Search

In order to better foramize it, the notorious inverse-QSAR problem (finding structures of given QSAR-predicted properties) is considered in this paper as a two-step process including (i) finding "seed" descriptor vectors corresponding to user-constrained QSAR model output values and (ii) identifying the chemical structures best matching the "seed" vectors. The main development effort here was focused on the latter stage, proposing a new attention-based conditional variational autoencoder neural-network architecture based on recent developments in attention-based methods. The obtained results show that this workflow was capable of generating compounds predicted to display desired activity while being completely novel compared to the training database (ChEMBL). Moreover, the generated compounds show acceptable druglikeness and synthetic accessibility. Both pharmacophore and docking studies were carried out as "orthogonal"

Nowadays, drug discovery is inevitably intertwined with the usage of large compound collections. Understanding of their chemotype composition and physicochemical property profiles is of the highest importance for successful hit identification. Efficient polyfunctional tools allowing multifaceted analysis of constantly growing chemical libraries must be Big Data-compatible. Here, we present the freely accessible ChemSpace Atlas (https://chematlas.chimie.unistra.fr), which includes almost 40K hierarchically organized Generative Topographic Maps (GTM) accommodating up to 500 M compounds covering fragment-like, lead-like, drug-like, PPI-like, and NP-like chemical subspaces. They allow users to navigate and analyze ZINC, ChEMBL, and COCONUT from multiple perspectives on different scales: from a bird's eye view of the entire library to structural pattern detection in small clusters. Around 20 physicochemical properties and almost 750 biological activities can be visualized (associated with map zones), supporting activity profiling and analogue search. Moreover, ChemScape Atlas will be extended toward new chemical subspaces (e.g., DNA-encoded libraries and synthons) and functionalities (ADMETox profiling and property-guided de novo compound generation).

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.

Graph-based architectures are becoming increasingly popular as a tool for structure generation. Here, we introduce novel open-source architecture HyFactor in which, similar to the InChI linear notation, the number of hydrogens attached to the heavy atoms was considered instead of the bond types. HyFactor was benchmarked on the ZINC 250K, MOSES, and ChEMBL data sets against conventional graph-based architecture ReFactor, representing our implementation of the reported DEFactor architecture in the literature. On average, HyFactor models contain some 20% less fitting parameters than those of ReFactor. The two architectures display similar validity, uniqueness, and reconstruction rates. Compared to the training set compounds, HyFactor generates more similar structures than ReFactor. This could be explained by the fact that the latter generates many open-chain analogues of cyclic structures in the training set. It has been demonstrated that the reconstruction error of heavy molecules can be significantly reduced using the data augmentation technique. The codes of HyFactor and ReFactor as well as all models obtained in this study are publicly available from our GitHub repository: https://github.com/Laboratoire-de-Chemoinformatique/HyFactor.

COVID-19 has resulted in huge numbers of infections and deaths worldwide and brought the most severe disruptions to societies and economies since the Great Depression. Massive experimental and computational research effort to understand and characterize the disease and rapidly develop diagnostics, vaccines, and drugs has emerged in response to this devastating pandemic and more than 130 000 COVID-19-related research papers have been published in peer-reviewed journals or deposited in preprint servers. Much of the research effort has focused on the discovery of novel drug candidates or repurposing of existing drugs against COVID-19, and many such projects have been either exclusively computational or computer-aided experimental studies. Herein, we provide an expert overview of the key computational methods and their applications for the discovery of COVID-19 small-molecule therapeutics that have been reported in the research literature. We further outline that, after the first year the COVID-19 pandemic, it appears that drug repurposing has not produced rapid and global solutions. However, several known drugs have been used in the clinic to cure COVID-19 patients, and a few repurposed drugs continue to be considered in clinical trials, along with several novel clinical candidates. We posit that truly impactful computational tools must deliver actionable, experimentally testable hypotheses enabling the discovery of novel drugs and drug combinations, and that open science and rapid sharing of research results are critical to accelerate the development of novel, much needed therapeutics for COVID-19., We cover diverse methodologies, computational approaches, and case studies illustrating the ongoing efforts to develop viable drug candidates for treatment of COVID-19.

International audience; The days when medicinal chemistry was limited to a few series of compounds of therapeutic interest are long gone. Nowadays, no human may succeed to acquire a complete overview of more than a billion existing or feasible compounds within which the potential “blockbuster drugs” are well hidden and yet only a few mouse clicks away. To reach these “hidden treasures”, we adapted the generative topographic mapping method to enable efficient navigation through the chemical space, from a global overview to a structural pattern detection, covering, for the first time, the complete ZINC library of purchasable compounds, relative to 1.6 million biologically relevant ChEMBL molecules. About 40 000 hierarchical maps of the chemical space were constructed. Structural motifs inherent to only one library were identified. Roughly 20 000 off-market ChEMBL compound families represent incentives to enrich commercial catalogs. Alternatively, 125 000 ZINC-specific compound classes, absent in structure–activity bases, are novel paths to explore in medicinal chemistry. The complete list of these chemotypes can be downloaded using the link https://forms.gle/B6bUJj82t9EfmttV6.

