pCoMole Uses Discrete Flow Matching to Shrink Biomolecules, Wet-Lab Validated on GFP
rishabh16_ · x · 2026-10-03
A NeurIPS-accepted paper introduces pCoMole, a Pareto-constrained molecule editing framework built on discrete flow matching.
- It steers a pre-trained Edit Flow toward user preferences while enforcing hard biochemical and manufacturability constraints, using a Tchebycheff utility with feasibility-gated terminal distribution and a Doob-h transform; short Monte Carlo rollouts approximate the required harmonic function.
- Demonstrations include shrinking GFP while retaining fluorescence, shortening Cas9 orthologs while preserving PAM specificity, and compressing peptide binders into peptidomimetics optimizing seven drug properties.
- Wet-lab testing: two 229-residue designed eGFP variants retained clear green fluorescence in BL21 cells after 10 deletions.
More from Research
- Symbolic supervision gives video models equal reasoning at ~1/30 the compute, Rubik's Cube study finds — niloofar_mire · 2026-10-03
- Sony AI open-sources PAVAS, a physics-aware video-to-audio model accepted as CVPR 2026 Oral — mittu1204 · 2026-10-03
- Maryland RCT: GPT-4o tutor offering left students 4 points lower, 15% used it — lmoroney · 2026-10-03
- OpenAI paper: simulating deployment predicts LLM safety before release — JacquesThibs · 2026-10-03
- PyTorch Helion DSL integrated into vLLM beats CUTLASS and DeepGEMM with 10%+ throughput gains — PyTorch · 2026-10-03
- Neural memory as an unbounded 2D lattice: writes and reads through a tiny 3x3 bump — CFGeek · 2026-10-03