GraphML News (March 23rd) - Profluent round, Biology 2.0, TacticAI

💸 Profluent, a Berkley biotech startup founded in 2022, raises $35M (overall $44M so far). The company focuses on protein generation models in the context of CRISPR gene editing. VC funding in the biotech industry is on fire in 2024!

🧬 A huge blogpost The Road to Biology 2.0 Will Pass Through Black-Box Data by Michael Bronstein and Luca Naef offers a new perspective on the area of ML for biology and its common problem of lacking large amounts of labeled data. The idea is to leverage low-cost high-throughput data (eg, obtained from experimental facilities), coined as “black-box data”, that might not be directly understandable by humans (or experts) but can be used for training large-scale ML models even in the self-supervised regime. It is then hypothesized that the competitive edge would belong to the companies that manage to build such data pipelines and models. Time to convince old-school chemists about the benefits of black-box data.

⚽ Google DeepMind officially introduced TacticAI with the publication in Nature Communication (we wrote about it in the End-Of-The-Year post a few months ago at the preprint stage). TacticAI uses group-equivariant convnets and is designed for football games to give tactical insights for many practical cases such as corner kicks. Interestingly, experts prefer TacticAI outputs 90% of the time. Equivariance + ⚽ = 📈

Weekend reading:

Atomically accurate de novo design of single-domain antibodies from the Baker Lab - RFDiffusion for antibodies

Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning by Raffaele Paolino, Sohir Maskey, Pascal Welke, and Gitta Kutyniok - WL visited one more location ✅