Santiago Carmona 🧬 🖥️ 🧑🏾‍🔬

UCell and pyUCell: single-cell gene signature scoring for R and python AbstractSummary. Gene signature scoring provides a simple yet powerful approach for quantifying biological signals within single-cell omics datasets. UCell

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 - Nature The combination of computational design, laboratory-based screening and biophysical validation enables the de novo generation of variable heavy-chain antibody fragments and antibodies that precis...

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

Tumour-reactive heterotypic CD8 T cell clusters from clinical samples - Nature Tumour-reactive CD8+ T cells are enriched in functional clusters with tumour cells and/or antigen-presenting cells and can be isolated and expanded from clinical samples.

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...

beautiful work, contrats!!

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 The rapid development of updated and new commercially available single-cell transcriptomics platforms provides users with a range of experimental options. Cost, sensitivity, throughput, flexibility, a...

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

Mechanical confinement governs phenotypic plasticity in melanoma - Nature Mechanical confinement of cancer cells at the tumour–microenvironment interface induces phenotype switching through chromatin remodelling by HMGB2, leading to a more invasive and drug-resistant state ...

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

Identification of malignant cells in single-cell transcriptomics data - Communications Biology This review article discusses the challenges of identifying cancer cells in single-cell data, summarizing current computational solutions as well as underexplored features of malignancy.

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...

Identification of malignant cells in single-cell transcriptomics data - Communications Biology This review article discusses the challenges of identifying cancer cells in single-cell data, summarizing current computational solutions as well as underexplored features of malignancy.

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...

Evolution of T cell responses in the tuberculin skin test reveals generalisable Mtb-reactive T cell metaclones. T cells contribute to immune protection and pathogenesis in tuberculosis, but measurements of polyclonal responses have failed to resolve correlates of outcome. We report the first temporal…

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 Determining a gene’s functional significance within a specific cellular context has long been a challenge. We introduce a framework for quantifying gene importance by leveraging attributions learned b...

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!

T cell receptor cross-reactivity prediction improved by a comprehensive mutational scan database Banerjee et al. present a comprehensive T cell receptor cross-reactivity database and a hierarchical Bayesian framework to predict T cell receptor targets. Together, they reveal structural and biochem...

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!

Thank you for supporting our project!

Exciting, congrats!

AI-driven predictive biomarker discovery with contrastive learning to improve clinical trial outcomes Arango-Argoty et al. introduce the Predictive Biomarker Modeling Framework (PBMF), an AI-driven contrastive learning framework to identify putative predictive, rather than prognostic, biomarkers for c...

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...

Disease diagnostics using machine learning of B cell and T cell receptor sequences Clinical diagnosis typically incorporates physical examination, patient history, various laboratory tests, and imaging studies but makes limited use of the human immune system’s own record of antigen ...

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.

Transformers and genome language models - Nature Machine Intelligence Micaela Consens et al. discuss and review the recent rise of transformer-based and large language models in genomics. They also highlight promising directions for genome language models beyond the tra...

🔥 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 Cells regulate their functions through gene expression, driven by a complex interplay of transcription factors and other regulatory mechanisms that together can be modeled as gene regulatory networks ...

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

Great news, Congratulations!

Transcriptomic plasticity is a hallmark of metastatic pancreatic cancer Metastasis is the leading cause of cancer deaths; nonetheless, how tumor cells adapt to vastly different organ contexts is largely unknown. To investigate this question, we generated a transcriptomic ...

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...

Clonal dynamics and somatic evolution of haematopoiesis in mouse - Nature Isolating and studying haematopoietic stem cells in young and aged mice demonstrates evolutionary processes related to blood production and provides a framework for interpreting future work using labo...

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