Molecular Informatics最新文献

This paper reviews the application of machine learning to the inhibition of corrosion by organic molecules. The methodologies considered include quantitative structure-property relationships (QSPR) and related data-driven approaches. The characteristic features of their key components are considered as applied to corrosion inhibition, including datasets, response properties, molecular descriptors, machine learning methods, and structure-property models. It is shown that the most important factors determining their choice and application features are: (1) the small or very small size of datasets, (2) the mechanism of corrosion inhibition associated with the adsorption of inhibitor molecules on the metal surface, and (3) multifactorial conditioning and noisiness of response property. On this basis, the application of machine learning to the inhibition of corrosion of materials based on iron, aluminum, and magnesium is considered. The main trends in the development of QSPR and related data-driven modeling of corrosion inhibition are discussed, the shortcomings and common errors are considered, and the prospects for their further development are outlined.

ADME (Absorption, Distribution, Metabolism, Excretion) properties are key parameters to judge whether a drug candidate exhibits a desired pharmacokinetic (PK) profile. In this study, we tested multi-task machine learning (ML) models to predict ADME and animal PK endpoints trained on in-house data generated at Boehringer Ingelheim. Models were evaluated both at the design stage of a compound (i. e., no experimental data of test compounds available) and at testing stage when a particular assay would be conducted (i. e., experimental data of earlier conducted assays may be available). Using realistic time-splits, we found a clear benefit in performance of multi-task graph-based neural network models over single-task model, which was even stronger when experimental data of earlier assays is available. In an attempt to explain the success of multi-task models, we found that especially endpoints with the largest numbers of data points (physicochemical endpoints, clearance in microsomes) are responsible for increased predictivity in more complex ADME and PK endpoints. In summary, our study provides insight into how data for multiple ADME/PK endpoints in a pharmaceutical company can be best leveraged to optimize predictivity of ML models.

FFA4 has gained interest in recent years since its deorphanization in 2005 and the characterization of the Free Fatty Acids receptors family for their therapeutic potential in metabolic disorders. The expression of FFA4 (also known as GPR120) in numerous organs throughout the human body makes this receptor a highly potent target, particularly in fat sensing and diet preference. This offers an attractive approach to tackle obesity and related metabolic diseases. Recent cryo-EM structures of the receptor have provided valuable information for a potential active state although the previous studies of FFA4 presented diverging information. We performed molecular docking and molecular dynamics simulations of four agonist ligands, TUG-891, Linoleic acid, α-Linolenic acid, and Oleic acid, based on a homology model. Our simulations, which accumulated a total of 2 μs of simulation, highlighted two binding hotspots at Arg99^2.64 and Lys293 (ECL3). The results indicate that the residues are located in separate areas of the binding pocket and interact with various types of ligands, implying different potential active states of FFA4 and a highly adaptable binding intra-receptor pocket. This article proposes additional structural characteristics and mechanisms for agonist binding that complement the experimental structures.

