Table Of Content
One of the proposed concepts is the predictability, computability and stability framework for ‘veridical data science’90. Adequate selection of quality data has been specifically identified by leaders of the AI community as the major requirement for closing the ‘production gap’, or the inability of ML models to succeed when they are deployed in the real world, thus calling for a data-centric approach to AI91,92. There have also been attempts to develop tools to make AI ‘explainable’, that is, able to formulate some general trends in the data, specifically in the drug discovery applications93. In this review, we provide a brief introduction to CADD and include details of structure-based drug design (SBDD) and ligand-based drug design (LBDD), and their uses to identify potential drug candidates for NDs. In addition, we provide an up-to-date summary of the successes and limitations of CADD against NDs and discuss its future prospects. Identifying novel, potential drugs for NDs is difficult using traditional approaches of drug discovery [7].
Next frontier for drug discovery: SPACE?
As discussed above, physics-based and data-driven approaches have distinct advantages and limitations in predicting ligand potency. Structure-based docking predictions are naturally generalizable to any target with 3D structures and can be more accurate, especially in eliminating false positives as the main challenge of screening. Conversely, data-driven methods may work in lieu of structures and can be faster, especially with GPU acceleration, although they struggle to generalize beyond data-rich classes of targets. Therefore, there are numerous ongoing efforts to combine physics-based and data-driven approaches in some synergistic ways in general95, and in drug discovery specifically96. An alternative approach proposed to building chemical spaces generates hypothetically synthesizable compounds following simple rules of synthetic feasibility and chemical stability.
Ligand-Based Drug Design
If researchers used AI in this process at all in recent years, it was primarily to improve existing molecules. This chapter provides an overview on possible approaches to identify active scaffolds (including in silico approximations to approach that task) and computational methods to guide the subsequent optimization process. 6When constructing the final list of compound for experimental assays from VS, in addition to the binding score, drug likeness can be another criterion to further filter the list.
Artificial intelligence–enabled virtual screening of ultra-large chemical libraries with deep docking
Many molecular docking programs have been developed during recent years, such as, AutoDock [40], Dock [41], FlexX [42], Glide [43], Gold [44], Surflex [45], ICM, and LigandFit [46], and been used successfully in many computer based drug discovery projects. Typically, the major goal of molecular docking is to identify ligands that bind most favorably within receptor binding sites and to determine its most energetically favored binding orientations (poses). A binding pose either refers to a conformation of a ligand molecule within the binding site of its target protein which has been confirmed experimentally, or a computationally modelled hypothetical conformation. The search algorithm and the scoring function are two important components for determining protein-ligand interactions [47]. The search algorithm is responsible for searching different poses and conformations of a ligand within a given target protein and the scoring function estimates the binding affinities of generated poses, ranks them, and identifies the most favorable receptor/ligand binding modes [47, 48].
Although allowing comprehensive space coverage, the reaction path and success rate of generated compounds are unknown, and thus require computational prediction of their practical synthesizability. More recently, virtual on-demand chemical databases (fully enumerated) and spaces (not enumerated) allow fast parallel synthesis from available building blocks, using validated or optimized protocols, with synthetic success of more than 80% and delivery in 2–3 weeks (see the figure, part b). The virtual chemical spaces assure high chemical novelty and allow fast polynomial growth with the addition of new synthons and reaction scaffolds, including 4+ component reactions. Examples include Enamine REAL, Galaxy by WuXi, CHEMriya by Otava and private databases and spaces at pharmaceutical companies. Research suggests inhibition of this enzyme stops the production of β-amyloid, and thus, prevents NDs like Alzheimer's disease [68].
Despite the availability of advanced techniques, the structures of a large number of proteins have not been identified [30]. Homology modelling helps in this situation because it can be used to generate the structures of proteins on information available for similar proteins [31]. Following are the steps required to perform a standard MD simulation (see Note 2 for additional MD techniques). Initially applied to discover new chemotypes for cannabinoid receptor CB2 antagonists, V-SYNTHES has shown a hit rate of 23% for submicromolar ligands, which exceeded the hit rate of standard VLS by fivefold, while taking about 100 times less computational resources26.
The results obtained showed inhibitors had low cytotoxicities, suggesting potential for drug development [82]. Inhibition of these two enzymes constitutes treatment for neurological diseases like autism spectral disorder, Alzheimer, and fragile X syndrome. Alokam et al. reported the successful use of CADD to design dual inhibitors for these enzymes [76], by employing a combination of pharmacophores and using a molecular docking approach to identify chemical entities.
