A Primer on 2D Descriptors in Selectivity Modeling for Asymmetric Catalysis.

Machine learning has permeated all fields of research, including chemistry, and is now an integral part of the design of novel compounds with desired properties. In the field of asymmetric catalysis, the preference still lies with models based on a physical understanding of the catalysis phenomenon and the electronic and steric properties of catalysts. However, such models require quantum chemical calculations and are thus limited by their computational cost. Here, we highlight the recent advances in modeling catalyst selectivity by using the 2D structures of catalysts and substrates. While these have a less explicit mechanistic connection to the modeled property, 2D descriptors, such as topological indices, molecular fingerprints, and fragments, offer the tremendous advantages of low cost and high speed of calculations. This makes them optimal for the in-silico screening of large amounts of data. We provide an overview of common quantitative structure-property relationship workflow, model building and validation techniques, applications of these methodologies in asymmetric catalysis design, and an outlook on improving the understanding of 2D-based models.

Multi-Instance Learning Approach to the Modeling of Enantioselectivity of Conformationally Flexible Organic Catalysts.

Computational design of chiral organic catalysts for asymmetric synthesis is a promising technology that can significantly reduce the material and human resources required for the preparation of enantiopure compounds. Herein, for the modeling of catalysts' enantioselectivity, we propose to use the multi-instance learning approach accounting for multiple catalyst conformers and requiring neither conformer selection nor their spatial alignment. A catalyst was represented by an ensemble of conformers, each encoded by three-dimesinonal (3D) pmapper descriptors. A catalyzed reactant transformation was converted into a single molecular graph, a condensed graph of reaction, encoded by 2D fragment descriptors. A whole chemical reaction was finally encoded by concatenated 3D catalyst and 2D transformation descriptors. The performance of the proposed method was demonstrated in the modeling of the enantioselectivity of homogeneous and phase-transfer reactions and compared with the state-of-the-art approaches.

Predicting Highly Enantioselective Catalysts Using Tunable Fragment Descriptors.

Catalyst optimization processes typically rely on inductive and qualitative assumptions of chemists based on screening data. While machine learning models using molecular properties or calculated 3D structures enable quantitative data evaluation, costly quantum chemical calculations are often required. In contrast, readily available binary fingerprint descriptors are time- and cost-efficient, but their predictive performance remains insufficient. Here, we describe a machine learning model based on fragment descriptors, which are fine-tuned for asymmetric catalysis and represent cyclic or polyaromatic hydrocarbons, enabling robust and efficient virtual screening. Using training data with only moderate selectivities, we designed theoretically and validated experimentally new catalysts showing higher selectivities in a challenging asymmetric tetrahydropyran synthesis.

CGRdb2.0: A Python Database Management System for Molecules, Reactions, and Chemical Data.

This work introduces CGRdb2.0─an open-source database management system for molecules, reactions, and chemical data. CGRdb2.0 is a Python package connecting to a PostgreSQL database that enables native searches for molecules and reactions without complicated SQL syntax. The library provides out-of-the-box implementations for similarity and substructure searches for molecules, as well as similarity and substructure searches for reactions in two ways─based on reaction components and based on the Condensed Graph of Reaction approach, the latter significantly accelerating the performance. In benchmarking studies with the RDKit database cartridge, we demonstrate that CGRdb2.0 performs searches faster for smaller data sets, while allowing for interactive access to the retrieved data.

Atom-to-atom Mapping: A Benchmarking Study of Popular Mapping Algorithms and Consensus Strategies.

In this paper, we compare the most popular Atom-to-Atom Mapping (AAM) tools: ChemAxon,[1] Indigo,[2] RDTool,[3] NameRXN (NextMove),[4] and RXNMapper[5] which implement different AAM algorithms. An open-source RDTool program was optimized, and its modified version ("new RDTool") was considered together with several consensus mapping strategies. The Condensed Graph of Reaction approach was used to calculate chemical distances and develop the "AAM fixer" algorithm for an automatized correction of erroneous mapping. The benchmarking calculations were performed on a Golden dataset containing 1851 manually mapped and curated reactions. The best performing RXNMapper program together with the AMM Fixer was applied to map the USPTO database. The Golden dataset, mapped USPTO and optimized RDTool are available in the GitHub repository https://github.com/Laboratoire-de-Chemoinformatique.

