数据处理光谱分析与数据挖掘.PPT

Identification of microRNA AUCGUGCAGAGACUAGACUGACAUCGUGCAGAGACUAGACUGACAUCGUGCAGAGACUAGACUGACAUCGUGCAGAGA CUAGACUGACAUCGUGCAGAGACUAG ACUGAC 1 tgcgcgaauucacccauggauccauucaucuuccaagggcaccagc 2 agcgcgaauuccaagucacccauggauccauucaucuggcagcgu 3 agucgcgaauucaucaucuuccaagggcacccauggauccaucca * Ref: Xue C, et al. Classification of real and pseudo microRNA precursors using local structure-sequence features and support vector machine. BMC Bioinformatics, 2005, 6(1): 310. * Ref: Xue C, et al. Classification of real and pseudo microRNA precursors using local structure-sequence features and support vector machine. BMC Bioinformatics, 2005, 6(1): 310. microRNA prediction based on machine learning obvious differences weak generalization * Importance of negative samples Decision Boundary Positive Training Set Negative Training Set Negative Testing Set * Importance of negative samples New Decision Boundary Positive Training Set New Negative Training Set Negative Testing Set * 100nt 100nt Parameter Filter Prediction Model Extend Compute Secondary Structures Extract Human CDs Human Mature microRNAs Blast Mature-like Reads Original Negative Set Mined Sequences Rebuilt Replace innovation point * * */30 /~wly/mirnaDetect.html Novel miRNA found by our method 1 */30 Dinoflagellates genome (甲藻) Lin, et al. The Symbiodinium kawagutii genome illuminates dinoflagellate gene expression and coral symbiosis. Science. 2015, 350(6261): 691-694. Hierarchical learning in bioinformatics Protein fold pattern Enzyme identification microRNA family High dimensionality problems Gene expression Methylation profile GWAS Outline High dimensionality problems Sparse Noisy Gene expression data Methylation / GWAS(Genome-wide association study) Machine learning in GWAS Genome, GWAS and Watson 15-19岁，芝加哥大学 19-22岁，印第安纳大学，博士学位 导师：Salvador Luria （1969年诺奖） 偶像：穆勒（1946年诺奖，摩尔根的学生） 22-25岁，剑桥大学卡文迪许实验室 领导：小布拉格（最年轻的诺奖得主） 《Nature》