Francesca Grisoni

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

Beware of Unreliable Q2! A Comparative Study of Regression Metrics for Predictivity Assessment of QSAR Models

Validation is an essential step of QSAR modeling, and it can be performed by both internal validation techniques (e.g., cross-validation, bootstrap) or by an external set of test objects, that is, objects not used for model development and/or optimization. The evaluation of model predictive ability is then completed by comparing experimental and predicted values of test molecules. When dealing with quantitative QSAR models, validation results are generally expressed in terms of Q2 metrics. In this work, four fundamental mathematical principles, which should be respected by any Q2 metric, are introduced. Then, the behavior of five different metrics (QF12, QF22, QF32, QCCC2, and QRm2) is compared and critically discussed. The conclusions highlight that only the QF32 metric satisfies all the stated conditions, while the remaining metrics show different theoretical flaws.

In Silico Prediction of Cytochrome P450-Drug Interaction: QSARs for CYP3A4 and CYP2C9

Cytochromes P450 (CYP) are the main actors in the oxidation of xenobiotics and play a crucial role in drug safety, persistence, bioactivation, and drug-drug/food-drug interaction. This work aims to develop Quantitative Structure-Activity Relationship (QSAR) models to predict the drug interaction with two of the most important CYP isoforms, namely 2C9 and 3A4. The presented models are calibrated on 9122 drug-like compounds, using three different modelling approaches and two types of molecular description (classical molecular descriptors and binary fingerprints). For each isoform, three classification models are presented, based on a different approach and with different advantages: (1) a very simple and interpretable classification tree; (2) a local (k-Nearest Neighbor) model based classical descriptors and; (3) a model based on a recently proposed local classifier (N-Nearest Neighbor) on binary fingerprints. The salient features of the work are (1) the thorough model validation and the applicability domain assessment; (2) the descriptor interpretation, which highlighted the crucial aspects of P450-drug interaction; and (3) the consensus aggregation of models, which largely increased the prediction accuracy.

QSAR models for bioconcentration: Is the increase in the complexity justified by more accurate predictions?

This study compares nine QSAR models for the prediction of BCF on fish: four KOW based models (Veith, Mackay, Bintein and TGD equations) and five complex models (EPI Suite BCFBAF, VEGA CAESAR, VEGA Meylan, VEGA Read-across and VEGA consensus). The aim is to test if increasing complexity leads to predictions that are more accurate than those based only on KOW are. To this end, experimental BCF data for 1056 compounds, along with experimental and predicted KOW values, were collected and used for the comparison. A particular focus has been placed on compounds for which metabolism, elimination and specific interactions with tissues can be hypothesized. VEGA Read-across improved global predictions with respect to the KOW based models and resulted to be a good approach to take into account metabolism and interactions with tissues. For the other complex models, several drawbacks were highlighted. Finally, for different classes of compounds (i.e. Perfluorinated Compounds, Organophosphorous Compounds, Synthetic Pyrethroids and Polychlorinated Biphenyls) results confirmed the mechanistic interpretation of the processes involved in their bioconcentration.

Investigating the mechanisms of bioconcentration through QSAR classification trees

This paper proposes a scheme to predict whether a compound (1) is mainly stored within lipid tissues, (2) has additional storage sites (e.g., proteins), or (3) is metabolized/eliminated with a reduced bioconcentration. The approach is based on two validated QSAR (Quantitative Structure-Activity Relationship) trees, whose salient features are: (a) descriptor interpretability and (b) simplicity. Trees were developed for 779 organic compounds, the TGD approach was used to quantify the lipid-driven bioconcentration, and a refined machine-learning optimization procedure was applied. We focused on molecular descriptor interpretation, which allowed us to gather new mechanistic insights into the bioconcentration mechanisms.

De Novo Design of Bioactive Small Molecules by Artificial Intelligence

Generative artificial intelligence offers a fresh view on molecular design. We present the first‐time prospective application of a deep learning model for designing new druglike compounds with desired activities. For this purpose, we trained a recurrent neural network to capture the constitution of a large set of known bioactive compounds represented as SMILES strings. By transfer learning, this general model was fine‐tuned on recognizing retinoid X and peroxisome proliferator‐activated receptor agonists. We synthesized five top‐ranking compounds designed by the generative model. Four of the compounds revealed nanomolar to low‐micromolar receptor modulatory activity in cell‐based assays. Apparently, the computational model intrinsically captured relevant chemical and biological knowledge without the need for explicit rules. The results of this study advocate generative artificial intelligence for prospective de novo molecular design, and demonstrate the potential of these methods for future medicinal chemistry.

