In silico modelling of permeation enhancement potency in Caco-2 monolayers based on molecular descriptors and random forest

Quantum-Informed Molecular Representation Learning Enhancing ADMET Property Prediction

We examined pretraining tasks leveraging abundant labeled data to effectively enhance molecular representation learning in downstream tasks, specifically emphasizing graph transformers to improve the prediction of ADMET properties. Our investigation revealed limitations in previous pretraining tasks and identified more meaningful training targets, ranging from 2D molecular descriptors to extensive quantum chemistry simulations. These data were seamlessly integrated into supervised pretraining tasks. The implementation of our pretraining strategy and multitask learning outperforms conventional methods, achieving state-of-the-art outcomes in 7 out of 22 ADMET tasks within the Therapeutics Data Commons by utilizing a shared encoder across all tasks. Our approach underscores the effectiveness of learning molecular representations and highlights the potential for scalability when leveraging extensive data sets, marking a significant advancement in this domain.

Combining SILCS and Artificial Intelligence for High-Throughput Prediction of the Passive Permeability of Drug Molecules

Membrane permeability of drug molecules plays a significant role in the development of new therapeutic agents. Accordingly, methods to predict the passive permeability of drug candidates during a medicinal chemistry campaign offer the potential to accelerate the drug design process. In this work, we combine the physics-based site identification by ligand competitive saturation (SILCS) method and data-driven artificial intelligence (AI) to create a high-throughput predictive model for the passive permeability of druglike molecules. In this study, we present a comparative analysis of four regression models to predict membrane permeabilities of small druglike molecules; of the tested models, Random Forest was the most predictive yielding an R2 of 0.81 for the independent data set. The input feature vector used to train the developed prediction model includes absolute free energy profiles of ligands through a POPC-cholesterol bilayer based on ligand grid free energy (LGFE) profiles obtained from the SILCS approach. The use of the membrane free energy profiles from SILCS offers information on the physical forces contributing to ligand permeability, while the use of AI yields a more predictive model trained on experimental PAMPA permeability data for a collection of 229 molecules. This combination allows for rapid estimations of ligand permeability at a level of accuracy beyond currently available predictive models while offering insights into the contributions of the functional groups in the ligands to the permeability barrier, thereby offering quantitative information to facilitate rational ligand design.

Gaultheria leucocarpa var. yunnanensis for Treating Rheumatoid Arthritis-An Assessment Combining Machine Learning-Guided ADME Properties Prediction, Network Pharmacology, and Pharmacological Assessment

Background: Dianbaizhu (Gaultheria leucocarpa var. yunnanensis), a traditional Chinese/ethnic medicine (TC/EM), has been used to treat rheumatoid arthritis (RA) for a long time. The anti-rheumatic arthritis fraction (ARF) of G. yunnanensis has significant anti-inflammatory and analgesic activities and is mainly composed of methyl salicylate glycosides, flavonoids, organic acids, and others. The effective ingredients and rudimentary mechanism of ARF remedying RA have not been elucidated to date. Purpose: The aim of the present study is to give an insight into the effective components and mechanisms of Dianbaizhu in ameliorating RA, based on the estimation of the absorption, distribution, metabolism, and excretion (ADME) properties, analysis of network pharmacology, and in vivo and in vitro validations. Study design and methods: The IL-1β-induced human fibroblast-like synoviocytes of RA (HFLS-RA) model and adjuvant-induced arthritis in the rat model were adopted to assess the anti-RA effect of ARF. The components in ARF were identified by using UHPLC-LTQ-Orbitrap-MSⁿ. The quantitative structure-activity relationship (QSAR) models were developed by using five machine learning algorithms, alone or in combination with genetic algorithms for predicting the ADME properties of ARF. The molecular networks and pathways presumably referring to the therapy of ARF on RA were yielded by using common databases and visible software, and the experimental validations of the key targets conducted in vitro. Results: ARF effectively relieved RA in vivo and in vitro. The five optimized QSAR models that were developed showed robustness and predictive ability. The characterized 48 components in ARF had good biological potency. Four key signaling pathways were obtained, which were related to both cytokine signaling and cell immune response. ARF suppressed IL-1β-induced expression of EGFR, MMP 9, IL2, MAPK14, and KDR in the HFLS-RA . Conclusions: ARF has good druggability and high exploitation potential. Methyl salicylate glycosides and flavonoids play essential roles in attuning RA. ARF may partially attenuate RA by regulating the expression of multi-targets in the inflammation-immune system. These provide valuable information to rationalize ARF and other TC/EMs in the treatment of RA.

Development of a Hierarchical Support Vector Regression-Based In Silico Model for Caco-2 Permeability

Drug absorption is one of the critical factors that should be taken into account in the process of drug discovery and development. The human colon carcinoma cell layer (Caco-2) model has been frequently used as a surrogate to preliminarily investigate the intestinal absorption. In this study, a quantitative structure–activity relationship (QSAR) model was generated using the innovative machine learning-based hierarchical support vector regression (HSVR) scheme to depict the exceedingly confounding passive diffusion and transporter-mediated active transport. The HSVR model displayed good agreement with the experimental values of the training samples, test samples, and outlier samples. The predictivity of HSVR was further validated by a mock test and verified by various stringent statistical criteria. Consequently, this HSVR model can be employed to forecast the Caco-2 permeability to assist drug discovery and development.

