Machine and deep learning approaches for cancer drug repurposing

Abstract

Knowledge of the underpinnings of cancer initiation, progression and metastasis has increased exponentially in recent years. Advanced "omics" coupled with machine learning and artificial intelligence (deep learning) methods have helped elucidate targets and pathways critical to those processes that may be amenable to pharmacologic modulation. However, the current anti-cancer therapeutic armamentarium continues to lag behind. As the cost of developing a new drug remains prohibitively expensive, repurposing of existing approved and investigational drugs is sought after given known safety profiles and reduction in the cost barrier. Notably, successes in oncologic drug repurposing have been infrequent. Computational in-silico strategies have been developed to aid in modeling biological processes to find new disease-relevant targets and discovering novel drugtarget and drug-phenotype associations. Machine and deep learning methods have especially enabled leaps in those successes. This review will discuss these methods as they pertain to cancer biology as well as immunomodulation for drug repurposing opportunities in oncologic diseases.

Overcoming cancer therapeutic bottleneck by drug repurposing

“…Computational approaches based on molecular theory (MOT) Understanding a drug at the molecular level, and matching it with clinical symptoms of neoplasms different from those for which it was originally approved or developed, is key for computational approaches based on MOT leading to drug repurposing. [441][442][443] Such approaches involve comprehensive analysis of experimental data, such as chemical or protein structure, gene or protein expression, and various omics data, which assist researchers to put forward a repurposing hypothesis. [444][445][446][447] Molecular structure analysis.…”

Pathway-Based Drug-Repurposing Schemes in Cancer: The Role of Translational Bioinformatics

“…Machine learning (ML) studies, for instance, are providing means of discovery relying more on the increasing abundance of omic and clinical data than on a deep knowledge of cancer biology (which is the case for most of the approaches already presented). The recent work of Issa and collaborators ( 124 ) summarizes well recent ML applications. Of noteworthy attention is the fact that some computational learning algorithms are already being applied beyond genomic and transcriptomic data.…”

“…Deep learning methods such as Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), Support Vector Machines (SVM), and Naive Bayesian analysis (NB), as well as Natural Language Processing (NLP), have also been used to find patterns, useful to predict pharmacological effects, from transcriptomic, genomic, EHR, and bibliographic data ( 124 ). A DNN method, for instance, was introduced in a study analyzing perturbation experiments from 678 drugs across several cell lines from the LINCS project ( 152 ).…”

Bird Eye View of Protein Subcellular Localization Prediction

“…The traditional neural network architecture is the feed forward neural network with one hidden layer, in which each input neuron is connected to each neuron in the hidden layer and which is further connected to each neuron in the output layer. Apart from the subcellular localization prediction [ 13 , 79 ], deep learning is successfully applied in many other biological fields such as the prediction of splicing pattern prediction [ 80 , 81 ], protein secondary structure prediction [ 82 , 83 ], different types of cancer and drug-target interactions [ 84 , 85 , 86 , 87 ], and the patterns in the biomedical imaging datasets [ 88 ].…”