Santiago Carmona 🧬 🖥️ 🧑🏾‍🔬

TCR specificity prediction is advancing rapidly. The central question is not only which TCR sequence recognizes an antigen, but also which TCR pairings make recognition possible & where is the binding boundary? Our new paper tackles these questions. 🧵 www.science.org/doi/10.1126/...

Latest preprint from the lab! Evaluating cell type annotations in single-cell omics in the absence of ground truth www.biorxiv.org/content/10.6...

KLRG1 identifies circulating cytotoxic CD4 T cells with selective anti-tumor function in human cancer @biorxivpreprint.bsky.social www.biorxiv.org/content/10.6... @carmonation.bsky.social

Cell type composition drives patient stratification in single-cell RNA-seq cohorts www.biorxiv.org/content/10.6...

UCell (v2) and pyUCell: single-cell gene signature scoring for R and Python. We discuss updates and key parameters academic.oup.com/bioinformati...

Atomically accurate de novo design of antibodies with RFdiffusion www.nature.com/articles/s41...

Tumour-reactive heterotypic CD8 T cell multiplets from clinical samples www.nature.com/articles/s41...

@natrevimmunol.nature.com Guidelines for T cell nomenclature www.nature.com/articles/s41...

Very happy to share our latest manuscript about TCR-epitope recognition specificity: www.biorxiv.org/content/10.1...

Cool paper on scRNA T cell annotation. However, a note for ProjecTILs users: I wouldn’t rely on the ProjecTILs benchmark in this work, as it was run using a mouse reference map to classify human T cells (even though human CD4/CD8 T cell maps are available github.com/carmonalab/P...)

Your favourite single-cell gene signature scoring method now in Python #scverse and much faster! pypi.org/project/pyuc...

Introducing ParTIpy, a python package for Pareto Task Inference that scales to large-scale datasets, including single-cell and spatial transcriptomics. 🔗 Manuscript: www.biorxiv.org/content/10.1... 💻 Code: partipy.readthedocs.io

Evaluating the practical aspects and performance of commercial single-cell RNA sequencing technologies www.biorxiv.org/content/10.1...

www.nature.com/articles/s41...

A new review on the challenges of identifying cancer cells in single-cell data, summarizing current computational solutions as well as underexplored features of malignancy. From scientists ‪@sib.swiss‬ www.nature.com/articles/s42...

Identifying malignant cells in single-cell transcriptomics data – from first principles to computational solutions, framed around the hallmarks of cancer www.nature.com/articles/s42...

Interested in T cell immunity in TB? Check out our new pre-print on antigen-agnostic identification of generalisable human in vivo Mtb-reactive T cell responses: www.biorxiv.org/content/10.1... with @qimmuno.bsky.social & @innate2adaptive.bsky.social

Foundation Model Attributions Reveal Shared Inflammatory Program Across Diseases www.biorxiv.org/content/10.1...

📢 We have an open position at University of Geneva for a PhD student with CS/Math/Physics background to study adaptive immune responses using deep learning. If interested please contact me directly!

Check out how we tackled one of the fundamental challenges in immunology, out today @cp-cellsystems.bsky.social: www.cell.com/cell-systems.... Our major innovations are BATCAVE and BATMAN, two new players to get us closer to solving TCR-pMHC predictions!

AI-driven predictive biomarker discovery with contrastive learning to improve clinical trial outcomes: Cancer Cell www.cell.com/cancer-cell/...

Excited to share our new study revealing the intricate dynamics of pregnancy & postpartum physiology! We analyzed 40M lab tests from 300K pregnancies and 160K women (cross-sectional) and mapped week-by-week changes starting from preconception to months-long postpartum recovery.

Exited to share our recent work on TF isoforms! Amazing work by @kaiamattioli.bsky.social Luke Lambourne and Clarissa Santoso and many other collaborators.

scRepertoire 2: Enhanced and Efficient Toolkit for Single-Cell Immune Profiling www.biorxiv.org/content/10.1...

The recent "Mal-ID" paper in Science diagnoses diseases from immune repertoires. But a powerful model like Mal-ID can learn differences between groups of immune repertoires that are unrelated to the diseases of interest. We explore these pitfalls in our eLetter response.

🔥 Unveiling the Future of Genomics with Genome Language Models (gLMs)! 🔥 Our comprehensive review, "Transformers and genome language models," is finally published in Nature Machine Intelligence! ​ Link: nature.com/articles/s42...

