QSAR Modeling of Human Serum Protein Binding with Several Modeling Techniques Utilizing Structure−Information Representation

Machine learning methods for unveiling the potential of antioxidant short peptides in goat milk-derived proteins during in vitro gastrointestinal digestion

Milk serves as an important dietary source of bioactive peptides, offering notable benefits to individuals. Among the antioxidant short peptides (di- and tripeptides) generated from gastrointestinal digestion are characterized by enhanced bioavailability and bioaccessibility, while assessing them individually presents a labor-intensive and expensive challenge. Based on 4 distinct types of AA descriptors (physicochemical, 3-dimensional structural, quantum, and topological attributes) and genetic algorithms for feature selection, 1 and 4 machine learning-predicted models separately for di- and tripeptides with 2,2-azinobis(3-ethylbenzothiazoline-6-sulfonic acid) diammonium salt radical scavenging capacity exhibited excellent fitting and prediction ability with random forest regression as machine learning algorithm. Intriguingly, the electronic properties of N-terminal AA were considered as only factor affecting the antioxidant capacity of dipeptides containing both tyrosine and tryptophan. Four peptides from the potential di- and tripeptides exhibited highly predicted values by the constructed predicted models. Subsequently, a total of 45 dipeptides and 52 tripeptides were screened by a customized workflow in goat milk during in vitro simulated digestion. In addition to 5 known antioxidant dipeptides, 9 peptides were quantified during digestion, exhibiting concentrations ranging from 0.04 to 1.78 mg L-1. Particularly noteworthy was the promising in vivo functionality of antioxidant dipeptides with N-terminal tyrosine, supported by in silico assays. Overall, this investigation explored crucial molecular properties influencing antioxidant short peptides and high-throughput screening potential peptides with antioxidant activity from goat milk aided by machine learning, thereby facilitating the discovery of novel functional peptides from milk-derived proteins and paving the way for understanding their metabolites during digestion.

The state-of-the-art machine learning model for Plasma Protein Binding Prediction: computational modeling with OCHEM and experimental validation

Plasma protein binding (PPB) is closely related to pharmacokinetics, pharmacodynamics and drug toxicity. Existing models for predicting PPB often suffer from low prediction accuracy and poor interpretability, especially for high PPB compounds, and are most often not experimentally validated. Here, we carried out a strict data curation protocol, and applied consensus modeling to obtain a model with a coefficient of determination of 0.90 and 0.91 on the training set and the test set, respectively. This model (available on the OCHEM platform https://ochem.eu/article/29) was further retrospectively validated for a set of 63 poly-fluorinated molecules and prospectively validated for a set of 25 highly diverse compounds, and its performance for both these sets was superior to that of the other previously reported models. Furthermore, we identified the physicochemical and structural characteristics of high and low PPB molecules for further structural optimization. Finally, we provide practical and detailed recommendations for structural optimization to decrease PPB binding of lead compounds.

Exploring molecular fragments for fraction unbound in human plasma of chemicals: a fragment-based cheminformatics approach

Fraction unbound in plasma (fu,p) of drugs is an significant factor for drug delivery and other biological incidences related to the pharmacokinetic behaviours of drugs. Exploration of different molecular fragments for fu,p of different small molecules/agents can facilitate in identification of suitable candidates in the preliminary stage of drug discovery. Different researchers have implemented strategies to build several prediction models for fu,p of different drugs. However, these studies did not focus on the identification of responsible molecular fragments to determine the fraction unbound in plasma. In the current work, we tried to focus on the development of robust classification-based QSAR models and evaluated these models with multiple statistical metrics to identify essential molecular fragments/structural attributes for fractions unbound in plasma. The study unequivocally suggests various N-containing aromatic rings and aliphatic groups have positive influences and sulphur-containing thiadiazole rings have negative influences for the fu,p values. The molecular fragments may help for the assessment of the fu,p values of different small molecules/drugs in a speedy way in comparison to experiment-based in vivo and in vitro studies.

Systematic evaluation of high-throughput PBK modelling strategies for the prediction of intravenous and oral pharmacokinetics in humans

Physiologically based kinetic (PBK) modelling offers a mechanistic basis for predicting the pharmaco-/toxicokinetics of compounds and thereby provides critical information for integrating toxicity and exposure data to replace animal testing with in vitro or in silico methods. However, traditional PBK modelling depends on animal and human data, which limits its usefulness for non-animal methods. To address this limitation, high-throughput PBK modelling aims to rely exclusively on in vitro and in silico data for model generation. Here, we evaluate a variety of in silico tools and different strategies to parameterise PBK models with input values from various sources in a high-throughput manner. We gather 2000 + publicly available human in vivo concentration-time profiles of 200 + compounds (IV and oral administration), as well as in silico, in vitro and in vivo determined compound-specific parameters required for the PBK modelling of these compounds. Then, we systematically evaluate all possible PBK model parametrisation strategies in PK-Sim and quantify their prediction accuracy against the collected in vivo concentration-time profiles. Our results show that even simple, generic high-throughput PBK modelling can provide accurate predictions of the pharmacokinetics of most compounds (87% of Cmax and 84% of AUC within tenfold). Nevertheless, we also observe major differences in prediction accuracies between the different parameterisation strategies, as well as between different compounds. Finally, we outline a strategy for high-throughput PBK modelling that relies exclusively on freely available tools. Our findings contribute to a more robust understanding of the reliability of high-throughput PBK modelling, which is essential to establish the confidence necessary for its utilisation in Next-Generation Risk Assessment.