International audience; The Generalized Born (GB) solvent model is offering the best accuracy/computing effort ratio yet requires drastic simplifications to estimate of the Effective Born Radii (EBR) in bypassing a too expensive volume integration step. EBRs are a measure of the degree of burial of an atom and not very sensitive to small changes of geometry: in molecular dynamics, the costly EBR update procedure is not mandatory at every step. This work however aims at implementing a GB model into the Sampler for Multiple Protein−Ligand Entities (S4MPLE) evolutionary algorithm with mandatory EBR updates at each step triggering arbitrarily large geometric changes. Therefore, a quantitative structure−property relationship has been developed in order to express the EBRs as a linear function of both the topological neighborhood and geometric occupancy of the space around atoms. A training set of 810 molecular systems, starting from fragment-like to drug-like compounds, proteins, host−guest systems, and ligand−protein complexes, has been compiled. For each species, S4MPLE generated several hundreds of random conformers. For each atom in each geometry of each species, its "standard" EBR was calculated by numeric integration and associated to topological and geometric descriptors of the atom neighborhood. This training set (EBR, atom descriptors) involving >5 M entries was subjected to a boot-strapping multilinear regression process with descriptor selection. In parallel, the strategy was repurposed to also learn atomic solvent-accessible areas (SA) based on the same descriptors. Resulting linear equations were challenged to predict EBR and SA values for a similarly compiled external set of >2000 new molecular systems. Solvation energies calculated with estimated EBR and SA match "standard" energies within the typical error of a force-field-based approach (a few kilocalories per mole). Given the extreme diversity of molecular systems covered by the model, this simple EBR/SA estimator covers a vast applicability domain.

New iron(II) complexes with 2,6-bis(benzimidazol-2-yl)pyridine (L), in particular, [FeL2]A2·nH2O (A = Br− (I), NO3− (II), C2N3− (III); n = 1 (I), 0.5 (II), 2 (III)) and [NiL2]Br2·1.23H2O·3.33EtOH (IV), have been synthesized and studied using single-crystal and powder X-ray diffraction techniques, UV-vis (diffuse reflection), IR and Mossbauer spectroscopy, as well as static magnetic susceptibility measurements. According to the experimental μeff(T) curves all the studied iron(II) compounds exhibit 1A1 ↔ 5T2 spin-crossover.

Carbon capture and storage technologies are projected to increasingly contribute to cleaner energy transitions by significantly reducing CO2 emissions from fossil fuel-driven power and industrial plants. The industry standard technology for CO2 capture is chemical absorption with aqueous alkanolamines, which are often being mixed with an activator, piperazine, to increase the overall CO2 absorption rate. Inefficiency of the process due to the parasitic energy required for thermal regeneration of the solvent drives the search for new tertiary amines with better kinetics. Improving the efficiency of experimental screening using computational tools is challenging due to the complex nature of chemical absorption. We have developed a novel computational approach that combines kinetic experiments, molecular simulations and machine learning for the in silico screening of hundreds of prospective candidates and identify a class of tertiary amines that absorbs CO2 faster than a typical commercial solvent when mixed with piperazine, which was confirmed experimentally.

Dynamic combinatorial libraries (DCLs) display adaptive behavior, enabled by the reversible generation of their molecular constituents from building blocks, in response to external effectors, e.g., protein receptors. So far, chemoinformatics has not yet been used for the design of DCLs-which comprise a radically different set of challenges compared to classical library design. Here, we propose a chemoinformatic model for theoretically assessing the composition of DCLs in the presence and the absence of an effector. An imine-based DCL in interaction with the effector human carbonic anhydrase II (CA II) served as a case study. Support vector regression models for the imine formation constants and imine-CA II binding were derived from, respectively, a set of 276 imines synthesized and experimentally studied in this work and 4350 inhibitors of CA II from ChEMBL. These models predict constants for all DCL constituents, to feed software assessing equilibrium concentrations. They are publicly available on the dedicated website. Models rationally selected two amines and two aldehydes predicted to yield stable imines with high affinity for CA II and provided a virtual illustration on how effector affinity regulates DCL members.

Catalyst optimization process is typically relying on an inductive and qualitative assumption 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 previously unaddressed transformation.

The ability to efficiently synthesize desired compounds can be a limiting factor for chemical space exploration in drug discovery. This ability is conditioned not only by the existence of well-studied synthetic protocols but also by the availability of corresponding reagents, so-called building blocks (BB). In this work, we present a detailed analysis of the chemical space of 400K purchasable BB. The chemical space was defined by corresponding synthons – fragments contributed to the final molecules upon reaction. They allow an analysis of BB physicochemical properties and diversity, unbiased by the leaving and protective groups in actual reagents. The main classes of BB were analyzed in terms of their availability, rule-of-two-defined quality, and diversity. Available BBs were eventually compared to a reference set of biologically relevant synthons derived from ChEMBL fragmentation, in order to illustrate how well they cover the actual medicinal chemistry needs. This was performed on a newly constructed universal generative topographic map of synthon chemical space, allowing to visualize both libraries and analyze their overlapping and library-specific regions.

