iiinova — where your digital self keeps evolving

Surag Nair @suragnair.bsky.social · 13/04/2026

more details here: bsky.app/profile/sura...

Surag Nair @suragnair.bsky.social · 13/04/2026

Agents for comp bio are advancing rapidly, but evals are lagging. Current benchmarks can be overly prescriptive. Full analysis vignettes are hard to verify. We introduce CompBioBench: 100 diverse, challenging, verifiable tasks. We benchmark Codex and Claude Code. biorxiv.org/content/10.6... 1/9

196

Reposted by Surag Nair

gokcen.bsky.social @gokcen.bsky.social · 10/11/2025

An artistic reinterpretation of the Nona model's schematics

051

Reposted by Surag Nair

gokcen.bsky.social @gokcen.bsky.social · 10/11/2025

Introducing Nona! 🧬 @suragnair.bsky.social 's brilliant idea to unify siloed genomic AI. Nona learns jointly from DNA seq + functional data, enabling new ways of modeling genomic data!

172

Surag Nair @suragnair.bsky.social · 10/11/2025

Excited to share Nona: a unifying multimodal masking framework for functional genomics. Models for DNA have evolved along separate paths: sequence-to-function (AlphaGenome), language models (Evo2), and generative models (DDSM). Can these be unified under a single paradigm? 1/15

13413

Reposted by Surag Nair

Peter Koo @pkoo562.bsky.social · 05/02/2025

[SAVE THE DATE] MLCB 2025 is happening Sept 10-11 at the NY Genome Center in NYC! Attend the premier conference at the intersection of ML & Bio, share your research and make lasting connections! Submission deadline: June 1 More details: mlcb.github.io Help spread the word—please RT! #MLCB2025

14027

Reposted by Surag Nair

Veera Rajagopal @doctorveera.bsky.social · 02/12/2024

An interesting diagnostic application of CRISPR is to activate expression of genes in tissues where they are not normally expressed. This is useful when studying functional consequence of suspect pathogenic variants in genes that are restricted to inaccessible tissues like brain, eyes etc. 1/

1142

Reposted by Surag Nair

Mitch Guttman @mitchguttman.bsky.social · 27/11/2024

Gene regulation involves thousands of proteins that bind DNA, yet comprehensively mapping these is challenging. Our paper in Nature Genetics describes ChIP-DIP, a method for genome-wide mapping of hundreds of DNA-protein interactions in a single experiment. www.nature.com/articles/s41...

nature.com

ChIP-DIP maps binding of hundreds of proteins to DNA simultaneously and identifies diverse gene regulatory elements - Nature Genetics

ChIP-DIP (ChIP done in parallel) is a highly multiplex assay for protein–DNA binding, scalable to hundreds of proteins including modified histones, chromatin regulators and transcription factors, offe...

9382150

Reposted by Surag Nair

Wei-Lin Qiu @613weilin.bsky.social · 25/11/2024

Excited to share our latest preprint on scE2G – a new model to link enhancers to target genes using single-cell data – with state-of-the-art performance across multiple perturbation benchmarks. biorxiv.org/cgi/content/... Read more below! 1/12

biorxiv.org

Mapping enhancer-gene regulatory interactions from single-cell data

Mapping enhancers and their target genes in specific cell types is crucial for understanding gene regulation and human disease genetics. However, accurately predicting enhancer-gene regulatory interac...

14320

Reposted by Surag Nair

Alex Thiery @alexxthiery.bsky.social · 23/11/2024

go.bsky.app/PFpnqeM

73316

Reposted by Surag Nair

Dan Roy @roydanroy.bsky.social · 22/11/2024

By demand, I've created the final starter pack in my ML Personality Starter Pack Series. I'm uncertain who belongs in this starter pack and so if you think you better fit in the Grumpy ML or Unreasonably Upbeat ML starter packs, let me know. (Self) nominations welcome go.bsky.app/5Suyk58

4313115

Reposted by Surag Nair

Patrick Phillips @patrickphillips.bsky.social · 22/11/2024

A reminder for new folks. BlueSky does not have an algorithm to raise posts of interest. It is incumbent upon you to do so via reposting. Liking things only provides feedback to the poster but does not promote the post. The signal to noise ratio is taking a brief beating, so great to help curate.

