Neural network development from pan-transcriptomic k-mer tables for RNA-Seq applications

Nicolas Jacquin

Despite a problematic dimensionality (several hundreds of millions of entries), using a neural network to obtain a low dimensionality “embedding” should allow for phenotype predictions with similar levels of performances to classic expression profile-based predictions.

Keywords: machine learning, k-mer tables, RNA-Seq, factorized embeddings

Sébastien Lemieux
Sébastien Lemieux
Principal Investigator