The removal of CO2 from gases is an important industrial process in the transition to a low-carbon economy. The use of selective physical (co-)solvents is especially perspective in cases when the a...

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.

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 .

Most of the existing computational tools for de novo library design are focused on the generation, rational selection, and combination of promising structural motifs to form members of the new library. However, the absence of a direct link between the chemical space of the retrosynthetically generated fragments and the pool of available reagents makes such approaches appear as rather theoretical and reality-disconnected. In this context, here we present Synthons Interpreter (SynthI), a new open-source toolkit for de novo library design that allows merging those two chemical spaces into a single synthons space. Here synthons are defined as actual fragments with valid valences and special labels, specifying the position and the nature of reactive centers. They can be issued from either the "breakup" of reference compounds according to 38 retrosynthetic rules or real reagents, after leaving group withdrawal or transformation. Such an approach not only enables the design of synthetically accessible libraries and analog generation but also facilitates reagents (building blocks) analysis in the medicinal chemistry context. SynthI code is publicly available at https://github.com/Laboratoire-de-Chemoinformatique/SynthI.

International audience; Treatment of hydrogen sulfide (H2S) is important in many industrial processes including oil refineries, natural and biogas processing, and coal gasification. The most mature technology for the selective capture of H2S is based on its absorption by chemical or physical solvents. However, only several compounds are currently used as physical (co)solvents in industry, and the search for new ones is an important task. The experimental screening of physical (co)solvents requires much time and many resources, while solubility modeling might enable one to reduce the number of solvents for the experimental evaluation. In this study, a workflow for the in silico discovery of new physical solvents for H2S absorption was suggested and experimentally validated. A data set composed of 99 H2S physical solvents was collected and predictive quantitative structure–property relationships for H2S solubility were built using a random forest algorithm and two types of molecular descriptors: ISIDA fragments and quantum-chemical descriptors. Virtual screening of industrially produced chemicals and their structural analogues enabled identification of the ones with predicted high solubility values. They can be suggested as starting points for further exploration of the H2S physical solvents chemical space. The predicted solubility value for one of the compounds found in virtual screening, 1,3-dimethyl-2-imidazolidinone, was confirmed experimentally.

In chemography, grid-based maps sample molecular descriptor space by injecting a set of nodes, and then linking them to some regular 2D grid representing the map. They include self-organizing maps (SOMs) and generative topographic maps (GTMs). Grid-based maps are predictive because any compound thereupon projected can "inherit" the properties of its residence node(s)-node properties themselves "inherited" from node-neighboring training set compounds. This Article proposes a formalism to define the trustworthiness of these nodes as "providers" of structure-activity information captured from training compounds. An empirical four-parameter node trustworthiness (NT) function of density (sparsely populated nodes are less trustworthy) and coherence (nodes with training set residents of divergent properties are less trustworthy) is proposed. Based upon it, a trustworthiness score T is used to delimit the applicability domain (AD) by means of a trustworthiness threshold TT. For each parameter setup, success of ensuing inside-AD predictions is monitored. It is seen that setup-specific success levels (averaged over large pools of prediction challenges) are highly covariant, irrespectively of the targets of prediction challenges, of the (classification or regression) type of problems, of the specific parametrization, and even of the nature (GTM or SOM) of underlying maps. Thus, success levels determined on the basis of regression problems (445 target-specific affinity QSAR sets) on GTMs and levels returned by completely unrelated classification problems (319 target-specific active-/inactive-labeled sets) on SOMs were seen to correlate to a degree of 70%. Therefore, a common, general-purpose setup of the herein proposed parametric AD definition was shown to generally apply to grid-based map-driven property prediction problems.

Nowadays quantum chemical calculations are widely used to generate extensive datasets for machine learning applications, however, generally these sets only include information on equilibrium structures and some close conformers. Exploration of potential energy surface provides an 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 resulted from quantum chemical calculations. Our tool allows to store, to assemble and to analyze reaction pathway data. It combines relational database CGR DB for handling compounds and reactions as molecular graphs with a graph database architecture for the pathway analysis by graph algorithms. Original Condensed Graph of Reaction Technology is used to store any chemical reaction as a single graph.

Prediction of chemical bioactivity and physical properties has been one of the most important applications of statistical and more recently, machine learning and artificial intelligence methods in chemical sciences. This field of research, broadly known as quantitative structure-activity relationships (QSAR) modeling, has developed many important algorithms and has found a broad range of applications in physical organic and medicinal chemistry in the past 55+ years. This Perspective summarizes recent technological advances in QSAR modeling but it also highlights the applicability of algorithms, modeling methods, and validation practices developed in QSAR to a wide range of research areas outside of traditional QSAR boundaries including synthesis planning, nanotechnology, materials science, biomaterials, and clinical informatics. As modern research methods generate rapidly increasing amounts of data, the knowledge of robust data-driven modelling methods professed within the QSAR field can become essential for scientists working both within and outside of chemical research. We hope that this contribution highlighting the generalizable components of QSAR modeling will serve to address this challenge.

