Florian Mock

BERTax uses deep learning to classify DNA sequences taxonomically without requiring known database relatives, outperforming existing methods for novel organisms and combining with databases to improve accuracy.

EpiDope uses a deep neural network to predict linear B-cell epitopes with higher accuracy than existing tools, reducing laboratory costs and time.

This paper introduces a deep learning method to predict viral hosts using only viral genome sequences, achieving high accuracy across three virus species.

The paper annotates and analyzes non-coding RNAs in 16 bat genomes, revealing new expression patterns and providing a resource for studying bat biology and host-virus interactions.