Leonid Chindelevitch

Proteome-wide variant calling builds amino acid phylogenomic alignments orders of magnitude faster than a BUSCO marker pipeline, with similar tree signal in three of four test taxa.

The paper introduces CABBAGE, a large-scale AMR genotype-phenotype database linking bacterial genomes to antibiotic susceptibility data and metadata, enabling analysis of resistance trends and predictive method benchmarks.

This paper introduces ska lo, a reference-free variant calling tool that uses a coloured De Bruijn graph to detect SNPs, insertions, deletions, and recombination events in pathogen genomes.

The paper introduces MANIAC, a tool for estimating ANI and AF in viral genomes, revealing an ANI gap in bacterial dsDNA viruses and showing its predictive power for taxonomy.

This paper optimizes machine learning prediction of MICs in Klebsiella pneumoniae by evaluating regression vs classification approaches based on antibiotic concentration levels.

This paper introduces SKA2, a method for rapid and accurate genotyping of bacterial populations, showing superior variant recall and no false positives in outbreak simulations.

hAMRonization standardizes AMR gene detection outputs from multiple tools into a unified format for easier analysis and integration.

This paper predicts disinfectant tolerance in Listeria monocytogenes using whole genome sequencing and machine learning, achieving high accuracy in classification and regression tasks.

fastlin rapidly and accurately types Mycobacterium tuberculosis complex lineages from sequencing data, detecting mixed-lineage strains and estimating proportions.

The paper introduces network science-based tree shape statistics for phylogenetic trees, showing they perform as well as or better than traditional measures.

This paper introduces an interpretable classification method for predicting drug resistance in M. tuberculosis, achieving high accuracy and flexibility.

The paper predicts drug resistance in M. tuberculosis using a gene burden-based approach with a Long-term Recurrent Convolutional Network (LRCN) architecture, showing improved performance over existing methods.

This study uses machine learning on whole-genome sequencing data from multiple geographic regions to predict drug resistance in Mycobacterium tuberculosis, finding that performance varies across datasets due to geographical heterogeneity.

The paper introduces MCS^2, a method to compute minimal cut sets in metabolic networks without requiring elementary flux modes, showing improved efficiency over existing methods.

A decentralized open-source web platform lets public health labs run outbreak sequencing pipelines on local compute, keeping data under their own governance while still exchanging results between instances.

MentaLiST is a fast and accurate MLST caller designed for large MLST schemes, outperforming existing tools in speed while maintaining or improving accuracy.