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 (logK

Prediction of chemical bioactivity and physical properties has been one of the most important applications of statistical and more recently, machine learning and artificial intelligence methods in chemical sciences. This field of research, broadly known as Quantitative Structure-Activity Relationships (QSAR) modeling, has developed many important algorithms and has found a broad range of applications in physical organic and medicinal chemistry in the past 55+ years. This Perspective summarizes recent technological advances in QSAR modeling. Importantly, it also highlights the applicability of algorithms, modeling methods, and validation practices developed in QSAR to a wide range of research areas beyond traditional QSAR fields. These fields include nanotechnology, materials science, biomaterials, clinical informatics, and others. As modern research methods generate rapidly increasing amounts of data, knowledge of robust data-driven modelling methods is becoming essential for scientists in many disciplines both within and outside of chemical research. We hope that this contribution will serve to address this challenge.

Universal generative topographic maps (GTMs) provide two-dimensional representations of chemical space selected for their "polypharmacological competence", that is, the ability to simultaneously represent meaningful activity and property landscapes, associated with many distinct targets and properties. Several such GTMs can be generated, each based on a different initial descriptor vector, encoding distinct structural features. While their average polypharmacological competence may indeed be equivalent, they nevertheless significantly diverge with respect to the quality of each property-specific landscape. In this work, we show that distinct universal maps represent complementary and strongly synergistic views of biologically relevant chemical space. Eight universal GTMs were employed as support for predictive classification landscapes, using more than 600 active/inactive ligand series associated with as many targets from the ChEMBL database (v.23). For nine of these targets, it was possible to extract, from the Directory of Useful Decoys (DUD), truly external sets featuring sufficient "actives" and "decoys" not present in the landscape-defining ChEMBL ligand sets. For each such molecule, projected on every class landscape of a particular universal map, a probability of activity was estimated, in analogy to a virtual screening (VS) experiment. Cross-validated (CV) balanced accuracy on landscape-defining ChEMBL data was unable to predict the success of that landscape in VS. Thus, the universal map with best CV results for a given property should not be prioritized as the implicitly best predictor. For a given map, predictions for many DUD compounds are not trustworthy, according to applicability domain considerations. By contrast, simultaneous application of all universal maps, and rating of the likelihood of activity as the mean returned by all applicable maps, significantly improved prediction results. Performance measures in consensus VS using multiple maps were always superior or similar to those of the best individual map.

International audience; Here we show that Generative Topographic Mapping (GTM) can be used to explore the latent space of the SMILES-based autoencoders and generate focused molecular libraries of interest. We have built a sequence-to-sequence neural network with Bidirectional Long Short-Term Memory layers and trained it on the SMILES strings from ChEMBL23. Very high reconstruction rates of the test set molecules were achieved (>98%), which are comparable to the ones reported in related publications. Using GTM, we have visualized the autoencoder latent space on the two-dimensional topographic map. Targeted map zones can be used for generating novel molecular structures by sampling associated latent space points and decoding them to SMILES. The sampling method based on a genetic algorithm was introduced to optimize compound properties "on the fly". The generated focused molecular libraries were shown to contain original and a priori feasible compounds which, pending actual synthesis and testing, showed encouraging behavior in independent structure-based affinity estimation procedures (pharmacophore matching, docking).

In this paper, we demonstrate that the kernel target alignment (KTA) parameter can efficiently be used to estimate the relevance of molecular descriptors for QSAR modeling on a given data set, i.e., as a modelability measure. The efficiency of KTA to assess modelability was demonstrated in two series of QSAR modeling studies, either varying different descriptor spaces for one same data set, or comparing various data sets within one same descriptor space. Considered data sets included 25 series of various GPCR binders with ChEMBL-reported pKi values, and a toxicity data set. Employed descriptor spaces covered more than 100 different ISIDA fragment descriptor types, and ChemAxon BCUT terms. Model performances (RMSE) were seen to anticorrelate consistently with the KTA parameter. Two other modelability measures were employed for benchmarking purposes: the Jaccard distance average over the data set (Div), and a measure related to the normalized mean absolute error (MAE) obtained in 1-nearest neighbors calculations on the training set (Sim = 1 - MAE). It has been demonstrated that both Div and Sim perform similarly to KTA. However, a consensus index combining KTA, Div and Sim provides a more robust correlation with RMSE than any of the individual modelability measures.

Predicting the activity profile of a molecule or discovering structures possessing a specific activity profile are two important goals in chemoinformatics, which could be achieved by bridging activity and molecular descriptor spaces. In this paper, we introduce the "Stargate" version of the Generative Topographic Mapping approach (S-GTM) in which two different multidimensional spaces (e.g., structural descriptor space and activity space) are linked through a common 2D latent space. In the S-GTM algorithm, the manifolds are trained simultaneously in two initial spaces using the probabilities in the 2D latent space calculated as a weighted geometric mean of probability distributions in both spaces. S-GTM has the following interesting features: (1) activities are involved during the training procedure; therefore, the method is supervised, unlike conventional GTM; (2) using molecular descriptors of a given compound as input, the model predicts a whole activity profile, and (3) using an activity profile as input, areas populated by relevant chemical structures can be detected. To assess the performance of S-GTM prediction models, a descriptor space (ISIDA descriptors) of a set of 1325 GPCR ligands was related to a B-dimensional (B = 1 or 8) activity space corresponding to pKi values for eight different targets. S-GTM outperforms conventional GTM for individual activities and performs similarly to the Lasso multitask learning algorithm, although it is still slightly less accurate than the Random Forest method.

