Pablo Rodriguez-Mier

Unifying multi-sample network inference from prior knowledge and omics data with CORNETO Mixed-integer optimization Mixed-integer programming is a type of constrained optimization problem that involves decision variables that can be both integer and continuous. A mixed-integer programming problem can be defined as follows: $$\begin{array}{ll}\mathop{\min }\limits_{{\bf{x}}\in {{\mathbb{R}}}^{n},\,{\bf{y}}\in {{\mathbb{Z}}}^{m}}&f({\bf{x}},{\bf{y}})\\ \,\text{subject to}\,&{g}_{i}({\bf{x}},{\bf{y}})\le 0,\quad i=1,2,\ldots ,k,\\...

Unifying multi-sample network inference from prior knowledge and omics data with CORNETO
->Nature | #Data | More info from EcoSearch

🚨 New preprint

We present an extended version of ScAPE, the method that won one of the prizes 🏆 in the @neuripsconf.bsky.social 2023 Single-Cell Perturbation Prediction challenge.

📄 preprint: doi.org/10.1101/2025...
🧬 code: github.com/scapeML/scape

ScAPE: A lightweight multitask learning baseline method to predict transcriptomic responses to perturbations https://www.biorxiv.org/content/10.1101/2025.09.08.674873v1

We present our MetaProViz #Rpackage for #metabolomics analysis & prior knowledge integration to generate mechanistic hypotheses on how metabolic changes affect metabolite classes, pathways & environment interaction

🔗
www.biorxiv.org/content/10.1...

📦
saezlab.github.io/MetaProViz/

🧵 Thread ⬇️

EMBO Practical Course. Causality in biomedicine: going beyond associations. 4 - 9 October 2026. Hinxton, UK. EMBO Practical Course and EMBL-EBI logos attached.

New course announced!

We're thrilled to be hosting the @embo.org Practical Course 'Causality in biomedicine: going beyond associations' from 4 – 9 October 2026.

Register your interest and be the first to hear when the course opens for applications: www.ebi.ac.uk/training/eve...

New course “EMBO Causality in Biomedicine”: We have organised the first EMBO course in *causal* stats/ML methods for quantitative biomedicine. @sjoerdvbeentjes.bsky.social @nimahejazi.org @pablormier.bsky.social @DariaSokolova @CarolineUhler

Very much looking forward to teaching and discussing!

This project has been in the making for quite some time. CORNETO not only integrates key concepts and methodologies in biological network inference, but also introduces a novel framework for multi-condition analysis. Congrats to the team, and especially to @pablormier.bsky.social for leading this.

🎉 The revised version of CORNETO, our unified Python framework for knowledge-driven network inference from omics data, is published in peer reviewed form
🔗 Paper: www.nature.com/articles/s42...
📖 News & Views: www.nature.com/articles/s42...
💻 Code: corneto.org
🧵 Thread 👇

CORNETO: machine learning to decode complex omics data New tool combines biological knowledge with machine learning to help researchers extract meaningful insights from complex omics data.

How can we find out what’s really going on inside cells when we’re generating so much complex data?

CORNETO is an open-source tool that uses machine learning to turn tangled omics datasets into clear maps of how genes, proteins, and signalling pathways interact.

www.ebi.ac.uk/about/news/r... 🧪

Learning tissue representation by identification of persistent local patterns in spatial omics data - Nature Communications Spatial omics reveal tissue structures and can aid patient stratification. The authors present a method to identify patterns in tissue patches, enabling analysis of disease progression and treatment r...

The latest version of the Kasumi manuscript is now published in Nature Comms www.nature.com/articles/s41... Kasumi identifies patterns in tissue patches, enabling analysis of disease progression and treatment response while providing insights into spatial coordination at cell-type or marker level

🚨 New preprint: Topography Aware Optimal Transport for Alignment of Spatial Omics Data

We present our new alignment framework TOAST www.biorxiv.org/content/10.1...

Pretraining virtual cells is useless the way we do it now

Turns out the way we usually pre-train foundational cell models adds very little information to the system - definitely not enough to make drug effect predictions work. Not what I've expected.
#virtualcells #foundationalmodels #compbio

blog.turbine.ai/p/pretrainin...

📄 Update on our preprint about Gene Regulatory Net (GRN) benchmarking 📄
We have included the original and decoupled version of SCENIC+, added a new metric and two more databases. Dictys and SCENIC+ outperformed others, but still performed poorly in causal mechanistic tasks.
doi.org/10.1101/2024... 👇

No need to feel bad! Also, congratulations on your work, and best wishes to Sakana!

Is someone feeling jealous? What's the beef here? 🥩

Haha, Peyman Milanfar blocked me within milliseconds after I liked a reply of somebody else defending @hardmaru.bsky.social and Sakana AI against his attacks.

Fastest block ever!

YouTube video by Stanford Online Stanford EE364A Convex Optimization I Stephen Boyd I 2023 I Lecture 1

Stephen Boyd's reaction when a student says they're using Genetic Algorithms for optimization is priceless 😂
youtu.be/kV1ru-Inzl4?...

In many countries we're seeing voters that have never known anything other than stability and a certain level of competence voting for anti- system candidates because they have convinced themselves of two things: things right now are awful; change will only be for the better.

This is also why vaccine-denial is so prevalent. People don’t have a memory of what mass death from smallpox looked like, or post-poli disability.

No AGI until LLMs can reliably produce useful LaTeX. Haven’t seen one that truly delivers.

We need a LLM LaTeX benchmark!

"LLaDA: Large Language Diffusion Models" Nie et al.

Just read this fascinating paper.

Scaled up Masked Diffusion Language Models to 8B params, and show that it can match #LLMs (including Llama 3) while solving some key limitations!

Let's dive in... 🧵

(1/8)

#genai

We are delighted to announce The Health Privacy Challenge, an interactive opportunity for advancement at the intersection of computational biology and privacy research, brought to you as a part of CAMDA Conference at #ISMB/ECCB2025 🫐🍅
Register to participate: benchmarks.elsa-ai.eu?ch=4

GRETA graphical abstract

We present Gene Regulatory nETwork Analsyis (GRETA), a framework to infer, compare and evaluate gene regulatory networks #GRNs. With it, we have benchmarked multimodal and unimodal GRN inference methods. Check the results here 👇
Paper: doi.org/10.1101/2024.12.20.629764
Code: github.com/saezlab/greta

The final chapter of my PhD thesis is now out! 🎉 We compared the latest gene regulatory network (#GRN) inference methods for #single-cell multimodal datasets and evaluated their performance across various tasks. Hard to believe this journey started in March 2021 and has finally reached this point 😅🥳

We present NetworkCommons, a unified platform 🪐 for network biology, providing access to omics data, knowledge, and contextualization methods, all with a consistent API 👇🧵
Paper: doi.org/10.1101/2024...
Docs: networkcommons.readthedocs.io

A benchmark for prediction of transcriptomic responses to chemical... Single-cell transcriptomics has revolutionized our understanding of cellular heterogeneity and drug perturbation effects. However, its high cost and the vast chemical space of potential drugs...

Very cool to see our model scAPE perform so well in this benchmark @pablormier.bsky.social !
openreview.net/forum?id=WTI...
Thanks to the organizers for this amazing competition.

How cute is this little guy? 😍

What are the key disrupted multicellular processes in heart failure? In our new work we combine 23 years of molecular data with recent single-cell atlases to draw a cross-study patient map
doi.org/10.1101/2024...

I remember I've also had issues following or seeing users from different servers