Alexandre Varnek

QSAR Modeling: Where have you been? Where are you going to?

Quantitative structure-activity relationship modeling is one of the major computational tools employed in medicinal chemistry. However, throughout its entire history it has drawn both praise and criticism concerning its reliability, limitations, successes, and failures. In this paper, we discuss (i) the development and evolution of QSAR; (ii) the current trends, unsolved problems, and pressing challenges; and (iii) several novel and emerging applications of QSAR modeling. Throughout this discussion, we provide guidelines for QSAR development, validation, and application, which are summarized in best practices for building rigorously validated and externally predictive QSAR models. We hope that this Perspective will help communications between computational and experimental chemists toward collaborative development and use of QSAR models. We also believe that the guidelines presented here will help journal editors and reviewers apply more stringent scientific standards to manuscripts reporting new QSAR studies, as well as encourage the use of high quality, validated QSARs for regulatory decision making.

Combinatorial QSAR Modeling of Chemical Toxicants Tested against Tetrahymena pyriformis

Selecting most rigorous quantitative structure-activity relationship (QSAR) approaches is of great importance in the development of robust and predictive models of chemical toxicity. To address this issue in a systematic way, we have formed an international virtual collaboratory consisting of six independent groups with shared interests in computational chemical toxicology. We have compiled an aqueous toxicity data set containing 983 unique compounds tested in the same laboratory over a decade against Tetrahymena pyriformis. A modeling set including 644 compounds was selected randomly from the original set and distributed to all groups that used their own QSAR tools for model development. The remaining 339 compounds in the original set (external set I) as well as 110 additional compounds (external set II) published recently by the same laboratory (after this computational study was already in progress) were used as two independent validation sets to assess the external predictive power of individual models. In total, our virtual collaboratory has developed 15 different types of QSAR models of aquatic toxicity for the training set. The internal prediction accuracy for the modeling set ranged from 0.76 to 0.93 as measured by the leave-one-out cross-validation correlation coefficient ( Q abs2). The prediction accuracy for the external validation sets I and II ranged from 0.71 to 0.85 (linear regression coefficient R absI2) and from 0.38 to 0.83 (linear regression coefficient R absII2), respectively. The use of an applicability domain threshold implemented in most models generally improved the external prediction accuracy but at the same time led to a decrease in chemical space coverage. Finally, several consensus models were developed by averaging the predicted aquatic toxicity for every compound using all 15 models, with or without taking into account their respective applicability domains. We find that consensus models afford higher prediction accuracy for the external validation data sets with the highest space coverage as compared to individual constituent models. Our studies prove the power of a collaborative and consensual approach to QSAR model development. The best validated models of aquatic toxicity developed by our collaboratory (both individual and consensus) can be used as reliable computational predictors of aquatic toxicity and are available from any of the participating laboratories.

Online chemical modeling environment (OCHEM): web platform for data storage, model development and publishing of chemical information.

The Online Chemical Modeling Environment is a web-based platform that aims to automate and simplify the typical steps required for QSAR modeling. The platform consists of two major subsystems: the database of experimental measurements and the modeling framework. A user-contributed database contains a set of tools for easy input, search and modification of thousands of records. The OCHEM database is based on the wiki principle and focuses primarily on the quality and verifiability of the data. The database is tightly integrated with the modeling framework, which supports all the steps required to create a predictive model: data search, calculation and selection of a vast variety of molecular descriptors, application of machine learning methods, validation, analysis of the model and assessment of the applicability domain. As compared to other similar systems, OCHEM is not intended to re-implement the existing tools or models but rather to invite the original authors to contribute their results, make them publicly available, share them with other users and to become members of the growing research community. Our intention is to make OCHEM a widely used platform to perform the QSPR/QSAR studies online and share it with other users on the Web. The ultimate goal of OCHEM is collecting all possible chemoinformatics tools within one simple, reliable and user-friendly resource. The OCHEM is free for web users and it is available online at http://www.ochem.eu.