Identification of "privileged structural motifs" associated with specific target families is of particular importance for designing novel bioactive compounds. Here, we demonstrate that they can be extracted from a data distribution represented on a two-dimensional map obtained by Generative Topographic Mapping (GTM). In GTM, structurally related molecules are grouped together on the map. Zones of the map preferentially populated by target-specific compounds were delineated, which helped to capture common substructures on the basis of which these compounds were grouped together by GTM. Such privileged structural motifs were identified across three major target superfamilies including proteases, kinases, and G protein coupled receptors. Traditionally, the search for privileged structural motifs focused on scaffolds, whereas motifs were detected here without prior knowledge of compound classification in GTMs. This alternative way of navigating medicinal chemistry space further extends the classical, scaffold-centric approach. Importantly, detected motifs might also comprise fuzzy sets of similar scaffolds, pharmacophore-like patterns, or, by contrast, well-defined scaffolds with specific substituent patterns.

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.

This paper is devoted to the analysis and visualization in 2-dimensional space of large data sets of millions of compounds using the incremental version of generative topographic mapping (iGTM). The iGTM algorithm implemented in the in-house ISIDA-GTM program was applied to a database of more than 2 million compounds combining data sets of 36 chemicals suppliers and the NCI collection, encoded either by MOE descriptors or by MACCS keys. Taking advantage of the probabilistic nature of GTM, several approaches to data analysis were proposed. The chemical space coverage was evaluated using the normalized Shannon entropy. Different views of the data (property landscapes) were obtained by mapping various physical and chemical properties (molecular weight, aqueous solubility, LogP, etc.) onto the iGTM map. The superposition of these views helped to identify the regions in the chemical space populated by compounds with desirable physicochemical profiles and the suppliers providing them. The data sets similarity in the latent space was assessed by applying several metrics (Euclidean distance, Tanimoto and Bhattacharyya coefficients) to data probability distributions based on cumulated responsibility vectors. As a complementary approach, data sets were compared by considering them as individual objects on a meta-GTM map, built on cumulated responsibility vectors or property landscapes produced with iGTM. We believe that the iGTM methodology described in this article represents a fast and reliable way to analyze and visualize large chemical databases.

This study is an exhaustive analysis of the neighborhood behavior over a large coherent data set (ChEMBL target/ligand pairs of known Ki, for 165 targets with >50 associated ligands each). It focuses on similarity-based virtual screening (SVS) success defined by the ascertained optimality index. This is a weighted compromise between purity and retrieval rate of active hits in the neighborhood of an active query. One key issue addressed here is the impact of Tversky asymmetric weighing of query vs candidate features (represented as integer-value ISIDA colored fragment/pharmacophore triplet count descriptor vectors). The nearly a 3/4 million independent SVS runs showed that Tversky scores with a strong bias in favor of query-specific features are, by far, the most successful and the least failure-prone out of a set of nine other dissimilarity scores. These include classical Tanimoto, which failed to defend its privileged status in practical SVS applications. Tversky performance is not significantly conditioned by tuning of its bias parameter α. Both initial "guesses" of α = 0.9 and 0.7 were more successful than Tanimoto (at its turn, better than Euclid). Tversky was eventually tested in exhaustive similarity searching within the library of 1.6 M commercial + bioactive molecules at http://infochim.u-strasbg.fr/webserv/VSEngine.html , comparing favorably to Tanimoto in terms of "scaffold hopping" propensity. Therefore, it should be used at least as often as, perhaps in parallel to Tanimoto in SVS. Analysis with respect to query subclasses highlighted relationships of query complexity (simply expressed in terms of pharmacophore pattern counts) and/or target nature vs SVS success likelihood. SVS using more complex queries are more robust with respect to the choice of their operational premises (descriptors, metric). Yet, they are best handled by "pro-query" Tversky scores at α > 0.5. Among simpler queries, one may distinguish between "growable" (allowing for active analogs with additional features), and a few "conservative" queries not allowing any growth. These (typically bioactive amine transporter ligands) form the specific application domain of "pro-candidate" biased Tversky scores at α < 0.5.

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.

