TF binding models paired with CATv1 chromatin models give direct variant-to-motif readouts
jmschreiber91 · x · 2026-10-31
Researcher jmschreiber91 explains how transcription factor binding models complement accessibility models: for variant interpretation, accessibility models show disrupted chromatin but require seqlet matching to infer the TF involved, while TF binding models more directly identify affected binding sites. Paired with the CATv1 models — following the ChromBPNet+BPNet and AlphaGenome Atlas paradigm of complementary readouts across genomic modalities — the Cherimoya models become especially powerful. Attached tracks show DNase-seq and TF footprint changes (NFE2, TEAD1, CEBPA) around specific variants in K562 and HepG2 cells.
More from Research
- SCOPE workshop proposed for ICLR 2027 asks what counts as an AI scientific discovery — mariyaivasileva · 2026-10-31
- New MolmoSpaces-CommonSense benchmark: no robot policy tops 30% on manipulation tasks — RanjayKrishna · 2026-10-31
- Mischief launches video model trained from lab-grown brain cells at 0.5¢ per second — evilsocket · 2026-10-31
- Stanford CS336 notes: Percy Liang on scaling recipes and hyperparameter transfer — stanfordnlp · 2026-10-31
- Composable LoRA directions for texture, geometry and lighting make 3D fine-tuning cheaper — burkov · 2026-10-31
- Moondream releases RefCOCO-M with pixel-accurate masks and cleaned prompts for grounding evals — victormustar · 2026-10-31