Application of Deep Learning in Target Identification Through Determining the Mechanism of Action Given Cellular Signature Data

Overview

Current techniques of target identification in drug development are costly, lengthy, and function with high degrees of uncertainty that a drug can succeed in modulating a target. To address this, the ability of computational approaches to leverage cellular signature data for in-silico target identification was explored. The NIH LINCS program has compiled and publicized data consisting of cell viability measurements and high-throughput gene-expression drug and target screens (measured by L1000 assay) of ~5000 small molecules and their respective mechanisms of action (MoA). This study involves the utilization of a neural network to convert this cellular signature data to an estimate of the mechanism of action of a compound. Validating on an isolated subset of our training data, our approach achieved 81.69% AUC (Receiver Operating Characteristic curve). After improving the performance of our model through Bayesian hyperparameter optimization, the final validation AUC increased to 91.51%. These promising results were also shown to significantly perform more efficiently than other machine learning approaches: one-dimensional convolutional neural network, and logistic regression (p< 0.05). Overall, the algorithm provides a reliable framework for expedited drug target identification.

Awards (2)

• Fourth Award of $500 $500
• Arizona State University: Arizona State University ISEF Scholarship

Competition history

• ISEF 2021 Computational Biology and Bioinformatics · Entry CBIO078T

Resources

• ISEF abstract page ↗

Related projects

Closest projects by meaning, across every fair and year in the corpus.