Call for Papers | Generative AI in Genomics (Gen²) Workshop ICLR Workshop on Generative AI in Genomics (Gen²).

📣 DEADLINE UPDATE: Good news! We’ve extended the Gen² paper submission deadline to:
📅 Feb 8, AoE

We look forward to hearing about your latest research in GenAI in Genomics at @iclr-conf.bsky.social !

🔗 genai-in-genomics.github.io/call_for_pap...

#ICLR2026 #GenAI #CompBio #BioML #Genomics 🧬🧪

<i>LETTER FROM THE EDITORS:</i> THE EMERGING NEED FOR BIOLOGICALLY INSPIRED AND MATHEMATICALLY GUIDED MACHINE LEARNING FOR KNOWLEDGE DISCOVERY IN BIOLOGY Published 4 issues per year

Why invest in mathematically guided ML for biology now? New special issue explores how math, biology & ML convergence enables deeper insights from complex datasets.

Read now: dl.begellhouse.com/journals/558...

#BioML #MathematicalModeling

Does anyone know of good conformation prediction software for PTMd peptides? There’s lots of good resources for unmodified peptides but many do not include PTMs, or extremely limited. Specifically interested in glycosylation.
#glycotime
#BioML

Open to conversations on:
• #BioML for RNA structure prediction + optimisation
• Improving genome and cell foundation models
• AI-enabled genome assembly
3/4

AlphaFold developer Google DeepMind to fund CASP as NIH funding falls short Protein structure prediction contest CASP gets temporary funding from Google DeepMind as NIH grant runs out.

NEW from me at STAT:

We've learned that DeepMind is going to fund CASP, the protein structure competition that brought Google DeepMind's #AlphaFold to prominence (and a Nobel Prize), as its NIH funding runs out.

More @statnews.com:
www.statnews.com/2025/07/21/c...

🖥️🩺🧪🧬 #bioML

Undruggable ‘disordered’ proteins become druggable with new AI techniques from David Baker In a new study, Nobel laureate David Baker and colleagues detail new methods for targeting undruggable "disordered" proteins.

In new studies, the Baker lab outlines two different ways to bind previously "undruggable" disordered proteins using diffusion AI models.

Come for the science, stay for the pasta analogies:
#bioML 🖥️🩺🧬🧪

www.statnews.com/2025/07/17/n...

Protein structure competition, of AlphaFold fame, nearing deal to replace lost NIH funding CASP, a popular research competition that spawned three Nobel laureates is set to lose NIH funding.

CASP, the protein structure competition that rocketed AlphaFold to fame and a Nobel, is losing its NIH funding.

David Baker on how CASP impacted his career (and Nobel Prize), and what's the latest on CASP's funding status:

#bioML 🧪🧬⚗️🩺🖥️
www.statnews.com/2025/07/16/c...

GenBio ICML Workshop 2025 GenBio focuses on solving fundamental problems in biology through generative AI.

Workshop webpage: genbio-workshop.github.io/2025/
#ICML2025 #ICML #GenAI #GenBio #BioML #BioimageAnalysis

Deep learning-based predictions of gene perturbation effects do not yet outperform simple linear baselines Advanced deep-learning methods, such as foundation models, promise to learn representations of biology that can be employed to predict in silico the outcome of unseen experiments, such as the effect o...

www.biorxiv.org/content/10.1...
#BioML #statistics

The ML for Biocatalysis workshop in Zurich was a great experience! Thank you to all the speakers, sponsors and the more than 100 participants! It was great to see that there is so much interest in this topic!

#MLforBiocat #enzymes #BioML

Are you interested in how machine learning will shape the future of biocatalysis? Then join us for the 𝐌𝐋 𝐟𝐨𝐫 𝐁𝐢𝐨𝐜𝐚𝐭𝐚𝐥𝐲𝐬𝐢𝐬 𝐖𝐨𝐫𝐤𝐬𝐡𝐨𝐩 in Zurich! 🧬🤖 Discover how ML & computational tools are advancing enzyme design and discuss challenges at the interface of wet lab and dry lab. #BioML

(a) Human U2OS cells treated with dimethyl sulfoxide (DMSO) and stained using the Cell Painting assay, which employs six dyes in five channels to label eight cellular compartments. The top row (from left to right) shows mitochondrial staining; actin, Golgi, and plasma membrane staining; and nucleolar and cytoplasmic RNA staining. The bottom row (from left to right) displays endoplasmic reticulum staining, DNA staining, and a montage of all five channels (from Cimini et al. [21]). (b) Thousands of features are extracted from each segmented cell in microscopy images of wells. A learned function f(x) (CytoSummaryNet) aggregates this data into a single feature vector: the sample’s profile. (c) An in-depth look at the model architecture used in this study. The model consists of three elements: a function φ(x), which maps the input data from ℝD to ℝL space, a summation, which collapses the cell dimension, and ρ(z), which maps the collapsed representation from ℝN to ℝL space. (d) During training, replicate compound profiles are forced to attract each other (green arrows) and simultaneously repel every other compound (red arrows) in the learned feature space. Here, all forces are drawn for a single profile of compound B.

Taking pictures of cells with a microscope, then extracting thousands of features from them is uncannily effective for quantifying cell state, esp. for genes and chemicals (e.g., Cell Painting). But we often average the rich single-cell data to simplify analysis. Can we do better?
#bioML 🧪
1/n

🧪 So proud of this work by the dream team of @johnarevalo.bsky.social and Ellen Su: a new graph dataset for predicting drug-target interactions, using information from Cell Painting.

Stop by their poster in a few hours @ #NeurIPS! (details below)

PS: John is on the job market 🚀

#bioML #MLSky

Nucleotide Transformer: building and evaluating robust foundation models for human genomics - Nature Methods Nucleotide Transformer is a series of genomics foundation models of different parameter sizes and training datasets that can be applied to various downstream tasks by fine-tuning.

🧪🧬🖥️ Nucleotide Transformer is now published in Nature Methods!

A foundational models for genomics, with up to 2.5 billion parameters, that are trained on genomes from 800+ species and 3000+ human individuals.

📄 www.nature.com/articles/s41...
💻 github.com/instadeepai/...

#Genomics #BioML #MLSky

Dear hivemind, in the absence of a fresh CAFA publication: what predictor(s) do people consider to be the state-of-the-art in protein function prediction nowadays? #bioinformatics #bioml #protein

This [1] has been helpful so far (made using Skyfeed), the only downside is it's a little slow*

[1] bsky.app/profile/did:...

* I'm testing out a new hosted version of it (starting from a blank feed)
[2] bsky.app/profile/rami...

#bioML

BTW I have no idea which #BioML feeds we should be using these days, suggestions welcome... 🧪🧶

@jameszou.bsky.social is here! #bioml #machinelearning #AI

Anyone in #biostats #bioml interested in discussing & maybe writing up similar guideline for bioML tasks? My stats is not top notch but I'm fully aware of how critical it is to add more rigor to model comparisons & evals. So would be interested in more structured discussion & exposition 2/2

Hello 🦋 #protein / #microbio / #BioML community! We are excited to release Gaia🌎, a context-aware protein search tool, extending protein search and discovery capabilities beyond sequence and structure, to include *genomic context*. Search your favorite protein sequences with on gaia.tatta.bio

@fabiantheis.bsky.social is here! #genomics #singlecell #bioml

Mystery solved. Thanks so much @kevinkaichuang.bsky.social. If you haven’t already, go check out his great #bioML pack.

Does the discovery feed account for your interests?

Following mainly #bioml people, yet my discovery is full of politics and cat pictures 😭 (I don't mind the latter)