Cheng Tan

writing and running computer programs to simulate wild biomolecules.

[Kresten Lindorff-Larsen @LindorffLarsen]

Are you analysing hydrophobicity in disordered proteins and still using something like the Kyte & Doolittle scale?

Maybe instead consider the "stickiness-scale" that Fan & Giulio derived using SAXS data for >100 IDPs

https://t.co/hN3KtuzsWh

[バイオステーション(Bio-station)/ポッドキャスト @Bio_stations]

生体分子凝縮体の形成を制御するタンパク質断片の設計

AlphaFold2をベースとした構造予測技術FragFoldにより、凝縮体の形成を抑制/促進するタンパク質断片を同定。がんや神経変性疾患の治療標的となるタンパク質の制御を可能に。ま��新たな凝集体形成機構の発見も
https://t.co/1WweqGUgKK

[Jeonghyeon Kim @jasonkeem8652]

Excited to share PRISM, our ICML 2026 paper from @romerolab1 on antibody language modeling 🎉

Most antibody LMs are systematically biased toward germline residues, washing out the rare mutations that actually drive binding.

PRISM fixes that. A short thread on how 👇

(1/6)

[Fang Wu @WUFang40615703]

Proteo-R1 (ICML 2026), the first reasoning protein foundation model for protein design, is out! 🚀🧬

Most protein design models generate structures without ever *reasoning* about which residues matter. We think that's backwards.

Human protein engineers👩‍🔧 don't work this way. They identify critical interaction residues first — charged anchors, hydrophobic hotspots, specificity-determining motifs — and only then optimize geometry around those decisions.

━━━━━━━━━━━━━━━━
🔬 THE CORE IDEA
━━━━━━━━━━━━━━━━

A dual-expert architecture that explicitly decouples molecular understanding from geometric generation:

→ ⚡A multimodal LLM (understanding expert) analyzes protein sequences, structures, and text to identify key functional residues governing binding and specificity
→ ⚡A diffusion model (generation expert) then co-designs sequence + structure — but with those residues locked in as hard constraints

━━━━━━━━━━━━━━━━
📐 HOW IT'S TRAINED
━━━━━━━━━━━━━━━━

Three-stage curriculum:

① Multimodal Alignment — freeze the LLM, train projections to bridge ESM-2 + AF3-style structural features into language space

② Structural Reasoning Mid-Training — unfreeze the LLM, teach it residue grounding → pairwise geometry → interface localization → hotspot prediction

③ Joint Reasoning-Guided Design — end-to-end on antibody-antigen complexes. Gradients from the diffusion objective flow back through the reasoning expert.

━━━━━━━━━━━━━━━━
📊 RESULTS
━━━━━━━━━━━━━━━━

Evaluated on simultaneous multi-CDR redesign and the RAbD CDR-H3 benchmark:

✅ Best RMSD & DockQ on RAbD — redesigned H3 loops are geometrically accurate *and* docked well
✅ Lowest backbone dihedral divergence (JSDbb) among all baselines
✅ Reduced intra- and inter-chain steric clashes
✅ Generated sequences score lower perplexity than native antibodies under IgLM & AbLang
✅ Plug-and-play: swapping the diffusion backend to UniMoMo still improves RMSD and IMP

━━━━━━━━━━━━━━━━
💡 WHY IT MATTERS
━━���━━━━━━━━━━━━━

Proteo-R1 isn't just a better antibody design model. It's a blueprint for coupling deliberative LLM reasoning with any physical generative process — interpretable, modular, and backend-agnostic.

📄 Paper: https://t.co/efquYg3O76
💻 Code: https://t.co/Qxm06IZ4xy
🌐 Demo: https://t.co/nkfEWY32OA

Great thanks to my wonderful collaborators Weihao Xuan, Heli Qi, @Hanqun_CAO, Heng-Jui Chang, @KKuanPang @XiangruTang Zehong Wang, @hcwww_ , @KejunYing @lupantech Chiho Im, Seungju Han, @richardxp888 @tikgiau. Also appreciate the guidance from advisors @YejinChoinka @jure @erranlli Naoto Yokoya, Masashi Sugiyama.

[Kresten Lindorff-Larsen @LindorffLarsen]

Why is it so difficult to predict accurate mutational effects on protein stability?

We explored the contribution from changes in native state configurational entropy in this paper, which also happens to be the last from my PhD 👴⌛️

https://t.co/1oXgNvv11O

[Cheng Tan @OiniL]

再见啦 #Linode 用了将近十年的 VPC 今天被我停掉啦。🥹🥹🥹

[Cheng Tan @OiniL]

暴雨延误4个小时，上机后干等一个半小时，现在居然开回来修理….😡😨

[PapiCon @PapilloteContet]

拙著「ひねくれ謎解き」が本日発売になりました。各種通販サイトや書店でお買い求めいただけます。これまで制作したクイズに加え新作も多数収録しておりますので、楽しんで頂けたら幸いです…！
https://t.co/oq6fx4mwkX

[Cheng Tan @OiniL]

突然发现， #伍佰 老同志的“#再度重相逢” 与 堺正章 “#さらば恋人” 也太像了吧！

[Cheng Tan @OiniL]

MacBook with a built-in JIS keyboard, ran into frustrating layout issues when connecting an external keyboard with a US layout... After trying various tools— InputSourceSelector, #Karabiner, and autokbisw—I found an incredibly simple solution add a new layout in AU!!!

[Cheng Tan @OiniL]

@teachaerli 鑀

[Cheng Tan @OiniL]

这个叫 #Monday 的模型果然很给力， 傲娇年轻人的感觉…

[Cheng Tan @OiniL]

AI 教做爹…

[Cheng Tan @OiniL]

日常play�� 果然 GPT4o 深得我心

[Cheng Tan @OiniL]

@_Nikisade 乍一听以为是开源世界爱好者来引战的， 仔细一看原来是语言引战…😂

[Kresten Lindorff-Larsen @LindorffLarsen]

CALVADOS-RNA

[Cheng Tan @OiniL]

@skywind3000 可以统计一下看看是否和编辑器有相关性。 如果有的话就可以说，你看我们emacs用户从来不做这些没用的事

[Cheng Tan @OiniL]

@bboczeng 并非完全如此。 本地部署deepseek r1 完全碾压之前的其他模型， 对于考虑隐私的人来说也是优点之一

[The Debian Project @debian]

The Debian Publicity Team will no longer post on X/Twitter. We took this decision since we feel X doesn't reflect Debian shared values as stated in our social contract, code of conduct and diversity statement. X evolved into a place where people we care about don't feel safe.

[Cheng Tan @OiniL]

deepseek 写着写着飙起了英文， 这……