Sulphotransferases (SULTs) are a major phase II metabolic enzyme class contributing ~20 % to the Phase II metabolism of FDA-approved drugs. Ignoring the potential for SULT-mediated metabolism leaves a strong potential for drug-drug interactions, often causing late-stage drug discovery failures or black-boxed warnings on FDA labels. The existing models use only accessibility descriptors and machine learning (ML) methods for class and site of sulfonation (SOS) predictions for SULT. In this study, a variety of accessibility, reactivity, and hybrid models and algorithms have been developed to make accurate substrate and SOS predictions. Unlike the literature models, reactivity parameters for the aliphatic or aromatic hydroxyl groups (R/Ar-O-H), the Bond Dissociation Energy (BDE) gave accurate models with a True Positive Rate (TPR)=0.84 for SOS predictions. We offer mechanistic insights to explain these novel findings that are not recognized in the literature. The accessibility parameters like the ratio of Chemgauss4 Score (CGS) and Molecular Weight (MW) CGS/MW and distance from cofactor (Dis) were essential for class predictions and showed TPR=0.72. Substrates consistently had lower BDE, Dis, and CGS/MW than non-substrates. Hybrid models also performed acceptablely for SOS predictions. Using the best models, Algorithms gave an acceptable performance in class prediction: TPR=0.62, False Positive Rate (FPR)=0.24, Balanced accuracy (BA)=0.69, and SOS prediction: TPR=0.98, FPR=0.60, and BA=0.69. A rule-based method was added to improve the predictive performance, which improved the algorithm TPR, FPR, and BA. Validation using an external dataset of drug-like compounds gave class prediction: TPR=0.67, FPR=0.00, and SOS prediction: TPR=0.80 and FPR=0.44 for the best Algorithm. Comparisons with standard ML models also show that our algorithm shows higher predictive performance for classification on external datasets. Overall, these models and algorithms (SOS predictor) give accurate substrate class and site (SOS) predictions for SULT-mediated Phase II metabolism and will be valuable to the drug discovery community in academia and industry. The SOS predictor is freely available for academic/non-profit research via the GitHub link.

Natural products have long been an important source of inspiration for medicinal chemistry and drug discovery. In the cosmetic field, they remain the major elements of the composition and serve as marketing asset. Recent research showed the implication of salt-inducible kinases on the melanin production in skin via MITF regulation. Finding new potent modulators on such target could open the way to several cosmetic applications to attenuate visible signs of photoaging and improve the tan without sun. Since virtual screening can be a powerful tool for detecting hit compounds in the early stages of a drug discovery process, we applied this method on salt-inducible kinase 2 to discover potential interesting compounds. Here, we present the different steps from the construction of a database of natural products, to the validation of a docking protocol and the results of the virtual screening. Hits from the screening were tested in vitro to confirm their efficiency and results are discussed.

The insulin superfamily proteins (ISPs), in particular, insulin, IGFs and relaxin proteins are key modulators of animal physiology. They are known to have evolved from the same ancestral gene and have diverged into proteins with varied sequences and distinct functions, but maintain a similar structural architecture stabilized by highly conserved disulphide bridges. The recent surge of sequence data and the structures of these proteins prompted a need for a comprehensive analysis, which connects the evolution of these sequences (427 sequences) in the light of available functional and structural information including representative complex structures of ISPs with their cognate receptors. This study reveals (a) unusually high sequence conservation of IGFs (>90 % conservation in 184 sequences) and provides a possible structure-based rationale for such high sequence conservation; (b) provides an updated definition of the receptor-binding signature motif of the functionally diverse relaxin family members (c) provides a probable non-canonical C-peptide cleavage site in a few insulin sequences. The high conservation of IGFs appears to represent a classic case of resistance to sequence diversity exerted by physiologically important interactions with multiple partners. We also propose a probable mechanism for C-peptide cleavage in a few distinct insulin sequences and redefine the receptor-binding signature motif of the relaxin family. Lastly, we provide a basis for minimally modified insulin mutants with potential therapeutic application, inspired by concomitant changes observed in other insulin superfamily protein members supported by molecular dynamics simulation.

The assessment of compound blood-brain barrier (BBB) permeability poses a significant challenge in the discovery of drugs targeting the central nervous system. Conventional experimental approaches to measure BBB permeability are labor-intensive, cost-ineffective, and time-consuming. In this study, we constructed six machine learning classification models by combining various machine learning algorithms and molecular representations. The model based on ExtraTree algorithm and random partitioning strategy obtains the best prediction result, with AUC value of 0.932±0.004 and balanced accuracy (BA) of 0.837±0.010 for the test set. We employed the SHAP method to identify important features associated with BBB permeability. In addition, matched molecular pair (MMP) analysis and representative substructure derivation method were utilized to uncover the transformation rules and distinctive structural features of BBB permeable compounds. The machine learning models proposed in this work can serve as an effective tool for assessing BBB permeability in the drug discovery for central nervous system disease.