←
Jacob West-Roberts2,234 posts
Jacob West-Roberts avatar

Jacob West-Roberts

@Jwestrob

Computational biologist, rock hunter, prokaryote enthusiast, wizard.

◷ Joined December 2008▧ 77 Photos and videos
Sergey Ovchinnikov avatar
⟳ Jacob West-Roberts retweeted
Sergey Ovchinnikov@sokrypton·15h

Claude Fable 5.2 correctly predicted contacts of a denovo protein. 😎

Post attachment
Megha Srivastava avatar
⟳ Jacob West-Roberts retweeted
Megha Srivastava@megha_byte·Nov 12

Which predicted protein-ligand pose is closer to the crystallographic binding mode? 🧬 Modern cofolding models let us sample infinite candidate poses, but can we reliably *rank* them for drug discovery? Check out Pyrite, a pose ranking benchmark and AI agent framework w/ @genesismolai!

Rory Gao avatar
⟳ Jacob West-Roberts retweeted
Rory Gao@gaorory·Nov 10

I'm excited to announce my first first-author paper ZeUS has been accepted to NeurIPS 2026! ZeUS (Zero Shot Unified Symmetry) is an inference-time framework that allows efficient generation of large scale symmetric protein assemblies. We enable the generation capsids of up to 10,000 residues on a single GPU, up from the previous maximum of 2,000. 🧵 1/

0:58
Jacob West-Roberts avatar
Jacob West-Roberts@Jwestrob·Nov 12

Fable 5.2 is amazing and I love being able to work with it on bio stuff. But twice now it has launched 'smoke tests' where it tries to run ESM-++ 6B SINGLE THREADED ON CPU. Brother. WHY. You have an IQ of like 400 why are you doing this.

Zeke Hausfather avatar
⟳ Jacob West-Roberts retweeted
Zeke Hausfather@hausfath·Oct 28

Google has specifically prevented its AI tool from telling users who won the 2020 presidential election, even though it happily tells us that Trump won in 2016 and 2024. This sort of political intervention into LLM responses is deeply problematic. (h/t to Charles Mann)

Post attachment
Neil Renic avatar
⟳ Jacob West-Roberts retweeted
Neil Renic@NC_Renic·Oct 28

Two stages of research: 1) I think I’m onto something 2) oh no

Bo Wang avatar
⟳ Jacob West-Roberts retweeted
Bo Wang@BoWang87·Sep 17

This is super cool result for AI & protein design! Claude wrote CUDA kernels that beat NVIDIA's own cuEquivariance on triangle attention by 2.7–2.9x, and triangle multiplication by 1.7–3.2x. Two engineers supervised it. Neither had prior kernel engineering experience. 30+ models such as AlphaFold3, Boltz-2, OpenFold3, protein LMs, genomics, done in 4 weeks. Triangle ops are the cubic bottleneck in Pairformer-based structure prediction. Fix them and the whole stack gets cheaper: 4x average speedup, 100x fewer GPU hours for comparable protein design results. FlashPairformer is now open-sourced: anthropic.com/research/claud…

Biologists use specialized open-source models for tasks like modeling the structure of molecular systems, designing drug-like molecules, and predicting the effects of genetic mutations. But these models are often expensive to run, potentially limiting their impact. In our latest Science Blog, we share how Claude was able to optimize inference for more than 30 open-source models, making them 4x faster on average, partly by writing custom software for GPUs. We’re open sourcing all of the optimization code. Read more: anthropic.com/research/claud…

0:18
Lior Pachter avatar
⟳ Jacob West-Roberts retweeted
Lior Pachter@lpachter·Sep 9

Mathematics has now fully morphed into biology: Project costs millions $ ✅ Put out paper that nobody has read ✅ Massive paper supplement nobody will read ✅ Advertise with pretty art ✅ Vicious authorship fight ✅ Say you're curing cancer ✅

Post attachmentPost attachment
Riccardo De Santi avatar
⟳ Jacob West-Roberts retweeted
Riccardo De Santi@r_de_santi·Aug 26

Generative models can’t discover what they can’t reach. We’re excited to introduce ActFlow: a continued pre-training scheme that actively expands the valid design space reachable by flow and diffusion models. We call this generable set expansion — a new learning principle for out-of-distribution generative modeling, and a step toward evolvable search spaces for scientific discovery. (1/5)

0:19
Jorge Bravo Abad avatar
⟳ Jacob West-Roberts retweeted
Jorge Bravo Abad@bravo_abad·Aug 24

UMAP makes useful pictures, but what structure does it destroy? Daan H. de Groot and coauthors introduce Bonsai, a Bayesian method that represents high-dimensional data as a tree rather than forcing it into a conventional two-dimensional embedding. The motivation comes from single-cell biology. Methods such as UMAP and t-SNE are extraordinarily useful for visual exploration, but their geometry is not a faithful representation of the original high-dimensional space. Local and global relationships can be distorted, and changing visualization parameters can change the apparent biological story. Bonsai takes a different approach. Each cell is treated as a noisy point in high-dimensional gene-expression space, complete with uncertainty estimates. The method then reconstructs the maximum-likelihood tree connecting those points under a probabilistic model of how expression states can change. Because a tree can always be drawn in two dimensions, visualization no longer requires projecting the data onto two artificial coordinates. On synthetic benchmarks, Bonsai almost perfectly reconstructs structures that PCA and UMAP largely fail to recover. It also preserves cell-to-cell distances much more faithfully. And the biological payoff is not only prettier visualization. Applied to cord-blood single-cell data, Bonsai recovers established differentiation relationships and identifies an apparently previously undescribed subset of natural-killer cells associated with the myeloid rather than lymphoid lineage. The method also scales through a backbone implementation to datasets exceeding one million cells. There is a broader scientific lesson here. Dimensionality reduction is not a neutral preprocessing step. When ML changes the representation of scientific data, it can also change which hypotheses become visually plausible. Paper: de Groot et al., Nature Biotechnology (2026), CC BY 4.0 | DOI: 10.1038/s41587-026-03220-2

Post attachment
Jacob West-Roberts avatar
Jacob West-Roberts@Jwestrob·Aug 21

Genuinely feel like I should start a blog on all the cool shit i see in random genomes that I can't be bothered to ever publish on. Somebody needs to be out here advocating for the Armatimonadetes

Jacob West-Roberts avatar
Jacob West-Roberts@Jwestrob·Aug 21

Who is out here trying to use protein design to make novel active sites and then go back and find matching ones in nature? Anybody?

Coban Brooks avatar
⟳ Jacob West-Roberts retweeted
Coban Brooks@cobanbrooks·Aug 17

I’m really excited to share our new preprint, out today, where we built a fully autonomous system for enzyme engineering — integrating a self-driving lab with a generative protein language model that worked together over a month to engineer substrate specificity in glycoside hydrolase (GH1) enzymes. biorxiv.org/content/10.64898… [1/n]

Ryo Yamamoto avatar
⟳ Jacob West-Roberts retweeted
Ryo Yamamoto@RyoYbioinfo·Aug 4

Silico can also improve drug design and lots of other AI x bio work via interpretability! Last week, I found that by reading the internal representation of protein-folding model, we can better rank and generate ligand-binding poses, up to 4x! 🧵 1/

Silico, the platform for ambitious AI research, is publicly available today. AI is advancing fast. The tools to understand it need to advance even faster. Silico lets you interpret and train your models at frontier scale. Learn more + get access 🧵

1:00