专利内容由知识产权出版社提供
专利名称：SYSTEMS AND METHODS FOR GENERATING
AND TRAINING CONVOLUTIONAL NEURALNETWORKS USING BIOLOGICAL SEQUENCESAND RELEVANCE SCORES DERIVED FROMSTRUCTURAL, BIOCHEMICAL, POPULATIONAND EVOLUTIONARY DATA
发明人：XIONG, Hui Yuan,FREY,Brendan申请号：EP16907692.4申请日：20160704公开号：EP3479304A1公开日：20190508
摘要：We describe systems and methods for generating and training convolutionalneural networks using biological sequences and relevance scores derived from structural,biochemical, population and evolutionary data. The convolutional neural networks takeas input biological sequences and additional information and output molecularphenotypes. Biological sequences may include DNA, RNA and protein sequences.Molecular phenotypes may include protein-DNA interactions, protein-RNA interactions,protein-protein interactions, splicing patterns, polyadenylation patterns, and microRNA-RNA interactions, which may be described using numerical, categorical or ordinalattributes. Intermediate layers of the convolutional neural networks are weighted usingrelevance score sequences, for example, conservation tracks. The resulting molecularphenotype convolutional neural networks may be used in genetic testing, to identifydrug targets, to identify patients that respond similarly to a drug, to ascertain health
risks, or to connect patients that have similar molecular phenotypes.
申请人：Deep Genomics Incorporated
地址：101 College Street Suite 320 Toronto, Ontario M5G 1L7 CA
国籍：CA
代理机构：J A Kemp
更多信息请下载全文后查看
