A prediction model for oral bioavailability of drugs using physicochemical properties by support vector machine

Probabilistic Modelling of the Food Matrix Effects on Curcuminoid's In Vitro Oral Bioaccessibility

The bioaccessibility of bioactive compounds plays a major role in the nutritional value of foods, but there is a lack of systematic studies assessing the effect of the food matrix on bioaccessibility. Curcuminoids are phytochemicals extracted from Curcuma longa that have captured public attention due to claimed health benefits. The aim of this study is to develop a mathematical model to predict curcuminoid's bioaccessibility in biscuits and custard based on different fibre type formulations. Bioaccessibilities for curcumin-enriched custards and biscuits were obtained through in vitro digestion, and physicochemical food properties were characterised. A strong correlation between macronutrient concentration and bioaccessibility was observed (p = 0.89) and chosen as a main explanatory variable in a Bayesian hierarchical linear regression model. Additionally, the patterns of food matrix effects on bioaccessibility were not the same in custards as in biscuits; for example, the hemicellulose content had a moderately strong positive correlation to bioaccessibility in biscuits (p = 0.66) which was non-significant in custards (p = 0.12). Using a Bayesian hierarchical approach to model these interactions resulted in an optimisation performance of r2 = 0.97 and a leave-one-out cross-validation score (LOOCV) of r2 = 0.93. This decision-support system could assist the food industry in optimising the formulation of novel food products and enable consumers to make more informed choices.

Computational Predictions of Nonclinical Pharmacokinetics at the Drug Design Stage

Although computational predictions of pharmacokinetics (PK) are desirable at the drug design stage, existing approaches are often limited by prediction accuracy and human interpretability. Using a discovery data set of mouse and rat PK studies at Roche (9,685 unique compounds), we performed a proof-of-concept study to predict key PK properties from chemical structure alone, including plasma clearance (CLp), volume of distribution at steady-state (Vss), and oral bioavailability (F). Ten machine learning (ML) models were evaluated, including Single-Task, Multitask, and transfer learning approaches (i.e., pretraining with in vitro data). In addition to prediction accuracy, we emphasized human interpretability of outcomes, especially the quantification of uncertainty, applicability domains, and explanations of predictions in terms of molecular features. Results show that intravenous (IV) PK properties (CLp and Vss) can be predicted with good precision (average absolute fold error, AAFE of 1.96-2.84 depending on data split) and low bias (average fold error, AFE of 0.98-1.36), with AutoGluon, Gaussian Process Regressor (GP), and ChemProp displaying the best performance. Driven by higher complexity of oral PK studies, predictions of F were more challenging, with the best AAFE values of 2.35-2.60 and higher overprediction bias (AFE of 1.45-1.62). Multi-Task approaches and pretraining of ChemProp neural networks with in vitro data showed similar precision to Single-Task models but helped reduce the bias and increase correlations between observations and predictions. A combination of GP-computed prediction variance, molecular clustering, and dimensionality-reduction provided valuable quantitative insights into prediction uncertainty and applicability domains. SHAPley Additive exPlanations (SHAPs) highlighted molecular features contributing to prediction outcomes of Vss, providing explanations that could aid drug design. Combined results show that computational predictions of PK are feasible at the drug design stage, with several ML technologies converging to successfully leverage historical PK data sets. Further studies are needed to unlock the full potential of this approach, especially with respect to data set sizes and quality, transfer learning between in vitro and in vivo data sets, model-independent quantification of uncertainty, and explainability of predictions.

Machine learning & deep learning in data-driven decision making of drug discovery and challenges in high-quality data acquisition in the pharmaceutical industry

Predicting novel small molecule bioactivities for the target deconvolution, hit-to-lead optimization in drug discovery research, requires molecular representation. Previous reports have demonstrated that machine learning (ML) and deep learning (DL) have substantial implications in virtual screening, peptide synthesis, drug ADMET screening and biomarker discovery. These strategies can increase the positive outcomes in the drug discovery process without false-positive rates and can be achieved in a cost-effective way with a minimum duration of time by high-quality data acquisition. This review substantially discusses the recent updates in AI tools as cheminformatics application in medicinal chemistry for the data-driven decision making of drug discovery and challenges in high-quality data acquisition in the pharmaceutical industry while improving small-molecule bioactivities and properties.