Advances in Modeling Approaches for Oral Drug Delivery: Artificial Intelligence, Physiologically-Based Pharmacokinetics, and First-Principles Models

Oral drug absorption is the primary route for drug administration. However, this process hinges on multiple factors, including the drug's physicochemical properties, formulation characteristics, and gastrointestinal physiology. Given its intricacy and the exorbitant costs associated with experimentation, the trial-and-error method proves prohibitively expensive. Theoretical models have emerged as a cost-effective alternative by assimilating data from diverse experiments and theoretical considerations. These models fall into three categories: (i) data-driven models, encompassing classical pharmacokinetics, quantitative-structure models (QSAR), and machine/deep learning; (ii) mechanism-based models, which include quasi-equilibrium, steady-state, and physiologically-based pharmacokinetics models; and (iii) first principles models, including molecular dynamics and continuum models. This review provides an overview of recent modeling endeavors across these categories while evaluating their respective advantages and limitations. Additionally, a primer on partial differential equations and their numerical solutions is included in the appendix, recognizing their utility in modeling physiological systems despite their mathematical complexity limiting widespread application in this field.

A Combination of Machine Learning and PBPK Modeling Approach for Pharmacokinetics Prediction of Small Molecules in Humans

PURPOSE

Recently, there has been rapid development in model-informed drug development, which has the potential to reduce animal experiments and accelerate drug discovery. Physiologically based pharmacokinetic (PBPK) and machine learning (ML) models are commonly used in early drug discovery to predict drug properties. However, basic PBPK models require a large number of molecule-specific inputs from in vitro experiments, which hinders the efficiency and accuracy of these models. To address this issue, this paper introduces a new computational platform that combines ML and PBPK models. The platform predicts molecule PK profiles with high accuracy and without the need for experimental data.

METHODS

This study developed a whole-body PBPK model and ML models of plasma protein fraction unbound ( f up ), Caco-2 cell permeability, and total plasma clearance to predict the PK of small molecules after intravenous administration. Pharmacokinetic profiles were simulated using a "bottom-up" PBPK modeling approach with ML inputs. Additionally, 40 compounds were used to evaluate the platform's accuracy.

RESULTS

Results showed that the ML-PBPK model predicted the area under the concentration-time curve (AUC) with 65.0 % accuracy within a 2-fold range, which was higher than using in vitro inputs with 47.5 % accuracy.

CONCLUSION

The ML-PBPK model platform provides high accuracy in prediction and reduces the number of experiments and time required compared to traditional PBPK approaches. The platform successfully predicts human PK parameters without in vitro and in vivo experiments and can potentially guide early drug discovery and development.

Isolation, Virtual Screening, and Evaluation of Hazelnut-Derived Immunoactive Peptides for the Inhibition of SARS-CoV-2 Main Protease

The aim of this study is to validate the activity of hazelnut (Corylus avellana L.)-derived immunoactive peptides inhibiting the main protease (Mpro) of SARS-CoV-2 and further unveil their interaction mechanism using in vitro assays, molecular dynamics (MD) simulations, and binding free energy calculations. In general, the enzymatic hydrolysis components, especially molecular weight < 3 kDa, possess good immune activity as measured by the proliferation ability of mouse splenic lymphocytes and phagocytic activity of mouse peritoneal macrophages. Over 866 unique peptide sequences were isolated, purified, and then identified by nanohigh-performance liquid chromatography/tandem mass spectrometry (NANO-HPLC-MS/MS) from hazelnut protein hydrolysates, but Trp-Trp-Asn-Leu-Asn (WWNLN) and Trp-Ala-Val-Leu-Lys (WAVLK) in particular are found to increase the cell viability and phagocytic capacity of RAW264.7 macrophages as well as promote the secretion of the cytokines nitric oxide (NO), tumor necrosis factor-α (TNF-α), and interleukin-1β (IL-1β). Fluorescence resonance energy transfer assay elucidated that WWNLN and WAVLK exhibit excellent inhibitory potency against Mpro, with IC50 values of 6.695 and 16.750 μM, respectively. Classical all-atom MD simulations show that hydrogen bonds play a pivotal role in stabilizing the complex conformation and protein-peptide interaction. Molecular Mechanics/Generalized Born Surface Area (MM/GBSA) calculation indicates that WWNLN has a lower binding free energy with Mpro than WAVLK. Furthermore, adsorption, distribution, metabolism, excretion, and toxicity (ADMET) predictions illustrate favorable drug-likeness and pharmacokinetic properties of WWNLN compared to WAVLK. This study provides a new understanding of the immunomodulatory activity of hazelnut hydrolysates and sheds light on peptide inhibitors targeting Mpro.

