QSAR Modeling Based on Conformation Ensembles Using a Multi-Instance Learning Approach.

Modern QSAR approaches have wide practical applications in drug discovery for designing potentially bioactive molecules. If such models are based on the use of 2D descriptors, important information contained in the spatial structures of molecules is lost. The major problem in constructing models using 3D descriptors is the choice of a putative bioactive conformation, which affects the predictive performance. The multi-instance (MI) learning approach considering multiple conformations in model training could be a reasonable solution to the above problem. In this study, we implemented several multi-instance algorithms, both conventional and based on deep learning, and investigated their performance. We compared the performance of MI-QSAR models with those based on the classical single-instance QSAR (SI-QSAR) approach in which each molecule is encoded by either 2D descriptors computed for the corresponding molecular graph or 3D descriptors issued for a single lowest energy conformation. The calculations were carried out on 175 data sets extracted from the ChEMBL23 database. It is demonstrated that (i) MI-QSAR outperforms SI-QSAR in numerous cases and (ii) MI algorithms can automatically identify plausible bioactive conformations.

Prediction of Optimal Conditions of Hydrogenation Reaction Using the Likelihood Ranking Approach.

The selection of experimental conditions leading to a reasonable yield is an important and essential element for the automated development of a synthesis plan and the subsequent synthesis of the target compound. The classical QSPR approach, requiring one-to-one correspondence between chemical structure and a target property, can be used for optimal reaction conditions prediction only on a limited scale when only one condition component (e.g., catalyst or solvent) is considered. However, a particular reaction can proceed under several different conditions. In this paper, we describe the Likelihood Ranking Model representing an artificial neural network that outputs a list of different conditions ranked according to their suitability to a given chemical transformation. Benchmarking calculations demonstrated that our model outperformed some popular approaches to the theoretical assessment of reaction conditions, such as k Nearest Neighbors, and a recurrent artificial neural network performance prediction of condition components (reagents, solvents, catalysts, and temperature). The ability of the Likelihood Ranking model trained on a hydrogenation reactions dataset, (~42,000 reactions) from Reaxys® database, to propose conditions that led to the desired product was validated experimentally on a set of three reactions with rich selectivity issues.

Comprehensive Analysis of Applicability Domains of QSPR Models for Chemical Reactions.

Nowadays, the problem of the model's applicability domain (AD) definition is an active research topic in chemoinformatics. Although many various AD definitions for the models predicting properties of molecules (Quantitative Structure-Activity/Property Relationship (QSAR/QSPR) models) were described in the literature, no one for chemical reactions (Quantitative Reaction-Property Relationships (QRPR)) has been reported to date. The point is that a chemical reaction is a much more complex object than an individual molecule, and its yield, thermodynamic and kinetic characteristics depend not only on the structures of reactants and products but also on experimental conditions. The QRPR models' performance largely depends on the way that chemical transformation is encoded. In this study, various AD definition methods extensively used in QSAR/QSPR studies of individual molecules, as well as several novel approaches suggested in this work for reactions, were benchmarked on several reaction datasets. The ability to exclude wrong reaction types, increase coverage, improve the model performance and detect Y-outliers were tested. As a result, several "best" AD definitions for the QRPR models predicting reaction characteristics have been revealed and tested on a previously published external dataset with a clear AD definition problem.

Probabilistic Approach for Virtual Screening Based on Multiple Pharmacophores.

Pharmacophore modeling is usually considered as a special type of virtual screening without probabilistic nature. Correspondence of at least one conformation of a molecule to pharmacophore is considered as evidence of its bioactivity. We show that pharmacophores can be treated as one-class machine learning models, and the probability the reflecting model's confidence can be assigned to a pharmacophore on the basis of their precision of active compounds identification on a calibration set. Two schemes (Max and Mean) of probability calculation for consensus prediction based on individual pharmacophore models were proposed. Both approaches to some extent correspond to commonly used consensus approaches like the common hit approach or the one based on a logical OR operation uniting hit lists of individual models. Unlike some known approaches, the proposed ones can rank compounds retrieved by multiple models. These approaches were benchmarked on multiple ChEMBL datasets used for ligand-based pharmacophore modeling and externally validated on corresponding DUD-E datasets. The influence of complexity of pharmacophores and their performance on a calibration set on results of virtual screening was analyzed. It was shown that Max and Mean approaches have superior early enrichment to the commonly used approaches. Thus, a well-performing, easy-to-implement, and probabilistic alternative to existing approaches for pharmacophore-based virtual screening was proposed.

CGRtools: Python Library for Molecule, Reaction, and Condensed Graph of Reaction Processing.

CGRtools is an open-source Python library aimed to handle molecular and reaction information. It is the sole library developed so far which can process condensed graph of reaction (CGR) handling. CGR provides the possibility for advanced operations with reaction information and could be used for reaction descriptor calculation, structure-reactivity modeling, atom-to-atom mapping comparison and correction, reaction center extraction, reaction balancing, and some other related tasks. Unlike other popular libraries, CGRtools is fully written in Python with minor dependencies on other libraries and cross-platform. Reaction, molecule, and CGR objects in CGRtools support native Python methods and are comparable with the help of operations "equal to", "less than", and "bigger than". CGRtools supports common structural formats. CGRtools is distributed via an L-GPL license and available on https://github.com/cimm-kzn/CGRtools .