Reaction Data Curation I: Chemical Structures and Transformations Standardization.

The quality of experimental data for chemical reactions is a critical consideration for any reaction-driven study. However, the curation of reaction data has not been extensively discussed in the literature so far. Here, we suggest a 4 steps protocol that includes the curation of individual structures (reactants and products), chemical transformations, reaction conditions and endpoints. Its implementation in Python3 using CGRTools toolkit has been used to clean three popular reaction databases Reaxys, USPTO and Pistachio. The curated USPTO database is available in the GitHub repository (Laboratoire-de-Chemoinformatique/Reaction_Data_Cleaning).

Discovery of novel chemical reactions by deep generative recurrent neural network.

The "creativity" of Artificial Intelligence (AI) in terms of generating de novo molecular structures opened a novel paradigm in compound design, weaknesses (stability & feasibility issues of such structures) notwithstanding. Here we show that "creative" AI may be as successfully taught to enumerate novel chemical reactions that are stoichiometrically coherent. Furthermore, when coupled to reaction space cartography, de novo reaction design may be focused on the desired reaction class. A sequence-to-sequence autoencoder with bidirectional Long Short-Term Memory layers was trained on on-purpose developed "SMILES/CGR" strings, encoding reactions of the USPTO database. The autoencoder latent space was visualized on a generative topographic map. Novel latent space points were sampled around a map area populated by Suzuki reactions and decoded to corresponding reactions. These can be critically analyzed by the expert, cleaned of irrelevant functional groups and eventually experimentally attempted, herewith enlarging the synthetic purpose of popular synthetic pathways.

Combined Graph/Relational Database Management System for Calculated Chemical Reaction Pathway Data.

Presently, quantum chemical calculations are widely used to generate extensive data sets for machine learning applications; however, generally, these sets only include information on equilibrium structures and some close conformers. Exploration of potential energy surfaces provides important information on ground and transition states, but analysis of such data is complicated due to the number of possible reaction pathways. Here, we present RePathDB, a database system for managing 3D structural data for both ground and transition states resulting from quantum chemical calculations. Our tool allows one to store, assemble, and analyze reaction pathway data. It combines relational database CGR DB for handling compounds and reactions as molecular graphs with a graph database architecture for pathway analysis by graph algorithms. Original condensed graph of reaction technology is used to store any chemical reaction as a single graph.

Predicting Synergism of Cancer Drug Combinations Using NCI-ALMANAC Data.

Drug combinations are of great interest for cancer treatment. Unfortunately, the discovery of synergistic combinations by purely experimental means is only feasible on small sets of drugs. In silico modeling methods can substantially widen this search by providing tools able to predict which of all possible combinations in a large compound library are synergistic. Here we investigate to which extent drug combination synergy can be predicted by exploiting the largest available dataset to date (NCI-ALMANAC, with over 290,000 synergy determinations). Each cell line is modeled using primarily two machine learning techniques, Random Forest (RF) and Extreme Gradient Boosting (XGBoost), on the datasets provided by NCI-ALMANAC. This large-scale predictive modeling study comprises more than 5,000 pair-wise drug combinations, 60 cell lines, 4 types of models, and 5 types of chemical features. The application of a powerful, yet uncommonly used, RF-specific technique for reliability prediction is also investigated. The evaluation of these models shows that it is possible to predict the synergy of unseen drug combinations with high accuracy (Pearson correlations between 0.43 and 0.86 depending on the considered cell line, with XGBoost providing slightly better predictions than RF). We have also found that restricting to the most reliable synergy predictions results in at least 2-fold error decrease with respect to employing the best learning algorithm without any reliability estimation. Alkylating agents, tyrosine kinase inhibitors and topoisomerase inhibitors are the drugs whose synergy with other partner drugs are better predicted by the models. Despite its leading size, NCI-ALMANAC comprises an extremely small part of all conceivable combinations. Given their accuracy and reliability estimation, the developed models should drastically reduce the number of required in vitro tests by predicting in silico which of the considered combinations are likely to be synergistic.

Classical scoring functions for docking are unable to exploit large volumes of structural and interaction data.