Attention Mechanism-Based Graph Neural Network Model for Effective Activity Prediction of SARS-CoV-2 Main Protease Inhibitors: Application to Drug Repurposing as Potential COVID-19 Therapy

Compared to de novo drug discovery, drug repurposing provides a time-efficient way to treat coronavirus disease 19 (COVID-19) that is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). SARS-CoV-2 main protease (Mpro) has been proved to be an attractive drug target due to its pivotal involvement in viral replication and transcription. Here, we present a graph neural network-based deep-learning (DL) strategy to prioritize the existing drugs for their potential therapeutic effects against SARS-CoV-2 Mpro. Mpro inhibitors were represented as molecular graphs ready for graph attention network (GAT) and graph isomorphism network (GIN) modeling for predicting the inhibitory activities. The result shows that the GAT model outperforms the GIN and other competitive models and yields satisfactory predictions for unseen Mpro inhibitors, confirming its robustness and generalization. The attention mechanism of GAT enables to capture the dominant substructures and thus to realize the interpretability of the model. Finally, we applied the optimal GAT model in conjunction with molecular docking simulations to screen the Drug Repurposing Hub (DRH) database. As a result, 18 drug hits with best consensus prediction scores and binding affinity values were identified as the potential therapeutics against COVID-19. Both the extensive literature searching and evaluations on adsorption, distribution, metabolism, excretion, and toxicity (ADMET) illustrate the premium drug-likeness and pharmacokinetic properties of the drug candidates. Overall, our work not only provides an effective GAT-based DL prediction tool for inhibitory activity of SARS-CoV-2 Mpro inhibitors but also provides theoretical guidelines for drug discovery in the COVID-19 treatment.

Investigation of the Binding Fraction of PFAS in Human Plasma and Underlying Mechanisms Based on Machine Learning and Molecular Dynamics Simulation

More than 7000 per- and polyfluorinated alkyl substances (PFAS) have been documented in the U.S. Environmental Protection Agency's CompTox Chemicals database. These PFAS can be used in a broad range of industrial and consumer applications but may pose potential environmental issues and health risks. However, little is known about emerging PFAS bioaccumulation to assess their chemical safety. This study focuses specifically on the large and high-quality data set of fluorochemicals from the related environmental and pharmaceutical chemicals databases, and machine learning (ML) models were developed for the classification prediction of the unbound fraction of compounds in plasma. A comprehensive evaluation of the ML models shows that the best blending model yields an accuracy of 0.901 for the test set. The predictions suggest that most PFAS (∼92%) have a high binding fraction in plasma. Introduction of alkaline amino groups is likely to reduce the binding affinities of PFAS with plasma proteins. Molecular dynamics simulations indicate a clear distinction between the high and low binding fractions of PFAS. These computational workflows can be used to predict the bioaccumulation of emerging PFAS and are also helpful for the molecular design of PFAS to prevent the release of high-bioaccumulation compounds into the environment.

The Trends and Future Prospective of In Silico Models from the Viewpoint of ADME Evaluation in Drug Discovery

Drug discovery and development are aimed at identifying new chemical molecular entities (NCEs) with desirable pharmacokinetic profiles for high therapeutic efficacy. The plasma concentrations of NCEs are a biomarker of their efficacy and are governed by pharmacokinetic processes such as absorption, distribution, metabolism, and excretion (ADME). Poor ADME properties of NCEs are a major cause of attrition in drug development. ADME screening is used to identify and optimize lead compounds in the drug discovery process. Computational models predicting ADME properties have been developed with evolving model-building technologies from a simplified relationship between ADME endpoints and physicochemical properties to machine learning, including support vector machines, random forests, and convolution neural networks. Recently, in the field of in silico ADME research, there has been a shift toward evaluating the in vivo parameters or plasma concentrations of NCEs instead of using predictive results to guide chemical structure design. Another research hotspot is the establishment of a computational prediction platform to strengthen academic drug discovery. Bioinformatics projects have produced a series of in silico ADME models using free software and open-access databases. In this review, we introduce prediction models for various ADME parameters and discuss the currently available academic drug discovery platforms.

