Augmenting LASSO regression with decision tree for identifying the correlation of genetic polymorphism and adverse events

A novel algorithm that combines LASSO regression and decision tree is proposed to explore the correlation of adverse events (AE) and genetic polymorphism of CYP2D6*2, *10, *14, CYP1A2*1C, *1F in human subjects in a clinical trial. The genotypes of 30 healthy human subjects in a clinical trial for a natural herbal drug and 53 subjects in the blank group were detected by polymerase chain reaction (PCR) and DNA sequencing. The AEs occurring during the trial were recorded. The correlations of AE and genetic polymorphism are analyzed by the new combined algorithm. 53 AEs are reported in the end of the study. Five gene subtypes are selected as correlative factors to the specific AEs by the new algorithm: wild type of CYP1A2*1F and abnormal platelet counting, homozygous CYP1A2*1C and abnormal fibrinogen, heterozygous CYP1A2*1C and abnormal blood chlorine, heterozygous CYP1A2*1C and abnormal urobilinogen, wild type of CYP2D6*2 and abnormal APTT (activated partial thromboplastin time). The result indicates the novel algorithm is effective and is able to detect the correlation of AEs and genetic polymorphism in clinical trials.