headerSearch form

Changing the World through Creative Research

A deep learning model for cell growth inhibition IC50 prediction and its application for gastric cancer patients

Journal
IJMS(International Journal of Molecular Sciences)
Date
2019.12.13
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 responsivenss classes, based on 27756 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 cacner (GC) is not only one of the lethal cancer types in East Asia, but also a heterogenous cancer type. Currently approved targeted therapies in GC are only trastuzumab and ramucirumab. Responsive GC patietns 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.
Reference
Int. J. Mol. Sci. 2019, 20(24), 6276
DOI
http://dx.doi.org/10.3390/ijms20246276