Emilio Xavier Esposito

Findings of the Challenge To Predict Aqueous Solubility

The Solubility Challenge is based upon intrinsic solubility data measured in one laboratory for a set of biologically relevant compounds. More than 100 entries to the Solubility Challenge have been received. In several cases multiple entries came from the same person or group. In addition, more than 5% of the prediction sheet entries were incomplete in that predictions were not reported for all 32 compounds of the prediction set. These incomplete entries are not included in the overall findings given here, but the submitted prediction sheets, like those of all other entries, have been scored and will be returned by email to the contestants along with a copy of this report. Overall, 99 completed entries were scored and are reported here.

In Silico Binary Classification QSAR Models Based on 4D-Fingerprints and MOE Descriptors for Prediction of hERG Blockage

Blockage of the human ether-a-go-go related gene (hERG) potassium ion channel is a major factor related to cardiotoxicity. Hence, drugs binding to this channel have become an important biological end point in side effects screening. A set of 250 structurally diverse compounds screened for hERG activity from the literature was assembled using a set of reliability filters. This data set was used to construct a set of two-state hERG QSAR models. The descriptor pool used to construct the models consisted of 4D-fingerprints generated from the thermodynamic distribution of conformer states available to a molecule, 204 traditional 2D descriptors and 76 3D VolSurf-like descriptors computed using the Molecular Operating Environment (MOE) software. One model is a continuous partial least-squares (PLS) QSAR hERG binding model. Another related model is an optimized binary classification QSAR model that classifies compounds as active or inactive. This binary model achieves 91% accuracy over a large range of molecular diversity spanning the training set. Two external test sets were constructed. One test set is the condensed PubChem bioassay database containing 876 compounds, and the other test set consists of 106 additional compounds found in the literature. Both of the test sets were used to validate the binary QSAR model. The binary QSAR model permits a structural interpretation of possible sources for hERG activity. In particular, the presence of a polar negative group at a distance of 6-8 A from a hydrogen bond donor in a compound is predicted to be a quite structure-specific pharmacophore that increases hERG blockage. Since a data set of high chemical diversity was used to construct the binary model, it is applicable for performing general virtual hERG screening.

Dependence of QSAR Models on the Selection of Trial Descriptor Sets: A Demonstration Using Nanotoxicity Endpoints of Decorated Nanotubes

Little attention has been given to the selection of trial descriptor sets when designing a QSAR analysis even though a great number of descriptor classes, and often a greater number of descriptors within a given class, are now available. This paper reports an effort to explore interrelationships between QSAR models and descriptor sets. Zhou and co-workers (Zhou et al., Nano Lett. 2008, 8 (3), 859-865) designed, synthesized, and tested a combinatorial library of 80 surface modified, that is decorated, multi-walled carbon nanotubes for their composite nanotoxicity using six endpoints all based on a common 0 to 100 activity scale. Each of the six endpoints for the 29 most nanotoxic decorated nanotubes were incorporated as the training set for this study. The study reported here includes trial descriptor sets for all possible combinations of MOE, VolSurf, and 4D-fingerprints (FP) descriptor classes, as well as including and excluding explicit spatial contributions from the nanotube. Optimized QSAR models were constructed from these multiple trial descriptor sets. It was found that (a) both the form and quality of the best QSAR models for each of the endpoints are distinct and (b) some endpoints are quite dependent upon 4D-FP descriptors of the entire nanotube-decorator complex. However, other endpoints yielded equally good models only using decorator descriptors with and without the decorator-only 4D-FP descriptors. Lastly, and most importantly, the quality, significance, and interpretation of a QSAR model were found to be critically dependent on the trial descriptor sets used within a given QSAR endpoint study.

Oversampling to Overcome Overfitting: Exploring the Relationship between Data Set Composition, Molecular Descriptors, and Predictive Modeling Methods

The traditional biological assay is very time-consuming, and thus the ability to quickly screen large numbers of compounds against a specific biological target is appealing. To speed up the biological evaluation of compounds, high-throughput screening is widely used in the fields of biomedical, biological information, and drug discovery. The research presented in this study focuses on the use of support vector machines, a machine learning method, various classes of molecular descriptors, and different sampling techniques to overcome overfitting to classify compounds for cytotoxicity with respect to the Jurkat cell line. The cell cytotoxicity data set is imbalanced (a few active compounds and very many inactive compounds), and the ability of the predictive modeling methods is adversely affected in these situations. Commonly imbalanced data sets are overfit with respect to the dominant classified end point; in this study the models routinely overfit toward inactive (noncytotoxic) compounds when the imbalance was substantial. Support vector machine (SVM) models were used to probe the proficiency of different classes of molecular descriptors and oversampling ratios. The SVM models were constructed from 4D-FPs, MOE (1D, 2D, and 21/2D), noNP+MOE, and CATS2D trial descriptors pools and compared to the predictive abilities of CATS2D-based random forest models. Compared to previous results in the literature, the SVM models built from oversampled data sets exhibited better predictive abilities for the training and external test sets.

