Understanding human biology across scales - from molecules to cells to entire organisms - remains one of biomedicine's greatest challenges in the fight against disease.

Today, we are announcing Phenformer - a multi-scale genetic language model that learns to read and interpret human genomes by connecting DNA, cell and tissue context, molecules and clinical outcomes.

Phenformer is a generative model of molecular mechanisms that enables researchers to unravel the mysteries underlying disease, and could thereby accelerate the development of precise future therapeutics. Interpreting whole genomes is challenging because of the vast size of the human genome that spans more than 3 billion base pairs. If your genome were a library, it would encompass 6'000 books with 250 pages each.

This complexity is compounded by how genetic code functions at multiple biological scales - spanning from molecular to whole organism level. Current methods cannot yet comprehensively integrate these diverse levels of biological organization, limiting our ability to fully understand the mechanisms behind health and disease.

A long-standing challenge in supervised deep-learning has been to imbue neural networks with mechanistic -rather than associational - understanding.

We are excited to present DiffIntersort - a causal order regularizer enabling the differentiable optimization of deep-learning methods using interventional data 👇 Building on the theory of epsilon-interventional faithfulness introduced in Chevalley et al (2024), we reformulated Intersort using differentiable sorting and ranking.

This enables two key advances:
- seamless integration into modern deep learning frameworks as a differentiable regularizer
- computational scalability into large, realistic-scale problems for biological discovery (1'000s of intervened nodes!)

Unable to keep up with the deluge of amazing work happening in ML for Biology and Health at NeurIPS this year?

We've got you covered with a concise summary of #NeurIPS2023 content focussed at the exciting intersection of Biology, Health and AI!

thread 👇 Björn Ommer (Stable Diff) starts us off with defining human vision as grasping things without touch and perception as a process of prediction

He argues intelligence is learning under finite resources to support research outside scaling & makes case for accessible and open models

You couldn't make it to #NeurIPS2022 this year?

Nothing to worry - I curated a summary for you below focussing on key papers, presentations and workshops in the buzzing space of ML in Biology and Healthcare 👇 Starting off with Keynote presentations:

Back prop has become the workhorse in ML-
@geoffreyhinton challenges the community to rethink learning introducing the Forward-Forward Algorithm that are trained to have high goodness on positive and low goodness on negative samples.