1/ AI agents can now accomplish many research tasks. But tackling frontier problems requires deciding which questions matter and when to trust results.
We're excited to introduce DiscoveryAgent to empower scientists in their pursuit of rigorous, open-ended discovery 🧵
Can a person's T-cell repertoire from a blood draw diagnose disease? Many methods say yes, but each was developed on different cohorts, splits, and metrics.
Excited to present BenchRep-T, a benchmark comparing methods head-to-head, at #NeurIPS2026 Evaluations & Datasets 1/🧵
Excited to partner with @naturemethods to launch AI Bytes, a new monthly column explaining AI concepts to life science researchers!
Our first piece discusses foundation models for biology @CarlMaZijiannature.com/articles/s41592-0…
Topic suggestions welcome!
We are excited to introduce a new regular column, called "AI bytes". These educational pieces will be written by AI experts and aim to simplify technical concepts for life science researchers. Read about it in our Editorial:
nature.com/articles/s41592-0…
🚀 Can AI scientists come up with truly creative ideas?
A creative idea needs more than good performance. It must be original, useful and non-obvious.
Yet AI scientists are usually given as much task information as possible, which anchors them on familiar approaches.
We introduce BVSR: Blind Variation, Selective Retention, a discovery framework inspired by a classic theory of human creativity.
✅ Plugs into existing AI-scientist workflows.
Paperclip Datasets is very useful for creating multi-modal datasets!
For example, in minutes it curated a dataset of post-immunotherapy pathology images from hundreds of papers. paperclip.gxl.ai/datasets
Very excited to introduce Paperclip Datasets!
Curate your own datasets from millions of papers in minutes. Just describe the dataset you want to build!
As example, we release the largest dataset of 20k half-life human measurements curated from 2400+ drugs💊
🖇️ Try it: paperclip.gxl.ai/datasets
📝 Blog: gxl.ai/blog/introducing-pape…
📊 Half-life dataset: huggingface.co/datasets/gxl-…
1/4 One DNA sequence, many chromatin states.
Excited to share SMFNet, a diffusion model predicting single-molecule chromatin accessibility. Explainer video below!
With co-first author Till (his thread: bsky.app/profile/tschwammle.…), Yuliya, Roze, @anshulkundaje & Arnaud Krebs.
I'm excited about this new class of generative models that allow us to understand how DNA sequence mediates regulation of transcription factor and nucleosome assemblies at single molecule resolution. 1/
1/4 One DNA sequence, many chromatin states.
Excited to share SMFNet, a diffusion model predicting single-molecule chromatin accessibility. Explainer video below!
With co-first author Till (his thread: bsky.app/profile/tschwammle.…), Yuliya, Roze, @anshulkundaje & Arnaud Krebs.
1/n Within 15 months of publication, most of the LLM claims we tested either no longer held or showed substantially diminished effects. How long does our knowledge of AI hold up? In our new study, we revisit 50 findings to see what fades, what persists, and what gets stronger. 🧵
🚀 Excited to share BindClaw! 🦀
Starting from a prompt or research paper, BindClaw connects biological mechanisms to protein design: identify targets and binding sites → build mechanism-specific computational assays → generate and assess binders → refine designs using the results.
We use agents to evaluate whether designs fit the intended biological objective, including competition with a native partner and preference for a particular molecular state. 🧬
In a human-guided calmodulin campaign, 15 of 18 designs showed binding to calcium-loaded CaM, including subnanomolar binders supported by both BLI and SPR.
This work is an incredible team effort together with @DidiKieran , @saint__ai, @ Kyle Gion and @sacdallago and many others!
📄paper/project: research.nvidia.com/labs/dbr…
💻code: will be released in a few weeks!
I've always had trouble mapping genomic motifs <-> TFs because many TFs can bind a motif. But.. this is important for understanding genomic S2F models and designed DNA. As my third drop, I'm releasing a Claude artifact for exploring these connections.
claude.ai/artifact/CrGrmZ7az…
I'm excited to announce that our team has been working closely with @Anthropic to develop new skills and workflows for drug development. We believe these tools can accelerate & improve our process of company creation, helping focus limited resources on the highest impact projects
Over the past few months, Anthropic scientists have engaged in deep research partnerships with six organizations developing new medicines. We've also begun drug discovery efforts of our own.
In doing so, we’ve learned much more about how Claude can support the many stages of drug development.
In this blog post, we share some early results from these efforts, and describe how this work fits in with our wider ambitions in the life sciences.
anthropic.com/research/early…
AI is now taking on some of the hardest open problems that scientists have posed. But research is broader than solving problems. Can AI also propose research questions that experts find genuinely interesting?
We built After42 to find out. Experts judged 45 of its 135 final questions genuinely interesting, across mathematics, statistics, theoretical computer science, and physics, with wide variation across subfields.
The key idea: develop questions by trying to solve them.
We also asked whether AI can judge which questions are interesting. We find that model judges' top choices align with expert consensus but do not consistently capture individual experts' preferences.
We release the expert-assessed questions as an open resource for researchers to discuss, refine, and pursue, as a step toward integrating AI into the broader research enterprise.
after42.org
Very excited to release ProVADA! It was so much fun working with the incredible @Xiaowei0402, @sluu_06, and the rest of the team. Check out Xiaowei's thread for more details!
We deimmunized a clinical CD19 CAR binder with experimentally detected HLA-I epitope depletion while retaining tumor killing, and rescued a secreted protease to function in the cytosol.
Both done with one unified design framework: ProVADA.
How it works and what we tested 🧵 (1/11)