Abstract
Computational methods have been widely used in drug design. The recent developments in machine learning techniques and the ever-growing chemical and biological databases are fertile ground for discoveries in this area. In this study, we evaluated the performance of Deep Learning models in comparison to Random Forest, and Support Vector Regression for predicting the biological activity (pIC50) of ALK-5 inhibitors as candidates to treat cancer. The generalization power of the models was assessed by internal and external validation procedures. A deep neural network model obtained the best performance in this comparative study, achieving a coefficient of determination of 0.658 on the external validation set with mean square error and mean absolute error of 0.373 and 0.450, respectively. Additionally, the relevance of the chemical descriptors for the prediction of biological activity was estimated using Permutation Importance. We can conclude that the forecast model obtained by the deep neural network is suitable for the problem and can be employed to predict the biological activity of new ALK-5 inhibitors.
Highlights
Cancer is considered one of the leading causes of death in the world and can be defined as a disease that arises from cumulative changes in the genetic material of normal cells, which change until they become malignant [1]
We developed machine learning models based on 2D molecular descriptors generated by the Mordred Python library software
The main prediction model related to the ALK-5 inhibition was built by using a feedforward DNN model and the obtained results were compared to those obtained by two other machine learning (ML) methods (Random Forest and Support Vector Machines)
Summary
Cancer is considered one of the leading causes of death in the world and can be defined as a disease that arises from cumulative changes in the genetic material of normal cells, which change until they become malignant [1]. Since cancer incidence rates have substantially increased in last decades, several research groups are studying ways to treat its various forms, leading to the discovery and studies of several biological targets related to this pathology [5, 6]. Among these many targets, there is great interest in the TGF-β type I receptor (type I receptor transforming growth factor-beta), which is known as ALK-5 (activin receptor type-5 kinase, or receptor-like activin kinase 5), member of the TGF-β superfamily.
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
