A new way to measure how AI agents handle the routine analyses of wet-lab science—BioBasicsBench.
Developed with Ligo, a biotech company focused on enzyme design, the benchmark draws on 100 tasks from real experiments to test whether agents can interpret raw lab data, identify errors, and recognize when the evidence doesn’t support a conclusion.
Accelerating biological research starts with getting the everyday work right. BioBasicsBench shows where models need to improve, and helps us track what those gains mean for scientific progress, biosafety, and biosecurity.
openai.com/index/measuring-h…
GPT-Rosalind surfaced a new lead for drug discovery: could restoring cholesterol transport protect neurons from degeneration?
DCTN1 is a gene linked to Perry syndrome, a rare neurodegenerative disorder. In mouse-brain data, disrupting it increased expression of genes involved in making cholesterol. GPT-Rosalind suggested a possible explanation: cholesterol may not be reaching where neurons need it.
That gives scientists a specific mechanism to test and, if confirmed, a direction for developing new treatments for neurodegenerative disorders.
With @perturbai_tx and @scrippsresearch, a team of thousands of GPT-Rosalind agents worked in parallel, connecting gene-expression results from millions of mouse brain cells with scientific literature in just 32 minutes. We’re now expanding this collaboration to identify new drug targets.
openai.com/index/scaling-ai-…
Scientific research is scattered. @OpenAI's Rosalind Workbench allows life science researchers to analyze data, inspect evidence, and review outputs in one place.
tinyurl.com/2b4c4jwp
We're bringing together specialized life science tools from @boltz_bio , @tamarindbio , @biohub ESM, @nvidia BioNeMo , @adaptyvbio and many more allowing scientists to combine the strengths of human intelligence and their subject matter expertise with frontier AI intelligence and push the limits of what they can do in science
1
5
321
JSheldon retweeted
Bring stronger biological reasoning to your research with GPT-Rosalind in the API and Codex.
Connect findings across papers and experimental results, weigh the evidence for a biological target, and work through an analysis to plan what to test next.
JSheldon retweeted
Astra for antibody developability prediction:
GPT-6 Astra is now the best-performing frontier model for antibody developability prediction in our benchmark. 🧬
Finding an antibody that binds is only the beginning. Will it aggregate? Will it stay stable? Can it actually behave like a drug?
GPT-6 Astra predicts these developability properties better than the other frontier models we tested. 🤯
And yes, the interactive visualization showing how an antibody actually works was also built with Astra in about 1 hour.
This model looks seriously powerful.
Congrats @gbt @sama
#insilicoSOTAFM
JSheldon retweeted
At OpenAI, it's felt like our researchers & engineers have been living in the future with Codex.
Today, we're bringing that same experience to life science researchers with the Rosalind Workbench.
Discover your love for whole transcriptomic #spatialgenomics this #ValentinesDay with #VisiumHD from 10x Genomics. Check out the beautiful and distinct expression of these #cardiac muscle and #blood marker clusters in the developing mouse embryo ❤️#spatialtranscriptomics #Visium
JSheldon retweeted
Big week for us at #AACR22! We are honored to be recognized as a winner of the @SelectScience 2022 Scientist Choice Awards for Webinar of the Year! We look forward to continuing to provide our customers with high quality content about our single cell, spatial & in-situ products.
2016 Mast Ranch Cabernet Sauvignon @Laird_Wines #wines #travel #sunsets #love #California #weekend #winelover
… and then I realized, adventure was the best way to learn #london #travel #PhotoOfTheDay #beautiful #iPhone13 – at London, England
JSheldon retweeted
We developed a novel machine learning method (Perler), which robustly reconstructs spatial transcriptome from single-cell RNA-seq data with THE-STATE-OF-THE-ART accuracy. Good job @yasokochi!
Model-based prediction of spatial gene expression via generative linear mapping biorxiv.org/cgi/content/shor… #bioRxiv
JSheldon retweeted
Based on recent travel data, national parks could be ideal destinations this summer as people look to get away after spending weeks under stay-at-home orders nbcbay.com/HQ8p3BS
JSheldon retweeted
California is finally winning coronavirus battle, even as deaths keep rising latimes.com/california/story…

















