
for line in handle:
line = line.strip()
if line.startswith(">"):
name = line[1:].split()[0]
records[name] = ""
elif name:
records[name] += line
for name, seq in records.items():
gc = (seq.count("G") + seq.count("C")) / len(seq)
print(f"{name:<18} {len(seq):>4} bp GC {gc:.1%}")
stdout
NM_000546.6 120 bp GC 52.5%
NM_007294.4 120 bp GC 40.8%
ENST00000646891.2 120 bp GC 79.2%
