Abstract
Heterogeneity in intratumoral cancers leads to discrepancies in drug responsiveness, due to diverse genomics profiles. Thus, prediction of drug responsiveness is critical in precision medicine. So far, in drug responsiveness prediction, drugs’ molecular “fingerprints”, along with mutation statuses, have not been considered. Here, we constructed a 1-dimensional convolution neural network model, DeepIC50, to predict three drug responsiveness classes, based on 27,756 features including mutation statuses and various drug molecular fingerprints. As a result, DeepIC50 showed better cell viability IC50 prediction accuracy in pan-cancer cell lines over two independent cancer cell line datasets. Gastric cancer (GC) is not only one of the lethal cancer types in East Asia, but also a heterogeneous cancer type. Currently approved targeted therapies in GC are only trastuzumab and ramucirumab. Responsive GC patients for the drugs are limited, and more drugs should be developed in GC. Due to the importance of GC, we applied DeepIC50 to a real GC patient dataset. Drug responsiveness prediction in the patient dataset by DeepIC50, when compared to the other models, were comparable to responsiveness observed in GC cell lines. DeepIC50 could possibly accurately predict drug responsiveness, to new compounds, in diverse cancer cell lines, in the drug discovery process.
Highlights
IntroductionDrug responsiveness prediction is related to precision medicine (i.e., individualized therapy), to improve cancer patient treatment benefits [1,2,3]
Drug responsiveness prediction is related to precision medicine, to improve cancer patient treatment benefits [1,2,3]
This study showed that ccoonnvvoolluution nneural network (CNN) good ways for multi-class prediction, by incorporating genomic profiles, and drug chemical properties
Summary
Drug responsiveness prediction is related to precision medicine (i.e., individualized therapy), to improve cancer patient treatment benefits [1,2,3]. FFiirrsstt,, iitt iiss nnoott rreeaalliissttiicc ttoo mmeeaassuurreeddrruuggrreessppoonnssiivveenneessssbbyyttrreeaattiinnggppaattiieennttss;;iinnsstteeaadd,,cceelllllliinnee eexxppeerriimmeennttss,,aass pprrooxxiieess ffoorr ccaanncceerr patients, would be highly advantageous [9] This would be a more realistic strategy to construct drug responsiveness models using cancer cell lines, and applying those models to a concatenation vector of a patient mutation status vector and a drug chemical property vector. Concatenating mutation statuses of the new cell line and chemical properties of the new drug results in a input vector, which feeds into one-model to DeepIC50 It predicts responsiveness for the potency of the new drug, to the new cell line. We developed a 1D CNN model, DeepIC50, for predicting drug responsiveness, based on genomics (e.g., mutation statuses) and drug chemical properties, resulting in better performance, in comparison to the other baseline models Such approaches may have application to this new age of “precision medicine.”
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
