Pascal Notin

Sampling Protein Language Models for Functional Protein Design

This paper evaluates sampling methods for protein language models, showing that multi-mutant strategies outperform single-mutant approaches in capturing epistatic interactions for functional protein design.

Learning protein function through autonomous experimental interaction

This paper demonstrates an AI system that autonomously interacts with biological systems to discover new protein functions through continuous experimental feedback.

Machine learning guided cell-free expression maps the biochemical landscape of carbonic anhydrase

The paper uses machine learning to guide cell-free expression of carbonic anhydrases, identifying variants with improved stability under high temperatures.

Large-scale discovery, analysis, and design of protein energy landscapes

The paper measures conformational fluctuations of protein domains using hydrogen-deuterium exchange mass spectrometry and uses computational modeling to design mutations that stabilize low-stability segments.

Unified sampling framework and experimental benchmarking of sequence- and structure-based protein models

The paper benchmarks sequence- and structure-based protein models using a unified framework, showing structure-based models outperform others in generating functional variants.

Democratizing Protein Language Model Training, Sharing and Collaboration

The paper introduces SaprotHub, a platform that simplifies training and sharing of protein language models, enabling non-experts to build and collaborate on customized models.

RNAGym: Large-scale Benchmarks for RNA Fitness and Structure Prediction

RNAGym provides a benchmarking framework for RNA fitness, secondary structure, and tertiary structure prediction using diverse datasets and standardized assays.

Evolutionary-Scale Enzymology Enables Biochemical Constant Prediction Across a Multi-Peaked Catalytic Landscape

The paper measures catalytic constants for diverse Adenylate Kinase sequences and mutants, revealing distinct catalytic peaks and challenging existing hypotheses about thermophilic enzyme kinetics.

Epigenomic insights into extreme longevity in the world's oldest terrestrial animal, Jonathan

The paper analyzes the DNA sequence and methylome of Jonathan, a 192-year-old giant tortoise, to identify epigenomic features associated with extreme longevity.

A Genomic Language Model for Zero-Shot Prediction of PromoterVariant Effects

LOL-EVE predicts promoter variant effects using a transformer model trained on mammalian promoter sequences, showing improved performance in indel prediction and haplotype analysis.

ProteinGym: Large-Scale Benchmarks for Protein Design and Fitness Prediction

ProteinGym unifies over 250 deep mutational scans and ~65k clinical variants to benchmark over 70 models in zero-shot and supervised settings; TranceptEVE ranks best overall.

ProteinNPT: Improving Protein Property Predictionand Design with Non-Parametric Transformers

This paper introduces ProteinNPT, a non-parametric transformer for protein property prediction and design, showing improved performance in label-scarce and multi-task settings.

TranceptEVE: Combining Family-specific and Family-agnostic Models of Protein Sequences for Improved Fitness Prediction

Blending an alignment-based family model with an autoregressive protein language model, weighted by how deep the alignment is, reportedly improves mutation-effect prediction against experimental assays and ClinVar.

Mixtures of large-scale dynamic functional brain network modes

This paper introduces DyNeMo, a model for dynamic functional brain networks that outperforms HMM in capturing non-exclusive network modes in MEG data.

Large-scale clinical interpretation of genetic variants using evolutionary data and deep learning

The paper predicts the pathogenicity of 11 million genetic variants across 1,081 disease genes using a deep learning model that leverages evolutionary data instead of clinical labels.