Exploring QSAR models for activity-cliff prediction.

INTRODUCTION AND METHODOLOGY: Pairs of similar compounds that only differ by a small structural modification but exhibit a large difference in their binding affinity for a given target are known as activity cliffs (ACs). It has been hypothesised that QSAR models struggle to predict ACs and that ACs thus form a major source of prediction error. However, the AC-prediction power of modern QSAR methods and its quantitative relationship to general QSAR-prediction performance is still underexplored. We systematically construct nine distinct QSAR models by combining three molecular representation methods (extended-connectivity fingerprints, physicochemical-descriptor vectors and graph isomorphism networks) with three regression techniques (random forests, k-nearest neighbours and multilayer perceptrons); we then use each resulting model to classify pairs of similar compounds as ACs or non-ACs and to predict the activities of individual molecules in three case studies: dopamine receptor D2, factor Xa, and SARS-CoV-2 main protease. RESULTS AND CONCLUSIONS: Our results provide strong support for the hypothesis that indeed QSAR models frequently fail to predict ACs. We observe low AC-sensitivity amongst the evaluated models when the activities of both compounds are unknown, but a substantial increase in AC-sensitivity when the actual activity of one of the compounds is given. Graph isomorphism features are found to be competitive with or superior to classical molecular representations for AC-classification and can thus be employed as baseline AC-prediction models or simple compound-optimisation tools. For general QSAR-prediction, however, extended-connectivity fingerprints still consistently deliver the best performance amongs the tested input representations. A potential future pathway to improve QSAR-modelling performance might be the development of techniques to increase AC-sensitivity.

Graph Convolutional Capsule Regression (GCCR): A Model for Accelerated Filtering of Novel Potential Candidates for SARS-CoV-2 Based on Binding Affinity.

BACKGROUND: There has been a growing interest in discovering a viable drug for the new coronavirus (SARS-CoV-2) since the beginning of the pandemic. Protein-ligand interaction studies are a crucial step in the drug discovery process, as it helps us narrow the search space for potential ligands with high drug-likeness. Derivatives of popular drugs like Remdesivir generated through tools employing evolutionary algorithms are usually considered potential candidates. However, screening promising molecules from such a large search space is difficult. In a conventional screening process, for each ligand-target pair, there are time-consuming interaction studies that use docking simulations before downstream tasks like thermodynamic, kinetic, and electrostatic-potential evaluation. METHODS: In this work, 'Graph Convolutional Capsule Regression' (GCCR), a model which uses Capsule Neural Networks (CapsNet) and Graph Convolutional Networks (GCN) to predict the binding energy of a protein-ligand complex is being proposed. The model's predictions were further validated with kinetic and free energy studies like Molecular Dynamics (MD) for kinetic stability and MM/GBSA analysis for free energy calculations. RESULTS: The GCCR showed an RMSE value of 0.0978 for 81.3% of the concordance index. The RMSE of GCCR converged around the iteration of just 50 epochs scoring a lower RMSE than GCN and GAT. When training with Davis Dataset, GCCR gave an RMSE score of 0.3806 with a CI score of 87.5%. CONCLUSION: The proposed GCCR model shows great potential in improving the screening process based on binding affinity and outperforms baseline machine learning models like DeepDTA, KronRLS, SimBoost, and other Graph Neural Networks (GNN) based models like Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT).

Molecule generation toward target protein (SARS-CoV-2) using reinforcement learning-based graph neural network via knowledge graph.

AI-driven approaches are widely used in drug discovery, where candidate molecules are generated and tested on a target protein for binding affinity prediction. However, generating new compounds with desirable molecular properties such as Quantitative Estimate of Drug-likeness (QED) and Dopamine Receptor D2 activity (DRD2) while adhering to distinct chemical laws is challenging. To address these challenges, we proposed a graph-based deep learning framework to generate potential therapeutic drugs targeting the SARS-CoV-2 protein. Our proposed framework consists of two modules: a novel reinforcement learning (RL)-based graph generative module with knowledge graph (KG) and a graph early fusion approach (GEFA) for binding affinity prediction. The first module uses a gated graph neural network (GGNN) model under the RL environment for generating novel molecular compounds with desired properties and a custom-made KG for molecule screening. The second module uses GEFA to predict binding affinity scores between the generated compounds and target proteins. Experiments show how fine-tuning the GGNN model under the RL environment enhances the molecules with desired properties to generate 100 % valid and 100 % unique compounds using different scoring functions. Additionally, KG-based screening reduces the search space of generated candidate molecules by 96.64 % while retaining 95.38 % of promising binding molecules against SARS-CoV-2 protein, i.e., 3C-like protease (3CLpro). We achieved a binding affinity score of 8.185 from the top rank of generated compound. In addition, we compared top-ranked generated compounds to Indinavir on different parameters, including drug-likeness and medicinal chemistry, for qualitative analysis from a drug development perspective. Supplementary Information: The online version contains supplementary material available at 10.1007/s13721-023-00409-2.

Analysis of the Neutralizing Activity of Antibodies Targeting Open or Closed SARS-CoV-2 Spike Protein Conformations.

SARS-CoV-2 infection elicits a polyclonal neutralizing antibody (nAb) response that primarily targets the spike protein, but it is still unclear which nAbs are immunodominant and what distinguishes them from subdominant nAbs. This information would however be crucial to predict the evolutionary trajectory of the virus and design future vaccines. To shed light on this issue, we gathered 83 structures of nAbs in complex with spike protein domains. We analyzed in silico the ability of these nAbs to bind the full spike protein trimer in open and closed conformations, and predicted the change in binding affinity of the most frequently observed spike protein variants in the circulating strains. This led us to define four nAb classes with distinct variant escape fractions. By comparing these fractions with those measured from plasma of infected patients, we showed that the class of nAbs that most contributes to the immune response is able to bind the spike protein in its closed conformation. Although this class of nAbs only partially inhibits the spike protein binding to the host's angiotensin converting enzyme 2 (ACE2), it has been suggested to lock the closed pre-fusion spike protein conformation and therefore prevent its transition to an open state. Furthermore, comparison of our predictions with mRNA-1273 vaccinated patient plasma measurements suggests that spike proteins contained in vaccines elicit a different nAb class than the one elicited by natural SARS-CoV-2 infection and suggests the design of highly stable closed-form spike proteins as next-generation vaccine immunogens.

MANORAA: A machine learning platform to guide protein-ligand design by anchors and influential distances.

The MANORAA platform uses structure-based approaches to provide information on drug design originally derived from mapping tens of thousands of amino acids on a grid. In-depth analyses of the pockets, frequently occurring atoms, influential distances, and active-site boundaries are used for the analysis of active sites. The algorithms derived provide model equations that can predict whether changes in distances, such as contraction or expansion, will result in improved binding affinity. The algorithm is confirmed using kinetic studies of dihydrofolate reductase (DHFR), together with two DHFR-TS crystal structures. Empirical analyses of 881 crystal structures involving 180 ligands are used to interpret protein-ligand binding affinities. MANORAA links to major biological databases for web-based analysis of drug design. The frequency of atoms inside the main protease structures, including those from SARS-CoV-2, shows how the rigid part of the ligand can be used as a probe for molecular design (http://manoraa.org).