Kathleen ChenData Scientist, Genomics, CCB, Flatiron Institute
Title: Developing sequence-based deep learning models: software and applications
Abstract: Networks trained on high-throughput sequencing data (for example, ChIP-seq), or ‘sequence-based models’, have become the de facto standard for predicting the regulatory and disease impact of mutations. In this talk, I will provide an overview to sequence-based deep learning and briefly discuss how we developed Selene to enable fast and easy development of deep learning models for biological sequences. I will also present an ongoing project to develop and apply a large-scale DNA-based model with comprehensive coverage of the known regulatory factors in human.