Al. recently explored the molecular mechanism of polymyxin E (colistin) resistance in mobile colistin-resistant (mcr-1) bacteria (6). Colistin is the only FDA-approved membrane-active drug to tackle Gram-negative bacteria despite its high toxicity. The simulation results provide clues for the design of new membrane disruptors to treat mcr-1 infections. The advent of fast and practical methods for screening gigascale chemical spaces for drug discovery stimulates further growth of these on-demand spaces, supporting better diversity and the overall quality of identified hits and leads.
4. Site identification using SILCS-Hotspots
Nevertheless, most of the lead compounds undergo structural modification to meet their certain biological properties, so-called lead optimization. However, the investigated lead compound has to satisfy five characteristics to act as a bioactive drug molecule. They are potency, duration, safety, availability, and pharmaceutical acceptability, where potency involves the capability of any molecule to exhibit desirable pharmaceutical properties in smaller quantities. Bioavailability marks the transportation of drug compounds with multiple barriers to reach the target site is called bioavailability.
Dr. Pellecchia is a Professor of Biomedical Sciences at the School of Medicine of the University of California Riverside (UCR) and is the founding Director of the Center for Molecular and Translational Medicine at UCR. His research laboratory focuses on the design of novel pharmacological tools and therapeutics in oncology, neurodegeneration, and other disease areas. Dr. Rogawski is Professor of Neurology and Pharmacology at the University of California, Davis School of Medicine.
The recent tendency in drug design is to rationally design potent therapeutics with multi-targeting effects, higher efficacies, and fewer side effects, especially in terms of toxicity. "It's a real breakthrough for drug discovery," says Gisbert Schneider, Professor at ETH Zurich's Department of Chemistry and Applied Biosciences. Together with his former doctoral student Kenneth Atz, he has developed an algorithm that uses artificial intelligence (AI) to design new active pharmaceutical ingredients.
Click chemistry-aided drug discovery: A retrospective and prospective outlook - ScienceDirect.com
Click chemistry-aided drug discovery: A retrospective and prospective outlook.
Posted: Mon, 15 Jan 2024 08:00:00 GMT [source]
Figure 1 illustrates the basic CADD workflow that can be interactively used with experimental techniques to identify novel lead compounds as well as direct iterative ligand optimization (3, 4, 21, 22). The process starts with the biological identification of a putative target to which ligand binding should lead to antimicrobial activity. In SDBB, the 3D structure of the target can be identified by X-ray crystallography or NMR or using homology modeling.
Advances in computational hardware and algorithms and emerging CADD methods are enhancing the accuracy and ability of CADD in drug design and development. In this chapter, an update to our previous chapter is provided with a focus on new CADD approaches from our laboratory and other peers that can be employed to facilitate the development of antibiotic therapeutics. To speed up virtual screening of ultra-large chemical libraries, several groups have suggested hybrid iterative approaches, in which results of structure-based docking of a sparse library subset are used to train ML models, which are then used to filter the whole library to further reduce its size. These methods, including MolPal25, Active Learning110 and DeepDocking111, report as much as 14–100 reduction in the computational cost for libraries of 1.4 billion compounds, although it is not clear how they would scale to rapidly growing chemical spaces. In virtual screening approaches, a synergetic use of physics-based docking with data-based scoring functions may be highly beneficial.
The ML workflow was verified to be able to generate models not only capable of predicting resistance profiles but also identifying the responsible genes. Al. conducted an antibiotic activity assay screen of near 2,300 chemically diverse FDA approved and natural product compounds targeting E. Deep neural network-based DL models were then trained to predict the inhibition probabilities from the chemical structures and properties of tested compounds alone.
The structural elucidation of pharmacological drug targets and the discovery of preclinical drug candidate molecules have accelerated both structure-based as well as ligand-based drug design. This review article will help the clinicians and researchers to exploit the immense potential of computer-aided drug design in designing and identification of drug molecules and thereby helping in the management of fatal disease. The long-used traditional methodology for novel drug discovery and drug development is an immensely challenging, multifaceted, and prolonged process. To overcome this limitation, a new advanced approach was developed and adopted over time which is referred to as computer-aided drug discovery (CADD). Over the course, CADD has accelerated the overall traditional time-consuming process of new drug entity development with the advancement of computational tools and methods.
No comments:
Post a Comment