Laurent Jacob

Fox predicts host-symbiont co-evolution event rates directly from sequence alignments without tree reconstruction, achieving high accuracy and speed compared to existing methods.

The paper introduces a deep learning framework for estimating epidemiological parameters from viral sequences, achieving high accuracy and speed compared to traditional methods.

This paper shows that graph neural networks with a new pooling method can accurately estimate diversification parameters in complex models where likelihoods are intractable.

Phyloformer uses deep learning to quickly and accurately reconstruct phylogenetic trees from protein sequences, outperforming existing methods on simulated and real data.

This study evaluates the realism of sequence evolution simulations by testing how well supervised learning can distinguish simulated from empirical MSAs.

The paper introduces SEISM, a selective inference method to test the association between sequence motifs extracted from neural networks and phenotypes, improving analysis in regulatory genomics and GWAS.

CALDERA improves bacterial GWAS by testing subgraphs of De Bruijn graphs, enhancing power and interpretability while managing computational complexity.

This paper introduces a hybrid model combining convolutional neural networks and kernel methods for biological sequence analysis, showing improved performance on small datasets and interpretability for motif discovery.

DBGWAS is a fast, alignment-free method for bacterial GWAS that identifies interpretable genetic variants associated with phenotypes by analyzing kmer-based subgraphs.

The paper introduces a new statistical test for differential protein abundance in proteomics data, showing improved performance over existing methods.

This paper introduces an alignment-free GWAS method using compacted De Bruijn graphs to detect variable-length haplotypes associated with antimicrobial resistance in bacterial genomes.