Revolution, interrupted: Why AI has failed to live up to the hype in drug development theglobeandmail.com/business/artic…

biorxiv.org/content/10.110… Nice benchmark of single cell "foundation models" (scGPT, scFoundation) and GEARS (a GNN model) further hyped as "virtual cell models" against linear baselines on perturbation prediction. Long-story short: they can't beat the linear baselines. 1/

PhD applications at Gatsby Computational Neuroscience Unit now open! Fully funded regardless of nationality. See below for application details!

Wow. Hopfield model and Boltzmann machine.

Congrats John and Geoff! Both are former colleagues. I did my postdoc in Geoff's lab in Toronto. After that, I joined Bell Labs, where John was a part-time scientist (and a professor at Caltech). In fact, John was the reason why the department I joined was working on neural nets.

Our paper on using machine learning to predict the impact of rare genetic variants is out! #DeepRVAT utilizes a fully data-driven approach to analyze annotated variants. DKFZ press release: dkfz.de/en/presse/pres……Publication in Nature Genetics: nature.com/articles/s4158…

Orthrus: Towards Evolutionary and Functional RNA Foundation Models 1/ Orthrus is a groundbreaking RNA foundation model that uses a novel self-supervised contrastive learning method, leveraging biological augmentations to improve the prediction of RNA properties with fewer data

1/ We had a great time working on Orthrus, a mature RNA rep learning model, with co-first author Ian Shi and collaborating with Karin(a) Isaev. Blog: philechka.com/science/orthrus Code: github.com/bowang-lab/Ort… Paper: shorturl.at/cPE9D

Looking for postdoc candidate, who is interested in RNA-protein interactions, RNA localization and gene regulation. Candidates with backgrounds in biophysics (particularly single-molecule imaging), chemical biology and cell biology are all welcome to apply! Please help retweet 🙏

💥💥💥New preprint 💥💥💥on the EuPRI resource. Where we reconstruct the motifs for 34,736 RBPs and study their function and evolution. Joint work with Tim Hughes (Toronto), Matt Weirauch, @LXandR_, Deb Ray, Kaitlin Laverty and many more. More details to come

is there any sweeter way to start the weekend than an email saying "Dear Dr. Lai, we are delighted to accept your manuscript for publication at Science". oh yeah, let's gooooo !!!!!

Alireza is amazing. So much impressive work in his PDF.

I created a genomics+bioinformatics starter pack on the other place 🦋 go.bsky.app/B5YYBfq If I left you off, *please* reply and I'll add you!

Thrilled to share our paper now out nature delineating #plasticity during #CRC #metastasis, a fantastic collaboration led by Andrew Moorman Ellie Benitez, and @f_cambuli from the Karuna Ganesh Lab and @dana_per lab! nature.com/articles/s4158… rdcu.be/dYAVK. A 🧵

Extensive binding of uncharacterized human transcription factors to genomic dark matter (Razavi et al., 2024) biorxiv.org/content/10.110… ▶️166 uncharacterized human TFs ▶️"Dark TFs", mainly bind closed chromatin enriched for transposable elements ▶️Some Dark TFs contain KRAB domain

Perspectives on Codebook: sequence specificity of uncharacterized human transcription factors biorxiv.org/content/10.110… ▶️This preprint provides a summary of the release of a bunch of new preprints by the Codebook Consortium (see three posts below). #TFbinding

We're excited to release 𝐦𝐑𝐍𝐀𝐁𝐞𝐧𝐜𝐡, a new benchmark suite for mRNA biology containing 10 diverse datasets with 59 prediction tasks, evaluating 18 foundation model families. Paper: biorxiv.org/content/10.110… GitHub: github.com/morrislab/mRNA… Blog: blank.bio/post/mrnabench

I am excited to introduce mRNABench, a comprehensive benchmarking suite that we used to evaluate the representational capabilities of 18 families of nucleotide foundation models on mature mRNA specific tasks. Paper: doi.org/10.1101/2025.0… Code: github.com/morrislab/mRNA… A 🧵

We're excited to introduce our new work on mature mRNA property prediction, co-first authored with the amazing Ian Shi and Taykhoom Dalal. We introduce mRNABench to standardize evaluation and present a study on building more efficient RNA foundation models. 🧵