David Vallenet

BRIDGE: Biological Antimicrobial Resistance Inference viaDomain-Knowledge Graph Embeddings

Figure 1

Figure 2

Figure 4

BRIDGE: Biological Antimicrobial Resistance Inference viaDomain-Knowledge Graph Embeddings [new]
infers novel AMR gene links by integrating gene nbhd and protein interact networks into a comprehensive knowledge graph for prediction.

Expanding the Enzymatic Landscape for Polyurethane Degradation of Novel Bacterial Urethanases

Figure 1

Figure 2

Figure 3

Expanding the Enzymatic Landscape for Polyurethane Degradation of Novel Bacterial Urethanases [new]
struct. characterizes novel bacterial urethanases, detailing carbamate bond hydrolysis mech., advancing PUR biocatalytic recycling.

BactoTraits: a trait database for exploring functional diversity of bacterial communities www.nature.com/articles/s41... #jcampubs

Pool PaRTI: A PageRank-Based Pooling Method for Identifying Critical Residues and Enhancing Protein Sequence Representations

Figure 2

Figure 3

Figure 4

Pool PaRTI: A PageRank-Based Pooling Method for Identifying Critical Residues and Enhancing Protein Sequence Representations [updated]

Happy to announce that I've started my postdoctoral position at @icelabumu.bsky.social ! 🎉
My project focuses on developing AI models (ML/DL) to predict protein levels from RNA-seq data in bacterial infections, to identify new therapeutic targets to combat #AMR🦠🤖
#AIforScience #Postdoc

🧬 Just out in Bioinformatics Advances: "OMAnnotator: A novel approach to building an annotated consensus genome sequence". 

Full article available: https://doi.org/10.1093/bioadv/vbag015 

Authors include: @dessimoz.bsky.social, @whynevers.bsky.social

Multiple protein structure alignment at scale with FoldMason Protein structure is conserved beyond sequence, making multiple structural alignment (MSTA) essential for analyzing distantly related proteins. Computational prediction methods have vastly extended ou...

FoldMason is out now in @science.org. It generates accurate multiple structure alignments for thousands of protein structures in seconds. Great work by Cameron L. M. Gilchrist and @milot.bsky.social.
📄 www.science.org/doi/10.1126/...
🌐 search.foldseek.com/foldmason
💾 github.com/steineggerla...

#microsky
Massive update of preprint with @polardlab.bsky.social!
Bacteria have evolved two systems to recombine extracellular DNA
www.biorxiv.org/content/10.1...
Kudos to lead authors Léo Hardy, Violette Morales and Clothilde Rousseau, and to outstanding Dalia's lab and @epcrocha.bsky.social
🧵⬇️

PanForest: predicting genes in genomes using random forests AbstractMotivation. The presence or absence of some genes in a genome can influence whether other genes are likely to be present or absent. Understanding t

PanForest: predicting genes in genomes using random forests academic.oup.com/bioinformati... #jcampubs

Integrative mobilizable elements are pervasive throughout Pseudomonadota www.biorxiv.org/content/10.6... #jcampubs

Genomic Islands as minimal hitchers of conjugative elements https://www.biorxiv.org/content/10.64898/2026.01.13.699239v1

Phold's manuscript is now available @narjournal.bsky.social thanks to @susiegriggo.bsky.social @npbhavya.bsky.social @vijinim.bsky.social @linsalrob.bsky.social @martinsteinegger.bsky.social @milot.bsky.social @eunbelivable.bsky.social & others not on bsky #phagesky academic.oup.com/nar/article/...

Engineer for the development of new methods in pangenomics - LABGeM Prokaryotes —bacteria and archaea— are diverse, ubiquitous organisms with vast impacts on health, soil, and ocean ecosystems. Large-scale genome sequencing and pangenomics have revealed their molecula...

📢 Hiring: Bioinformatics Engineer position funded by the ANR PanGAIMiX, for the development of new methods in the PPanGGOLiN software suite.

💻 Build cool tools for #pangenomics
🔬 computer science × biology

📍 Evry, France | ⏳ Fixed-term contract
👉 Interested? Contact us
🔗 bit.ly/3NfSP8o

Ingénieur en bioinformatique pour le développement de la plateforme MicroScope - LABGeM Localisé au CEA/Genoscope, un centre de recherche scientifique dédié à la génomique environnementale, le Laboratoire d’Analyses Bioinformatiques pour la Génomique et le Métabolisme (LABGeM, UMR8030, l...