MOTIVATION: Studies have shown that the accuracy of random forest (RF)-based scoring functions (SFs), such as RF-Score-v3, increases with more training samples, whereas that of classical SFs, such as X-Score, does not. Nevertheless, the impact of the similarity between training and test samples on this matter has not been studied in a systematic manner. It is therefore unclear how these SFs would perform when only trained on protein-ligand complexes that are highly dissimilar or highly similar to the test set. It is also unclear whether SFs based on machine learning algorithms other than RF can also improve accuracy with increasing training set size and to what extent they learn from dissimilar or similar training complexes. RESULTS: We present a systematic study to investigate how the accuracy of classical and machine-learning SFs varies with protein-ligand complex similarities between training and test sets. We considered three types of similarity metrics, based on the comparison of either protein structures, protein sequences or ligand structures. Regardless of the similarity metric, we found that incorporating a larger proportion of similar complexes to the training set did not make classical SFs more accurate. In contrast, RF-Score-v3 was able to outperform X-Score even when trained on just 32% of the most dissimilar complexes, showing that its superior performance owes considerably to learning from dissimilar training complexes to those in the test set. In addition, we generated the first SF employing Extreme Gradient Boosting (XGBoost), XGB-Score, and observed that it also improves with training set size while outperforming the rest of SFs. Given the continuous growth of training datasets, the development of machine-learning SFs has become very appealing. AVAILABILITY AND IMPLEMENTATION: https://github.com/HongjianLi/MLSF. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

AntiMalarial Mode of Action (AMMA) Database: Data Selection, Verification and Chemical Space Analysis.

This paper presents the effort of collecting and curating a data set of 15461 molecules tested against the malaria parasite, with robust activity and mode of action annotations. The set is compiled from in-house experimental data and the public ChEMBL database subsets. We illustrate the usefulness of the dataset by building QSAR models for antimalarial activity and QSPR models for modes of actions, as well as by the analysis of the chemical space with the Generative Topographic Mapping method. The GTM models perform well in prediction of both activity and mode of actions, on par with the classical SVM methods. The visualization of obtained maps helps to understand the distribution of molecules corresponding to different modes of action: molecules with similar targets are located close to each other on the map. Therefore, this analysis may suggest new modes of action for non-annotated or even annotated compounds. In perspective, this can be used as a tool for prediction of both antimalarial activity and target for novel, untested compounds.

QSAR modeling and chemical space analysis of antimalarial compounds.

Generative topographic mapping (GTM) has been used to visualize and analyze the chemical space of antimalarial compounds as well as to build predictive models linking structure of molecules with their antimalarial activity. For this, a database, including ~3000 molecules tested in one or several of 17 anti-Plasmodium activity assessment protocols, has been compiled by assembling experimental data from in-house and ChEMBL databases. GTM classification models built on subsets corresponding to individual bioassays perform similarly to the earlier reported SVM models. Zones preferentially populated by active and inactive molecules, respectively, clearly emerge in the class landscapes supported by the GTM model. Their analysis resulted in identification of privileged structural motifs of potential antimalarial compounds. Projection of marketed antimalarial drugs on this map allowed us to delineate several areas in the chemical space corresponding to different mechanisms of antimalarial activity. This helped us to make a suggestion about the mode of action of the molecules populating these zones.

Redox Polypharmacology as an Emerging Strategy to Combat Malarial Parasites.

3-Benzylmenadiones are potent antimalarial agents that are thought to act through their 3-benzoylmenadione metabolites as redox cyclers of two essential targets: the NADPH-dependent glutathione reductases (GRs) of Plasmodium-parasitized erythrocytes and methemoglobin. Their physicochemical properties were characterized in a coupled assay using both targets and modeled with QSPR predictive tools built in house. The substitution pattern of the west/east aromatic parts that controls the oxidant character of the electrophore was highlighted and accurately predicted by QSPR models. The effects centered on the benz(o)yl chain, induced by drug bioactivation, markedly influenced the oxidant character of the reduced species through a large anodic shift of the redox potentials that correlated with the redox cycling of both targets in the coupled assay. Our approach demonstrates that the antimalarial activity of 3-benz(o)ylmenadiones results from a subtle interplay between bioactivation, fine-tuned redox properties, and interactions with crucial targets of P. falciparum. Plasmodione and its analogues give emphasis to redox polypharmacology, which constitutes an innovative approach to antimalarial therapy.