Descriptor-Free Deep Learning QSAR Model for the Fraction Unbound in Human Plasma

Chemical-specific parameters are either measured in vitro or estimated using quantitative structure-activity relationship (QSAR) models. The existing body of QSAR work relies on extracting a set of descriptors or fingerprints, subset selection, and training a machine learning model. In this work, we used a state-of-the-art natural language processing model, Bidirectional Encoder Representations from Transformers, which allowed us to circumvent the need for calculation of these chemical descriptors. In this approach, simplified molecular-input line-entry system (SMILES) strings were embedded in a high-dimensional space using a two-stage training approach. The model was first pre-trained on a masked SMILES token task and then fine-tuned on a QSAR prediction task. The pre-training task learned meaningful high-dimensional embeddings based upon the relationships between the chemical tokens in the SMILES strings derived from the "in-stock" portion of the ZINC 15 dataset─a large dataset of commercially available chemicals. The fine-tuning task then perturbed the pre-trained embeddings to facilitate prediction of a specific QSAR endpoint of interest. The power of this model stems from the ability to reuse the pre-trained model for multiple different fine-tuning tasks, reducing the computational burden of developing multiple models for different endpoints. We used our framework to develop a predictive model for fraction unbound in human plasma (fu,p). This approach is flexible, requires minimum domain expertise, and can be generalized for other parameters of interest for rapid and accurate estimation of absorption, distribution, metabolism, excretion, and toxicity.

Recent Studies of Artificial Intelligence on In Silico Drug Distribution Prediction

Drug distribution is an important process in pharmacokinetics because it has the potential to influence both the amount of medicine reaching the active sites and the effectiveness as well as safety of the drug. The main causes of 90% of drug failures in clinical development are lack of efficacy and uncontrolled toxicity. In recent years, several advances and promising developments in drug distribution property prediction have been achieved, especially in silico, which helped to drastically reduce the time and expense of screening undesired drug candidates. In this study, we provide comprehensive knowledge of drug distribution background, influencing factors, and artificial intelligence-based distribution property prediction models from 2019 to the present. Additionally, we gathered and analyzed public databases and datasets commonly utilized by the scientific community for distribution prediction. The distribution property prediction performance of five large ADMET prediction tools is mentioned as a benchmark for future research. On this basis, we also offer future challenges in drug distribution prediction and research directions. We hope that this review will provide researchers with helpful insight into distribution prediction, thus facilitating the development of innovative approaches for drug discovery.

IDL-PPBopt: A Strategy for Prediction and Optimization of Human Plasma Protein Binding of Compounds via an Interpretable Deep Learning Method

The prediction and optimization of pharmacokinetic properties are essential in lead optimization. Traditional strategies mainly depend on the empirical chemical rules from medicinal chemists. However, with the rising amount of data, it is getting more difficult to manually extract useful medicinal chemistry knowledge. To this end, we introduced IDL-PPBopt, a computational strategy for predicting and optimizing the plasma protein binding (PPB) property based on an interpretable deep learning method. At first, a curated PPB data set was used to construct an interpretable deep learning model, which showed excellent predictive performance with a root mean squared error of 0.112 for the entire test set. Then, we designed a detection protocol based on the model and Wilcoxon test to identify the PPB-related substructures (named privileged substructures, PSubs) for each molecule. In total, 22 general privileged substructures (GPSubs) were identified, which shared some common features such as nitrogen-containing groups, diamines with two carbon units, and azetidine. Furthermore, a series of second-level chemical rules for each GPSub were derived through a statistical test and then summarized into substructure pairs. We demonstrated that these substructure pairs were equally applicable outside the training set and accordingly customized the structural modification schemes for each GPSub, which provided alternatives for the optimization of the PPB property. Therefore, IDL-PPBopt provides a promising scheme for the prediction and optimization of the PPB property and would be helpful for lead optimization of other pharmacokinetic properties.

HelixADMET: a robust and endpoint extensible ADMET system incorporating self-supervised knowledge transfer

MOTIVATION

Accurate ADMET (an abbreviation for "absorption, distribution, metabolism, excretion, and toxicity") predictions can efficiently screen out undesirable drug candidates in the early stage of drug discovery. In recent years, multiple comprehensive ADMET systems that adopt advanced machine learning models have been developed, providing services to estimate multiple endpoints. However, those ADMET systems usually suffer from weak extrapolation ability. First, due to the lack of labelled data for each endpoint, typical machine learning models perform frail for the molecules with unobserved scaffolds. Second, most systems only provide fixed built-in endpoints and cannot be customised to satisfy various research requirements. To this end, we develop a robust and endpoint extensible ADMET system, HelixADMET (H-ADMET). H-ADMET incorporates the concept of self-supervised learning to produce a robust pre-trained model. The model is then fine-tuned with a multi-task and multi-stage framework to transfer knowledge between ADMET endpoints, auxiliary tasks, and self-supervised tasks.

RESULTS

Our results demonstrate that H-ADMET achieves an overall improvement of 4%, compared with existing ADMET systems on comparable endpoints. Additionally, the pre-trained model provided by H-ADMET can be fine-tuned to generate new and customised ADMET endpoints, meeting various demands of drug research and development requirements.

