Moses Lab

Designing enhancers is key for gene therapy but limited by a lack of experimental data. To overcome this, we developed EnhancAR, a generative model trained on 1.7M enhancer homolog families (~230M sequences) to leverage functional information conserved over evolution.

Announcing our preprint: Predicting evolutionary rate as a pretraining task improves genome language model representations: biorxiv.org/content/10.648… Genome language models (gLMs) have the potential to further understanding of regulatory genomics without requiring labeled data...

@shrinivaslab @RyanKrue @BrennerGroup1 JAX! awesome!

Excited for 1st paper from our lab - led by the amazing @RyanKrue in collab. with @BrennerGroup1. How do we design intrinsically disordered proteins (IDPs) that lack a stable structure and are continuously shapeshifting for different target functions? doi.org/10.1101/2024.1…

Very happy to share what I've been working on in Barcelona with @BenLehner ! We made many (>400k) mutations in a disordered peptide and the globular domain it interacts with to gain a comprehensive map of how specificity is encoded in a partially fuzzy protein interaction (1/n)

Looks interesting: "A Functional Map of the Human Intrinsically Disordered Proteome" 🍝 by @IPritisanac, @ReidAlderson, @KolaricJess, ..., @JulieFormanKay1, @AMosesLab doi.org/10.1101/2024.0…

Do current genomic language models (pre-trained on whole genomes) learn a foundational understanding of biology in the non-coding region of human genomes? A new evaluation led by @AmberZqt suggests not yet! 1/N paper: biorxiv.org/content/10.110…

Really like the idea from this paper -- biorxiv.org/content/10.110… Also, I like the accuracy of the study, e.g authors compare model trained with their procedure (train on augmented data + finetune on real) not only with baseline model (train on real) but on finetuned baseline model

Hi Twitter! This is mostly an automated bot that will publish content directly from our website and blog.