Matrix-based Molecular Descriptors for Prospective Virtual Compound Screening.

Molecular descriptors capture diverse structural information of molecules and are a prerequisite for ligand‐based similarity searching. In this study, we introduce topological matrix‐based descriptors to virtual screening for hit discovery. We evaluated the usefulness of matrix‐based descriptors in a retrospective setting and compared them with topological pharmacophore descriptors. Special attention was given to the influence of data pre‐processing and the applied similarity metric on the virtual screening performance. Overall, the MB descriptors showed a competitive and complementary performance to other descriptors. A prospective screen of a commercial compound library led to the discovery of a novel natural‐product‐derived cyclooxygenase‐2 inhibitor predicted to interact differently with the target protein compared to the query compound ibuprofen. The results of our study motivate the use of matrix‐based descriptors for molecular similarity‐based virtual screening and scaffold hopping.

Expert QSAR system for predicting the bioconcentration factor under the REACH regulation

Expert systems are a rational integration of several models that generally aim to exploit their advantages and overcome their drawbacks. This work is founded on our previously published Quantitative Structure-Activity Relationship (QSAR) classification scheme, which detects compounds whose Bioconcentration Factor (BCF) is (1) well predicted by the octanol-water partition coefficient (KOW), (2) underestimated by KOW or (3) overestimated by KOW. The classification scheme served as the starting point to identify and combine the best BCF model for each class among three VEGA models and one KOW-based equation. The rationalized model integration showed stability and surprising performance on unknown data when compared with benchmark BCF models. Model simplicity, transparency and mechanistic interpretation were fostered in order to allow for its application and acceptance within the REACH framework.

Reshaped Sequential Replacement for variable selection in QSPR: comparison with other reference methods

The objective of the present work was to compare the Reshaped Sequential Replacement (RSR) algorithm with other well‐known variable selection techniques in the field of Quantitative Structure–Property Relationship (QSPR) modelling. RSR algorithm is based on a simple sequential replacement procedure with the addition of several ‘reshaping’ functions that aimed to (i) ensure a faster convergence upon optimal subsets of variables and (ii) reject models affected by chance correlation, overfitting and other pathologies. In particular, three reference variable selection methods were chosen for the comparison (stepwise forward selection, genetic algorithms and particle swarm optimization), aiming to identify benefits and drawbacks of RSR with respect to these methods. To this end, several QSPR datasets regarding different physical–chemical properties and characterized by different objects/variables ratios were used to build ordinary least squares models; in addition, some well‐known (Y‐scrambling) and more recent (R‐based functions) statistical tools were used to analyse and compare the results. The study highlighted the good capability of RSR to find optimal subsets of variables in QSPR modelling, comparable or better than those found by the other reference variable selection methods. Moreover, RSR resulted to be faster than some of the analysed variable selection techniques, despite its extensive exploration of the variables space. Copyright

A QSTR-Based Expert System to Predict Sweetness of Molecules

This work describes a novel approach based on advanced molecular similarity to predict the sweetness of chemicals. The proposed Quantitative Structure-Taste Relationship (QSTR) model is an expert system developed keeping in mind the five principles defined by the Organization for Economic Co-operation and Development (OECD) for the validation of (Q)SARs. The 649 sweet and non-sweet molecules were described by both conformation-independent extended-connectivity fingerprints (ECFPs) and molecular descriptors. In particular, the molecular similarity in the ECFPs space showed a clear association with molecular taste and it was exploited for model development. Molecules laying in the subspaces where the taste assignation was more difficult were modeled trough a consensus between linear and local approaches (Partial Least Squares-Discriminant Analysis and N-nearest-neighbor classifier). The expert system, which was thoroughly validated through a Monte Carlo procedure and an external set, gave satisfactory results in comparison with the state-of-the-art models. Moreover, the QSTR model can be leveraged into a greater understanding of the relationship between molecular structure and sweetness, and into the design of novel sweeteners.