Activity cliffs (ACs) are formed by structurally similar compounds with large differences in activity. Accordingly, ACs are of high interest for the exploration of structure-activity relationships (SARs). ACs reveal small chemical modifications that result in profound biological effects. The ability to foresee such small chemical changes with significant biological consequences would represent a major advance for drug design. Nevertheless, only few attempts have been made so far to predict whether a pair of analogues is likely to represent an AC-and even fewer went further to quantitatively predict how "deep" a cliff might be. This might be due to the fact that such predictions must focus on compound pairs. Matched molecular pairs (MMPs), defined as pairs of structural analogs that are only distinguished by a chemical modification at a single site, are a preferred representation of ACs. Herein, we report new strategies for AC prediction that are based upon two different approaches: (i) condensed graphs of reactions, which were originally introduced for modeling of chemical reactions and were here adapted to encode MMPs, and, (ii) plain descriptor recombination-a strategy used for quantitative structure-property relationship (QSPR) modeling of nonadditive mixtures (MQSPR). By applying these concepts, ACs were encoded as single descriptor vectors used as input for support vector machine (SVM) classification and support vector regression (SVR), yielding accurate predictions of AC status (i.e., cliff vs noncliff) and potency differences, respectively. The latter were predicted in a compound order-sensitive manner returning the signed value of expected potency differences between AC compounds.

This paper describes the Structural and Physico-Chemical Interpretation (SPCI) approach, which is an extension of a recently reported method for interpretation of quantitative structure-activity relationship (QSAR) models. This approach can efficiently be used to reveal structural motifs and the major physicochemical factors affecting the investigated properties. Its efficacy was demonstrated both on the classical Free-Wilson data set and on several data sets with different end points (permeability of the blood-brain barrier, fibrinogen receptor antagonists, acute oral toxicity). Structure-activity patterns extracted from QSAR models with SPCI were in good correspondence with experimentally observed relationships and molecular docking, regardless of the machine learning method used. Comparison of SPCI with the matched molecular pair (MMP) method clearly shows an advantage of our approach over MMP, especially for small or structurally diverse data sets. The developed approach has been implemented in the SPCI software tool with a graphical user interface, which is publicly available at http://qsar4u.com/pages/sirms_qsar.php .

Curation, standardization and data fusion of the antiviral information present in the ChEMBL public database led to the definition of a robust data set, providing an association of antiviral compounds to seven broadly defined antiviral activity classes. Generative topographic mapping (GTM) subjected to evolutionary tuning was then used to produce maps of the antiviral chemical space, providing an optimal separation of compound families associated with the different antiviral classes. The ability to pinpoint the specific spots occupied (responsibility patterns) on a map by various classes of antiviral compounds opened the way for a GTM-supported search for privileged structural motifs, typical for each antiviral class. The privileged locations of antiviral classes were analyzed in order to highlight underlying privileged common structural motifs. Unlike in classical medicinal chemistry, where privileged structures are, almost always, predefined scaffolds, privileged structural motif detection based on GTM responsibility patterns has the decisive advantage of being able to automatically capture the nature ("resolution detail"-scaffold, detailed substructure, pharmacophore pattern, etc.) of the relevant structural motifs. Responsibility patterns were found to represent underlying structural motifs of various natures-from very fuzzy (groups of various "interchangeable" similar scaffolds), to the classical scenario in medicinal chemistry (underlying motif actually being the scaffold), to very precisely defined motifs (specifically substituted scaffolds).

Machine learning (SVM and JRip rule learner) methods have been used in conjunction with the Condensed Graph of Reaction (CGR) approach to identify errors in the atom-to-atom mapping of chemical reactions produced by an automated mapping tool by ChemAxon. The modeling has been performed on the three first enzymatic classes of metabolic reactions from the KEGG database. Each reaction has been converted into a CGR representing a pseudomolecule with conventional (single, double, aromatic, etc.) bonds and dynamic bonds characterizing chemical transformations. The ChemAxon tool was used to automatically detect the matching atom pairs in reagents and products. These automated mappings were analyzed by the human expert and classified as "correct" or "wrong". ISIDA fragment descriptors generated for CGRs for both correct and wrong mappings were used as attributes in machine learning. The learned models have been validated in n-fold cross-validation on the training set followed by a challenge to detect correct and wrong mappings within an external test set of reactions, never used for learning. Results show that both SVM and JRip models detect most of the wrongly mapped reactions. We believe that this approach could be used to identify erroneous atom-to-atom mapping performed by any automated algorithm.

Quantitative structure–property relationship (QSPR) modeling of the stability constant logK of the 1:1 (M:L) complexes of 6 transition-metal cations (M) with 261 (Mn2+), 87 (Fe2+), 105 (Y3+), 186 (La3+), 226 (Pb2+), and 66 (UO22+) organic ligands (L) in aqueous solutions at 298 K and an ionic strength 0.1 M was performed using ensemble multiple linear regression analysis and substructural molecular fragments as descriptors. The models have been validated in external 5-fold cross-validations procedure and on new ligands recently reported in the literature. Predicted logK values were calculated by consensus models as arithmetic means of 315 (Mn2+), 119 (Fe2+), 260 (Y3+), 290 (La3+), 304 (Pb2+), and 249 (UO22+) individual models. Absolute prediction error of logK is below 1.0 for 75% (UO22+), 70% (Mn2+, Fe2+, La3+), 65% (Pb2+), and 60% (Y3+) of the ligands and comparable with the systematic errors in experimental data. The developed QSPR models were used to screen selective ligands for the studied cations. T...

