Stanford kundajelab releases MotifCompendium, GPU-accelerated motif analysis toolkit
anshulkundaje · x · 2026-10-05
Stanford's Kundaje lab released MotifCompendium V1.0, a GPU-accelerated package for comparing, clustering, annotating, filtering and analyzing DNA sequence motifs at scale.
- Ships with ENCODE GRAMMAR (Genomic Regulatory Atlas) and ENCODE MotifCompendium, a unified collection of predictive motifs, described in a technical note
- Released early after internal vetting; feedback from the DeepMind team and others helped fix edge-case bugs and add features, with a new release coming soon
- Code and tutorials open-sourced on GitHub
More from Research
- Single-layer transformer's MLP block invents a brand-new word — Sauers_ · 2026-10-05
- Ben Goertzel: What AGI, RSI and Superintelligence Originally Meant and How They Got Confused — bengoertzel · 2026-10-05
- Evolutionary LISP kernel uses LLMs to self-modify apps with zero-downtime hot reload — max_paperclips · 2026-10-05
- Neuroscientists say AI is accelerating brain science: a field report from CoSyNe 2026 — HistedLab · 2026-10-05
- Schmidhuber joins Sakana AI as chief scientific advisor, free Tokyo symposium Oct 26 — hardmaru · 2026-10-05
- ibUMAP paper: coherent field evaluation speeds up UMAP up to 5.79x with better stability — leland_mcinnes · 2026-10-05