ABSTRACT
Introduction
Modern drug discovery is generally accessed by useful information from previous large databases or uncovering novel data. The lack of biological and/or chemical data tends to slow the development of scientific research and innovation. Here, approaches that may help provide solutions to generate or obtain enough relevant data or improve/accelerate existing methods within the last five years were reviewed.
Areas covered
One-shot learning (OSL) approaches, structural modeling, molecular docking, scoring function space (SFS), molecular dynamics (MD), and quantum mechanics (QM) may be used to amplify the amount of available data to drug design and discovery campaigns, presenting methods, their perspectives, and discussions to be employed in the near future.
Expert opinion
Recent works have successfully used these techniques to solve a range of issues in the face of data scarcity, including complex problems such as the challenging scenario of drug design aimed at intrinsically disordered proteins and the evaluation of potential adverse effects in a clinical scenario. These examples show that it is possible to improve and kickstart research from scarce available data to design and discover new potential drugs.
Article highlights
Limited data in medicinal chemistry has been an issue since early drug discovery stages, implying in the design, screening and experimental testing of small and large chemical libraries.
One-shot learning are based in different specific approaches (e.g. HM, docking, SFS, MD and QM) to be employed to various purposes, taking the diversity of available compounds (natural, semi-synthetic, and synthetic) to a singular problem solving (lack of data), or target-specific drug design.
Regarding SBDD approaches, HM may be an initial step to augment or make available new structural data, ultimately leading to ligand–target interactions studies with molecular docking, resulting in the enrichment of ligand’s information or in a higher performance of predictive binding modes.
Scoring functions are mathematical models that can be applied to chemical (ligand) and protein (target) spaces to predict binding affinity studies and provide more adequate functions or better performance of predictive models to even provide more available affinity data.
Molecular dynamics simulations ultimately assess the binding affinity and stability of ligands to targets in a complex, able to result in more data from docking poses and binding modes, as a post-docking processing tool, and even considering or providing an ensemble of conformational structures.
QM calculation methods can be employed in LBDD and/or SBDD approaches to improve scoring functions, augment atomic and molecular properties calculations, and accurately approximate the binding affinity of a ligand to a target, generating more available data to even build new predictive models.
Declaration of interest
The authors have no relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript. This includes employment, consultancies, honoraria, stock ownership or options, expert testimony, grants or patents received or pending, or royalties.
Reviewer disclosures
Peer reviewers on this manuscript have no relevant financial or other relationships to disclose