Kevin K. Yang 楊凱筌
@kevinkaichuang.bsky.social
Principal Researcher in BioML at Microsoft Research. He/him/他. 🇹🇼 yangkky.github.io
Pinned
Three BioML starter packs now!
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
Pack 3: go.bsky.app/NAKYUok
DM if you want to be included (or nominate people who should be!)
Pack 1: go.bsky.app/2VWBcCd
Pack 2: go.bsky.app/Bw84Hmc
Pack 3: go.bsky.app/NAKYUok
DM if you want to be included (or nominate people who should be!)
Use deep learning to convert the oncoprotein K-Ras(G12C) into a self-labeling fluorescent protein tag!
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
October 12, 2026 at 7:10 PM
Use deep learning to convert the oncoprotein K-Ras(G12C) into a self-labeling fluorescent protein tag!
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
Combine a chemical knowledge, generative modeling, and structure prediction into a pipeline that can design enzymes for new-to-nature chemistry.
@zacharywu.bsky.social @alexechu.bsky.social @francesarnold.bsky.social @pushmeet.bsky.social @juewang.bsky.social
www.biorxiv.org/content/10.6...
@zacharywu.bsky.social @alexechu.bsky.social @francesarnold.bsky.social @pushmeet.bsky.social @juewang.bsky.social
www.biorxiv.org/content/10.6...
October 5, 2026 at 9:44 PM
Combine a chemical knowledge, generative modeling, and structure prediction into a pipeline that can design enzymes for new-to-nature chemistry.
@zacharywu.bsky.social @alexechu.bsky.social @francesarnold.bsky.social @pushmeet.bsky.social @juewang.bsky.social
www.biorxiv.org/content/10.6...
@zacharywu.bsky.social @alexechu.bsky.social @francesarnold.bsky.social @pushmeet.bsky.social @juewang.bsky.social
www.biorxiv.org/content/10.6...
A genome language model reveals the interactions hidden in non-coding DNA, pointing to new putative RNAs and repetitive elements in bacterial genomes.
@garykbrixi.bsky.social @maxewilkinson.bsky.social @mfgrp.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
@garykbrixi.bsky.social @maxewilkinson.bsky.social @mfgrp.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
September 23, 2026 at 8:21 PM
A genome language model reveals the interactions hidden in non-coding DNA, pointing to new putative RNAs and repetitive elements in bacterial genomes.
@garykbrixi.bsky.social @maxewilkinson.bsky.social @mfgrp.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
@garykbrixi.bsky.social @maxewilkinson.bsky.social @mfgrp.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
Use reward-guided search in a generative model's latent space to design high-affinity protein binders to proteins and carbohydrates.
@karstenkreis.bsky.social @pierceogden.bsky.social
www.biorxiv.org/content/10.6...
@karstenkreis.bsky.social @pierceogden.bsky.social
www.biorxiv.org/content/10.6...
September 22, 2026 at 2:57 PM
Use reward-guided search in a generative model's latent space to design high-affinity protein binders to proteins and carbohydrates.
@karstenkreis.bsky.social @pierceogden.bsky.social
www.biorxiv.org/content/10.6...
@karstenkreis.bsky.social @pierceogden.bsky.social
www.biorxiv.org/content/10.6...
Use a genomic language model to optimize a polyketide synthase go produce a non-natural product.
@nathanlanclos.bsky.social @ancornman1.bsky.social @kortemmelab.bsky.social @keaslinglab.bsky.social @microyunha.bsky.social
www.biorxiv.org/content/10.6...
@nathanlanclos.bsky.social @ancornman1.bsky.social @kortemmelab.bsky.social @keaslinglab.bsky.social @microyunha.bsky.social
www.biorxiv.org/content/10.6...
September 18, 2026 at 8:40 PM
Use a genomic language model to optimize a polyketide synthase go produce a non-natural product.
@nathanlanclos.bsky.social @ancornman1.bsky.social @kortemmelab.bsky.social @keaslinglab.bsky.social @microyunha.bsky.social
www.biorxiv.org/content/10.6...
@nathanlanclos.bsky.social @ancornman1.bsky.social @kortemmelab.bsky.social @keaslinglab.bsky.social @microyunha.bsky.social
www.biorxiv.org/content/10.6...
FoldDir: A flow-matching structure-conditioned protein sequence design model with excellent computational results and some functional nanobody redesigns.
@rbaltman.bsky.social
www.biorxiv.org/content/10.6...
@rbaltman.bsky.social
www.biorxiv.org/content/10.6...
September 16, 2026 at 12:24 PM
FoldDir: A flow-matching structure-conditioned protein sequence design model with excellent computational results and some functional nanobody redesigns.
@rbaltman.bsky.social
www.biorxiv.org/content/10.6...
