Machine Learning Classification and Structure–Functional Analysis of Cancer Mutations Reveal Unique Dynamic and Network Signatures of Driver Sites in Oncogenes and Tumor Suppressor Genes

Abstract

In this study, we developed two cancer-specific machine learning classifiers for prediction of driver mutations in cancer-associated genes that were validated on canonical data sets of functionally validated mutations and applied to a large cancer genomics data set. By examining sequence, structure, and ensemble-based integrated features, we have shown that evolutionary conservation scores play a critical role in classification of cancer drivers and provide the strongest signal in the machine learning prediction. Through extensive comparative analysis with structure−functional experiments and multicenter mutational calling data from Pan Cancer Atlas studies, we have demonstrated the robustness of our models and addressed the validity of computational predictions. To address the interpretability of cancer-specific classification models and obtain novel insights about molecular signatures of driver mutations, we have complemented machine learning predictions with structure−functional analysis of cancer driver mutations in several important oncogenes and tumor suppressor genes. By examining structural and dynamic signatures of known mutational hotspots and the predicted driver mutations, we have shown that the greater flexibility of specific functional regions targeted by driver mutations in oncogenes may facilitate activating conformational changes, while loss-of-function driver mutations in tumor suppressor genes can preferentially target structurally rigid positions that mediate allosteric communications in residue interaction networks and modulate protein binding interfaces. By revealing molecular signatures of cancer driver mutations, our results highlighted limitations of the binary driver/passenger classification, suggesting that functionally relevant cancer mutations may span a continuum spectrum of driverlike effects. Based on this analysis, we propose for experimental testing a group of novel potential driver mutations that can act by altering structure, global dynamics, and allosteric interaction networks in important cancer genes.

Allosteric Regulation at the Crossroads of New Technologies: Multiscale Modeling, Networks, and Machine Learning

“…Deep neural network methods were successfully applied to predict intrinsic molecular properties such as atomization energy based on simple molecular geometry and element types (Rupp et al, 2012 ). DL models were recently used for structure-functional prediction of cancer mutations and functional hotspots of ligand binding in cancer-associated genes (Agajanian et al, 2018 ). The developed models can capture ~90% of experimentally validated mutational hotspots and yield novel information about molecular signatures of driver mutations.…”

“…There has been an explosion of interest in transparent and interpretable ML models to enable more efficient data mining and scientific knowledge discovery (Holzinger et al, 2014 ). Our investigations have also provided a roadmap how to combine DL predictions of functional sites with subsequent biophysical analysis to aid in the interpretability of ML models and facilitate their applications in biological problems (Agajanian et al, 2018 , 2019 ).…”

Autoinhibition can identify rare driver mutations and advise pharmacology

“…However, mutational events can promote it, resulting in orders of magnitude difference. 73 Clustering of mutations in protein sequences 74 and structures, 75 as well as MD simulations and residue interaction networks, 76 machine learning classification which reveals dynamics signatures 77,78 and additional parameters 79 can also be employed. 57,58 By breaking or forming interactions, allosteric events stabilize (or destabilize) certain states.…”

“…This can emerge from altered PTMs (eg, phosphorylation, ubiquitination, etc.) 76,77 If a mutation is rare, and not observed to have functional or signaling ramifications, current schemes would label it a passenger. Mutations in the proteins leading to functional consequences or in the proteins that execute the linkage of the PTM are more likely to be drivers.…”

Review of Machine Learning Technologies and Neural Networks in Drug Synergy Combination pharmacological research

“…The synergy of Deep Learning scores and integrated metrics derived from protein sequence conservation scores can allow us to improve treatment development. Machine Learning predictions are leveraged in molecular simulations, protein stability, and network-based analysis to obtain insights about molecular signatures and enhance efficiency (Agajanian et al 2018;Deist et al 2018;Agajanian et al 2019).…”