AVAILABILITY

H-ADMET is freely accessible at https://paddlehelix.baidu.com/app/drug/admet/train.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Predicting biochemical and physiological effects of natural products from molecular structures using machine learning

Covering: 2016 to 2021Discovery of novel natural products has been greatly facilitated by advances in genome sequencing, genome mining and analytical techniques. As a result, the volume of data for natural products has increased over the years, which started to serve as ingredients for developing machine learning models. In the past few years, a number of machine learning models have been developed to examine various aspects of a molecule by effectively processing its molecular structure. Understanding of the biological effects of natural products can benefit from such machine learning approaches. In this context, this Highlight reviews recent studies on machine learning models developed to infer various biological effects of molecules. A particular attention is paid to molecular featurization, or computational representation of a molecular structure, which is an essential process during the development of a machine learning model. Technical challenges associated with the use of machine learning for natural products are further discussed.

Designing QSARs for Parameters of High-Throughput Toxicokinetic Models Using Open-Source Descriptors

The intrinsic metabolic clearance rate (Cl_int) and the fraction of the chemical unbound in plasma (f_up) serve as important parameters for high-throughput toxicokinetic (TK) models, but experimental data are limited for many chemicals. Open-source quantitative structure-activity relationship (QSAR) models for both parameters were developed to offer reliable in silico predictions for a diverse set of chemicals regulated under the U.S. law, including pharmaceuticals, pesticides, and industrial chemicals. As a case study to demonstrate their utility, model predictions served as inputs to the TK component of a risk-based prioritization approach based on bioactivity/exposure ratios (BERs), in which a BER < 1 indicates that exposures are predicted to exceed a biological activity threshold. When applied to a subset of the Tox21 screening library (6484 chemicals), we found that the proportion of chemicals with BER <1 was similar using either in silico (1133/6484; 17.5%) or in vitro (148/848; 17.5%) parameters. Further, when considering only the chemicals in the Tox21 set with in vitro data, there was a high concordance of chemicals classified with either BER <1 or >1 using either in silico or in vitro parameters (767/848, 90.4%). Thus, the presented QSARs may be suitable for prioritizing the risk posed by many chemicals for which measured in vitro TK data are lacking.

Discovery of 5-(or 6)-benzoxazoles and oxazolo[4,5-b]pyridines as novel candidate antitumor agents targeting hTopo IIα

Discovery of novel anticancer drugs which have low toxicity and high activity is very significant area in anticancer drug research and development. One of the important targets for cancer treatment research is topoisomerase enzymes. In order to make a contribution to this field, we have designed and synthesized some 5(or 6)-nitro-2-(substitutedphenyl)benzoxazole (1a-1r) and 2-(substitutedphenyl)oxazolo[4,5-b]pyridine (2a-2i) derivatives as novel candidate antitumor agents targeting human DNA topoisomerase enzymes (hTopo I and hTopo IIα). Biological activity results were found very promising for the future due to two compounds, 5-nitro-2-(4-butylphenyl)benzoxazole (1i) and 2-(4-butylphenyl)oxazolo[4,5-b]pyridine (2i), that inhibited hTopo IIα with 2 µM IC₅₀ value. These two compounds were also found to be more active than reference drug etoposide. However, 1i and 2i did not show any satisfactory cyctotoxic activity on the HeLa, WiDR, A549, and MCF7 cancer cell lines. Moreover, molecular docking and molecular dynamic simulations studies for the most active compounds were applied in order to understand the mechanism of inhibition activity of hTopo IIα. In addition, in silico ADME/Tox studies were performed to predict drug-likeness and pharmacokinetic properties of all the tested compounds.

In Silico Prediction of Fraction Unbound in Human Plasma from Chemical Fingerprint Using Automated Machine Learning

Predicting the fraction unbound of a drug in plasma plays a significant role in understanding its pharmacokinetic properties during in vitro studies of drug design and discovery. Owing to the gaining reliability of machine learning in biological predictive models and development of automated machine learning techniques for the ease of nonexperts of machine learning to optimize and maximize the reliability of the model, in this experiment, we built an in silico prediction model of a fraction unbound drug in human plasma using a chemical fingerprint and a freely available AutoML framework. The predictive model was trained on one of the largest data sets ever of 5471 experimental values using four different AutoML frameworks to compare their performance on this problem and to choose the most significant one. With a coefficient of determination of 0.85 on the test data set, our best prediction model showed better performance than other previously published models, giving our model significant importance in pharmacokinetic modeling.

Coloring Molecules with Explainable Artificial Intelligence for Preclinical Relevance Assessment

Graph neural networks are able to solve certain drug discovery tasks such as molecular property prediction and de novo molecule generation. However, these models are considered "black-box" and "hard-to-debug". This study aimed to improve modeling transparency for rational molecular design by applying the integrated gradients explainable artificial intelligence (XAI) approach for graph neural network models. Models were trained for predicting plasma protein binding, hERG channel inhibition, passive permeability, and cytochrome P450 inhibition. The proposed methodology highlighted molecular features and structural elements that are in agreement with known pharmacophore motifs, correctly identified property cliffs, and provided insights into unspecific ligand-target interactions. The developed XAI approach is fully open-sourced and can be used by practitioners to train new models on other clinically relevant endpoints.

