LifeSciBench: Evaluating Language Models on Realistic, Expert-Level Tasks in the Life Sciences (PDF): cdn.openai.com/pdf/b4299379...
Blog post: openai.com/index/introd...
Stephen Turner
Our congratulations to Ludwig @princeton.edu’s @skinnider.bsky.social on his being named a Pew Scholar. The award will support his rapidly advancing efforts to enlist AI to identify the countless small molecules in our bodies, often called the “dark matter” of the metabolome. bit.ly/43A3f7F
Our lab website is finally online! pacesalab.com
You can find information about our research, publications, and on-going developments in the lab.
Excited to present sampleworks: a modular platform for generating biomolecular conformational ensembles by coupling AI structure predictors to experimental data. Our first publication of @diffuseproject.bsky.social, led by @karsonchrispens.bsky.social + Marcus Collins. thestacks.org/publications...
Happy to share that this work led by @mihkeljesse.bsky.social has now been published at PLOS Genetics! journals.plos.org/plosgenetics... A couple of thoughts below.
New preprint! In collaboration with @xujwet.bsky.social, @pedrobeltrao.bsky.social, and Akhmanova and Beekman groups, we determined the structure of the transition zone microtubule doublet in mammalian motile cilia, providing potential insights into the regulation of IFT: tinyurl.com/fssnevuc
Lots is made (including by me) of studies showing little difference between preprints and the articles subsequently published in journals. BUT this may not tell us much about what articles would look like if passing formal peer review was not the goal www.linkedin.com/feed/update/...
We've been looking at how to compare and cluster large numbers of genomes, such as those in large isolate databases such as AllTheBacteria, and metagenome assemblies (e.g. SPIRE, MGnify).
On a combined dataset of 5.6 million assemblies, we can now cluster/dereplicate everything in under a day!
The ciliary transition zone gates bidirectional protein trafficking to maintain the specialized ciliary proteome using microtubule doublets as a scaffold. While ciliary axonemal doublets are well-char...
Some scientists still don't trust preprints (crazy right?).
But how much do claims really change from preprint to published paper? We plan using LLMs (Claude by Anthropic) to track exactly that acro...
@jengreitz.bsky.social l & my lab want to co-hire a computational biologist/biostatistician with project management expertise to help map the regulatory code of the human genome and discover genetic mechanisms of disease.
Details below
careersearch.stanford.edu/jobs/computa...
Plz RT
John Lees
Here is an example of what I expect we will start seeing more of, a single author bioinformatics paper that looks like it was made with AI assistance. The figures look very much straight out of Claude Code. It does have a "Use of AI tools" disclaimer section journals.plos.org/ploscompbiol...
Author summary Most tools that predict whether a TP53 mutation is disease-causing rely on machine learning trained on large datasets. These models can be accurate but typically cannot explain why a pa...
Author summary Over 90% of human genetic variants associated with human traits and diseases lie in non-coding regions of the genome, making it difficult to interpret the mechanisms by which these vari...
🧬 New preprint! We clustered 5.6 million bacterial genomes into genomically cohesive units (GCUs) 500× faster than existing tools. (In just 14 hours, 16.5 GB RAM using 48 CPUs). 🦠🐙Meet gemsparcl 💎✨!
www.biorxiv.org/content/10.6...
After 1.5 years of work in @kauralasoo.bsky.social’s lab, we finally published my preprint! We introduce gpu-coloc, a GPU-accelerated implementation of coloc, show comparability to CLPP and aim to provide practical guidelines. Now accessible on BioRxiv: www.biorxiv.org/content/10.1...
Johanna von Wachsmann
Colocalisation is a powerful approach to assess if two genetic association signals are likely to share a causal variant. However, association analyses in large biobanks and molecular quantitative trai...