Recent Applications of Artificial Intelligence in detection of Gastrointestinal, Hepatic and Pancreatic Diseases

There is substantial progress in artificial intelligence (AI) algorithms and their medical sciences applications in the last two decades. AI-assisted programs have already been established for remotely health monitoring using sensors and smartphones. A variety of AI-based prediction models available for the gastrointestinal inflammatory, non-malignant diseases, and bowel bleeding using wireless capsule endoscopy, electronic medical records for hepatitis-associated fibrosis, pancreatic carcinoma using endoscopic ultrasounds. AI-based models may be of immense help for healthcare professionals in the identification, analysis, and decision support using endoscopic images to establish prognosis and risk assessment of patient's treatment using multiple factors. Although enough randomized clinical trials are warranted to establish the efficacy of AI-algorithms assisted and non-AI based treatments before approval of such techniques from medical regulatory authorities. In this article, available AI approaches and AI-based prediction models for detecting gastrointestinal, hepatic, and pancreatic diseases are reviewed. The limitation of AI techniques in such disease prognosis, risk assessment, and decision support are discussed.

SMILES to Smell: Decoding the Structure-Odor Relationship of Chemical Compounds Using the Deep Neural Network Approach

Finding the relationship between the structure of an odorant molecule and its associated smell has always been an extremely challenging task. The major limitation in establishing the structure-odor relation is the vague and ambiguous nature of the descriptor-labeling, especially when the sources of odorant molecules are different. With the advent of deep networks, data-driven approaches have been substantiated to achieve more accurate linkages between the chemical structure and its smell. In this study, the deep neural network (DNN) with physiochemical properties and molecular fingerprints (PPMF) and the convolution neural network (CNN) with chemical-structure images (IMG) are developed to predict the smells of chemicals using their SMILES notations. A data set of 5185 chemical compounds with 104 smell percepts was used to develop the multilabel prediction models. The accuracies of smell prediction from DNN + PPMF and CNN + IMG (Xception based) were found to be 97.3 and 98.3%, respectively, when applied on an independent test set of chemicals. The deep learning architecture combining both DNN + PPMF and CNN + IMG prediction models is proposed, which classifies smells and may help understand the generic mechanism underlying the relationship between chemical structure and smell perception.

Prediction of Oral Bioavailability in Rats: Transferring Insights from in Vitro Correlations to (Deep) Machine Learning Models Using in Silico Model Outputs and Chemical Structure Parameters

Oral administration of drug products is a strict requirement in many medical indications. Therefore, bioavailability prediction models are of high importance for prioritization of compound candidates in the drug discovery process. However, oral exposure and bioavailability are difficult to predict, as they are the result of various highly complex factors and/or processes influenced by the physicochemical properties of a compound, such as solubility, lipophilicity, or charge state, as well as by interactions with the organism, for instance, metabolism or membrane permeation. In this study, we assess whether it is possible to predict intravenous (iv) or oral drug exposure and oral bioavailability in rats. As input parameters, we use (i) six experimentally determined in vitro and physicochemical endpoints, namely, membrane permeation, free fraction, metabolic stability, solubility, pK_a value, and lipophilicity; (ii) the outputs of six in silico absorption, distribution, metabolism, and excretion models trained on the same endpoints, or (iii) the chemical structure encoded as fingerprints or simplified molecular input line entry system strings. The underlying data set for the models is an unprecedented collection of almost 1900 data points with high-quality in vivo experiments performed in rats. We find that drug exposure after iv administration can be predicted similarly well using hybrid models with in vitro- or in silico-predicted endpoints as inputs, with fold change errors (FCE) of 2.28 and 2.08, respectively. The FCEs for exposure after oral administration are higher, and here, the prediction from in vitro inputs performs significantly better in comparison to in silico-based models with FCEs of 3.49 and 2.40, respectively, most probably reflecting the higher complexity of oral bioavailability. Simplifying the prediction task to a binary alert for low oral bioavailability, based only on chemical structure, we achieve accuracy and precision close to 70%.

