After fine-tuning on potentially malicious insertions, the model reached 0.95 AUROC and 0.95 AUPRC. This indicates that such edits do leave detectable genomic-context signatures, without relying on marker genes or predefined databases. Congrats @EdanGabay!!! 👏👏👏 4/4

No unified large dataset of engineered bacterial genomes. So we built scalable simulations of random and potentially harmful gene insertions. We trained a classifier on those, along with natural sequences and natural occurrences of the inserted genes as hard negatives. 3/4

Edan used gene-level language models, treating genes as words and genomic regions as sentences. A language model solution made sense since, in natural language, it is easy to recognize a word out of context put in the wrong cranberry 🤖 2/4

So many bacterial genomes are being edited… Could we spot them in the wild even without obvious markers??? Worry not! Our @EdanGabay has you covered. In our new preprint, she pinpoints such genes disrupting the natural genomic "grammar": biorxiv.org/content/10.64898… 1/4

Genomes are full of dark matter of unknown functions. We present Minerva, a new method for discovery guided by genome language models. Minerva reveals the interactions hidden in non-coding DNA, pointing to hundreds of new putative RNAs and repetitive elements per bacterial genome. Minerva allows us to find and study elements invisible to traditional methods at orders of magnitude greater scale than before.

Excited to share Minerva, our approach using genome language models for biological discovery! Using Minerva, we find that UG27 reverse transcriptase systems encode variable arrays of diverse ncRNAs with a shared structure, each templating a short DNA hairpin. With @garykbrixi.

ʙɪɴᴅᴄʀᴀꜰᴛ2 is out, and we're not waiting for the paper. The full code drops today, free for academic and industry use. We're releasing it early so you can start designing right now, and bring its full power to the current Adaptyv competition. github.com/PacesaLab/BindCra…

FAMUS is modular by design. Got your own HMM database? We built a preprocessing pipeline to turn it into a FAMUS database too. It is all, of course, open source: github.com/burstein-lab/famu…, also on conda: `conda install -c conda-forge -c bioconda famus` 6/8

Benchmarking on KEGG and PANTHER, FAMUS improves on KofamScan and InterProScan when most sequences are unannotated, a realistic case for metagenomics and non-model organisms. This led us to compile FAMUS databases from KEGG, InterPro, eggNOG, and OrthoDB. 4/8

It annoyed us that annotation tools aren't great at saying "I just don't know". That's a real problem for metagenomes and non-model organisms, where it usually means picking some threshold and hoping for the best. We built FAMUS to try and fix this. doi.org/10.64898/2026.03.08.… 1/8

Now available in bioinformatics! Congrats @EllaRannon 🎉

🧬 New preprint alert! Protein language models have transformed bioinformatics, but what about the tokens they read? In our new preprint, 👑@EllaRannon👑 studies how tokenization choices shape pLM performance and efficiency. 🧵(1/5) biorxiv.org/content/10.64898…

1/4 Ever wanted to predict bacterial protein-protein interactions (PPI) on a large scale? We wanted to, but realized there’s no such algorithm that is both rapid and optimized for bacterial protein analysis. This led our ⭐️Chen Agassy⭐️ to develop B-PPI: doi.org/10.64898/2025.12.23.…

1/6 🧬📊 Curious about the buzz around NLP in biology? Feeling overwhelmed by the rapid developments? We've got you covered! Our review on NLP applications in genomics, by the wonderful @EllaRannon, is now out as a pre-print! #NLP #Bioinformatics arxiv.org/abs/2506.02212

🚨New paper alert! The amazing @EllaRannon developed DRAMMA, a machine learning model that enhances antimicrobial resistance gene detection using diverse biological data🧬. Superbugs, beware! tinyurl.com/26b9x2ud #Bioinformatics #MachineLearning #AMR 1/6

👑

We are deeply thankful to this amazing community for being so generous with advice, support, materials, and opportunities to present and discuss this study. 🙏🙏🙏 2/2

Fellow microbial immunity, mobile elements, and plasmid enthusiasts: the paper of our wonderful @BruriaSamuel on anti-defense genes in plasmids is now published in @Nature!!! Check out her thread below for highlights of our new results. 1/2

We couldn't be more proud of @BruriaSamuel!! Thank you @PlasmidSociety for a great conference and opportunity to interact with so many amazing plasmid enthusiastics.

Thrilled to have played a small role in this fascinating project by the brilliant @SternLab! They analyzed > 11M viral genomes to detect chronic infections and investigate their potential contribution to the evolution of novel SARS-CoV-2 variants. Read more 👇