YK

バイオインフォマン、ケモインフォマンになろう

[YK @yktsnd]

バイオインフォマティクス Advent Calendar 2021（13日目）を投稿しました。
遅れてすみませんでした。

機械学習/深層学習を用いた生物配列解析 https://t.co/240iDjkRTA #Qiita #Bioinformatics

[鸭哥 @grapeot]

Anthropic 发了 Fable 5，244 页安全报告。报告里藏了一个小实验。

六位生物学博士加 AI，两天干完了人工两个半月的活。配了领域专家的组输了，配普通博士的组赢了。Mythos 5 把标准答案存在时的找答案能力，直接打平了专家。

但有一个变量从头到尾没动：每组都配了一位 LLM 专家。这个人干的事不是写 prompt，是知道模型什么时候会胡说、什么时候过度乐观、什么时候该踩刹车。

AI 越强，越绕不开这个盯住它的人。

阅读全文：
https://t.co/pZjeDvVbUT

配图：
https://t.co/bcZXnKnkz0

[きゅうもるの中の人 @cuemolnohito]

fable、cybersecurity or biology topicsとか言われて途中で勝手にopusに戻されてた😇

[YK @yktsnd]

AlphaFoldの時からそうか

[YK @yktsnd]

一部のバイオ・ケミカルの最先端研究はAnthropicやOpenAIのようなAI企業が主導する世界になっちゃったな

[YK @yktsnd]

Fable5，バイオ・ケミカル分野で自動ナーフされるの萎えすぎる

[Joshua Meier @joshim5]

Today we are announcing our collaboration with Pfizer to put Chai's frontier AI—including our latest model, Chai-3—directly into the hands of one of the world's leading pharmaceutical teams.

[YK @yktsnd]

みんなESM-CのChat機能で遊んでる
構造-物性相関をAIが理解してるような感覚で、ChatGPTが出てきたときの衝撃に近いかも
タンパク質設計を自然言語で行う時代もすぐ来るわ、これは

[YK @yktsnd]

@tbsng_ktkm0923 Boltz-2、Protenix-v2、Chai-2との比較が無いの、恣意的なんですかねぇ…

[Alex Rives @alexrives]

Today we're announcing ESMFold2, an open scientific engine to power prediction, design, and discovery across protein biology.

The new model delivers state of the art performance on protein interactions, especially antibodies, a critical modality for therapeutics.

We have designed and validated miniprotein binders and single chain antibodies across five therapeutic targets that are important in cancer and immunology. We are seeing very high success rates, and affinities at levels consistent with therapeutic activity.

We’re also releasing an atlas of 6.8 billion proteins, and 1.1 billion predicted structures.

ESMFold2 is built on a state of the art language model that has been trained on billions of protein sequences.

A world model of protein biology emerges through language modeling.

We’ve used the techniques of mechanistic interpretability developed to understand large language models to understand the concepts ESM uses to represent proteins.

The model’s representation space has a compositional organization of features across scales, levels of complexity, and abstraction, that reflects and mirrors the understanding of protein biology developed through a century of empirical science.

This understanding emerges without prior knowledge, just from language modeling of protein sequences.

Language models are becoming a powerful substrate to understand and program biology.

The design of protein interactions is one of the most fundamental problems in biophysics, and has critical implications for the discovery of new medicines. A simple gradient based search with the model was able to discover high-affinity protein binders.

I'm excited by the potential this has to accelerate basic science and the understanding of proteins. And especially for the new avenues it opens up for therapeutic design and medicine.

[Yehlin Cho @ChoYehlin]

🚀 Excited to share our new work: Absolute Stability Predictor!

📊: https://t.co/gtgQjPRAX6

Built the MGnify Stability Dataset (1.8M+ measurements) and developed stability prediction models, together with @grocklin, @KotaroTsuboyama, @sokrypton, and teams.

[AMBER md @ambermdprog]

Amber26 and AmberTools26 have now been released!
Full info is at https://t.co/quQSVY2j5E

[YK @yktsnd]

@tbsng_ktkm0923 そういうことでしたか！

[YK @yktsnd]

@cuemolnohito @tbsng_ktkm0923 定量的に評価されていて、問題解決もされていたのですね、勉強になります
AF3一辺倒ではなく、適切にモデル選択することが大事ですね
お教えいただきありがとうございました

[きゅうもるの中の人 @cuemolnohito]

@yktsnd @tbsng_ktkm0923 論文の方では言及してなかったですが、最新版のでは、リガンドとタンパク質の反発項がはいっていて、めり込みはほぼ防げるようです。https://t.co/AwPE2KreV3
↑これは一応 https://t.co/PFecry4hK7 こちらで試せます

[YK @yktsnd]

@tbsng_ktkm0923 @cuemolnohito しっかり読んでないんですが、精度は同等な感じなんですね、教えていただきありがとうございます
紹介いただいた論文はキラリティの精度向上に関するもので、力場での衝突判定みたいな物理的な制約ではなさそうですね……
物理モデルも深層学習モデル内の重みに代替されていく流れなんですかねぇ

[YK @yktsnd]

@tbsng_ktkm0923 勉強になります！
AF3以降、AF2にあった最終構造の力場optステップが無くなってるモデルばかりみたいなので、物理的におかしい構造が出やすい印象なんですよね……
MM optするか、話題の大上研boltzinaだとマシな構造出るようになるんですかね

[Sebastian S. Cocioba🪄🌷 @ATinyGreenCell]

I am challenging myself to make enough progress on my vibecoded TUI plasmid editor before my SnapGene subscription expires. Follow allong by simply typing in:

pipx install splicecraft

into your terminal or check out my github here:
https://t.co/3mkWtVqa1T

[OpenAI Newsroom @OpenAINewsroom]

We’re introducing a Bio Bug Bounty for GPT‑5.5 and accepting applications

In our ongoing work to strengthen our safeguards for advanced AI capabilities in biology, we’re inviting researchers with experience in AI red teaming, security, or biosecurity to try to find a universal jailbreak that can defeat our 5-question bio safety challenge.

Learn more in our blog ⬇️
https://t.co/2vexvsX6Xy

[Minji Lee @m1nj12]

We introduce ConforNets, a mechanism for conformational control in AlphaFold3 models

- SoTA at producing diverse conformations on every multistate benchmark (N=104)
- Novel capability: transfer state from one protein to another

Outperforms BioEmu, ConforMix and AFsample3

🧵1/8