Development and Use of Hydrophobic Surface Area (HSA) Descriptors for Computer-Assisted Quantitative Structure−Activity and Structure−Property Relationship Studies

Exploring blood-brain barrier passage using atomic weighted vector and machine learning

CONTEXT

This study investigates the potential of leveraging molecular properties, as determined by MD-LOVIs software and machine learning techniques, to predict the ability of compounds to cross the blood-brain barrier (BBB). Accurate prediction of BBB permeation is critical for the development of central nervous system (CNS) drugs. The study applies various machine learning models, including both classification and regression techniques, to predict BBB passage and molecular activity. Notably, classification models such as GBM-AWV (accuracy = 0.801), GLM-CN (accuracy = 0.808), SVMPoly-means (accuracy = 0.980), SVMPoly-AC (accuracy = 0.980), SVMPoly-MI_TI_SI (accuracy = 0.900), SVMPoly-GI (accuracy = 0.900), RF-means (accuracy = 0.870), and GLM-means (accuracy = 0.818) demonstrate high accuracy in predicting BBB passage. In contrast, regression models like ES-RLM-AG (R2 = 0.902), IB-IBK (R2 = 0.82), IB-Kstar (R2 = 0.834), IB-MLP (R2 = 0.843), and DRF-AWV (R2 = 0.810) exhibit strong performance in predicting molecular activity. The results show that classification models like GBM-AWV, GLM-CN, and SVMPoly variants, as well as regression models like ES-RLM-AG and IB-MLP, achieve high performance, demonstrating the effectiveness of machine learning in predicting BBB permeability.

METHODS

The computational methods employed in this study include the MD-LOVIs software for generating molecular descriptors and several machine learning algorithms, including gradient boosting machines (GBM), generalized linear models (GLM), support vector machines (SVM) with polynomial kernels, random forests (RF), ensemble regression models, and instance-based learning algorithms. These models were trained and validated using various datasets to predict BBB passage and molecular activity, with the performance metrics reported for each model. Standard computational techniques were employed throughout, ensuring the reliability of the predictions.

Rational Design of Cholesterol Derivative for Improved Stability of Paclitaxel Cationic Liposomes

PURPOSE

This work explores synthesis of novel cholesterol derivative for the preparation of cationic liposomes and its interaction with Paclitaxel (PTX) within liposome membrane using molecular dynamic (MD) simulation and in-vitro studies.

METHODS

Cholesteryl Arginine Ethylester (CAE) was synthesized and characterized. Cationic liposomes were prepared using Soy PC (SPC) at a molar ratio of 77.5:15:7.5 of SPC/CAE/PTX. Conventional liposomes were composed of SPC/cholesterol/PTX (92:5:3 M ratio). The interaction between paclitaxel, ligand and the membrane was studied using 10 ns MD simulation. The interactions were studied using Differential Scanning Calorimetry (DSC) and Small Angle Neutron Scattering analysis. The efficacy of liposomes was evaluated by MTT assay and endothelial cell migration assay on different cell lines. The safety of the ligand was determined using the Comet Assay.

RESULTS

The cationic liposomes improved loading efficiency and stability compared to conventional liposomes. The increased PTX loading could be attributed to the hydrogen bond between CAE and PTX and deeper penetration of PTX in the bilayer. The DSC study suggested that inclusion of CAE in the DPPC bilayer eliminates T_g. SANS data showed that CAE has more pronounced membrane thickening effect as compared to cholesterol. The cationic liposomes showed slightly improved cytotoxicity in three different cell lines and improved endothelial cell migration inhibition compared to conventional liposomes. Furthermore, the COMET assay showed that CAE alone does not show any genotoxicity.

CONCLUSIONS

The novel cationic ligand (CAE) retains paclitaxel within the phospholipid bilayer and helps in improved drug loading and physical stability. Graphical Abstract ᅟ.