59271

Reposted by Surag Nair

Graham Heimberg @gheimberg.bsky.social · 22/11/2024

1/ Introducing SCimilarity, a new foundation model to explore single-cell RNA-seq data across tissues and diseases! It learns a common measure of cell similarity by training a deep metric learning model on millions of cells from various human tissues and conditions. www.nature.com/articles/s41...

nature.com

A cell atlas foundation model for scalable search of similar human cells - Nature

Nature - A cell atlas foundation model for scalable search of similar human cells

2176

Reposted by Surag Nair

Jesse Engreitz @jengreitz.bsky.social · 20/11/2024

Impressive study from Alex Stark lab identifying 3 new types of silencer elements in Drosophila New TF binds a particular isolated motif in non-accessible sites to recruit G9a. Deletion of these elements can lead to upregulation of nearby gene www.sciencedirect.com/science/arti...

15116

Reposted by Surag Nair

Pooja Kathail @poojakathail.bsky.social · 20/11/2024

We also review variant effect prediction evaluations that have been performed to date on genomic deep learning models, highlighting strengths and limitations of current models and the need for more comprehensive evaluation. 3/4

Overview of variant effect prediction evaluations that have been
performed to date using current genomic deep learning models.

131

Reposted by Surag Nair

Pooja Kathail @poojakathail.bsky.social · 20/11/2024

Super excited to share our review on genomic deep learning models for non-coding variant effect prediction, with Ayesha Bajwa and Nilah Ioannidis. We’d like this review to be a useful resource, and welcome any feedback, comments, or questions! 1/4 arxiv.org/abs/2411.11158

arxiv.org

Leveraging genomic deep learning models for non-coding variant effect prediction

The majority of genetic variants identified in genome-wide association studies of complex traits are non-coding, and characterizing their function remains an important challenge in human genetics. Gen...

13413

Reposted by Surag Nair

Shaun Mahony @shaunmahony.bsky.social · 18/11/2024

Really intriguing model of AP-1 driven aging. @anshulkundaje.bsky.social @suragnair.bsky.social - thinking of your AP1-related results in the ChromBPNet paper here...

1156

Surag Nair @suragnair.bsky.social · 19/11/2024

Highly recommend if you’re considering a PhD in ML for genomics. Jacob is a phenomenal scientist, knows how to dive deep into the nitty-gritty of things, is incredibly patient, and just a very fun person to work with. His weakness? Incosistent joke quality.

170

Reposted by Surag Nair

Kevin K. Yang 楊凱筌 @kevinkaichuang.bsky.social · 18/11/2024

Two BioML starter packs now: Pack 1: go.bsky.app/2VWBcCd Pack 2: go.bsky.app/Bw84Hmc DM if you want to be included (or nominate people who should be!)

1011956

Reposted by Surag Nair

Shaun Mahony @shaunmahony.bsky.social · 14/11/2024

Dusting off this account since it seems like BlueSky is suddenly the place to be! Here's a couple of resources for anyone interested in gene regulation, chromatin, or genomics: First, a long list of relevant accounts: bsky.app/profile/shau... (will make some starter packs at some point)

2298

Reposted by Surag Nair

Anshul Kundaje @anshulkundaje.bsky.social · 13/11/2024

Incredible resource for DNA binding protein specificity from the Codebook consortium. www.biorxiv.org/content/10.1... www.biorxiv.org/content/10.1... www.biorxiv.org/content/10.1... www.biorxiv.org/content/10.1... Am reading these in detail & will have a lot to say. Stay tuned for thoughts.

biorxiv.org

Extensive binding of uncharacterized human transcription factors to genomic dark matter

Most of the human genome is thought to be non-functional, and includes large segments often referred to as "dark matter" DNA. The genome also encodes hundreds of putative and poorly characterized tran...

311947