📢 Job opening — Bioinformatics Engineer
Join the MicroScope platform (LABGeM, CEA/Genoscope) to develop tools and pipelines for microbial genomics.

📍 Evry, France | ⏳ Fixed-term contract
🔗 bit.ly/3Z5WSXc

@ifb-elixir-fr.bsky.social

Dual-encoder contrastive learning accelerates enzyme discovery

Figure 1

Figure 2

Figure 3

Dual-encoder contrastive learning accelerates enzyme discovery [updated]
Dual encoder learns enzymes, validated.

MetaNetMap: automatic mapping of metabolomic data onto metabolic networks www.biorxiv.org/content/10.6... #jcampubs

New preprint from my lab (with Arya Kaul, @fernpizza.bsky.social, and @brinda.eu), in which we explore new genes hitchhiking on the beneficial deletion that fused them together, and find them in the LTEE, M. Tb/bovis, and across the bacterial tree of life

Panorama: a robust pangenome-based method for predicting and comparing biological systems across species Over the last decade, the expansion in the number of available genomes has profoundly transformed the study of genetic diversity, evolution, and ecological adaptation in prokaryotes. However, traditio...

🔍 Want to dive deeper?
Read the preprint and try the tool:
📄 doi.org/10.64898/202...
💻 github.com/labgem/PANOR...

@ifb-elixir-fr.bsky.social @genoscopeumr.bsky.social @genopole.bsky.social
#Bioinformatics #Pangenomics #Genomics

💡 Example use case on defense systems
We showcase PANORAMA for predicting defense systems in 941 Pseudomonas aeruginosa genomes and >6,000 genomes from four Enterobacteriaceae species.
A fully reproducible Google Colab notebook is available on GitHub:
github.com/labgem/PANOR...

Panorama: a robust pangenome-based method for predicting and comparing biological systems across species Over the last decade, the expansion in the number of available genomes has profoundly transformed the study of genetic diversity, evolution, and ecological adaptation in prokaryotes. However, traditio...

🚀 New preprint out!
We are happy to introduce PANORAMA, a new bioinformatics tool for comparative pangenomics, designed to predict and compare biological systems across prokaryotic pangenomes.

It has been developed by @jpjarnoux.bsky.social

📄 Preprint: doi.org/10.64898/202...

Fast, accurate construction of multiple sequence alignments from protein language embeddings www.biorxiv.org/content/10.6... 🧬🖥️🧪 github.com/Singh-Lab/AR...

Panorama: a robust pangenome-based method for predicting and comparing biological systems across species https://www.biorxiv.org/content/10.64898/2025.12.22.695875v1

epsSMASH uncovers exopolysaccharide biosynthetic gene clusters in environmental and human microbiomes https://www.biorxiv.org/content/10.64898/2025.12.21.693542v1

Microbial degradation of a widely used model polyethylene is restricted to medium- and long-chain alkanes and their oxidized derivatives academic.oup.com/ismej/advanc... #jcampubs

Everything is everywhere but Escherichia coli adapts to different niches academic.oup.com/ismej/advanc... #jcampubs

Abstract Benchmarking datasets for machine learning in protein function prediction

Figure 1

Table 1

Figure 2

Benchmarking datasets for machine learning in protein function prediction [new]
Provides large-scale datasets (PAD) with proteins/annotations to benchmark ML models for predicting protein functions, overcoming data scarcity.

Figure 1

Figure 2

Figure 5

Figure 3

Evolutionary Decoding of the Bacillus subtilis Secretome: Insights from Pan-Genomics and Deep Learning [new]
Signal peptides show housekeeping/adaptive split via pan-genomics/DL, highlighting evolutionary decoupling.

Beyond magnetosomes: ubiquitous and diverse intracellular inclusions expand the role of magnetotactic bacteria in biogeochemical cycling https://www.biorxiv.org/content/10.64898/2025.12.17.695019v1

hypeR-GEM: connecting metabolite signatures to enzyme-coding genes via genome-scale metabolic models https://www.biorxiv.org/content/10.64898/2025.12.08.692998v1

Gempipe: a tool for drafting, curating, and analyzing pan and multi-strain genome-scale metabolic models journals.asm.org/doi/full/10.... #jcampubs