Kabir Dhillon

HyperSketch provides a structure-aware genomic similarity method using de Bruijn graphs and Hyperdimensional Computing, achieving high-resolution strain clustering and deep evolutionary scaling.

This paper uses Hyperdimensional Computing to predict chemical compound toxicity efficiently, showing it can classify compounds as toxic or non-toxic with computational advantages over traditional methods.

The paper introduces a Vector-Symbolic Architecture for encoding viral pangenomes and evaluates its effectiveness in species classification, finding that a flat species-level model outperforms genus-level and hierarchical approaches.