Broadening the horizon: Integrative pharmacophore-based and cheminformatics screening of novel chemical modulators of mitochondria ATP synthase towards interventive Alzheimer's disease therapy

The proven efficacy of J147 in the treatment of Alzheimer's disease (AD) has been emphatic, particularly since its selective modulatory roles towards mitochondrial ATP synthase (mATPase) were defined. This prospect, if methodically probed, could further pave way for the discovery of novel anti-AD drugs with improved pharmacokinetics and therapeutic potential. To this effect, for the first time, we employed a four-step paradigm that integrated our in-house per-residue energy decomposition (PRED) protocol coupled with molecular dynamics, cheminformatics and analytical binding free energy methods. This was geared towards the screening and identification of new leads that exhibit modulatory potentials towards mATPase in a J147-similar pattern. Interestingly, from a large-scale library of compounds, we funnelled down on three potential hits that demonstrated selective and high-affinity binding activities towards α-F1-ATP synthase (ATP5A) relative to J147. Moreover, these compounds exhibited higher binding propensity with a differential ΔGs greater than -1 kcal/mol comparative to J147, and also elicited distinct modulatory effects on ATP5A domain structures. More interestingly, per-residue pharmacophore modeling of these lead compounds revealed similar interactive patterns with crucial residues at the α-site region of ATP5A characterized by high energy contributions based on binding complementarity. Recurrent target residues involved in high-affinity interactions with the hit molecules relative to J147 include Arg1112 and Gln426. Furthermore, assessments of pharmacokinetics revealed that the lead compounds were highly drug-like with minimal violations of the Lipinski's rule of five. As developed in this study, the most extrapolative pharmacophore model of the selected hits encompassed three electron donors and one electron acceptor. We speculate that these findings will be fundamental to the reformation of anti-AD drug discovery procedures.

Synthesis of pyrazolo-1,2,4-triazolo[4,3-a]quinoxalines as antimicrobial agents with potential inhibition of DHPS enzyme

AIM

The development of a new class of antimicrobial agents is the optimal lifeline to scrap the escalating jeopardy of drug resistance.

EXPERIMENTAL

This study aims to design and synthesize a series of pyrazolo-1,2,4-triazolo[4,3-a]quinoxalines, to develop agents having antimicrobial activity through potential inhibition of dihyropteroate synthase enzyme. The target compounds have been evaluated for their in-vitro antimicrobial activity.

RESULTS & DISCUSSION

Compounds 5b, 5c were equipotent (minimal inhibitory concentration = 12.5 μg/ml) to ampicillin. The docking patterns of 5b and 5c demonstrated that both fit into Bacillus Anthracis dihydropteroate synthase pterin and p-amino benzoic acid-binding pockets. Moreover, their physicochemical properties and pharmacokinetic profiles recommend that they can be considered drug-like candidates. The results highlight some significant information for the future design of lead compounds as antimicrobial agents.

Adversarial Threshold Neural Computer for Molecular de Novo Design

In this article, we propose the deep neural network Adversarial Threshold Neural Computer (ATNC). The ATNC model is intended for the de novo design of novel small-molecule organic structures. The model is based on generative adversarial network architecture and reinforcement learning. ATNC uses a Differentiable Neural Computer as a generator and has a new specific block, called adversarial threshold (AT). AT acts as a filter between the agent (generator) and the environment (discriminator + objective reward functions). Furthermore, to generate more diverse molecules we introduce a new objective reward function named Internal Diversity Clustering (IDC). In this work, ATNC is tested and compared with the ORGANIC model. Both models were trained on the SMILES string representation of the molecules, using four objective functions (internal similarity, Muegge druglikeness filter, presence or absence of sp³-rich fragments, and IDC). The SMILES representations of 15K druglike molecules from the ChemDiv collection were used as a training data set. For the different functions, ATNC outperforms ORGANIC. Combined with the IDC, ATNC generates 72% of valid and 77% of unique SMILES strings, while ORGANIC generates only 7% of valid and 86% of unique SMILES strings. For each set of molecules generated by ATNC and ORGANIC, we analyzed distributions of four molecular descriptors (number of atoms, molecular weight, logP, and tpsa) and calculated five chemical statistical features (internal diversity, number of unique heterocycles, number of clusters, number of singletons, and number of compounds that have not been passed through medicinal chemistry filters). Analysis of key molecular descriptors and chemical statistical features demonstrated that the molecules generated by ATNC elicited better druglikeness properties. We also performed in vitro validation of the molecules generated by ATNC; results indicated that ATNC is an effective method for producing hit compounds.

