Deep Learning Algorithms for Variant Calling in Oxford Nanopore Sequencing
|Title:||Deep Learning Algorithms for Variant Calling in Oxford Nanopore Sequencing|
|Date:||April 12, 2019 (Friday)|
|Time:||4:00 pm - 5:00 pm|
|Venue:||Room 121, 1/F, Ho Sin-Hang Engineering Building, The Chinese University of Hong Kong, Shatin, N.T.|
|Speaker:|| Dr. Luo Ruibang
Department of Computer Science
The University of Hong Kong
The accurate identification of DNA sequence variants is an important, but challenging task in genomics. It is particularly difficult for single molecule sequencing, which has a per- nucleotide error rate of ~5–15%. Meeting this demand, we developed Clairvoyante, a multi- task five-layer convolutional neural network model for predicting variant type (SNP or indel), zygosity, alternative allele and indel length from aligned reads. For the well-characterized NA12878 human sample, Clairvoyante achieves 99.67, 95.78, 90.53% F1-score on 1KP common variants, and 98.65, 92.57, 87.26% F1-score for whole-genome analysis, using Illumina, PacBio, and Oxford Nanopore data, respectively. Training on a second human sample shows Clairvoyante is sample agnostic and finds variants in less than 2h on a standard server. Furthermore, we present 3,135 variants that are missed using Illumina but supported independently by both PacBio and Oxford Nanopore reads. Clairvoyante is avail- able open-source (https://github.com/aquaskyline/Clairvoyante), with modules to train, utilize and visualize the model.
Dr. Luo joined HKUCS in Jan 2018. He received his B.E. degree in bio-engineering from the South China University of Technology in 2010 and his Ph.D. degree in computational biology from the University of Hong Kong in 2015. He was a postdoctoral fellow in the Center of Computational Biology, McKusick-Nathans Institute of Genetic Medicine, Johns Hopkins University School of Medicine. Dr. Luo is a researcher working on bioinformatics software and biological, clinical and pharmaceutical projects. His interdisciplinary research results have been published in peer-reviewed journals such as Nature, Nature Biotechnology, and Bioinformatics. His research covers a diversity of topics in computational biology, from technique-driven research, whose aim is to develop algorithms for two fundamental sequence-analysis problems, 'genome assembly' and 'genome alignment', to hypothesis-driven investigations, such as studying the genetic background of hundreds of cancer cell lines, where the primary aim is to discover and advance clinical knowledge. His research also includes engineering problems for which the accuracy and efficiency of algorithms are crucial, as well as problems for which innovative modeling and analysis of data are more important.
Enquiries: Mr. Cyrus Lee at tel. 3943 8440
For more information, please refer to http://www.cse.cuhk.edu.hk/en/events