Identifying Tissue Origin of Cancer Cells with Somatic Mutations and Copy Number Alterations
时间：2017-04-27 14:00 ~ 15:00
A substantial proportion of cancer cases present with a metastatic tumor and require further testing to determine the primary site; many of these are never fully diagnosed and remain cancer of unknown primary origin (CUP). It has been previously demonstrated that epigenomic variations detected in whole-genome bisulfite sequencing data of plasma cell-free DNA can be used to identify its site of origin with limited accuracy. Recently, tissue-specific mutation accumulation pattern were found. We hypothesized that tissue origin of cancer cells can be identified by genomic variations detected from whole genome/exome sequencing data of tumor cells even plasma cell-free DNA. We presented a kernel machine to identify tissue origin based on somatic single nucleotide variations, copy number alterations and mutational signature from whole genome/exome sequencing 5610 cases across 24 cancer types from TCGA. The model achieved 80% of accuracy (79% of the F1 score) and the 88% of top2 accuracy (88% of the top2 F1 score) with 100 replicates of 5-fold cross-validation.
About the Speaker:
凌少平博士现任志诺维思基因科技有限公司CEO兼首席科学家，自动化学士、信号与信息处理硕士、基因组学博士，师从著名华人进化遗传学家吴仲义院士。凌少平博士曾任中科院北京基因组研究所生物信息技术主管、计算肿瘤基因组研究组组长，在肿瘤异质性、肿瘤演化基因组和生物信息学方面具有较深的研究基础，曾在Nature Genetics、PNAS、Annual Review of Genetics、Molecular Biology & Evolution等权威杂志上发表多篇文章。他主导设计的算法已经应用于肝癌（HCC）、急性白血病（AML）、侵袭性NK细胞白血病（ANKL）、结直肠癌（CRC）、垂体瘤、宫颈癌等诸多肿瘤基因组研究工作中。