Fragment-Based Ligand Designing

Fragment-based drug design strategies have been used in drug discovery since it was first demonstrated using experimental structural biology techniques such as nuclear magnetic resonance (NMR) and X-ray crystallography. The underlying idea is that existing or new chemical entities with known desirable properties may serve both as tool compounds and as starting points for hit-to-lead expansion. Despite the recent advancements, there remain challenges to overcome, such as assembly of the synthetically feasible structures, development of scoring functions to correlate structure and their activities, and fine tuning of the promising molecules. This chapter first covers the theoretical background needed to understand the concepts and the challenges related to the field of study, followed by the description of important protocols and related software. Case studies are presented to demonstrate practical applications.

Chemometric Evaluation of THz Spectral Similarity for the Selection of Early Drug Candidates

In this paper we discuss the link between the domain of physical parameters - molecular descriptors of a drug, and terahertz (THz) spectra. We measured the derivatives of the well-known anti-inflammatory drug Piroxicam using THz spectroscopy and employed Principal Component Analysis to build similarity maps in the molecular descriptor and spectral domains. We observed, that the spatial neighborhood on the molecular descriptors map is highly correlated with the spectral neighbourhood within a group of structurally-similar molecules. We built a Partial Least Squares (PLS) predictive model to quantify the relationship between the spectra and the melting point, which can guide the selection of early drug candidates.

Linking existing in vitro dermal absorption data to physicochemical properties: Contribution to the design of a weight-of-evidence approach for the safety evaluation of cosmetic ingredients with low dermal bioavailability

To characterize the risk of cosmetic ingredients when threshold toxicity is assumed, often the "margin of safety" (MoS) is calculated. This uncertainty factor is based on the systemic no observable (adverse) effect level (NO(A)EL) which can be derived from in vivo repeated dose toxicity studies. As in vivo studies for the purpose of the cosmetic legislation are no longer allowed in Europe and a validated in vitro alternative is not yet available, it is no longer possible to derive a NO(A)EL value for a new cosmetic ingredient. Alternatively, cosmetic ingredients with a low dermal bioavailability might not need repeated dose data, as internal exposure will be minimal and systemic toxicity might not be an issue. This study shows the possibility of identifying compounds suspected to have a low dermal bioavailability based on their physicochemical properties (molecular weight, melting point, topological polar surface area and log P) and their in vitro dermal absorption data. Although performed on a limited number of compounds, the study suggests a strategic opportunity to support the safety assessor's reasoning to omit a MoS calculation and to focus more on local toxicity and mutagenicity/genotoxicity for ingredients for which limited systemic exposure is to be expected.

Drug/nondrug classification using Support Vector Machines with various feature selection strategies

In conjunction with the advance in computer technology, virtual screening of small molecules has been started to use in drug discovery. Since there are thousands of compounds in early-phase of drug discovery, a fast classification method, which can distinguish between active and inactive molecules, can be used for screening large compound collections. In this study, we used Support Vector Machines (SVM) for this type of classification task. SVM is a powerful classification tool that is becoming increasingly popular in various machine-learning applications. The data sets consist of 631 compounds for training set and 216 compounds for a separate test set. In data pre-processing step, the Pearson's correlation coefficient used as a filter to eliminate redundant features. After application of the correlation filter, a single SVM has been applied to this reduced data set. Moreover, we have investigated the performance of SVM with different feature selection strategies, including SVM-Recursive Feature Elimination, Wrapper Method and Subset Selection. All feature selection methods generally represent better performance than a single SVM while Subset Selection outperforms other feature selection methods. We have tested SVM as a classification tool in a real-life drug discovery problem and our results revealed that it could be a useful method for classification task in early-phase of drug discovery.