i am a huge proponent of incorporating knowledge graphs in ML to improve performance and this work on using KGs on smaller datasets where p>>n is very exciting!

🚀🎉 Excited to announce 🌟 PyTorch Frame 🌟 - our new open-source initiative in PyTorch! Dive into multi-modal tabular deep learning like never before! Link: github.com/pyg-team/pytor… #PyTorch #OpenSource (1/6)

1/🧵Introducing Perturb-seq-in-the-loop: a sequential experimental design strategy for perturbation screens guided by multimodal priors, with 3X speedup over state-of-the-art active learning methods! With amazing Romain Lopez Jan-Christian Huetter Taka Kudo Antonio Rios Aviv Regev

In our latest work, we describe how inverse folding with a multimodal language model enables unsupervised ML-guided protein evolution with the strongest experimental success rates to-date. We evolve antibodies to have ~10-30X better pseudoviral neutralization with improved

Excited to share new work led by Varun Shanker -- Varun shows how using ESM-IF to propose antibody mutations leads to unprecedented improvements in pseudoviral neutralization of viral escape variants, with leading success rates for ML-guided directed evolution!

Loyal's in good company!

I've had an interesting year to say the least -- almost exactly a year ago I started moonlighting on Guardrails AI in my spare time. To celebrate my ~1 year anniversary, I'm giving the keynote at the AI in production conference, with some 4000+ registrations already(!) Why you

💊Clinical trials cost $100M’s, yet 1 in 3 fail due to insufficient patient enrollment.🚨Despite costing $15B/yr, patient recruitment is a key unsolved bottleneck in drug discovery. Our latest work shows how LLMs can help solve this! 🌐Site: clinicaltrialmatch.stanford.edu (1/7)

Our 🪐SATURN method is now out in Nature Methods! SATURN paves the way for universal cell embeddings, enabling integration of datasets across different species 🐒🐁🧍🐟🐸 Using protein language models, we encode biological meaning of genes in scRNA-seq datasets.

Our paper “Towards Generalist Biomedical AI” was just published in NEJM AI! Congrats to the team. ai.nejm.org/doi/full/10.10…

Happy International Women's Day to all the women in startups who break glass ceilings (founders, investors, operators, LPs) Last week, we hosted our very first Pear VC Female Founder Circle Retreat and it was truly incredible to be vulnerable and candid with 100 brilliant women

Amazing work Maria Brbic Michi Yasunaga !

Thrilled to have matched at MassGeneral Medicine in the Stanbury PSTP! Thanks to all my mentors, family, and friends for the support and love. Thank you to all the patients who have taught me so much so far and the ones that I will learn from on my next journey! Doctorin’ soon! 🩺🫡

Excited to share our newest work! 📝 Evaluation of LLMs is hard, especially for health equity. We provide a multifaceted human assessment framework, 7 newly-released adversarial datasets, and perform the largest human eval study on this topic to date. 🧵: arxiv.org/abs/2403.12025

We Monther Abu-Remaileh wrote a review titled "The BMP Hypothesis" go.shr.lc/49z2JXX We hope its hypotheses will democratize understanding of the fundamental biology and translational potential of BMP in disease and aging. "Theories are nets: only one who casts will catch."

Thank you for being a guiding light :)

Unlock the Power of Synthetic Data in Computer/Machine Vision 🔐 🚀 With AI vision blowing up in manufacturing and robotics, you have many options for vision system hardware and software 📸 Nevertheless, researchers agree that the data you use to train these systems is actually

Honored to have my thesis work recognized by the 2024 Sammy Kuo Award in Neuroscience!

Evo has been published in @Science! A true privilege to work with such an amazing team! So many exciting new experimental results in this emerging field of Generative Genomics, including AI generated and *validated* CRISPR-Cas systems and transposons