Matt McPartlon
@Mattmcpartlon1
Followers
379
Following
135
Media
1
Statuses
44
This is the first time I've seen an inverse folding model that produces *convincingly* more designable sequences than ProteinMPNN. Nice work @richardwshuai and team!
Excited to share Caliby 🐈, our new model for structure-conditioned sequence design! Caliby is a Potts model-based sequence design method that can condition on structural ensembles. We use this to average out non-structural signal (e.g. evolutionary bias) learned by models 🧵1/N
1
9
125
Today we’re releasing real-world experimental data for over 1000 novel AI-designed proteins on our new platform @proteinbase!
11
108
410
🚀 Chai Discovery has been named to the Endpoints News 11 list of the most promising biotech companies of 2025!
1
7
13
Beyond excited to welcome Dr. Mikael Dolsten to the @chaidiscovery board. His leadership in bringing transformative medicines to patients is unmatched, and we’re thrilled to have his guidance as we scale Chai-2 and beyond!
🧬 Dr. Mikael Dolsten is joining the @ChaiDiscovery board! In 15 years as @Pfizer's Chief Scientific Officer he: ⚛️ Progressed 150 molecules to clinical trials 💊 Delivered 36 approved medicines, from vaccines to cancer therapies
0
0
18
Excited to re-share work from @yoakiyama and @ZhidianZ on MSA pairformer.
Excited to share work with @ZhidianZ, Milot Mirdita, Martin Steinegger, and @sokrypton
https://t.co/pkWeguhQ4l TLDR: We introduce MSA Pairformer, a 111M parameter protein language model that challenges the scaling paradigm in self-supervised protein language modeling 🧵
2
14
70
Thanks @saranormous for being with us from day one and even providing us our first office space 😊
.@chaidiscovery is *the* AI lab transforming end-to-end biological discovery into an engineering problem. investor from the beginning, and a huge believer in @joshim5 @_jackdent @Mattmcpartlon1 @j_boitreaud and team - more flops for the fire
0
0
3
Thanks to everyone on the Chai team for making this possible!
Proud to announce @ChaiDiscovery has raised a $70M Series A from @MenloVentures & Anthology Fund (@AnthropicAI), @ThriveCapital, @OpenAI + others. 🧬 Chai is an applied AI lab building frontier tools for molecular design. This funding will power our new models, coming soon👇
1
2
43
🚀 Welcome to the portfolio, @chaidiscovery! Their Chai-2 model achieved a 100x improvement in antibody design. This is how you transform drug discovery. Thrilled to back this world-class team: @joshim5 @_jackdent @Mattmcpartlon1 @j_boitreaud For more on why we invested👉
2
9
34
Congrats to the winners! It's a privilege to work alongside @ZhuoranQ every day :)
Congratulations to the winners of the 2024 Chen Institute and @ScienceMagazine AI Prize! Winners share $50,000 in cash awards and their research essays will be published in Science. Learn more about grand prize winner @ZhuoranQ and finalists @Roobaert_Alizee and @neuronair here:
3
0
9
These guys are crushing all of the benchmarks 🦾. Congrats to @tomasgeffner, @DidiKieran and team!
Presenting La-Proteina! A new model for scalable, all-atom protein design 🧬 Backbone + sequence + side-chains, indexed and unindexed atomistic motif scaffolding, scalable up to 800 residues, and more… A thread 🧵
1
4
33
Some scientists see the increasingly impressive results from protein binding models and argue "solving" this problem actually has marginal return on an end-to-end drug campaign in practice. Generally, they claim (1) traditional immunization / hybridoma assays are already quite
5
19
127
Chai-2: Zero-shot antibody design in a 24-well plate １．Chai-2 is a multimodal generative model for protein design that achieves a 16% hit rate in fully de novo antibody generation—over 100x higher than previous methods—without requiring high-throughput screening. ２．In a
We’re excited to introduce Chai-2, a major breakthrough in molecular design. Chai-2 enables zero-shot antibody discovery in a 24-well plate, exceeding previous SOTA by >100x. Thread👇
1
18
70
Chai Discovery (@joshim5 @chaidiscovery) just released Chai-2, a model for "zero-shot antibody design in a 24-well plate." The most existing result? Chai-2 successfully generated binders for 50% of the 52 targets they assayed (100x better than SOTA)! Some thoughts below:
2
47
276
It's been a privilege work alongside the most uniquely talented group of individuals I've ever encountered on this breakthrough result @Kevin_E_Wu, @_nathanrollins, @j_boitreaud, @danny_nkjg, @_jackdent , @joshim5, @ZhuoranQ and others. You all made this possible!
We’re excited to introduce Chai-2, a major breakthrough in molecular design. Chai-2 enables zero-shot antibody discovery in a 24-well plate, exceeding previous SOTA by >100x. Thread👇
2
3
33
We're excited to partner with the UK Government on OpenBind, an effort to create the largest open dataset of drug-protein interactions in history. More data → smarter AI models → better medicines https://t.co/2xNdXOCq7i
4
41
236
Chai-1 has always been available for commercial use via our server. Today, we're also making Chai-1(r) code and weights available under an Apache 2.0 license, which permits broad commercial use. https://t.co/EFz6edbreN
github.com
Chai-1, SOTA model for biomolecular structure prediction - chaidiscovery/chai-lab
5
61
276
Today we’re releasing Chai-1r, an updated version of Chai-1 with full support for restraints. Prompting Chai-1r with prior structural knowledge can boost accuracy by >2x. https://t.co/aCYtHl207n
1
53
240
Have you ever wanted to design protein binders with ease? Today we present 𝑩𝒊𝒏𝒅𝑪𝒓𝒂𝒇𝒕, a user-friendly and open-source pipeline that allows to anyone to create protein binders de novo with high experimental success rates. @befcorreia @sokrypton
https://t.co/IPhMFpRgHh
26
434
2K