Thomas Pierrot

CellScribe is a generative framework that unifies cell identity and state by using a language model to generate cell type annotations and meta-program profiles, outperforming baselines and identifying new cell types through in-context learning.

NTv3 is a foundation model that predicts genome function, annotates genes, and designs DNA sequences across species, outperforming existing models in multiple tasks.

The paper introduces SegmentNT, a DNA foundation model for genome annotation, achieving state-of-the-art performance in identifying 14 genic and regulatory elements across species.

This paper introduces a bimodal model for bulk RNA-seq and DNA methylation that uses masked language modeling to learn representations, achieving state-of-the-art performance in cancer classification and survival prediction.

The paper introduces the Nucleotide Transformer, a foundation model for genomics, showing it can predict molecular phenotypes from DNA sequences with transfer learning across tasks and organisms.

This study evaluates genomic language models on protein tasks, showing they are competitive with proteomic models and benefit from joint genomic-proteomic training and optimized tokenization.

This paper introduces a large language model for plant genomics that provides state-of-the-art predictions for regulatory annotations and variant prioritization, along with a benchmark dataset for deep learning methods.

BulkRNABert uses a pre-trained transformer model on bulk RNA-seq data to improve cancer classification and survival prediction across multiple cancer types.

ChatNT is a conversational agent that understands biological sequences and achieves state-of-the-art results on genomics tasks while being accessible to non-coders.

The paper introduces BioCLIP, a contrastive learning framework for pre-training Protein Structure Models using Protein Language Models, achieving performance comparable to specialized methods on various tasks.

A COVID-19 Early Warning System combines structural modelling with machine learning to detect and monitor high risk SARS-CoV-2 variants, identifying all 16 WHO designated variants on average more than one and a half months in advance by selecting on average less than 0.3% of the weekly novel variants.