A scalable computational quantum mechanics method for non-covalent protein-ligand interactions will be developed based on "extended" symmetry-adapted perturbation theory (XSAPT), a cubic-scaling, fragment-based approach that is specifically designed for large supramolecular complexes, and which affords a demonstrated accuracy of ;$ 1 kcal/mo! with respect to the best-available ab initio benchmarks. In Phase I of this work, we will enhance the efficiency of XSAPT via better parallelization that will enable routine application to protein-ligand models containing 300+ atoms, using only modest computational resources. A bootstrap procedure will be developed to assess the accuracy of the method and a data set will be generated that includes protein-ligand interaction energies and their components: electrostatics, steric repulsion, dispersion, polarization, and charge transfer. The data set will build upon standard ones derived from crystal structures but will also include nonequilibrium structures as well as small ligand fragments for which crystal structures and other experimental data are not available; the latter are representative of fragment-based drug discovery strategies. These are challenging cases for interaction energy computations that can only be addressed quantitatively by using the predictive power of quantum mechanics, not by empirical scoring functions or by fits to experimental data. In Phase II, this data set will be used to train a machine learning (ML) model that is capable of ranking-ordering ligand binding energies in a reliable and quantitative way, something that existing scoring functions ( even those based on ML) cannot do. Additional Phase II work will integrate the ML-XSAPT scoring function into virtual drug-discovery workflows (including flexible docking protocols), which will facilitate both lead generation and lead optimization in drug discovery, based on quantitative ab initio energetics.
Public Health Relevance Statement: Project Narrative A scalable computational quantum mechanics method will be developed that can predict binding energies of small molecules ( drug candidates) to therapeutic targets (proteins) with quantitative accuracy. The current phase of the project will enhance the scalability of the method, which is needed for large protein-ligand models, and will generate a data set of high-accuracy protein-ligand interaction energies. These data will be used in the second phase to generate scoring functions via machine learning, and these will be integrated into drug-discovery workflows for rapid identification of candidate ligands.
Project Terms: aminoacid; Amino Acids; Theriacs; Antidotes; Binding Sites; Combining Site; Reactive Site; Biological Assay; Assay; Bioassay; Biologic Assays; Charge; Drug Design; Pharmaceutical Preparations; Drugs; Medication; Pharmaceutic Preparations; drug/agent; Eligibility Determination; Eligibility; Protocol Screening; Exhibits; Foundations; Goals; Lead; Pb element; heavy metal Pb; heavy metal lead; Ligands; Methods; Biological Models; Biologic Models; Model System; Molecular Weight; Physics; Proteins; Resources; Research Resources; Testing; Time; Water; Hydrogen Oxide; Work; Generations; Data Set; density; Procedures; Phase; Chemicals; Training; tool; Machine Learning; machine based learning; Electrostatics; Complex; Oral; Protocols documentation; Protocol; Benchmarking; Best Practice Analysis; benchmark; quantum chemistry; computational quantum chemistry; lipophilicity; TRANCE protein; ODF factor; OPGL protein; Osteoclast Differentiation Factor; Osteoprotegerin Ligand; RANK ligand; Receptor Activator of Nuclear Factor Kappa B Ligand; TNF-Related Activation-Induced Cytokine; Tumor Necrosis Factor Ligand Superfamily Member 11; Free Energy; Structure; Modeling; theories; drug development; high throughput screening; High Throughput Assay; drug discovery; Molecular Interaction; Binding; Pharmaceutical Agent; Pharmaceuticals; Pharmacological Substance; pharmaceutical; Pharmacologic Substance; small molecule; Address; Affinity; Data; Quantum Mechanics; Ligand Binding; Molecular; Process; Docking; Development; developmental; cost; virtual; computer aided; Computer Assisted; designing; design; computational resources; computing resources; therapeutic target; candidate identification; drug candidate; flexible; flexibility; screenings; screening; perturbation theory; quantum coding; quantum computation; quantum error correcting codes; quantum computing; parallelization; experiment; experimental research; experiments; experimental study; lead optimization; in silico; virtual screenings; virtual screening; machine learning model; machine learning based model