Kundaje Lab Releases MotifCompendium, a GPU-Accelerated Motif Analysis Package
anshulkundaje · x · 2026-09-09
The Kundaje lab highlights two tools: FiNeMo (by Austin T. Wang) finds motif instances in sequences using model-derived contribution scores, maps them to TF-MODISCO motifs, and models motif competition; MotifCompendium is a GPU-accelerated open-source package for efficient clustering, unification, indexing, and annotation of massive numbers of contribution-score-aware motifs. V1.0 is now on the main branch, described in a technical note alongside the ENCODE GRAMMAR resource.
Related event: Kundaje Lab Open-Sources GPU-Accelerated Motif Analysis Tools(2 posts)→
More from Research
- HarnessMM cuts agent tokens per task by up to 88% while raising success rates — omarsar0 · 2026-10-26
- Ben Recht: The world needs a truly open language model, and it's easier to build than you think — beenwrekt · 2026-10-26
- New Blog Breaks Black-Box Distillation Into Five Practical Steps — chrisrohlf · 2026-10-26
- DetectorScope turns black-box AI text detectors into auditable ones with sparse autoencoders — _akhaliq · 2026-10-26
- OPST paper shows LLMs self-improve with zero human data, guided only by topic descriptions — _akhaliq · 2026-10-26
- Tencent's HiSTEVE 1.0: hierarchical VLA agent plays Minecraft with native keyboard and mouse, hits 85% SOTA — _akhaliq · 2026-10-26