Python in Bioinformatics
summary
Python glues compiled CLI tools into pipelines, running BLAST, Bowtie, Samtools inside containers, uploading results with boto3 and Docker and orchestrating nodes via Nextflow; Biopython and pyranges turn genbank and interval files into tables. Meta’s ESM models provide embeddings (trained on ~500 billion sequences) used for fast cosine similarity and candidate ranking rather than full alignments. Challenges noted: dependency and reproducibility headaches, large-memory indexes, limited labeled data, compute cost, and often glue code—does the pipeline actually finish and produce usable filtered results.
AI-written summary · about
chapters (6)
- 0:00Python in bioinformatics
- 2:51Productionizing bioinformatics jobs
- 10:01Cloud scaling of bioinformatics tools
- 17:21Large language models in bioinformatics
- 28:39Data munging with Biopython and Pyranges
- 36:02Summary
related talks
47mPython for Bioinformatics
29mPython for Bioinformatics for learning Python
30mBig data biology for pythonistas: getting in on the genomics revolution
22mPython for science, side projects and stuff!
25mProgramming microbes using Python
25mUsing Python Biopharm to Help Cure Cancer
51mSimplicity For Scale- Analyzing 15 Million DNA Samples With Python
42mPython’s role in accelerating biomedical science