Mappability of drug-like space: towards a polypharmacologically competent map of drug-relevant compounds.

Intuitive, visual rendering--mapping--of high-dimensional chemical spaces (CS), is an important topic in chemoinformatics. Such maps were so far dedicated to specific compound collections--either limited series of known activities, or large, even exhaustive enumerations of molecules, but without associated property data. Typically, they were challenged to answer some classification problem with respect to those same molecules, admired for their aesthetical virtues and then forgotten--because they were set-specific constructs. This work wishes to address the question whether a general, compound set-independent map can be generated, and the claim of "universality" quantitatively justified, with respect to all the structure-activity information available so far--or, more realistically, an exploitable but significant fraction thereof. The "universal" CS map is expected to project molecules from the initial CS into a lower-dimensional space that is neighborhood behavior-compliant with respect to a large panel of ligand properties. Such map should be able to discriminate actives from inactives, or even support quantitative neighborhood-based, parameter-free property prediction (regression) models, for a wide panel of targets and target families. It should be polypharmacologically competent, without requiring any target-specific parameter fitting. This work describes an evolutionary growth procedure of such maps, based on generative topographic mapping, followed by the validation of their polypharmacological competence. Validation was achieved with respect to a maximum of exploitable structure-activity information, covering all of Homo sapiens proteins of the ChEMBL database, antiparasitic and antiviral data, etc. Five evolved maps satisfactorily solved hundreds of activity-based ligand classification challenges for targets, and even in vivo properties independent from training data. They also stood chemogenomics-related challenges, as cumulated responsibility vectors obtained by mapping of target-specific ligand collections were shown to represent validated target descriptors, complying with currently accepted target classification in biology. Therefore, they represent, in our opinion, a robust and well documented answer to the key question "What is a good CS map?"

Electrochemical properties of substituted 2-methyl-1,4-naphthoquinones: redox behavior predictions.

In the context of the investigation of drug-induced oxidative stress in parasitic cells, electrochemical properties of a focused library of polysubstituted menadione derivatives were studied by cyclic voltammetry. These values were used, together with compatible measurements from literature (quinones and related compounds), to build and evaluate a predictive structure-redox potential model (quantitative structure-property relationship, QSPR). Able to provide an online evaluation (through Web interface) of the oxidant character of quinones, the model is aimed to help chemists targeting their synthetic efforts towards analogues of desired redox properties.

Probiotics restore bowel flora and improve liver enzymes in human alcohol-induced liver injury: a pilot study.

The effects of chronic alcohol consumption on the bowel flora and the potential therapeutic role of probiotics in alcohol-induced liver injury have not previously been evaluated. In this study, 66 adult Russian males admitted to a psychiatric hospital with a diagnosis of alcoholic psychosis were enrolled in a prospective, randomized, clinical trial to study the effects of alcohol and probiotics on the bowel flora and alcohol-induced liver injury. Patients were randomized to receive 5 days of Bifidobacterium bifidum and Lactobacillus plantarum 8PA3 versus standard therapy alone (abstinence plus vitamins). Stool cultures and liver enzymes were performed at baseline and again after therapy. Results were compared between groups and with 24 healthy, matched controls who did not consume alcohol. Compared to healthy controls, alcoholic patients had significantly reduced numbers of bifidobacteria (6.3 vs. 7.5 log colony-forming unit [CFU]/g), lactobacilli (3.15 vs. 4.59 log CFU/g), and enterococci (4.43 vs. 5.5 log CFU/g). The mean baseline alanine aminotransferase (ALT), aspartate aminotransferase (AST), and gamma-glutamyl transpeptidase (GGT) activities were significantly elevated in the alcoholic group compared to the healthy control group (AST: 104.1 vs. 29.15 U/L; ALT: 50.49 vs. 22.96 U/L; GGT 161.5 vs. 51.88 U/L), indicating that these patients did have mild alcohol-induced liver injury. After 5 days of probiotic therapy, alcoholic patients had significantly increased numbers of both bifidobacteria (7.9 vs. 6.81 log CFU/g) and lactobacilli (4.2 vs. 3.2 log CFU/g) compared to the standard therapy arm. Despite similar values at study initiation, patients treated with probiotics had significantly lower AST and ALT activity at the end of treatment than those treated with standard therapy alone (AST: 54.67 vs. 76.43 U/L; ALT 36.69 vs. 51.26 U/L). In a subgroup of 26 subjects with well-characterized mild alcoholic hepatitis (defined as AST and ALT greater than 30 U/L with AST-to-ALT ratio greater than one), probiotic therapy was associated with a significant end of treatment reduction in ALT, AST, GGT, lactate dehydrogenase, and total bilirubin. In this subgroup, there was a significant end of treatment mean ALT reduction in the probiotic arm versus the standard therapy arm. In conclusion, patients with alcohol-induced liver injury have altered bowel flora compared to healthy controls. Short-term oral supplementation with B. bifidum and L. plantarum 8PA3 was associated with restoration of the bowel flora and greater improvement in alcohol-induced liver injury than standard therapy alone.