Conjugated Quantitative Structure-Property Relationship Models: Application to Simultaneous Prediction of Tautomeric Equilibrium Constants and Acidity of Molecules.

Here, we describe a concept of conjugated models for several properties (activities) linked by a strict mathematical relationship. This relationship can be directly integrated analytically into the ridge regression (RR) algorithm or accounted for in a special case of "twin" neural networks (NN). Developed approaches were applied to the modeling of the logarithm of the prototropic tautomeric constant (logKT) which can be expressed as the difference between the acidity constants (pKa) of two related tautomers. Both conjugated and individual RR and NN models for logKT and pKa were developed. The modeling set included 639 tautomeric constants and 2371 acidity constants of organic molecules in various solvents. A descriptor vector for each reaction resulted from the concatenation of structural descriptors and some parameters for reaction conditions. For the former, atom-centered substructural fragments describing acid sites in tautomer molecules were used. The latter were automatically identified using the condensed graph of reaction approach. Conjugated models performed similarly to the best individual models for logKT and pKa. At the same time, the physically grounded relationship between logKT and pKa was respected only for conjugated but not individual models.

Hydration of copper(II) amino acids complexes.

Hydration of the copper(II) bis-complexes with glycine, serine, lysine, and aspartic acid was studied by DFT and MD simulation methods. The distances between copper(II) and water molecules in the 1st and 2nd coordination shells, the average number of water molecules and their mean residence times in the hydration shells were calculated. Good agreement was observed between the values obtained and those found by DFT and NMR relaxation methods. Influence of the functional groups of the ligands and the cis-trans isomerism of the complexes on the structural and dynamical parameters of the hydration shells was displayed and explained. Analysis of the MD trajectories reveals the competition for a copper(II) axial position between water molecules or water molecules and the functional chain groups of the ligands and confirms the suggestion on the pentacoordination of copper(II) in such complexes. MD simulations show that only one axial position of Cu(II) is basically occupied at each time step while in average the coordination number more than 5 is observed. © 2017 Wiley Periodicals, Inc.

Automatized Assessment of Protective Group Reactivity: A Step Toward Big Reaction Data Analysis.

We report a new method to assess protective groups (PGs) reactivity as a function of reaction conditions (catalyst, solvent) using raw reaction data. It is based on an intuitive similarity principle for chemical reactions: similar reactions proceed under similar conditions. Technically, reaction similarity can be assessed using the Condensed Graph of Reaction (CGR) approach representing an ensemble of reactants and products as a single molecular graph, i.e., as a pseudomolecule for which molecular descriptors or fingerprints can be calculated. CGR-based in-house tools were used to process data for 142,111 catalytic hydrogenation reactions extracted from the Reaxys database. Our results reveal some contradictions with famous Greene's Reactivity Charts based on manual expert analysis. Models developed in this study show high accuracy (ca. 90%) for predicting optimal experimental conditions of protective group deprotection.

The nature of the interaction of dimethylselenide with IIIA group element compounds.

The first systematic theoretical study of the nature of intermolecular bonding of dimethylselenide as donor and IIIA group element halides as acceptors was made with the help of the approach of Quantum Theory of Atoms in Molecules. Density Functional Theory with "old" Sapporo triple-ζ basis sets was used to calculate geometry, thermodynamics, and wave function of Me2Se···AX3 complexes. The analysis of the electron density distribution and the Laplacian of the electron density allowed us to reveal and explain the tendencies in the influence of the central atom (A = B, Al, Ga, In) and halogen (X = F, Cl, Br, I) on the nature of Se···A bonding. Significant changes in properties of the selenium lone pair upon complexation were described by means of the analysis of the Laplacian of the charge density. Charge transfer characteristics and the contributions to it from electron localization and delocalization were analyzed in terms of localization and delocalization indexes. Common features of the complexation and differences in the nature of bonding were revealed. Performed analysis evidenced that gallium and indium halide complexes can be attributed to charge transfer-driven complexes; aluminum halides complexes seem to be mainly of an electrostatic nature. The nature of bonding in different boron halides essentially varies; these complexes are stabilized mainly by covalent Se···B interaction. In all the complexes under study covalence of the Se···A interaction is rather high.

Efficient design of peptide-binding polymers using active learning approaches.

