BPNet and Cherimoya excel at correcting chromatin confounders in genomic models
anshulkundaje · x · 2026-10-31
Anshul Kundaje explains that whether genomic deep learning models properly control for confounding signals depends on training choices: explicitly correcting for input DNA effects and how the genome is sampled.
He notes BPNet and Cherimoya are particularly effective at correcting open chromatin confounders that affect many multitask models, pointing to a BPNet vs DeepSEA comparison on MYC in the tangermeme paper.
More from Research
- krishnan on autonomous lab agents: criticism changed the next search, not just verdicts — krishnan · 2026-10-31
- Testing agents with explicit rejection records: a cheaper path to verified troubleshooting answers — krishnan · 2026-10-31
- krishnan proposes logging ruled-out troubleshooting hypotheses for future reopening — krishnan · 2026-10-31
- Multi-agent AI lab autonomously researches quantum spins in diamond, revises drifting experiments — krishnan · 2026-10-31
- PI agent rejected 75 proposals in 30 hours; manager banned recurring bad ideas — krishnan · 2026-10-31
- Next 9 proposals explored 7 new directions: rejection became information — krishnan · 2026-10-31