Significance: Our method, DeepNovo, introduces deep learning to de novo peptide sequencing from tandem MS data, the key technology for protein characterization in proteomics research. DeepNovo achieves major improvement of sequencing accuracy over state of the art methods and subsequently enables complete assembly of protein sequences without assisting databases. Our model is retrainable to adapt to any sources of data and provides a complete end-to-end training and prediction solution, an important feature given the growing massive amount of data. Our study also presents an innovative approach to combine deep learning and dynamic programming to solve optimization problems.

Deep neural networks for graphs (DNNGs) represent an emerging field that studies how the deep learning method can be generalized to graph-structured data. Since graphs are a powerful and flexible tool to represent complex information in the form of patterns and their relationships, ranging from molecules to protein-to-protein interaction networks, to social or transportation networks, or up to knowledge graphs, potentially modeling systems at very different scales, these methods have been exploited for many application domains.

Motivation: The next generation sequencing technologies are generating billions of short reads daily. Resequencing and personalized medicine need much faster software to map these deep sequencing reads to a reference genome, to identify SNPs or rare transcripts. Results: We present a framework for how full sensitivity mapping can be done in the most efficient way, via spaced seeds. Using the framework, we have developed software called ZOOM, which is able to map the Illumina/Solexa reads of 15× coverage of a human genome to the reference human genome in one CPU-day, allowing two mismatches, at full sensitivity. Availability: ZOOM is freely available to non-commercial users at http://www.bioinfor.com/zoom Contact:bma@csd.uwo.ca, mli@uwaterloo.ca