Active learning (AL) has become a subject of active recent research both in industry and academia as an efficient approach for rapid design and discovery of novel chemicals, materials, and polymers. Herein, we have assessed the applicability of AL for the discovery of polymeric micelle formulations for poorly soluble drugs. We were motivated by the key advantages of this approach making it a desirable strategy for rational design of drug delivery systems due toto its ability to (i) employ relatively small datasets for model development, (ii) iterate between model development and model assessment using small external datasets that can be either generated in focused experimental studies or formed from subsets of the initial training data, and (iii) progressively evolve models towards increasingly more reliable predictions and the identification of novel chemicals with the desired properties. In this study, we compared various AL protocols for their effectiveness in finding biologically active molecules using synthetic datasets. We have investigated the dependency of AL performance on the size of the initial training set, the relative complexity of the task, and the choice of the initial training dataset. We found that AL techniques as applied to regression modeling offer no benefits over random search, while AL used for classification tasks performs better than models built for randomly selected training sets but still quite far from perfect. Using the best performing AL protocol,. Finally, the best performing AL approach was employed to discover and experimentally validate novel binding polymers for a case study of asialoglycoprotein receptor (ASGPR).

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.

The nature of the interaction of organoselenium molecules with diiodine.

The electronic structure of charge-transfer complexes of organoselenium compounds with diiodine has been studied at several levels of theory (Hartree-Fock, second order Møller-Plesset, and density functional theory). The complexation energies, optimized geometries, and the topology of the electron density and its Laplacian distribution, including domain averaged properties, have been analyzed. Special attention was paid to the influence of basis set superposition error on the energy of complexation. A tendency of organoselenium molecules to form more covalent intermolecular bonds with electron acceptors than with nitrogen atoms or other conventional electron donors has been revealed. The changes in atomic charges under complexation follow the main trends expected for the charge transfer. By means of the interacting quantum atoms (IQA) approach it has been found that the Se···I interaction is dominated by its quantum mechanical exchange-correlation contribution, the electrostatic interaction having a minor, repulsive role. IQA data have also been used to explain the value of the Se···I-I valence angle, as well as the topological charges on the iodine atoms in the complexes studied.

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).

Theoretical Insights into the Catalytic Effect of Transition-Metal Ions on the Aquathermal Degradation of Sulfur-Containing Heavy Oil: A DFT Study of Cyclohexyl Phenyl Sulfide Cleavage.

Steam injection is the most widely used technique for effectively reducing the viscosity of heavy oil in heavy oil production, in which in situ upgrading of heavy oil by aquathermolysis plays an important role. Earlier, transition-metal catalysts have been used for improving the efficiency of steam injection by catalytic aquathermolysis and achieving a higher degree of in situ oil upgrading. However, the unclear mechanism of aquathermolysis makes it difficult to choose efficient catalysts for different types of heavy oil. This theoretical study is aimed at deeply understanding the mechanism of in situ upgrading of sulfur-containing heavy oil and its catalysis. For this purpose, cyclohexyl phenyl sulfide (CPS) is selected as a model compound of sulfur-containing oil components, and, for the first time, a catalytic effect of transition metals on the thermochemistry and kinetics of its aquathermolysis is investigated by the density functional theory (DFT) methods with the use of the Becke three-parameter Lee-Yang-Parr (B3LYP), ωB97X-D, and M06-2X functionals. Calculation results show that the hydrolysis of CPS is characterized by fairly high energy barriers in comparison with other possible reaction routes leading to the cleavage of C-S bonds, while the heterolysis of C-S bonds in the presence of protons has a substantially lower kinetic barrier. According to the theoretical analysis, transition-metal ions significantly reduce the kinetic barrier of heterolysis. The Cu2+ ion outperforms the other investigated metal ions and the hydrogen ion in the calculated rate constant by 5-6 (depending on the metal) and 7 orders of magnitude, respectively. The catalytic activity of the investigated transition-metal ions is arranged in the following sequence, depending on the used DFT functional: Cu2+ ≫ Co2+ ≈ Ni2+ > Fe2+. It is theoretically confirmed that transition-metal ions, especially Cu2+, can serve as effective catalysts in aquathermolysis reactions. The proposed quantum-chemical approach for studying the catalytic aquathermolysis provides a new supplementary theoretical tool that can be used in the development of catalysts for different chemical transformations of heavy oil components in reservoirs due to hydrothermal treatment.

"Additive" cooperativity of hydrogen bonds in complexes of catechol with proton acceptors in the gas phase: FTIR spectroscopy and quantum chemical calculations.

Experimental study of hydrogen bond cooperativity in hetero-complexes in the gas phase was carried out by IR-spectroscopy method. Stretching vibration frequencies of O-H groups in phenol and catechol molecules as well as of their complexes with nitriles and ethers were determined in the gas phase using a specially designed cell. O-H groups experimental frequency shifts in the complexes of catechol induced by the formation of intermolecular hydrogen bonds are significantly higher than in the complexes of phenol due to the hydrogen bond cooperativity. It was shown that the cooperativity factors of hydrogen bonds in the complexes of catechol with nitriles and ethers in the gas phase are approximately the same. Quantum chemical calculations of the studied systems have been performed using density functional theory (DFT) methods. It was shown, that theoretically obtained cooperativity factors of hydrogen bonds in the complexes of catechol with proton acceptors are in good agreement with experimental values. Cooperative effects lead to a strengthening of intermolecular hydrogen bonds in the complexes of catechol on about 30%, despite the significant difference in the proton acceptor ability of the bases. The analysis within quantum theory of atoms in molecules was carried out for the explanation of this fact.