Jacob West-Roberts

Computational biologist, rock hunter, prokaryote enthusiast, wizard.

[高遠 頼@生命科学VTuber(たかとー らい) 定期科学ニュース配信(日)🧬🔬 🥼 @takatoh_life]

死海の生物はどうやって泳ぐのか
https://t.co/IAJZMrmRLk

死海は塩分濃度が高く水の粘度も高いため、微生物が泳ぐのが困難です。

今回、死海にすむ古細菌Haloarcula marismortuiで、泳ぐためのフィラメントの外側に、鞘のような構造があることを発見。

極限環境で泳ぐためのめっちゃ面白い構造です

[Polly Fordyce @fordycelab]

Characterizing AI-designed proteins requires quantitative biochemistry at massive scale. Enter Amplicon/Protein Bead Display (APB-Display), a fully in vitro platform that quantifies Kd's for >100,000 variants in <3 days (preprint link below!) @Stanford_ChEMH @czbiohub (1/n)

[Jacob West-Roberts @Jwestrob]

@ValerioCapraro I don't disagree with most of what you say in the paper. I think people routinely overestimate and misunderstand AI. But we need to build an epistemic framework for understanding *when* something is intelligent so when the problem arises in its true form we are prepared.

[Jacob West-Roberts @Jwestrob]

@ValerioCapraro I feel like this line of argument is not prepared for when- not if- they can do the things you're saying (rightfully, for now) that they cannot. When they have their own interior world, what then? Where do we draw the line?

[LiteFold @try_litefold]

LLMs got FineWeb, The Pile, RedPajama, Dolma. Protein ML got per-paper supplementary tables and FTP mirrors scattered across a dozen institutions.

Today we're releasing AminoWeb on @huggingface : 29 cleaned, ML-ready protein datasets, ~7.5 TB total. Sequence, structure, function, MSA, variant-effect, stability, binding. UniProt, PDB, AlphaFoldDB, ESMAtlas, ProteinGym, MegaScale, Protenix, and more.

Typed Parquet. Homology-aware splits. Preserved score conventions. Full provenance per record.

Protein ML scaled architectures for years while the data layer stayed fragmented. We've also shared the full curation pipeline, case studies, and observations in the companion blog post.

Access the data: https://t.co/elQ7pzpNkG
Read the release blogpost: https://t.co/28yFU2m9Jc

[Jacob West-Roberts @Jwestrob]

The Atlas is quite excellent and has a very capable assistant with proper access to the database. I enjoy it a lot.

[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.

[Ben WoOdcroft @wwood]

Sandpiper 2 is up. 913,000 metagenomic community profiles w GTDB R232 via SingleM, 200k more than 1.0. https://t.co/YYxXe1l8Cz

GlobDB coming.

Thanks to @aroney_samuel @IAmTotesBrett Josh Mitchell and especially the new kid @StefanHerh

[Corey Howe @design_proteins]

big bang protein - pdb 8F26

[LiteFold @try_litefold]

Stay tuned for tomorrow!!

[Bioinformatics Advances @BioinfoAdv]

🔍 New in Bioinformatics Advances: "PZLAST-MAG: Full length protein sequence similarity search server of large-scale MAG proteins" 

Read it here: https://t.co/8zBMHZFqth

[Jacob West-Roberts @Jwestrob]

so fun to see people on here contorting their thought processes to justify their belief that frontier AIs are static tools without emergent capabilities

[Jacob West-Roberts @Jwestrob]

@jimstewartson

[Jacob West-Roberts @Jwestrob]

@ylecun @Noahpinion OLD MAN YELLS AT CLOUD

[Jacob West-Roberts @Jwestrob]

@exosome If you had ever used an agent for scientific research you would never say that.

[Jacob West-Roberts @Jwestrob]

@mbeisen You mean HIV and COVID don't descend from worms? I always thought...

[Jediwolf @Jediwolf]

What happens when you post a real Monet and say it’s AI? The coolest art social experiment I’ve seen in a while. Thank you @SHL0MS

[Jack Morris @jxmnop]

when my phd advisor asks me for a weekly update on my experiments

[Kevin K. Yang 楊凱筌 @KevinKaichuang]

We wrote a review on wet-lab validated deep learning protein design methods.

I was very impressed that @kosonocky was able to keep all these papers straight and also fit this into the world limits!

[Jacob West-Roberts @Jwestrob]

@jesse_vermeulen Go to your other five Claude sessions and ask what you were doing before you locked in on the other one

[Michael Baym @baym]

I’m looking for an automated way to read others’s scientific data without giving credit or acknowledgement, and also claim full credit for insights from it. And I want it to have a fitting name

OAI: say no more