Quantitative structure–property relationship (QSPR) modeling of normal boiling point temperature (Taz) and the composition (weight fraction, X1w) of 176 binary azeotropic mixtures was performed using ensemble multiple linear regression analysis and fragment descriptors implemented in ISIDA software. The models have been validated in external 5-fold cross-validations procedure and on an additional test set of 24 azeotropes. The prediction errors (3–4 K for Taz and 10–14 wt % for X1w) are comparable with the noise in experimental data. A simple empirical relationship linking Taz with boiling points of two molecular components of azeotrope has been suggested.

Complex [FeL2(NCS)2]·H2O (L = 3,5-di(pyrimidin-2-yl)-4H-1,2,4-triazol-4-amine) was prepared as the first example of complex compounds of transition metals with 3,5-di(pyrimidin-2-yl)-4H-1,2,4-triazol-4-amines. The coordination core of the iron atom is a distorted octahedron FeN6. In the range 80–300 K the complex is high-spin, μeff ∼ 5.3 MB. The parameter of the crystal field splitting, 10Dq, for [FeL2(NCS)2]·H2O is ∼10800 cm−1.

The iron compounds resulting from the impregnation of the most common supports—alumina and silica gel-with an aqueous FeSO4 · 7H2O solution and subsequent heat treatment in air are identified by thermal analysis and Mossbauer spectroscopy. The state of the active component of the iron-containing catalysts depends strongly on the nature of the support.

Methods for the synthesis of iron(II) complexes with 1,2,4-triazole (HTrz) and 4-amino-1,2,4-triazole (NH2Trz) containing the decahydro-closo-decaborate ion [B10H10]2-were developed. The empirical formulas of the complexes were Fe(HTrz)3B10H10 · H2O (I) and Fe(NH2Trz)3B10H10 · H2O (II). The complexes were examined by static magnetic susceptibility measurements (2–300 K) and Moessbauer, IR, and electronic spectroscopy. Complex I exhibits the reversible spin transition 1 A 1 ⇄ 5 T 2 and pink ⇄ white thermochromism. The temperatures of the forward and reverse transitions in complex I were 246 and 233 K, respectively. Complex II remained in the high-spin state over the whole temperature range. The sharp decrease in its effective magnetic moment at T < 78 K was attributed to antiferromagnetic exchange interactions between Fe2+ ions.

A benchmark of several popular methods, Associative Neural Networks (ANN), Support Vector Machines (SVM), k Nearest Neighbors (kNN), Maximal Margin Linear Programming (MMLP), Radial Basis Function Neural Network (RBFNN), and Multiple Linear Regression (MLR), is reported for quantitative-structure property relationships (QSPR) of stability constants logK1 for the 1:1 (M:L) and logbeta2 for 1:2 complexes of metal cations Ag+ and Eu3+ with diverse sets of organic molecules in water at 298 K and ionic strength 0.1 M. The methods were tested on three types of descriptors: molecular descriptors including E-state values, counts of atoms determined for E-state atom types, and substructural molecular fragments (SMF). Comparison of the models was performed using a 5-fold external cross-validation procedure. Robust statistical tests (bootstrap and Kolmogorov-Smirnov statistics) were employed to evaluate the significance of calculated models. The Wilcoxon signed-rank test was used to compare the performance of methods. Individual structure-complexation property models obtained with nonlinear methods demonstrated a significantly better performance than the models built using multilinear regression analysis (MLRA). However, the averaging of several MLRA models based on SMF descriptors provided as good of a prediction as the most efficient nonlinear techniques. Support Vector Machines and Associative Neural Networks contributed in the largest number of significant models. Models based on fragments (SMF descriptors and E-state counts) had higher prediction ability than those based on E-state indices. The use of SMF descriptors and E-state counts provided similar results, whereas E-state indices lead to less significant models. The current study illustrates the difficulties of quantitative comparison of different methods: conclusions based only on one data set without appropriate statistical tests could be wrong.

This paper is devoted to computer-aided design of new extractants of the uranyl cation involving three main steps: (i) a QSPR study, (ii) generation and screening of a virtual combinatorial library, and (iii) synthesis of several predicted compounds and their experimental extraction studies. First, we performed a QSPR modeling of the distribution coefficient (logD) of uranyl extracted by phosphoryl-containing podands from water to 1,2-dichloroethane. Two different approaches were used: one based on classical structural and physicochemical descriptors (implemented in the CODESSA PRO program) and another one based on fragment descriptors (implemented in the TRAIL program). Three statistically significant models obtained with TRAIL involve as descriptors either sequences of atoms and bonds or atoms with their close environment (augmented atoms). The best models of CODESSA PRO include its own molecular descriptors as well as fragment descriptors obtained with TRAIL. At the second step, a virtual combinatorial library of 2024 podands has been generated with the CombiLib program, followed by the assessment of logD values using developed QSPR models. At the third step, eight of these hypothetical compounds were synthesized and tested experimentally. Comparison with experiment shows that developed QSPR models successfully predict logD values for 7 of 8 compounds from that "blind test" set.

