🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

If Twitter dies and I actually have to go back to journal TOCs and pubmed searches for finding about about interesting publications I’m gonna be pissed.

ViWrap: A modular pipeline to identify, bin, classify, and predict viral-host relationships for viruses from metagenomes biorxiv.org/cgi/content/sh… #biorxiv_bioinfo

As a bioengineer, I am PUMPED for all of the emerging deep-learning based approaches for protein engineering! However, many of these methods are simply difficult to use, whether they require background ML knowledge or special hardware. Hopefully, I have a solution...

Can large language models understand genomic sequences and uncover new biology? 🧬🧬🧬 Excited to share a new #preprint with Sergey Ovchinnikov, Andre Cornman, and Pierre Deep Sea. TLDR: A Large Language Model for genomic sequences! #genomics #AI #machinelearning #NLP biorxiv.org/content/10.110… 1/

The Anantharaman Microbiome lab, 2023. The Anantharaman Lab UW-Madison Department of Bacteriology

It’s been a busy & fun summer passing prelims with @KatieKlierMicro & Cody Martin, presenting a poster at #ISMSM23 with @val_deanda & @KatieKlierMicro & an early career grant from #FEMS, reuniting with #UTMSI colleagues to celebrate Ian M Rambo, and now aboard the RV Falkor Too

Check out the preprint of my first PhD chapter! 🤗 Thank you to my other coauthors Cody Martin Faith Koester and Chao (Zhichao) Zhou. Feedback welcome!!

Excited to share our latest work on development of PST, a genome language model for viruses and phage. We believe PST can be a foundation model for viromics and enable broad viral ecology and bioengineering applications. Led by PhD student Cody Martin. biorxiv.org/content/10.110…

Our Protein Set Transformer preprint is now on bioRxiv. Read on to see what we mean by a protein-based genome language model. Work led by Cody Martin and Karthik Anantharaman. 1/

It's great to see more work being done on *contextualizing* protein embeddings with genomic context information! Check out this new viral gLM work by Cody Martin et al!🎉

Introducing the 😱OMG dataset and 🤖gLM2! OMG is a massive Open MetaGenomic corpus totaling 3.1Tbp of data and 3.3B proteins. We train gLM2, the first mixed-modality genomic language model, on OMG. 1/🧵 #BioML #AI4Science

.Cody Martin (UW–Madison) and colleagues published a new preprint on Protein Set Transformer: A protein-based genome language model to power high diversity #viromics. buff.ly/4dkI6lb

If you are interested in chatting about our work on genome language models, stop by my poster on Thursday afternoon at #ISME19 PS3.16.042

Are you interested in soil viruses? Do you want to know how viral communities are structured in natural, damaged, and restored peatlands? Or do you just want to chat about viromics and soil viral ecology? If you’re at #ISME19, stop by my poster on Thursday morning! (PS3.16.029)

New paper alert: Our 20-year study of viral ecology and evolution reveals viral roles in microbial dynamics, phage genome evolution over time, and key interactions with hosts. Chao (Zhichao) Zhou Patricia Tran, PhD Cody Martin Robin Rohwer Trina McMahon 🌪 @archaeal nature.com/articles/s4156…