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 towards 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.

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 .

This article is about the hierarchical quantitative structure-activity relationship technology (HiT QSAR) based on the Simplex representation of molecular structure (SiRMS) and its application for different QSAR/QSP(property)R tasks. The essence of this technology is a sequential solution (with the use of the information obtained on the previous steps) to the QSAR problem by the series of enhanced models of molecular structure description [from one dimensional (1D) to four dimensional (4D)]. It is a system of permanently improved solutions. In the SiRMS approach, every molecule is represented as a system of different simplexes (tetratomic fragments with fixed composition, structure, chirality and symmetry). The level of simplex descriptors detailing increases consecutively from the 1D to 4D representation of the molecular structure. The advantages of the approach reported here are the absence of "molecular alignment" problems, consideration of different physical-chemical properties of atoms (e.g. charge, lipophilicity, etc.), the high adequacy and good interpretability of obtained models and clear ways for molecular design. The efficiency of the HiT QSAR approach is demonstrated by comparing it with the most popular modern QSAR approaches on two representative examination sets. The examples of successful application of the HiT QSAR for various QSAR/QSPR investigations on the different levels (1D-4D) of the molecular structure description are also highlighted. The reliability of developed QSAR models as predictive virtual screening tools and their ability to serve as the base of directed drug design was validated by subsequent synthetic and biological experiments, among others. The HiT QSAR is realized as a complex of computer programs known as HIT QSAR: software that also includes a powerful statistical block and a number of useful utilities.

Structural alerts are widely accepted in chemical toxicology and regulatory decision support as a simple and transparent means to flag potential chemical hazards or group compounds into categories for read-across. However, there has been a growing concern that alerts disproportionally flag too many chemicals as toxic, which questions their reliability as toxicity markers. Conversely, the rigorously developed and properly validated statistical QSAR models can accurately and reliably predict the toxicity of a chemical; however, their use in regulatory toxicology has been hampered by the lack of transparency and interpretability. We demonstrate that contrary to the common perception of QSAR models as “black boxes” they can be used to identify statistically significant chemical substructures (QSAR-based alerts) that influence toxicity. We show through several case studies, however, that the mere presence of structural alerts in a chemical, irrespective of the derivation method (expert-based or QSAR-based), should be perceived only as hypotheses of possible toxicological effect. We propose a new approach that synergistically integrates structural alerts and rigorously validated QSAR models for a more transparent and accurate safety assessment of new chemicals.

This review is devoted to the critical analysis of advantages and disadvantages of existing mixture descriptors and their usage in various QSAR/QSPR tasks. We describe good practices for the QSAR modeling of mixtures, data sources for mixtures, a discussion of various mixture descriptors and their application, recommendations about proper external validation specific for mixture QSAR modeling, and future perspectives of this field. The biggest problem in QSAR of mixtures is the lack of reliable data about the mixtures' properties. Various mixture descriptors are used for the modeling of different endpoints. However, these descriptors have certain disadvantages, such as applicability only to 1 : 1 binary mixtures, and additive nature. The field of QSAR of mixtures is still under development, and existing efforts could be considered as a foundation for future approaches and studies. The usage of non-additive mixture descriptors, which are sensitive to interaction effects, in combination with best practices of QSAR model development (e.g., thorough data collection and curation, rigorous external validation, etc.) will significantly improve the quality of QSAR studies of mixtures.

Many metal oxide nanoparticles are able to cause persistent stress to live organisms, including humans, when discharged to the environment. To understand the mechanism of metal oxide nanoparticles' toxicity and reduce the number of experiments, the development of predictive toxicity models is important. In this study, performed on a series of nanoparticles, the comparative quantitative-structure activity relationship (nano-QSAR) analyses of their toxicity towards E. coli and HaCaT cells were established. A new approach for representation of nanoparticles' structure is presented. For description of the supramolecular structure of nanoparticles the "liquid drop" model was applied. It is expected that a novel, proposed approach could be of general use for predictions related to nanomaterials. In addition, in our study fragmental simplex descriptors and several ligand-metal binding characteristics were calculated. The developed nano-QSAR models were validated and reliably predict the toxicity of all studied metal oxide nanoparticles. Based on the comparative analysis of contributed properties in both models the LDM-based descriptors were revealed to have an almost similar level of contribution to toxicity in both cases, while other parameters (van der Waals interactions, electronegativity and metal-ligand binding characteristics) have unequal contribution levels. In addition, the models developed here suggest different mechanisms of nanotoxicity for these two types of cells.

This work is devoted to the application of the random forest approach to QSAR analysis of aquatic toxicity of chemical compounds tested on Tetrahymena pyriformis. The simplex representation of the molecular structure approach implemented in HiT QSAR Software was used for descriptors generation on a two-dimensional level. Adequate models based on simplex descriptors and the RF statistical approach were obtained on a modeling set of 644 compounds. Model predictivity was validated on two external test sets of 339 and 110 compounds. The high impact of lipophilicity and polarizability of investigated compounds on toxicity was determined. It was shown that RF models were tolerant for insertion of irrelevant descriptors as well as for randomization of some part of toxicity values that were representing a "noise". The fast procedure of optimization of the number of trees in the random forest has been proposed. The discussed RF model had comparable or better statistical characteristics than the corresponding PLS or KNN models.

In this paper we offer a novel approach for the structural interpretation of QSAR models. The major advantage of our developed methodology is its universality, i.e., it can be applied to any QSAR/QSPR model irrespective of chemical descriptors and machine learning methods applied. This universality was achieved by using only the information obtained from substructures of the compounds of interest to interpret model outcomes. Reliability of the offered approach was confirmed by the results of three case studies, including end-points of different types (continuous and binary classification) and nature (solubility, mutagenicity, and inhibition of Transglutaminase 2), various fragment and whole-molecule descriptors (Simplex and Dragon), and multiple modeling techniques (partial least squares, random forest, and support vector machines). We compared the global contributions of molecular fragments obtained using our methodology with known SAR rules derived experimentally. In all cases high concordance between our interpretation and results published by others was observed. Although the proposed interpretation approach could be easily extended to any type of descriptors, we would recommend using Simplex descriptors to achieve a larger variety of investigated molecular fragments. The developed approach is a good tool for interpretation of such "black box" models like random forest, neural networks, etc. Analysis of fragment global contributions and their deviation across a dataset could be useful for the identification of key fragments and structural alerts. This information could be helpful to maximize the positive influence of structural surroundings on the given fragment and to decrease the negative effects.