The great descriptor melting pot: mixing descriptors for the common good of QSAR models

The usefulness and utility of QSAR modeling depends heavily on the ability to estimate the values of molecular descriptors relevant to the endpoints of interest followed by an optimized selection of descriptors to form the best QSAR models from a representative set of the endpoints of interest. The performance of a QSAR model is directly related to its molecular descriptors. QSAR modeling, specifically model construction and optimization, has benefited from its ability to borrow from other unrelated fields, yet the molecular descriptors that form QSAR models have remained basically unchanged in both form and preferred usage. There are many types of endpoints that require multiple classes of descriptors (descriptors that encode 1D through multi-dimensional, 4D and above, content) needed to most fully capture the molecular features and interactions that contribute to the endpoint. The advantages of QSAR models constructed from multiple, and different, descriptor classes have been demonstrated in the exploration of markedly different, and principally biological systems and endpoints. Multiple examples of such QSAR applications using different descriptor sets are described and that examined. The take-home-message is that a major part of the future of QSAR analysis, and its application to modeling biological potency, ADME-Tox properties, general use in virtual screening applications, as well as its expanding use into new fields for building QSPR models, lies in developing strategies that combine and use 1D through nD molecular descriptors.

Predictive toxicology modeling: protocols for exploring hERG classification and Tetrahymena pyriformis end point predictions.

The inclusion and accessibility of different methodologies to explore chemical data sets has been beneficial to the field of predictive modeling, specifically in the chemical sciences in the field of Quantitative Structure-Activity Relationship (QSAR) modeling. This study discusses using contemporary protocols and QSAR modeling methods to properly model two biomolecular systems that have historically not performed well using traditional and three-dimensional QSAR methodologies. Herein, we explore, analyze, and discuss the creation of a classification human Ether-a-go-go Related Gene (hERG) potassium channel model and a continuous Tetrahymena pyriformis (T. pyriformis) model using Support Vector Machine (SVM) and Support Vector Regression (SVR), respectively. The models are constructed with three types of molecular descriptors that capture the gross physicochemical features of the compounds: (i) 2D, 2 1/2D, and 3D physical features, (ii) VolSurf-like molecular interaction fields, and (iii) 4D-Fingerprints. The best hERG SVM model achieved 89% accuracy and the three-best SVM models were able to screen a Pubchem data set with an accuracy of 97%. The best T. pyriformis model had an R(2) value of 0.924 for the training set and was able to predict the continuous end points for two test sets with R(2) values of 0.832 and 0.620, respectively. The studies presented within demonstrate the predictive ability (classification and continuous end points) of QSAR models constructed from curated data sets, biologically relevant molecular descriptors, and Support Vector Machines and Support Vector Regression. The ability of these protocols and methodologies to accommodate large data sets (several thousands compounds) that are chemically diverse - and in the case of classification modeling unbalanced (one experimental outcome dominates the data set) - allows scientists to further explore a remarkable amount of biological and chemical information.

Exploring the Physicochemical Properties of Oxime-Reactivation Therapeutics for Cyclosarin, Sarin, Tabun, and VX Inactivated Acetylcholinesterase

The inactivation of acetylcholinesterase (AChE) by organophosphorus agent (OP) compounds is a serious problem regardless of how the individual was exposed. The reactivation of OP-inactivated AChE is dependent on the OP conjugate, and commonly a specific oxime is better at reactivating a specific OP conjugate than several diverse OP conjugates. The presented research explores the physicochemical properties needed for the reactivation of OP-inactivated AChE. Four different OPs, cyclosarin, sarin, tabun, and VX, were analyzed using the same set of oxime reactivators. A trial descriptor pool of semiempirical, traditional, and molecular interaction field descriptors was used to construct an ensemble of QSAR models for each OP-conjugate pair. Based on the molecular information and the cross-validation ability, individual QSAR models were selected to be part of an OP-conjugate consensus model. The OP-conjugate specific models provide important insight into the physicochemical properties required to reactivate the OP conjugates of interest. The reactivation of AChE inactivated with either cyclosarin or tabun requires the oxime therapeutic to possess an overall polar-positive surface area. Oxime therapeutics for the reactivation of sarin-inactivated AChE are conformationally dependent while oxime reverse therapeutics for VX require a compact region with a highly hydrophilic region and two positively charged pyridine rings.