Open Source Bayesian Models. 3. Composite Models for Prediction of Binned Responses

Bayesian models constructed from structure-derived fingerprints have been a popular and useful method for drug discovery research when applied to bioactivity measurements that can be effectively classified as active or inactive. The results can be used to rank candidate structures according to their probability of activity, and this ranking benefits from the high degree of interpretability when structure-based fingerprints are used, making the results chemically intuitive. Besides selecting an activity threshold, building a Bayesian model is fast and requires few or no parameters or user intervention. The method also does not suffer from such acute overtraining problems as quantitative structure–activity relationships or quantitative structure–property relationships (QSAR/QSPR). This makes it an approach highly suitable for automated workflows that are independent of user expertise or prior knowledge of the training data. We now describe a new method for creating a composite group of Bayesian models to extend the method to work with multiple states, rather than just binary. Incoming activities are divided into bins, each covering a mutually exclusive range of activities. For each of these bins, a Bayesian model is created to model whether or not the compound belongs in the bin. Analyzing putative molecules using the composite model involves making a prediction for each bin and examining the relative likelihood for each assignment, for example, highest value wins. The method has been evaluated on a collection of hundreds of data sets extracted from ChEMBL v20 and validated data sets for ADME/Tox and bioactivity.

Towards Better BBB Passage Prediction Using an Extensive and Curated Data Set

In the present report, the challenging task of drug delivery across the blood-brain barrier (BBB) is addressed via a computational approach. The BBB passage was modeled using classification and regression schemes on a novel extensive and curated data set (the largest to the best of our knowledge) in terms of log BB. Prior to the model development, steps of data analysis that comprise chemical data curation, structural, cutoff and cluster analysis (CA) were conducted. Linear Discriminant Analysis (LDA) and Multiple Linear Regression (MLR) were used to fit classification and correlation functions. The best LDA-based model showed overall accuracies over 85 % and 83 % for the training and test sets, respectively. Also a MLR-based model with acceptable explanation of more than 69 % of the variance in the experimental log BB was developed. A brief and general interpretation of proposed models allowed the estimation on how 'near' our computational approach is to the factors that determine the passage of molecules through the BBB. In a final effort some popular and powerful Machine Learning methods were considered. Comparable or similar performance was observed respect to the simpler linear techniques. Most of the compounds with anomalous behavior were put aside into a set denoted as controversial set and discussion regarding to these compounds is provided. Finally, our results were compared with methodologies previously reported in the literature showing comparable to better results. The results could represent useful tools available and reproducible by all scientific community in the early stages of neuropharmaceutical drug discovery/development projects.

Exploring QSTR modeling and toxicophore mapping for identification of important molecular features contributing to the chemical toxicity in Escherichia coli

Biodiversity deprivation can affect functions and services of the ecosystem. Changes in biodiversity alter ecosystem processes and change the resilience of ecosystems to ecological changes. Bacterial communities are the main form of biomass in the ecosystem and one of largest populations on the planet. Bacterial communities provide important services to biodiversity. They break down pollutants, municipal waste and ingested food, and they are the primary route for recycling of organic matter to plants and other autotrophs, conversion of inorganic matter into new biological tissue using sunlight, management of energy crisis through use of biofuel. In the present study, computational chemistry and statistical modeling have been used to develop mathematical equations which can be applied to calculate toxicity of new/unknown chemicals/biofuels/metabolites in Escherichia coli. 2D and 3D descriptors were generated from molecular structure of compounds and mathematical models have been developed using genetic function approximation followed by multiple linear regression (GFA-MLR) method. Model validity was checked through defined internal (R(2)=0.751 and Q(2)=0.711), and external (Rpred(2)=0.773) statistical parameters. Molecular features responsible for toxicity were also assessed through 3D toxicophore study. The toxicophore-based model was validated (R=0.785) using qualitative statistical metrics and randomization test (Fischer validation).

Molecular determinants of juvenile hormone action as revealed by 3D QSAR analysis in Drosophila

BACKGROUND

Postembryonic development, including metamorphosis, of many animals is under control of hormones. In Drosophila and other insects these developmental transitions are regulated by the coordinate action of two principal hormones, the steroid ecdysone and the sesquiterpenoid juvenile hormone (JH). While the mode of ecdysone action is relatively well understood, the molecular mode of JH action remains elusive.

METHODOLOGY/PRINCIPAL FINDINGS

To gain more insights into the molecular mechanism of JH action, we have tested the biological activity of 86 structurally diverse JH agonists in Drosophila melanogaster. The results were evaluated using 3D QSAR analyses involving CoMFA and CoMSIA procedures. Using this approach we have generated both computer-aided and species-specific pharmacophore fingerprints of JH and its agonists, which revealed that the most active compounds must possess an electronegative atom (oxygen or nitrogen) at both ends of the molecule. When either of these electronegative atoms are replaced by carbon or the distance between them is shorter than 11.5 A or longer than 13.5 A, their biological activity is dramatically decreased. The presence of an electron-deficient moiety in the middle of the JH agonist is also essential for high activity.

