Advances and Perspectives in Applying Deep Learning for Drug Design and Discovery

Abstract

Discovering (or planning) a new drug candidate involves many parameters, which makes this process slow, costly, and leading to failures at the end in some cases. In the last decades, we have witnessed a revolution in the computational area (hardware, software, large-scale computing, etc.), as well as an explosion in data generation (big data), which raises the need for more sophisticated algorithms to analyze this myriad of data. In this scenario, we can highlight the potentialities of artificial intelligence (AI) or computational intelligence (CI) as a powerful tool to analyze medicinal chemistry data. According to IEEE, computational intelligence involves the theory, the design, the application, and the development of biologically and linguistically motivated computational paradigms. In addition, CI encompasses three main methodologies: neural networks (NN), fuzzy systems, and evolutionary computation. In particular, artificial neural networks have been successfully applied in medicinal chemistry studies. A branch of the NN area that has attracted a lot of attention refers to deep learning (DL) due to its generalization power and ability to extract features from data. Therefore, in this mini-review we will briefly outline the present scope, advances, and challenges related to the use of DL in drug design and discovery, describing successful studies involving quantitative structure-activity relationships (QSAR) and virtual screening (VS) of databases containing thousands of compounds.

Data-Driven Discovery of Molecular Targets for Antibody-Drug Conjugates in Cancer Treatment

“…Recently, many efforts have been made in the discovery of molecular targets and prediction methods [ 20 – 23 ]. The accessibility of extensive open access biological data in the postgenomic era has revolutionized the field drug discovery.…”

“…In this light, virtual screening methods such as molecular docking, pharmacophore modeling, quantitative structure–activity relationships (QSAR), and ligand-based in silico target prediction were applied [ 21 ]. Also, machine-learning methods can play a substantial role in the field [ 22 , 23 ]. Some special features of ADC drugs raise the need for a unique algorithm to discover candidate ADC targets.…”

Artificial Intelligence (AI) to the Rescue: Deploying Machine Learning to Bridge the Biorelevance Gap in Antioxidant Assays

“…Deep learning has outperformed traditional techniques in some drug design-related applications, principally due to some peculiar characteristics of biological and chemical data, such as complexity, uncertainty, diversity, and high dimensionality. 28 Some drawbacks of applying ML techniques include the problem of overfitting of data, which is minimized by different strategies for different techniques. An ensemble of classifiers was proposed to minimize the inherent weaknesses of each ML technique; however, this approach generated other weaknesses like decreased comprehensibility of the model, increased storage, and increased computation requirement.…”

“…31 Other drawbacks of applying deep learning include the limited number of data in certain areas of study and difficult interpretation of the chemical and biological mechanisms involved in deep learning models. 28 Part of what is outstanding in current antioxidant research is to optimize the choice and dose of antioxidants in investigating the impact of antioxidant therapy on amelioration of specific diseases. In addition to creating a global index, because antioxidant efficacy depends on the dose of the antioxidant administered, one way to incorporate this variable into the ML workflow (input) is to ensure the assays that monitor the respective biomarkers incorporate the dose-response curve of a well-known oxidant.…”

“…27 Deep learning, a branch of ANN that has found successful application in medicinal chemistry, can be described as a class of representation-learning techniques that are able to discover, from the raw data, multiple-level representations of increasing complexity by composing nonlinear models. 28 …”