Alcohol expectancies in relation to personality and aggression among juvenile delinquents in Northern Russia.

The relationships between alcohol expectancies, level of alcohol use, alcohol-related problems, aggression, and personality factors in 198 Russian male juvenile delinquents were assessed. A clustering procedure was used in order to establish main patterns of alcohol expectancies, yielding three major clusters. Level of alcohol use, alcohol-related problems, aggression, and personality factors were compared across the identified clusters. It was established that juvenile delinquents with a high level of positive alcohol expectancies and aggression represented a risk-group for higher involvement in drinking behavior as well as problem drinking, which in turn are related to specific personality traits. Implications of these findings for alcohol prevention among the youth are discussed.

Alcohol abuse in Russian delinquent adolescents. Associations with comorbid psychopathology, personality and parenting.

INTRODUCTION: Adolescent delinquency and alcohol abuse have become a growing concern in Russia. Psychopathology, a dysfunctional family and specific personality factors have all been linked to addictive and antisocial behavior. Since delinquent youth represent a specific risk group, where alcohol misuse tends to be more pronounced than in the general population, the objectives of this study were: 1) to compare differences in personality and parenting factors, and in psychopathology in juvenile delinquents with and without alcohol abuse; and 2) to evaluate the associations between alcohol abuse, personality and parenting factors, after controlling for comorbid psychopathology. METHODS: Psychopathology, including alcohol abuse, was assessed by means of a psychiatric interview in 229 Russian incarcerated male juvenile delinquents. In addition, alcohol use, personality, and parenting factors were assessed by self-reports. RESULTS: Alcohol-abusing delinquents (n=138) scored significantly higher on novelty seeking and maternal emotional warmth and reported higher levels of psychopathology, as compared to nonalcohol-abusing delinquents (n=91). Logistic regression analysis demonstrated that personality and parenting factors were significantly related to alcohol abuse, even after controlling for comorbid psychopathology. CONCLUSION: Alcohol-abusing delinquents are at risk for a wide spectrum of psychiatric disorders. Alcohol abuse is associated with personality and parenting factors independently of comorbid psychopathology. Early interventions with high-risk youths may help to reduce their psychiatric problems and alcohol abuse.

Alcohol use in adolescents from northern Russia: the role of the social context.

Drinking alcohol is an essential and commonplace part of life in Russia. Alcohol-related problems in the general population and among adolescents in particular has become a major public health concern. The problem cannot be solely explained by the frequency and quantity of alcohol consumption. The social determinants of drinking alcohol also need to be considered. These are the focus of the present investigation. The social determinants of drinking behaviour were assessed by self-reports (Social Context of Drinking Scale, Adolescent Alcohol Involvement Scale and Rutgers Alcohol Problem Index) in 387 secondary school students in Arkhangelsk, Russia. The factor structure for the Social Context of Drinking Scale was similar to that noted in respect of the original study [Thombs and Beck (1994) Health Education and Research 9, 13-22]. Significant gender differences in problem drinking and the social contexts of drinking were found. High intensity girl drinkers were likely to drink in most social contexts, whereas high intensity drinking boys were more likely to drink in the context of Stress Control. Furthermore, boy problem drinkers were more likely to drink in the context of School Defiance and Peer Acceptance, whereas girl problem drinkers tended to drink in the contexts of School Defiance and Stress Control. In general, the Social Context of Drinking Scale demonstrated a good ability to discriminate high from low intensity drinkers, and high from low problem drinkers. These results may provide useful information for targeted prevention programmes for adolescents.