ISIDA - Platform for Virtual Screening Based on Fragment and Pharmacophoric Descriptors

In this paper we illustrate the application of the ISIDA (In SIlico design and Data Analysis) software to perform virtual screening of large databases of compounds and reactions and to assess some ADME/Tox properties. ISIDA represents an ensemble of tools allowing users to store, search and analyze the data, to perform similarity searches in large databases of molecules and reactions, to build and validate QSAR models, and to generate and screen virtual combinatorial libraries. It uses its own descriptors (substructural molecular fragments and fuzzy pharmacophore triplets). Workflow can be easily organized by combining different ISIDA modules. Several examples of ISIDA applications (similarity search of potent benzodiazepine ligands with FPT, QSAR modeling of aqueous solubility, aquatic toxicity, tissue-air partition coefficients, anti-HIV activity, and screening of the “Chimiotheque Nationale” Database), are discussed. Particular attention is paid to mining reaction databases using Condensed Reaction Graphs approach.

Exhaustive QSPR Studies of a Large Diverse Set of Ionic Liquids: How Accurately Can We Predict Melting Points?

Several popular machine learning methods--Associative Neural Networks (ANN), Support Vector Machines (SVM), k Nearest Neighbors (kNN), modified version of the partial least-squares analysis (PLSM), backpropagation neural network (BPNN), and Multiple Linear Regression Analysis (MLR)--implemented in ISIDA, NASAWIN, and VCCLAB software have been used to perform QSPR modeling of melting point of structurally diverse data set of 717 bromides of nitrogen-containing organic cations (FULL) including 126 pyridinium bromides (PYR), 384 imidazolium and benzoimidazolium bromides (IMZ), and 207 quaternary ammonium bromides (QUAT). Several types of descriptors were tested: E-state indices, counts of atoms determined for E-state atom types, molecular descriptors generated by the DRAGON program, and different types of substructural molecular fragments. Predictive ability of the models was analyzed using a 5-fold external cross-validation procedure in which every compound in the parent set was included in one of five test sets. Among the 16 types of developed structure--melting point models, nonlinear SVM, ASNN, and BPNN techniques demonstrate slightly better performance over other methods. For the full set, the accuracy of predictions does not significantly change as a function of the type of descriptors. For other sets, the performance of descriptors varies as a function of method and data set used. The root-mean squared error (RMSE) of prediction calculated on independent test sets is in the range of 37.5-46.4 degrees C (FULL), 26.2-34.8 degrees C (PYR), 38.8-45.9 degrees C (IMZ), and 34.2-49.3 degrees C (QUAT). The moderate accuracy of predictions can be related to the quality of the experimental data used for obtaining the models as well as to difficulties to take into account the structural features of ionic liquids in the solid state (polymorphic effects, eutectics, glass formation).

Substructural fragments: an universal language to encode reactions, molecular and supramolecular structures.

SummarySubstructural fragments are proposed as a simple and safe way to encode molecular structures in a matrix containing the occurrence of fragments of a given type. The knowledge retrieved from QSPR modelling can also be stored in that matrix in addition to the information about fragments. Complex supramolecular systems (using special bond types) and chemical reactions (represented as Condensed Graphs of Reactions, CGR) can be treated similarly. The efficiency of fragments as descriptors has been demonstrated in QSPR studies of aqueous solubility for a diverse set of organic compounds as well as in the analysis of thermodynamic parameters for hydrogen-bonding in some supramolecular complexes. It has also been shown that CGR may be an interesting opportunity to perform similarity searches for chemical reactions. The relationship between the density of information in descriptors/knowledge matrices and the robustness of QSPR models is discussed.