@rbaltman.bsky.social
www.biorxiv.org/content/10.6...
A nice review on ways to discover and engineer proteins that use fewer amino acids while maintaining structure and function.
@FilipBuchel @KlaraH_lab
www.sciencedirect.com/science/arti...
@FilipBuchel @KlaraH_lab
www.sciencedirect.com/science/arti...
September 14, 2026 at 9:00 PM
A nice review on ways to discover and engineer proteins that use fewer amino acids while maintaining structure and function.
@FilipBuchel @KlaraH_lab
www.sciencedirect.com/science/arti...
@FilipBuchel @KlaraH_lab
www.sciencedirect.com/science/arti...
The cost of gene synthesis prevents machine-learning guided directed evolution from reaching it's full potential.
A very nice perspective by the inimitable Bruce Wittmann.
arxiv.org/abs/2609.03046
A very nice perspective by the inimitable Bruce Wittmann.
arxiv.org/abs/2609.03046
September 10, 2026 at 2:31 PM
The cost of gene synthesis prevents machine-learning guided directed evolution from reaching it's full potential.
A very nice perspective by the inimitable Bruce Wittmann.
arxiv.org/abs/2609.03046
A very nice perspective by the inimitable Bruce Wittmann.
arxiv.org/abs/2609.03046
A fast method for building phylogenetic trees with millions of sequences and then a model that leverages the tree structure to predict viral protein evolution!
@seyonec.bsky.social @claudiadriscoll.bsky.social @garykbrixi.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
@seyonec.bsky.social @claudiadriscoll.bsky.social @garykbrixi.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
September 8, 2026 at 4:01 PM
A fast method for building phylogenetic trees with millions of sequences and then a model that leverages the tree structure to predict viral protein evolution!
@seyonec.bsky.social @claudiadriscoll.bsky.social @garykbrixi.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
@seyonec.bsky.social @claudiadriscoll.bsky.social @garykbrixi.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
The largest experimental protein sequence-fitness dataset: 13k measurements across 3 proteins reveals that fitness landscapes are rugged, there are many functional sequences between orthologs, and ML models can't distinguish functional and non-functional sequences.
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
August 31, 2026 at 7:50 PM
The largest experimental protein sequence-fitness dataset: 13k measurements across 3 proteins reveals that fitness landscapes are rugged, there are many functional sequences between orthologs, and ML models can't distinguish functional and non-functional sequences.
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
Use machine learning guided directed evolution to make a red-shifted fluorescent protein 4x brighter.
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
August 28, 2026 at 3:49 PM
Use machine learning guided directed evolution to make a red-shifted fluorescent protein 4x brighter.
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
Curate a molecule <-> text dataset, train a model, and use it to discover molecules that fight antibiotic resistance by deactivating beta-lactamase enzymes.
@kosonocky.bsky.social
www.biorxiv.org/content/10.6...
@kosonocky.bsky.social
www.biorxiv.org/content/10.6...
August 24, 2026 at 2:27 PM
Curate a molecule <-> text dataset, train a model, and use it to discover molecules that fight antibiotic resistance by deactivating beta-lactamase enzymes.
@kosonocky.bsky.social
www.biorxiv.org/content/10.6...
@kosonocky.bsky.social
www.biorxiv.org/content/10.6...
Binder design is nice and all, but here we have three agents sharing data and autonomously controlling a lab to design enzymes with shifted substrate scopes and high activity!
@cobanbrooks.bsky.social @pascalnotin.bsky.social @philromero.bsky.social
www.biorxiv.org/content/10.6...
@cobanbrooks.bsky.social @pascalnotin.bsky.social @philromero.bsky.social
www.biorxiv.org/content/10.6...
August 20, 2026 at 9:33 PM
Binder design is nice and all, but here we have three agents sharing data and autonomously controlling a lab to design enzymes with shifted substrate scopes and high activity!
@cobanbrooks.bsky.social @pascalnotin.bsky.social @philromero.bsky.social
www.biorxiv.org/content/10.6...
@cobanbrooks.bsky.social @pascalnotin.bsky.social @philromero.bsky.social
www.biorxiv.org/content/10.6...
ApexFold: condition predictions of peptide secondary structure on the chemical environment
@delafuentelab.bsky.social
www.biorxiv.org/content/10.6...
@delafuentelab.bsky.social
www.biorxiv.org/content/10.6...
August 12, 2026 at 3:52 PM
ApexFold: condition predictions of peptide secondary structure on the chemical environment
@delafuentelab.bsky.social
www.biorxiv.org/content/10.6...
@delafuentelab.bsky.social
www.biorxiv.org/content/10.6...
Use machine learning to design libraries of enzymes with broad substrate scope as starting points for engineering.