Comparison and evaluation of methods to infer gene regulatory networks from multimodal single-cell data | bioRxiv www.biorxiv.org/content/10.1...

1) I am delighted to share a manuscript long in the making (7 years), elucidating the forces that shape metastatic adaptation PDAC using scRNA-seq across multiple organs from a rapid autopsy combined with a powerful new clonal phylogeny inference algorithm www.biorxiv.org/content/10.1...

Cool www.nature.com/articles/s41...

Thrilled to share new work led by @jieyang437.bsky.social in the lab published today in @Nature. We find that Aspirin prevents metastasis by releasing T cells from immune suppression by platelet TXA2. @Cambridge_Uni @CRUKCamCentre rdcu.be/eci1U

The Biozentrum in Basel, Switzerland @biozentrum.unibas.ch welcomes students from all over the world. You can apply directly to individual labs or through our fellowship program. It is very similar to US programs. Rotations followed by choice of lab. www.biozentrum.unibas.ch/phd/internat...

Here is our centralized Calls for PhD students at University of Geneva. lifesciencesphd.unige.ch

In a new Science study, researchers present ESM3, a protein language model that enables the programmed generation of protein structure and sequence in response to user prompts. Learn more: scim.ag/40l2z3J

Applying LLMs to biomedical research today can go one of two ways: we either use a closed-source web app, or we get coding ourselves. Many researchers lack training for the latter, so their only choice is the former. We want to change that. www.nature.com/articles/s41...

Today, we're launching the Arc Virtual Cell Atlas, a growing resource for computation-ready single-cell measurements. arc-website-git-ben-virtual-cell-atlas-tool-arc-institute.vercel.app/news/news/ar...

@thejohnnyyu.bsky.social, @therealnima.bsky.social, and I, are excited to tell you about Tahoe-100M! The largest publicly available single-cell dataset that measures the effect of 1200 genes on 50 cell line models. The Vevo team has outdone itself. #Tahoe100M www.biorxiv.org/content/10.1...

Thrilled to share LUNA🌕 – our new generative AI model that reassembles tissue structures from dissociated cells! LUNA learns spatial priors over existing spatially resolved datasets with the aim to predict cell locations de novo. Check out our paper here: www.biorxiv.org/content/10.1...

Altered immune landscape of cervical lymph nodes reveals Epstein-Barr virus signature in multiple sclerosis | Science Immunology www.science.org/doi/abs/10.1...

Multiomic profiling of T cell lymphoma after therapy with anti-BCMA CAR T cells and GPRC5D-directed bispecific antibody | Nature Medicine www.nature.com/articles/s41...

Visualising the impact of wounding on cancer cells and the tumor microenvironment at single-cell resolution in situ! Happy to share updated paper with new spatial transcriptomics of human skin tumors using CosMx 6'000-gene panel. All data and code are available. www.biorxiv.org/content/10.1...

Disease diagnostics using B cell and T cell receptor sequences: the Mal-ID model www.science.org/doi/10.1126/...

Half the reason mRNA levels may differ from protein levels both across genes and within genes across samples ⬇️

[BC]² Basel Computational Biology Conference 2025 will take place on 8-10 September. The conference brings together over 500 international scientists from academia, industry, and healthcare to explore advancements at the intersection of #bioinformatics and artificial intelligence. See bc2.ch

🎤 It is a pleasure to welcome Itay Tirosh from the Weizmann Institute at [BC]². Itay will present in the session 'Bioinformatics for cancer research'. 🔹Session chaired by @valboeva.bsky.social and @carmonation.bsky.social 👉Interested? Submit your abstract before 27 Feb: tinyurl.com/49w6wthj

Our paper in @nature.com is finally published: a prospective trial of a personalized Neoantigen Vaccine in Kidney Cancer www.nature.com/articles/s41... This is teamwork with @danafarber.bsky.social @yalecancer.bsky.social @harvardmed.bsky.social + Wu lab www.nature.com/articles/s41...

🎤 It is a pleasure to welcome Itay Tirosh from the Weizmann Institute at [BC]². Itay will present in the session 'Bioinformatics for cancer research'. 🔹Session chaired by @valboeva.bsky.social and @carmonation.bsky.social 👉Interested? Submit your abstract before 27 Feb: tinyurl.com/49w6wthj

Biologically relevant integration of transcriptomics profiles from cancer cell lines, patient-derived xenografts, and clinical tumors www.science.org/doi/10.1126/...