CERAPP : Collaborative Estrogen Receptor Activity Prediction Project

Background: Humans are exposed to thousands of man-made chemicals in the environment. Some chemicals mimic natural endocrine hormones and, thus, have the potential to be endocrine disruptors. Most of these chemicals have never been tested for their ability to interact with the estrogen receptor (ER). Risk assessors need tools to prioritize chemicals for evaluation in costly in vivo tests, for instance, within the U.S. EPA Endocrine Disruptor Screening Program. Objectives: We describe a large-scale modeling project called CERAPP (Collaborative Estrogen Receptor Activity Prediction Project) and demonstrate the efficacy of using predictive computational models trained on high-throughput screening data to evaluate thousands of chemicals for ER-related activity and prioritize them for further testing. Methods: CERAPP combined multiple models developed in collaboration with 17 groups in the United States and Europe to predict ER activity of a common set of 32,464 chemical structures. Quantitative structure–activity relationship models and docking approaches were employed, mostly using a common training set of 1,677 chemical structures provided by the U.S. EPA, to build a total of 40 categorical and 8 continuous models for binding, agonist, and antagonist ER activity. All predictions were evaluated on a set of 7,522 chemicals curated from the literature. To overcome the limitations of single models, a consensus was built by weighting models on scores based on their evaluated accuracies. Results: Individual model scores ranged from 0.69 to 0.85, showing high prediction reliabilities. Out of the 32,464 chemicals, the consensus model predicted 4,001 chemicals (12.3%) as high priority actives and 6,742 potential actives (20.8%) to be considered for further testing. Conclusion: This project demonstrated the possibility to screen large libraries of chemicals using a consensus of different in silico approaches. This concept will be applied in future projects related to other end points. Citation: Mansouri K, Abdelaziz A, Rybacka A, Roncaglioni A, Tropsha A, Varnek A, Zakharov A, Worth A, Richard AM, Grulke CM, Trisciuzzi D, Fourches D, Horvath D, Benfenati E, Muratov E, Wedebye EB, Grisoni F, Mangiatordi GF, Incisivo GM, Hong H, Ng HW, Tetko IV, Balabin I, Kancherla J, Shen J, Burton J, Nicklaus M, Cassotti M, Nikolov NG, Nicolotti O, Andersson PL, Zang Q, Politi R, Beger RD, Todeschini R, Huang R, Farag S, Rosenberg SA, Slavov S, Hu X, Judson RS. 2016. CERAPP: Collaborative Estrogen Receptor Activity Prediction Project. Environ Health Perspect 124:1023–1033; http://dx.doi.org/10.1289/ehp.1510267

Quantitative structure-property relationship modeling of beta-cyclodextrin complexation free energies.

CODESSA-PRO was used to model binding energies for 1:1 complexation systems between 218 organic guest molecules and beta-cyclodextrin, using a seven-parameter equation with R2 = 0.796 and Rcv2 = 0.779. Fragment-based TRAIL calculations gave a better fit with R2 = 0.943 and Rcv2 = 0.848 for 195 data points in the database. The advantages and disadvantages of each approach are discussed, and it is concluded that a combination of the two approaches has much promise from a practical viewpoint.

ISIDA Property-Labelled Fragment Descriptors.

ISIDA Property‐Labelled Fragment Descriptors (IPLF) were introduced as a general framework to numerically encode molecular structures in chemoinformatics, as counts of specific subgraphs in which atom vertices are coloured with respect to some local property/feature. Combining various colouring strategies of the molecular graph – notably pH‐dependent pharmacophore and electrostatic potential‐based flagging – with several fragmentation schemes, the different subtypes of IPLFs may range from classical atom pair and sequence counts, to monitoring population levels of branched fragments or feature multiplets. The pH‐dependent feature flagging, pursued at the level of each significantly populated microspecies involved in the proteolytic equilibrium, may furthermore add some competitive advantage over classical descriptors, even when the chosen fragmentation scheme is one of the state‐of‐the‐art pattern extraction procedures (feature sequence or pair counts, etc.) in chemoinformatics. The implemented fragmentation schemes support counting (1) linear feature sequences, (2) feature pairs, (3) circular feature fragments a.k.a. “augmented atoms” or (4) feature trees. Fuzzy rendering – optionally allowing nonterminal fragment atoms to be counted as wildcards, ignoring their specific colours/features – ensures for a seamless transition between the “strict” counts (sequences or circular fragments) and the “fuzzy” multiplet counts (pairs or trees). Also, bond information may be represented or ignored, thus leaving the user a vast choice in terms of the level of resolution at which chemical information should be extracted into the descriptors. Selected IPLF subsets were – tree descriptors, in particular – successfully tested in both neighbourhood behaviour and QSAR modelling challenges, with very promising results. They showed excellent results in similarity‐based virtual screening for analogue protease inhibitors, and generated highly predictive octanol‐water partition coefficient and hERG channel inhibition models.

Chemoinformatics as a Theoretical Chemistry Discipline

Here, chemoinformatics is considered as a theoretical chemistry discipline complementary to quantum chemistry and force‐field molecular modeling. These three fields are compared with respect to molecular representation, inference mechanisms, basic concepts and application areas. A chemical space, a fundamental concept of chemoinformatics, is considered with respect to complex relations between chemical objects (graphs or descriptor vectors). Statistical Learning Theory, one of the main mathematical approaches in structure‐property modeling, is briefly reviewed. Links between chemoinformatics and its “sister” fields – machine learning, chemometrics and bioinformatics are discussed.