@francesarnold.bsky.social
www.biorxiv.org/content/10.6...
@francesarnold.bsky.social
www.biorxiv.org/content/10.6...
August 10, 2026 at 6:53 PM
Use machine learning to design libraries of enzymes with broad substrate scope as starting points for engineering.
@francesarnold.bsky.social
www.biorxiv.org/content/10.6...
@francesarnold.bsky.social
www.biorxiv.org/content/10.6...
August 6, 2026 at 1:31 PM
Reposted by Kevin K. Yang 楊凱筌
1/ I'm excited to share that we're launching NECB 2026, the inaugural New England Computational Biology Symposium. Oct 1-2 at Microsoft Research New England, Cambridge. Two days of keynotes,talks, and posters to bring our community together across institutions.Space is limited. newenglandcompbio.org
July 17, 2026 at 9:48 PM
1/ I'm excited to share that we're launching NECB 2026, the inaugural New England Computational Biology Symposium. Oct 1-2 at Microsoft Research New England, Cambridge. Two days of keynotes,talks, and posters to bring our community together across institutions.Space is limited. newenglandcompbio.org
Gaussian process kernels that encode evolutionary information and local linearity improve protein sequence-fitness predictions.
arxiv.org/abs/2606.11057
arxiv.org/abs/2606.11057
July 10, 2026 at 9:07 PM
Gaussian process kernels that encode evolutionary information and local linearity improve protein sequence-fitness predictions.
arxiv.org/abs/2606.11057
arxiv.org/abs/2606.11057
Proto: A probabilistic programming language for designing biomolecules.
Absolutely beautiful paper from top to bottom.
@adititm.bsky.social @bviggiano.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
Absolutely beautiful paper from top to bottom.
@adititm.bsky.social @bviggiano.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
July 1, 2026 at 9:01 PM
Proto: A probabilistic programming language for designing biomolecules.
Absolutely beautiful paper from top to bottom.
@adititm.bsky.social @bviggiano.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
Absolutely beautiful paper from top to bottom.
@adititm.bsky.social @bviggiano.bsky.social @brianhie.bsky.social
www.biorxiv.org/content/10.6...
TadA-Bench: a 31-round, million-variant wet-lab enzyme engineering dataset.
arxiv.org/abs/2606.02624
arxiv.org/abs/2606.02624
June 19, 2026 at 9:26 PM
TadA-Bench: a 31-round, million-variant wet-lab enzyme engineering dataset.
arxiv.org/abs/2606.02624
arxiv.org/abs/2606.02624
Aggregating many experiments into one zero-shot protein language model score obscures that current models cannot meaningfully rank a set of fit mutations or prioritize new-to-nature functions
@clauswilke.com
www.biorxiv.org/content/10.6...
@clauswilke.com
www.biorxiv.org/content/10.6...
June 15, 2026 at 7:40 PM
Aggregating many experiments into one zero-shot protein language model score obscures that current models cannot meaningfully rank a set of fit mutations or prioritize new-to-nature functions
@clauswilke.com
www.biorxiv.org/content/10.6...
@clauswilke.com
www.biorxiv.org/content/10.6...
Learn which structural domains are compatible with each other, then generate protein sequences conditioned on the desired structural domains.
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
May 29, 2026 at 7:47 PM
Learn which structural domains are compatible with each other, then generate protein sequences conditioned on the desired structural domains.
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
Reposted by Kevin K. Yang 楊凱筌
very very cool! i had the privilege of asking Mohammed AlQuraishi's opinion on this topic a couple years ago
Screen 1M random protein sequences to discover that biology-like folds are accessible from random sequences with surprising frequency
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
May 15, 2026 at 10:10 PM
very very cool! i had the privilege of asking Mohammed AlQuraishi's opinion on this topic a couple years ago
Screen 1M random protein sequences to discover that biology-like folds are accessible from random sequences with surprising frequency
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
May 15, 2026 at 9:10 PM
Screen 1M random protein sequences to discover that biology-like folds are accessible from random sequences with surprising frequency
www.biorxiv.org/content/10.6...
www.biorxiv.org/content/10.6...
Genie3: all-atom SE3-equivariance for fast and performant protein design.
@yeqinglin.bsky.social @moalquraishi.bsky.social
www.biorxiv.org/content/10.6...
@yeqinglin.bsky.social @moalquraishi.bsky.social
www.biorxiv.org/content/10.6...
May 11, 2026 at 9:42 PM
Genie3: all-atom SE3-equivariance for fast and performant protein design.
@yeqinglin.bsky.social @moalquraishi.bsky.social
www.biorxiv.org/content/10.6...
@yeqinglin.bsky.social @moalquraishi.bsky.social
www.biorxiv.org/content/10.6...