Alexandre Lomsadze

HPVarcall assigns HPV variant sequences to lineages and sublineages using statistical models trained on sublineage-specific genomic alignments, achieving high accuracy for sequences of 1000 nucleotides or longer.

GeneMark-ETP improves gene prediction accuracy in large eukaryotic genomes by integrating genomic, transcriptomic, and protein evidence, outperforming existing tools.

BRAKER3 improves eukaryotic genome annotation by integrating RNA-seq, protein data, and statistical models, achieving higher accuracy than previous tools.

The paper presents a chromosome-length genome assembly and annotation of the blackberry species Rubus argutus, identifying candidate genes for primocane-fruiting.

Gene caller that models GC-dependent ribosome binding and leaderless-promoter signals and detects TGA stop-codon reassignment, reported as more accurate than existing metagenomic gene finders.

The paper develops a tool to annotate phage genomes using multiple genetic codes and identifies viral contigs with such features in human gut microbiome data.

BRAKER2 improves eukaryotic genome annotation by integrating GeneMark-EP+ and AUGUSTUS with cross-species protein sequences, achieving higher accuracy than MAKER2 and BRAKER1 in certain conditions.

StartLink+ improves gene start prediction in prokaryotic genomes by integrating ab initio and multiple sequence alignment methods, achieving 98-99% accuracy on verified genes.

The paper introduces GeneMark-EP and -EP+, which improve eukaryotic gene prediction by integrating protein database information, showing better accuracy than previous methods, especially in large genomes.

The paper introduces GeneMarkS-2, an improved gene prediction algorithm that identifies diverse gene expression signals and reveals insights into prokaryotic transcription and translation mechanisms across genomes.