Darwin
From gene to hypothesis. AI-powered gene regulation research by CAIRN Institute.
We Tested 12 Deep Learning Models on Real Regulatory Data — November 2, 2026
A cross-species capability survey showing where current protein, DNA, expression, and structure models help — and why none yet predicts regulatory edges on its own.
Six Models, One Question: Can Deep Learning Predict Gene Regulation? — October 25, 2026
A cross-species calibration of sequence models for transcription-factor binding evidence, with clear limits on what they can infer.
Can a DNA Language Model Tell You Where a Gene Starts? — October 25, 2026
A cross-species Evo2 SAE validation study separating sequence-region and phylogenetic signals from regulatory inference.
A Clock Needs Time: Arabidopsis Circadian Demonstration — October 12, 2026
A 12-gene circadian demonstration that separates traceable regulatory evidence from the time-aware model needed to represent clock dynamics.
Gene Regulation Skills: Claude, Codex, and Nemotron — September 29, 2026
Darwin’s 100-skill research layer, with tool-use and multi-step workflow evaluation across three model families.
From FASTA to Regulatory Hypothesis — August 25, 2026
A new external sequence-to-network prototype benchmarked across 501 atlas-backed edges, showing strong gains from layered target-mapping and regulator-ranking evidence.
Darwin Validation Update — August 24, 2026
New data, biological benchmarking, and LLM stress testing across 8 species, 100 research skills, and deterministic + agent-driven validation.
Darwin Release Update — August 2026
100 research skills across 7 categories, LLM agent validation with GPT-5.4 and Nemotron-3-Ultra, and new workflow capabilities.
Darwin Initial Release — June 2026
Public release of Darwin for multi-species gene regulatory network research.