Bioinformatics Seminar
Time: 11AM
Venue: Davis Auditorium and Online
25 March 2025
This is a WEHI only event.Detection of Structural Variants from high throughput data using a Machine Learning-based integrative framework
Vladimir ShikovWEHI Bioinformatics
Structural variants (SVs) are large-scale chromosomal changes, which include insertions, deletions, duplications, inversions, and translocations, as well as large-scale catastrophic rearrangements of chromosomes. Despite its prominent biological role, structural variation remains an understudied topic due to difficulties that arise when calling SVs. A multitude of SV calling approaches have been developed, drawing from 4 different types of evidence: split reads, discordant read pairs, read depth, and de-novo assembly. Different methods integrate these data in different ways, but no method is perfect. Their performance varies greatly between different datasets, and most tools demonstrate inconsistent success when calling different types of SVs – e.g., deletions and insertions. Ensemble methods aim to improve SV calling performance by combining the strengths of several tools. However, most ensemble callers use ad-hoc merging algorithms. Here we present SVEnsemble2 – a novel instrument for SV detection that uses a Positive-Unlabeled Machine Learning model to evaluate and merge results from multiple SV callers. By adjusting the model to individual samples, SVEnsemble2 can improve structural variant calling consistency across samples, as well as achieve better performance in general SV detection.