Predicting JNK1 Inhibitors Regulating Autophagy in Cancer using Random Forest Classifier

Autophagy (in Greek: self-eating) is the cellular process for delivery of heterogenic intracellular material to lysosomal digestion. Protein kinases are integral to the autophagy process, and when dysregulated or mutated cause several human diseases. Atg1, the first autophagy-related protein identified is a serine/threonine protein kinases (STPKs). mTOR (mammalian Target of Rapamycin), AMPK (AMP-activated protein kinase), Akt, MAPK (mitogen-activated protein kinase) and PKC (protein kinase C) are other STPKs which regulate various components/steps of autophagy, and are often deregulated in cancer. MAPK have three subfamilies - ERKs, p38, and JNKs. JNKs (c-Jun N-terminal Kinases) have three isoforms in mammals - JNK1, JNK2, and JNK3, each with distinct cellular locations and functions. JNK1 plays role in starvation induced activation of autophagy, and the context-specific role of autophagy in tumorigenesis establish JNK1 a challenging anticancer drug target. Since JNKs are closely related to other members of MAPK family (p38, MAP kinase and the ERKs), it is difficult to design JNK-selective inhibitors. Designing JNK isoform-selective inhibitors are even more challenging as the ATP-binding sites among all JNKs are highly conserved. Although limited informations are available to explore computational approaches to predict JNK1 inhibitors, it seems diificult to find literature exploring machine learning techniques to predict JNKs inhibitors. This study aims to apply machine learning to predict JNK1 inhibitors regulating autophagy in cancer using Random Forest (RF). Here, RF algorithm is used for two purposes- to select and rank the molecular descriptors calculated using PaDEL descriptor software and as clasifier. The descriptors are prioritized by calculating Variable Importance Measures (VIMs) using functions based on mean square error (IncMSE) and node purity (IncNodePurity) of RF. The classification models based on a set of 22 prioritized descriptors shows accuracy 86.36%, precision 88.27% and AUC (Area Under ROC curve) 0.8914. We conclude that machine learning-based compound classification using Random Forest is one of the ligand-based approach that can be opted for virtual screening of large compound library of JNK1 bioactives.\n\nAuthor SummaryOut of the three isoforms of JNKs (cJun N-terminal Kinases) in human (each with distinct cellular locations and functions), JNK1 plays role in starvation induced activation of autophagy. The role of JNK1 in autophagy modulation and dual role of autophagy in tumor cells makes JNK1 a promising anticancer drug target. Since JNKs are closely related to other members of MAPK (Mitogen-Activated Protein Kinases) family, it is difficult to design JNK selective inhibitors. Designing JNK isoformselective inhibitors are even more challenging as the ATP binding sites among all JNKs are highly conserved. Random forest classifier usually outperforms several other machine learning algorithms for classification and prediction tasks in diverse areas of research. In this work, we have used Random Forest algorithm for two purposes: (i) calculating variable importance measures to rank and select molecular features, and (ii) predicting JNK1 inhibitors regulating autophagy in cancer. We have used paDEL calculated molecular features of JNK1 bioactivity dataset from ChEMBL database to build classification models using random forest classifier. Our results show that by optimally selecting features from top 10% based on variable importance measure the classification accuracy is high, and the classification model proposed in this study can be integrated with drug design pipeline to virtually screen compound libraries for predicting JNK1 inhibitors.