Evaluation of Quantitative Structure Property Relationship Algorithms for Predicting Plasma Protein Binding in Humans

The extent of plasma protein binding is an important compound-specific property that influences a compound's pharmacokinetic behavior and is a critical input parameter for predicting exposure in physiologically based pharmacokinetic (PBPK) modeling. When experimentally determined fraction unbound in plasma (fup) data are not available, quantitative structure-property relationship (QSPR) models can be used for prediction. Because available QSPR models were developed based on training sets containing pharmaceutical-like compounds, we compared their prediction accuracy for environmentally relevant and pharmaceutical compounds. Fup values were calculated using Ingle et al., Watanabe et al. and ADMET Predictor (Simulation Plus). The test set included 818 pharmaceutical and environmentally relevant compounds with fup values ranging from 0.01 to 1. Overall, the three QSPR models resulted in over-prediction of fup for highly binding compounds and under-prediction for low or moderately binding compounds. For highly binding compounds (0.01≤ fup ≤ 0.25), Watanabe et al. performed better with a lower mean absolute error (MAE) of 6.7% and a lower mean absolute relative prediction error (RPE) of 171.7 % than other methods. For low to moderately binding compounds, both Ingle et al. and ADMET Predictor performed better than Watanabe et al. with superior MAE and RPE values. The positive polar surface area, the number of basic functional groups and lipophilicity were the most important chemical descriptors for predicting fup. This study demonstrated that the prediction of fup was the most uncertain for highly binding compounds. This suggested that QSPR-predicted fup values should be used with caution in PBPK modeling.

Using Chemical Structure Information to Develop Predictive Models for In Vitro Toxicokinetic Parameters to Inform High-throughput Risk-assessment

The toxicokinetic (TK) parameters fraction of the chemical unbound to plasma proteins and metabolic clearance are critical for relating exposure and internal dose when building in vitro-based risk assessment models. However, experimental toxicokinetic studies have only been carried out on limited chemicals of environmental interest (~1000 chemicals with TK data relative to tens of thousands of chemicals of interest). This work evaluated the utility of chemical structure information to predict TK parameters in silico; development of cluster-based read-across and quantitative structure-activity relationship models of fraction unbound or fub (regression) and intrinsic clearance or Cl_int (classification and regression) using a dataset of 1487 chemicals; utilization of predicted TK parameters to estimate uncertainty in steady-state plasma concentration (C_ss); and subsequent in vitro-in vivo extrapolation analyses to derive bioactivity-exposure ratio (BER) plot to compare human oral equivalent doses and exposure predictions using androgen and estrogen receptor activity data for 233 chemicals as an example dataset. The results demonstrate that fub is structurally more predictable than Cl_int. The model with the highest observed performance for fub had an external test set RMSE/σ=0.62 and R²=0.61, for Cl_int classification had an external test set accuracy = 65.9%, and for intrinsic clearance regression had an external test set RMSE/σ=0.90 and R²=0.20. This relatively low performance is in part due to the large uncertainty in the underlying Cl_int data. We show that C_ss is relatively insensitive to uncertainty in Cl_int. The models were benchmarked against the ADMET Predictor software. Finally, the BER analysis allowed identification of 14 out of 136 chemicals for further risk assessment demonstrating the utility of these models in aiding risk-based chemical prioritization.

Comparison of statistical methods for predicting penetration capacity of drugs into human breast milk using physicochemical, pharmacokinetic and chromatographic descriptors

In silico methods are often used for predicting pharmacokinetic properties of drugs due to their simplicity and cost-effectiveness. This study evaluates the penetration of 83 active pharmaceutical ingredients into human breast milk with an experimental milk-to-plasma ratio (M/P) obtained from the literature. Multiple linear regression (MLR), partial least squares (PLS) and random forest (RF) regression methods were compared to uncover the relationship between physicochemical, pharmacokinetic and membrane crossing properties of active pharmaceutical ingredients (APIs) using their rapid reference measurement value (R_f values), thin-layer chromatography (TLC) data from albumin-impregnated plates. Molecular descriptors of APIs proven to be important for their crossing into breast milk, including protein binding, ionisation state and lipophilicity and TLC data, have been included in the development of the prediction models. The best regression results were achieved by MLR (r ² = 0.83 and r ² = 0.86, n = 28) and RF (r ² = 0.85, n = 58). In addition, the discriminant function analysis (DFA) was performed on acidic, basic and neutral drugs separately and showed a prediction accuracy of 93%, with M/P included as the discriminating variable.

