DEEP LEARNING-BASED VARIANT CLASSIFIER

专利名称：DEEP LEARNING-BASED VARIANT

CLASSIFIER

发明人：SCHULZ-TRIEGLAFF, Ole Benjamin,COX,

Anthony James,FARH, Kai-How

申请号：EP19703482.0申请日：20190114公开号：EP3619653B1公开日：20210519

摘要：The technology disclosed directly operates on sequencing data and derives itsown feature filters. It processes a plurality of aligned reads that span a target baseposition. It combines elegant encoding of the reads with a lightweight analysis toproduce good recall and precision using lightweight hardware. For instance, one milliontraining examples of target base variant sites with 50 to 100 reads each can be trained ona single GPU card in less than 10 hours with good recall and precision. A single GPU cardis desirable because it a computer with a single GPU is inexpensive, almost universallywithin reach for users looking at genetic data. It is readily available on could-basedplatforms.

代理机构：Robinson, David Edward Ashdown

更多信息请下载全文后查看