Gherman Novakovsky

ExplaiNN: interpretable and transparent neural networks for genomics

ExplaiNN provides interpretable deep learning models for genomics tasks, achieving comparable performance to state-of-the-art methods while offering transparent predictions.

In silico discovery of small molecules for efficient stem cell differentiation into definitive endoderm

The paper identifies small molecules that enhance stem cell differentiation into definitive endoderm, reducing costs by 90% through a drug repurposing approach.

Petabase-scale sequence alignment catalyses viral discovery

The paper develops a cloud computing infrastructure for petabase-scale sequence alignment, identifying over 105 novel RNA viruses and expanding known species by an order of magnitude.

Biologically-relevant transfer learning improves transcription factor binding prediction

This study shows that transfer learning improves transcription factor binding prediction by pre-training with biologically relevant TFs and fine-tuning single-task models.

bioSyntax: Syntax Highlighting For Computational Biology

bioSyntax provides syntax highlighting tools for computational biology data formats to improve readability and efficiency.