The method of Substructural Molecular Fragments (SMF) based on splitting of a molecular graph into a limited number of topological fragments and calculation of their contributions to a given property was applied to the structure—property modeling of (i) stability constants of the complexes formed by the K+ cation with phosphoryl-containing podands in a mixed THF—CHCl3 solvent, (ii) distribution coefficients for Hg and Pt extraction by podands from water into 1,2-dichloroethane, and (iii) stability constants of complexes of crown ethers with alkali metal cations in methanol. A procedure for the reduction of the number of fragment descriptors in structure—property relationship (QSPR) models based on the Student t-test was proposed. The use of selected variables improves the robustness of the structure—property models.

Fe(II) complexes with 4-R-1,2,4-triazoles of compositions FeL3A2 · nH2O (where L is 4-propyl-1,2,4-triazol; A is Br- (n = 4), CF3SO3 - (n = 5)), and FeL2A2 · nH2O (where L are 4-ethyl-, 4-propyl-, 4-isopropyl-1,2,4-triazoles (Ettrz, Prtrz, Iprtrz, respectively), A = NCS-, NO3 - (n = 0-2)) were synthesized. Magnetochemical studies revealed that FeL3A2 · nH2O complexes exhibit reversible spin transition (ST) 1 A 1 ⇄ 5 T 2 that is accompanied by thermochromism (a reversible change of color rose ⇄ white). The temperatures of direct (T s↑) and reverse (T s↓) spin transitions are, respectively, 252 and 247 K for Fe(Рrtrz)3Br2 · 4H2O and 207 and 202 K for Fe(Рrtrz)3(CF3SO3)2 · 5H2O. Dehydration of the complexes is attended by significant changes in the type and temperatures of ST.

XPS, Fe Lα,β and Cu Lα,β X-ray emission and Fe L-, Cu L-, S L-edge and O K-edge absorption spectroscopies, Mossbauer spectroscopy and cyclic voltammetry were applied to study reacted surface layers of natural chalcopyrite, CuFeS 2 . The surfaces became metal-depleted after the anodic oxidation in 1 M HCl and the leaching in 1 M H 2 SO 4 +0.2 M Fe 2 (SO 4 ) 3 or 1 M HCl+0.4 M FeCl 3 solutions, with the sulfur excess and iron/copper ratio been higher in the last instance, and were enriched in copper after the electrochemical reduction. The electronic structures of the metal-deficient layers up to several tenths of micrometer thick were similar to that of chalcopyrite, except that the density of the highest occupied states depended on sulfur anions formed (predominant S 3 -anions after the ferric sulfate treatment, S 4 -anions after the ferric chloride leaching or the potential sweep to 0.9 V, etc.). The layers created by the preliminary oxidation had only a small effect on the chalcopyrite voltammetry. We suggest a new reaction mechanism considering a role of the surface changes, including disordering and Anderson localization of the electronic states.

New complexes of iron(II) chloride and bromide with 1,2,4-triazole (Htrz) and 4-amino-1,2,4-tri-azole (NH2trz) of composition Fe(Htrz)3Cl2 · 1.5H2O, Fe(NH2trz)3Cl2 · 2H2O, Fe(Htrz)3Br2 · 2H2O, and the Fe(NH2trz)3SO4 · H2O complex were synthesized and studied by magnetochemical, electronic, IR and Mossbauer spectroscopy methods. Magnetochemical studies showed that these complexes exhibit 1 A 1 ⇄ 5 T 2 spin transition accompanied by thermochromism (a reversible pink ⇄ white change of color).

The estimation of accuracy and applicability of QSAR and QSPR models for biological and physicochemical properties represents a critical problem. The developed parameter of "distance to model" (DM) is defined as a metric of similarity between the training and test set compounds that have been subjected to QSAR/QSPR modeling. In our previous work, we demonstrated the utility and optimal performance of DM metrics that have been based on the standard deviation within an ensemble of QSAR models. The current study applies such analysis to 30 QSAR models for the Ames mutagenicity data set that were previously reported within the 2009 QSAR challenge. We demonstrate that the DMs based on an ensemble (consensus) model provide systematically better performance than other DMs. The presented approach identifies 30-60% of compounds having an accuracy of prediction similar to the interlaboratory accuracy of the Ames test, which is estimated to be 90%. Thus, the in silico predictions can be used to halve the cost of experimental measurements by providing a similar prediction accuracy. The developed model has been made publicly available at http://ochem.eu/models/1 .

The Substructural Molecular Fragments method (Solov'ev, V. P.; Varnek, A. A.; Wipff, G. J. Chem. Inf. Comput. Sci. 2000, 40, 847-858) was applied to assess stability constants (logK) of the complexes of crown-ethers, polyethers, and glymes with Na+, K+, and Cs+ in methanol. One hundred forty-seven computational models including different fragment sets coupled with linear or nonlinear fitting equations were applied for the data sets containing 69 (Na+), 123 (K+), and 31 (Cs+) compounds. To account for the "macrocyclic effect" for crown-ethers, an additional "cyclicity"descriptor was used. "Predicted" stability constants both for macrocyclic compounds and for their open-chain analogues are in good agreement with the experimental data reported earlier and with those studied experimentally in this work. The macrocyclic effect as a function of cation and ligand is quantitatively estimated for all studied crown-ethers.