Categorical QSAR models for skin sensitization based on local lymph node assay measures and both ground and excited state 4D-fingerprint descriptors

In previous studies we have developed categorical QSAR models for predicting skin-sensitization potency based on 4D-fingerprint (4D-FP) descriptors and in vivo murine local lymph node assay (LLNA) measures. Only 4D-FP derived from the ground state (GMAX) structures of the molecules were used to build the QSAR models. In this study we have generated 4D-FP descriptors from the first excited state (EMAX) structures of the molecules. The GMAX, EMAX and the combined ground and excited state 4D-FP descriptors (GEMAX) were employed in building categorical QSAR models. Logistic regression (LR) and partial least square coupled logistic regression (PLS-CLR), found to be effective model building for the LLNA skin-sensitization measures in our previous studies, were used again in this study. This also permitted comparison of the prior ground state models to those involving first excited state 4D-FP descriptors. Three types of categorical QSAR models were constructed for each of the GMAX, EMAX and GEMAX datasets: a binary model (2-state), an ordinal model (3-state) and a binary-binary model (two-2-state). No significant differences exist among the LR 2-state model constructed for each of the three datasets. However, the PLS-CLR 3-state and 2-state models based on the EMAX and GEMAX datasets have higher predictivity than those constructed using only the GMAX dataset. These EMAX and GMAX categorical models are also more significant and predictive than corresponding models built in our previous QSAR studies of LLNA skin-sensitization measures.

Experimental and Computational Studies of Physicochemical Properties Influence NSAID-Cyclodextrin Complexation

The objective of this research was to investigate physicochemical properties of an active pharmaceutical ingredient (API) that influence cyclodextrin complexation through experimental and computational studies. Native β-cyclodextrin (B-CD) and two hydroxypropyl derivatives were first evaluated by conventional phase solubility experiments for their ability to complex four poorly water-soluble nonsteroidal anti-inflammatory drugs (NSAIDs). Differential scanning calorimetry was used to confirm complexation. Secondly, molecular modeling was used to estimate Log P and aqueous solubility (So) of the NSAIDs. Molecular dynamics simulations (MDS) were used to investigate the thermodynamics and geometry of drug-CD cavity docking. NSAID solubility increased linearly with increasing CD concentration for the two CD derivatives (displaying an AL profile), whereas increases in drug solubility were low and plateaued in the B-CD solutions (type B profile). The calculated Log P and So of the NSAIDs were in good concordance with experimental values reported in the literature. Side chain substitutions on the B-CD moiety did not significantly influence complexation. Explicitly, complexation and the associated solubility increase were mainly dependent on the chemical structure of the NSAID. MDS indicated that each NSAID-CD complex had a distinct geometry. Moreover, complexing energy had a large, stabilizing, and fairly constant hydrophobic component for a given CD across the NSAIDs, while electrostatic and solvation interaction complex energies were quite variable but smaller in magnitude.

Exploring possible mechanisms of action for the nanotoxicity and protein binding of decorated nanotubes: interpretation of physicochemical properties from optimal QSAR models.

Carbon nanotubes have become widely used in a variety of applications including biosensors and drug carriers. Therefore, the issue of carbon nanotube toxicity is increasingly an area of focus and concern. While previous studies have focused on the gross mechanisms of action relating to nanomaterials interacting with biological entities, this study proposes detailed mechanisms of action, relating to nanotoxicity, for a series of decorated (functionalized) carbon nanotube complexes based on previously reported QSAR models. Possible mechanisms of nanotoxicity for six endpoints (bovine serum albumin, carbonic anhydrase, chymotrypsin, hemoglobin along with cell viability and nitrogen oxide production) have been extracted from the corresponding optimized QSAR models. The molecular features relevant to each of the endpoint respective mechanism of action for the decorated nanotubes are also discussed. Based on the molecular information contained within the optimal QSAR models for each nanotoxicity endpoint, either the decorator attached to the nanotube is directly responsible for the expression of a particular activity, irrespective of the decorators 3D-geometry and independent of the nanotube, or those decorators having structures that place the functional groups of the decorators as far as possible from the nanotube surface most strongly influence the biological activity. These molecular descriptors are further used to hypothesize specific interactions involved in the expression of each of the six biological endpoints.