Prediction of drug-induced cell viability by SAE-XGBoost algorithm based on LINCS-L1000 perturbation signal / 生物工程学报

Different cell lines have different perturbation signals in response to specific compounds, and it is important to predict cell viability based on these perturbation signals and to uncover the drug sensitivity hidden underneath the phenotype. We developed an SAE-XGBoost cell viability prediction algorithm based on the LINCS-L1000 perturbation signal. By matching and screening three major dataset, LINCS-L1000, CTRP and Achilles, a stacked autoencoder deep neural network was used to extract the gene information. These information were combined with the RW-XGBoost algorithm to predict the cell viability under drug induction, and then to complete drug sensitivity inference on the NCI60 and CCLE datasets. The model achieved good results compared to other methods with a Pearson correlation coefficient of 0.85. It was further validated on an independent dataset, corresponding to a Pearson correlation coefficient of 0.68. The results indicate that the proposed method can help discover novel and effective anti-cancer drugs for precision medicine.

The value of serum tumor markers AFP,CYFRA21-1 and NSE in the diagnosis and prognosis of lung cancer / 国际检验医学杂志

Objective To analyse the value of serum alpha fetoprotein(AFP),keratin antigen 21-1(CY-FRA21-1)and neuron specific enolase(NSE)in the diagnosis and prognosis of lung cancer.Methods A total of 89 patients with primary lung cancer were selected as the primary lung cancer group from June 2014 to June 2016.The other 59 cases of benign lung disease were selected as the benign lung disease group,and 63 cases of healthy physical examination were collected as normal group.The content of AFP,CYFRA21-1 and NSE were detected by electrochemiluminescence assay.Results Before treatment,the levels of AFP,CYFRA21-1 and NSE in the benign lung disease group and the primary lung cancer group were significantly higher than those in the normal group,those in the primary lung cancer group were significantly higher than those in the benign lung disease group(P<0.05).The levels of AFP,CYFRA21-1 and NSE in patients with stage Ⅲ aand Ⅲ b-Ⅳ were significantly higher than those in patients with stage Ⅰ - Ⅱ,and those in Ⅲ b- Ⅳ stage were signifi-cantly higher than those in Ⅲ astage(P<0.05).The sensitivity,specificity,accuracy of two joint tests were significantly higher than those of the single test,those of the three joint tests were significantly higher than those of the single test and the two combined tests,and the differences were statistically significant(P<0.05).The AFP,CYFRA21-1 and NSE of the patients in the ineffective group were significantly higher than those in the effective group,and the differences were statistically significant(P<0.05).Conclusion Tumor markers AFP,YFRA21-1 and NSE are of great value in the diagnosis and treatment of lung cancer,joint detec-tion could improve the positive rate and accuracy of diagnosis.