Design, synthesis, biological evaluation, common feature pharmacophore model and molecular dynamics simulation studies of ethyl 4-(phenoxymethyl)-2-phenylthiazole-5-carboxylate as Src homology-2 domain containing protein tyrosine phosphatase-2 (SHP2) inhibitors

SHP2 is a non-receptor protein tyrosine phosphatase (PTP) encoded by the PTPN11 gene involved in cell death pathway (PD-1/PD-L1) and cell growth and differentiation pathway (MAPK). Moreover, mutations in SHP2 have been implicated in Leopard syndrome (LS), Noonan syndrome (NS), juvenile myelomonocytic leukemia (JMML) and several types of cancer and solid tumors. Thus, SHP2 inhibitors are much needed reagents for evaluation of SHP2 as a therapeutic target. A series of novel ethyl 4-(phenoxymethyl)-2-phenylthiazole-5-carboxylate derivatives were designed and synthesized, and their SHP2 inhibitory activities (IC₅₀) were determined. Among the desired compounds, 1d shares the highest inhibitory activity (IC₅₀ = 0.99 μM) against SHP2. Additionally, a common feature pharmacophore model was established to explain the structure activity relationship of the desired compounds. Finally, molecular dynamics simulation was carried out to explore the most likely binding mode of compound 1d with SHP2. In brief, the findings reported here may at least provide a new strategy or useful insights in discovering novel effective SHP2 inhibitors.Communicated by Ramaswamy H. Sarma.

Computational prediction of interaction and pharmacokinetics profile study for polyamino-polycarboxylic ligands on binding with human serum albumin

Human serum albumin (HSA) is one of the most abundant plasma proteins available in blood and responsible for transport of fatty acids, drugs and metabolites at its binding sites which are very important for the assessment of pharmacokinetics profile of the polyamino-polycarboxylic ligands.

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

ISOPT Clinical Hot Topic Panel Discussion on Ocular Drug Delivery

Ocular drug delivery offers unique challenges and opportunities in the era of novel therapeutic agents ranging from small molecules to gene therapies. Noninvasive delivery of drugs into the back of the eye or any part of the eye is extremely limited by short precorneal residence time and formidable biological barriers. The eye is a sensitive, sensory organ that requires a high level of material and procedural safety, while achieving therapeutic efficacy. Some recent advances and unmet needs for ocular drug delivery and disposition are discussed in this article. Specifically, nanomedicines, physical and chemical means to enhance delivery, stimuli-responsive delivery systems, the role of vitreal binding on ocular pharmacokinetics, and the influence of aging eye on drug delivery, and the associated unmet needs are highlighted. Additionally, the unmet needs in the medication management for the elderly patients with eye diseases are discussed.

Development of Simplified in Vitro P-Glycoprotein Substrate Assay and in Silico Prediction Models To Evaluate Transport Potential of P-Glycoprotein

For efficient drug discovery and screening, it is necessary to simplify P-glycoprotein (P-gp) substrate assays and to provide in silico models that predict the transport potential of P-gp. In this study, we developed a simplified in vitro screening method to evaluate P-gp substrates by unidirectional membrane transport in P-gp-overexpressing cells. The unidirectional flux ratio positively correlated with parameters of the conventional bidirectional P-gp substrate assay ( R² = 0.941) and in vivo K_p,brain ratio (mdr1a/1b KO/WT) in mice ( R² = 0.800). Our in vitro P-gp substrate assay had high reproducibility and required approximately half the labor of the conventional method. We also constructed regression models to predict the value of P-gp-mediated flux and three-class classification models to predict P-gp substrate potential (low-, medium-, and high-potential) using 2397 data entries with the largest data set collected under the same experimental conditions. Most compounds in the test set fell within two- and three-fold errors in the random forest regression model (71.3 and 88.5%, respectively). Furthermore, the random forest three-class classification model showed a high balanced accuracy of 0.821 and precision of 0.761 for the low-potential classes in the test set. We concluded that the simplified in vitro P-gp substrate assay was suitable for compound screening in the early stages of drug discovery and that the in silico regression model and three-class classification model using only chemical structure information could identify the transport potential of compounds including P-gp-mediated flux ratios. Our proposed method is expected to be a practical tool to optimize effective central nervous system (CNS) drugs, to avoid CNS side effects, and to improve intestinal absorption.

Molecular Modeling Approaches for the Prediction of Selected Pharmacokinetic Properties

Poor profiles of potential drug candidates, including pharmacokinetic properties, have been acknowledged as a significant hindrance to the development of modern therapeutics. Contemporary drug discovery and development would be incomplete without the aid of molecular modeling (in-silico) techniques, allowing the prediction of pharmacokinetic properties such as clearance, unbound fraction, volume of distribution and bioavailability. As with all models, in-silico approaches are subject to their interpretability, a trait that must be balanced with accuracy when considering the development of new methods. The best models will always require reliable data to inform them, presenting significant challenges, particularly when appropriate in-vitro or in-vivo data may be difficult or time-consuming to obtain. This article seeks to review some of the key in-silico techniques used to predict key pharmacokinetic properties and give commentary on the current and future directions of the field.