Approaches for integrating heterogeneous RNA-seq data reveal cross-talk between microbes and genes in asthmatic patients

Sputum induction is a non-invasive method to evaluate the airway environment, particularly for asthma. RNA sequencing (RNA-seq) of sputum samples can be challenging to interpret due to the complex and heterogeneous mixtures of human cells and exogenous (microbial) material. In this study, we develop a pipeline that integrates dimensionality reduction and statistical modeling to grapple with the heterogeneity. LDA(Latent Dirichlet allocation)-link connects microbes to genes using reduced-dimensionality LDA topics. We validate our method with single-cell RNA-seq and microscopy and then apply it to the sputum of asthmatic patients to find known and novel relationships between microbes and genes.

Predicting HCV Incidence in Latinos with High-Risk Substance Use: A Data Science Approach

Hepatitis C virus (HCV) in the U.S. has tripled in the prior five years, and injecting drug use is the primary risk for HCV, with up to 90% of older and former people who inject drugs (PWIDs) testing positive. Laboratory testing of HCV for any PWIDs is the gold standard, however many PWIDs lack access to health treatment or services. Identifying risks of HCV via a data science approach would aid community health workers (CHW) to rapidly link those most at risk of infection with treatment. This study employed a data-science approach to determine the strongest risk factors of HCV in a sample of Mexican-Americans WIDs n = 221 (96 negative/125 positive). Data included 238 demographic and psychosocial predictors. A Random Forest machine learning algorithm demonstrated significant prediction improvement over baseline no information rate comparison. Strongest risks for positive HCV included sharing drug-use equipment and younger age at first heroin use; receiving drug-education during incarceration was protective. A ROC curve fit to the prediction yielded an area under the curve of 0.77. Predictive variables of HCV in the present analysis can be obtained via screening by CHW. Identification of patients most at risk of HCV within community settings can maximize treatment utilization.

Comparison of the Predictive Performance and Interpretability of Random Forest and Linear Models on Benchmark Data Sets

The ability to interpret the predictions made by quantitative structure-activity relationships (QSARs) offers a number of advantages. While QSARs built using nonlinear modeling approaches, such as the popular Random Forest algorithm, might sometimes be more predictive than those built using linear modeling approaches, their predictions have been perceived as difficult to interpret. However, a growing number of approaches have been proposed for interpreting nonlinear QSAR models in general and Random Forest in particular. In the current work, we compare the performance of Random Forest to those of two widely used linear modeling approaches: linear Support Vector Machines (SVMs) (or Support Vector Regression (SVR)) and partial least-squares (PLS). We compare their performance in terms of their predictivity as well as the chemical interpretability of the predictions using novel scoring schemes for assessing heat map images of substructural contributions. We critically assess different approaches for interpreting Random Forest models as well as for obtaining predictions from the forest. We assess the models on a large number of widely employed public-domain benchmark data sets corresponding to regression and binary classification problems of relevance to hit identification and toxicology. We conclude that Random Forest typically yields comparable or possibly better predictive performance than the linear modeling approaches and that its predictions may also be interpreted in a chemically and biologically meaningful way. In contrast to earlier work looking at interpretation of nonlinear QSAR models, we directly compare two methodologically distinct approaches for interpreting Random Forest models. The approaches for interpreting Random Forest assessed in our article were implemented using open-source programs that we have made available to the community. These programs are the rfFC package ( https://r-forge.r-project.org/R/?group_id=1725 ) for the R statistical programming language and the Python program HeatMapWrapper [ https://doi.org/10.5281/zenodo.495163 ] for heat map generation.

Intestinal permeation enhancers for oral peptide delivery

Intestinal permeation enhancers (PEs) are one of the most widely tested strategies to improve oral delivery of therapeutic peptides. This article assesses the intestinal permeation enhancement action of over 250 PEs that have been tested in intestinal delivery models. In depth analysis of pre-clinical data is presented for PEs as components of proprietary delivery systems that have progressed to clinical trials. Given the importance of co-presentation of sufficiently high concentrations of PE and peptide at the small intestinal epithelium, there is an emphasis on studies where PEs have been formulated with poorly permeable molecules in solid dosage forms and lipoidal dispersions.

Design and optimization of self-nanoemulsifying drug delivery systems for improved bioavailability of cyclovirobuxine D

Background

The main purpose of this research was to design a self-nanoemulsifying drug delivery system (SNEDDS) for improving the bioavailability of cyclovirobuxine D as a poorly water-soluble drug.

Materials and methods

Solubility trials, emulsifying studies, and pseudo-ternary phase diagrams were used to screen the SNEDDS formulations. The optimized drug-loaded SNEDDS was prepared at a mass ratio of 3:24:38:38 for cyclovirobuxine D, oleic acid, Solutol SH15, and propylene glycol, respectively. The optimized formulation was characterized in terms of physicochemical and pharmacokinetic parameters compared with marketed cyclovirobuxine D tablets.

Results

The optimized cyclovirobuxine-D-loaded SNEDDS was spontaneously dispersed to form a nanoemulsion with a globule size of 64.80±3.58 nm, which exhibited significant improvement of drug solubility, rapid absorption rate, and enhanced area under the curve, together with increased permeation and decreased efflux. Fortunately, there was a nonsignificant cytotoxic effect toward Caco-2 cells. The relative bioavailability of SNEDDS was 200.22% in comparison with market tablets, in rabbits.

Conclusion

SNEDDS could be a potential candidate for an oral dosage form of cyclovirobuxine D with improved bioavailability.