Performance and robustness of small molecule retention time prediction with molecular graph neural networks in industrial drug discovery campaigns.

This study explores how machine-learning can be used to predict chromatographic retention times (RT) for the analysis of small molecules, with the objective of identifying a machine-learning framework with the robustness required to support a chemical synthesis production platform. We used internally generated data from high-throughput parallel synthesis in context of pharmaceutical drug discovery projects. We tested machine-learning models from the following frameworks: XGBoost, ChemProp, and DeepChem, using a dataset of 7552 small molecules. Our findings show that two specific models, AttentiveFP and ChemProp, performed better than XGBoost and a regular neural network in predicting RT accurately. We also assessed how well these models performed over time and found that molecular graph neural networks consistently gave accurate predictions for new chemical series. In addition, when we applied ChemProp on the publicly available METLIN SMRT dataset, it performed impressively with an average error of 38.70 s. These results highlight the efficacy of molecular graph neural networks, especially ChemProp, in diverse RT prediction scenarios, thereby enhancing the efficiency of chromatographic analysis.

Mapping of Drug-like Chemical Universe with Reduced Complexity Molecular Frameworks.

The emergence of the DNA-encoded chemical libraries (DEL) field in the past decade has attracted the attention of the pharmaceutical industry as a powerful mechanism for the discovery of novel drug-like hits for various biological targets. Nuevolution Chemetics technology enables DNA-encoded synthesis of billions of chemically diverse drug-like small molecule compounds, and the efficient screening and optimization of these, facilitating effective identification of drug candidates at an unprecedented speed and scale. Although many approaches have been developed by the cheminformatics community for the analysis and visualization of drug-like chemical space, most of them are restricted to the analysis of a maximum of a few millions of compounds and cannot handle collections of 108-1012 compounds typical for DELs. To address this big chemical data challenge, we developed the Reduced Complexity Molecular Frameworks (RCMF) methodology as an abstract and very general way of representing chemical structures. By further introducing RCMF descriptors, we constructed a global framework map of drug-like chemical space and demonstrated how chemical space occupied by multi-million-member drug-like Chemetics DNA-encoded libraries and virtual combinatorial libraries with >1012 members could be analyzed and mapped without a need for library enumeration. We further validate the approach by performing RCMF-based searches in a drug-like chemical universe and mapping Chemetics library selection outputs for LSD1 targets on a global framework chemical space map.

Proteochemometrics mapping of the interaction space for retroviral proteases and their substrates.

Understanding the complex interactions of retroviral proteases with their ligands is an important scientific challenge in efforts to achieve control of retroviral infections. Development of drug resistance because of high mutation rates and extensive polymorphisms causes major problems in treating the deadly diseases these viruses cause, and prompts efforts to identify new strategies. Here we report a comprehensive analysis of the interaction of 63 retroviral proteases from nine different viral species with their substrates and inhibitors based on publicly available data from the past 17years of retroviral research. By correlating physico-chemical descriptions of retroviral proteases and substrates to their biological activities we constructed a highly statistically valid 'proteochemometric' model for the interactome of retroviral proteases. Analysis of the model indicated amino acid positions in retroviral proteases with the highest influence on ligand activity and revealed general physicochemical properties essential for tight binding of substrates across multiple retroviral proteases. Hexapeptide inhibitors developed based on the discovered general properties effectively inhibited HIV-1 proteases in vitro, and some exhibited uniformly high inhibitory activity against all HIV-1 proteases mutants evaluated. A generalized proteochemometric model for retroviral proteases interactome has been created and analysed in this study. Our results demonstrate the feasibility of using the developed general strategy in the design of inhibitory peptides that can potentially serve as templates for drug resistance-improved HIV retardants.

Generalized proteochemometric model of multiple cytochrome p450 enzymes and their inhibitors.