CONCLUSIONS/SIGNIFICANCE

The information from 3D QSAR provides guidelines and mechanistic scope for identification of steric and electrostatic properties as well as donor and acceptor hydrogen-bonding that are important features of the ligand-binding cavity of a JH target protein. In order to refine the pharmacophore analysis and evaluate the outcomes of the CoMFA and CoMSIA study we used pseudoreceptor modeling software PrGen to generate a putative binding site surrogate that is composed of eight amino acid residues corresponding to the defined molecular interactions.

Assessing how well a modeling protocol captures a structure-activity landscape

We introduce the notion of structure-activity landscape index (SALI) curves as a way to assess a model and a modeling protocol, applied to structure-activity relationships. We start from our earlier work [ J. Chem. Inf. Model., 2008, 48, 646-658], where we show how to study a structure-activity relationship pairwise, based on the notion of "activity cliffs"--pairs of molecules that are structurally similar but have large differences in activity. There, we also introduced the SALI parameter, which allows one to identify cliffs easily, and which allows one to represent a structure-activity relationship as a graph. This graph orders every pair of molecules by their activity. Here, we introduce the new idea of a SALI curve, which tallies how many of these orderings a model is able to predict. Empirically, testing these SALI curves against a variety of models, ranging over two-dimensional quantitative structure-activity relationship (2D-QSAR), three-dimensional quantitative structure-activity relationship (3D-QSAR), and structure-based design models, the utility of a model seems to correspond to characteristics of these curves. In particular, the integral of these curves, denoted as SCI and being a number ranging from -1.0 to 1.0, approaches a value of 1.0 for two literature models, which are both known to be prospectively useful.

Statistical cluster analysis of pharmaceutical solvents

High efficiency in polymorph screening and crystallization optimization can be gained by judicious selection of solvents for the study design. Examination of all 57 (classes 2 and 3) pharmaceutical solvents may enable a complete study design but is costly in terms of time and resources. Based on a 17 descriptor dataset specifically constructed for all the classes 2 and 3 pharmaceutical solvents recognized by the International Conference of Harmonization (ICH), an optimal two-stage cluster analysis was carried out together with principal component analysis as a dimensionality and colinearity reduction pre-processor. Both hierarchical average linkage cluster analysis and non-hierarchical K-means cluster analysis converged on a 20-cluster solution with strong statistical criteria support and excellent agreement in cluster memberships, which can be reasonably interpreted from a chemical perspective. This 20-cluster solution is offered as an option for design of more efficient solid state screening studies. Rather than designing a polymorph screen to include all 57 solvents, the inclusion of a single member from each of the 20 clusters would be expected to adequately represent the full range of solvent properties exhibited by the entire 57 member solvent set.

Enantiomeric separation and determination of absolute stereochemistry of asymmetric molecules in drug discovery—Building chiral technology toolboxes

The application of Chiral Technology, or the (extensive) use of techniques or tools for the determination of absolute stereochemistry and the enantiomeric or chiral separation of racemic small molecule potential lead compounds, has been critical to successfully discovering and developing chiral drugs in the pharmaceutical industry. This has been due to the rapid increase over the past 10-15 years in potential drug candidates containing one or more asymmetric centers. Based on the experiences of one pharmaceutical company, a summary of the establishment of a Chiral Technology toolbox, including the implementation of known tools as well as the design, development, and implementation of new Chiral Technology tools, is provided.

Correlating toxicities of organic compounds to select protozoa using the Abraham model

The Abraham solvation parameter model is used to construct mathematical correlations for describing the nonspecific toxicity of organic compounds to three protozoas (Entosiphon sulcantum, Uronema parduczi and Chilomonas paramecium). The derived mathematical correlations describe the observed published toxicity data to within an overall average standard deviation of approximately 0.35 log units. The correlations can be used to estimate aquatic toxicities of organic chemicals to the three aquatic organisms studied, and to help in identifying compounds whose toxic mode of action might involve chemical specific reactivity, rather than nonpolar or polar narcosis. A principal component analysis of the correlation equations found in this work shows that no water-solvent system we have investigated is a good model for nonspecific aquatic toxicity towards the three protozoas. Furthermore, correlation equations for nonspecific aqueous toxicity towards various biological systems, that we have found in this work and in previous studies, cover such a wide range that no single water-solvent system could ever be a good model for all the biological systems.