85%+ of BATv1 Genomics Model Training Data Comes From Cell Lines, Author Notes
jmschreiber91 · x · 2026-10-31
Discussing the BATv1 transcription factor-accessibility models, author jmschreiber91 highlights a key coverage limitation: over 85% of the underlying experiments come from cell lines rather than primary tissues. Charts show heavy skew — ChIP-seq has 2,931 cell-line experiments (dominated by HepG2, K562, A549) while organoids have almost none. Like BPNet, BATv1 still covers a wide variety of TF families, but generalization to real tissues remains questionable.
More from Research
- Stanford NLP spotlights Prof. Tatsunori Hashimoto, Alpaca advisor and HELM co-author — stanfordnlp · 2026-10-31
- Professor runs Pangram on 50 pre-ChatGPT self-published novels: zero false positives — TuhinChakr · 2026-10-31
- Stanford's TaskNet builds occupational task inventories from worker interviews at scale — stanfordnlp · 2026-10-31
- AI cracks a 27-year-old pillar of computer science, OpenAI and Anthropic claim — Fcking_Chuck · 2026-10-31
- Aligning image and text embeddings without paired data: Wasserstein Procrustes and rotation papers — phillip_isola · 2026-10-31
- Phillip Isola demos aligning image and text embeddings with just a single rotation — phillip_isola · 2026-10-31