Cytochrome P450 enzymes are a superfamily of heme-containing enzymes responsible for the oxidation of structurally diverse chemical compounds. Inhibition of CYP enzymes is probably the most common mechanism underlying acute drug toxicity, loss of therapeutic drug efficacy, and drug-drug interactions. The presence of polymorphic genetic variants of CYPs among the population makes it difficult to foresee undesired effects of drugs and is a common cause of drug candidate failure. Computational models that can predict early drug failures due to the inhibition of CYP isoforms can substantially reduce the cost of drug development. Although several computational models for CYP inhibition have been developed recently, all were constructed for one CYP isoform at a time, thus limiting their use for comprehensive analysis and generalizations to other CYP isoforms and polymorphisms. Here we report a novel approach based on the principles of proteochemometrics for the generalized concomitant modeling of multiple CYP isoforms and their inhibitors. We created a predictive and statistically valid proteochemometric model for CYP enzymes by combining data from a large number of publicly available reports that describe the interactions of 14 CYP enzyme subtypes and 375 structurally diverse inhibitors. Our results demonstrate that our model is capable of predicting the potential of new drug candidates to inhibit multiple CYP enzymes. Analysis of the CYP model also revealed molecular properties of CYP enzymes and xenobiotics that are important for CYP inhibition. This approach may aid in the selection of novel drug candidates that are unlikely to inhibit multiple CYP subtypes.

Proteochemometric analysis of small cyclic peptides' interaction with wild-type and chimeric melanocortin receptors.

The melanocortin (MC) system confines unique G-protein coupled receptor pathways, which include the MC(1-5) receptors and their endogenous agonists and antagonists, the MCs and the agouti and agouti-related proteins. The MC4 receptor is an important target for development of drugs for treatment of obesity and cachexia. While natural MC peptides are selective for the MC1 receptor, some cyclic pentapeptides, such as the HS-129 peptide, show high selectivity for the MC4 receptor. Here we gained insight into the mechanisms for its recognition by MC receptors. To this end we correlated the interaction data of four HS peptide analogues with four wild-type and 14 multiple chimeric MC receptors to the binary and physicochemical descriptions of the studied entities by use of partial least squares regression, which resulted in highly valid proteochemometric models. Analysis of the models revealed that the recognition sites of the HS peptides are different from the earlier proteochemometrically mapped linear MSH peptides' recognitions sites, although they overlap partially. The analysis also revealed important amino acids that explain the selectivity of the HS-129 peptide for the MC4 receptor.

Computational proteomics analysis of HIV-1 protease interactome.

HIV-1 protease is a small homodimeric enzyme that ensures maturation of HIV virions by cleaving the viral precursor Gag and Gag-Pol polyproteins into structural and functional elements. The cleavage sites in the viral polyproteins share neither sequence homology nor binding motif and the specificity of the HIV-1 protease is therefore only partially understood. Using an extensive data set collected from 16 years of HIV proteome research we have here created a general and predictive rule-based model for HIV-1 protease specificity based on rough sets. We demonstrate that HIV-1 protease specificity is much more complex than previously anticipated, which cannot be defined based solely on the amino acids at the substrate's scissile bond or by any other single substrate amino acid position only. Our results show that the combination of at least three particular amino acids is needed in the substrate for a cleavage event to occur. Only by combining and analyzing massive amounts of HIV proteome data it was possible to discover these novel and general patterns of physico-chemical substrate cleavage determinants. Our study is an example how computational biology methods can advance the understanding of the viral interactomes.

A look inside HIV resistance through retroviral protease interaction maps.

Retroviruses affect a large number of species, from fish and birds to mammals and humans, with global socioeconomic negative impacts. Here the authors report and experimentally validate a novel approach for the analysis of the molecular networks that are involved in the recognition of substrates by retroviral proteases. Using multivariate analysis of the sequence-based physiochemical descriptions of 61 retroviral proteases comprising wild-type proteases, natural mutants, and drug-resistant forms of proteases from nine different viral species in relation to their ability to cleave 299 substrates, the authors mapped the physicochemical properties and cross-dependencies of the amino acids of the proteases and their substrates, which revealed a complex molecular interaction network of substrate recognition and cleavage. The approach allowed a detailed analysis of the molecular-chemical mechanisms involved in substrate cleavage by retroviral proteases.