An Integrated Transfer Learning and Multitask Learning Approach for Pharmacokinetic Parameter Prediction

BACKGROUND

Pharmacokinetic evaluation is one of the key processes in drug discovery and development. However, current absorption, distribution, metabolism, and excretion prediction models still have limited accuracy.

AIM

This study aims to construct an integrated transfer learning and multitask learning approach for developing quantitative structure-activity relationship models to predict four human pharmacokinetic parameters.

METHODS

A pharmacokinetic data set included 1104 U.S. FDA approved small molecule drugs. The data set included four human pharmacokinetic parameter subsets (oral bioavailability, plasma protein binding rate, apparent volume of distribution at steady-state, and elimination half-life). The pretrained model was trained on over 30 million bioactivity data entries. An integrated transfer learning and multitask learning approach was established to enhance the model generalization.

RESULTS

The pharmacokinetic data set was split into three parts (60:20:20) for training, validation, and testing by the improved maximum dissimilarity algorithm with the representative initial set selection algorithm and the weighted distance function. The multitask learning techniques enhanced the model predictive ability. The integrated transfer learning and multitask learning model demonstrated the best accuracies, because deep neural networks have the general feature extraction ability; transfer learning and multitask learning improve the model generalization.

CONCLUSIONS

The integrated transfer learning and multitask learning approach with the improved data set splitting algorithm was first introduced to predict the pharmacokinetic parameters. This method can be further employed in drug discovery and development.

Computational prediction of plasma protein binding of cyclic peptides from small molecule experimental data using sparse modeling techniques

BACKGROUND

Cyclic peptide-based drug discovery is attracting increasing interest owing to its potential to avoid target protein depletion. In drug discovery, it is important to maintain the biostability of a drug within the proper range. Plasma protein binding (PPB) is the most important index of biostability, and developing a computational method to predict PPB of drug candidate compounds contributes to the acceleration of drug discovery research. PPB prediction of small molecule drug compounds using machine learning has been conducted thus far; however, no study has investigated cyclic peptides because experimental information of cyclic peptides is scarce.

RESULTS

First, we adopted sparse modeling and small molecule information to construct a PPB prediction model for cyclic peptides. As cyclic peptide data are limited, applying multidimensional nonlinear models involves concerns regarding overfitting. However, models constructed by sparse modeling can avoid overfitting, offering high generalization performance and interpretability. More than 1000 PPB data of small molecules are available, and we used them to construct a prediction models with two enumeration methods: enumerating lasso solutions (ELS) and forward beam search (FBS). The accuracies of the prediction models constructed by ELS and FBS were equal to or better than those of conventional non-linear models (MAE = 0.167-0.174) on cross-validation of a small molecule compound dataset. Moreover, we showed that the prediction accuracies for cyclic peptides were close to those for small molecule compounds (MAE = 0.194-0.288). Such high accuracy could not be obtained by a simple method of learning from cyclic peptide data directly by lasso regression (MAE = 0.286-0.671) or ridge regression (MAE = 0.244-0.354).

CONCLUSION

In this study, we proposed a machine learning techniques that uses low-dimensional sparse modeling to predict the PPB value of cyclic peptides computationally. The low-dimensional sparse model not only exhibits excellent generalization performance but also improves interpretation of the prediction model. This can provide common an noteworthy knowledge for future cyclic peptide drug discovery studies.

QSAR Development for Plasma Protein Binding: Influence of the Ionization State

Purpose

This study explored several strategies to improve the performance of literature QSAR models for plasma protein binding (PPB), such as a suitable endpoint transformation, a correct representation of chemicals, more consistency in the dataset, and a reliable definition of the applicability domain.

Methods

We retrieved human fraction unbound (Fu) data for 670 compounds from the literature and carefully checked them for consistency. Descriptors were calculated taking account of the ionization state of molecules at physiological pH (7.4), in order to better estimate the affinity of molecules to blood proteins. We used different algorithms and chemical descriptors to explore the most suitable strategy for modeling the endpoint. SMILES (simplified molecular input line entry system)-based string descriptors were also tested with the CORAL software (CORelation And Logic). We did an outlier analysis to establish the models to use (or not to use) in case of well recognized families.

Results

Internal validation of the selected models returned Q² values close to 0.60. External validation also gave r² values always greater than 0.60. The CORAL descriptor based model for √fu was the best, with r² 0.74 in external validation.

Conclusions

Performance in prediction confirmed the robustness of all the derived models and their suitability for real-life purposes, i.e. screening chemicals for their ADMET profiling. Optimization of descriptors can be useful in order to obtain the correct results with a ionized molecule.

Electronic supplementary material

The online version of this article (10.1007/s11095-018-2561-8) contains supplementary material, which is available to authorized users.

Predicting Fraction Unbound in Human Plasma from Chemical Structure: Improved Accuracy in the Low Value Ranges

Predicting the fraction unbound in plasma provides a good understanding of the pharmacokinetic properties of a drug to assist candidate selection in the early stages of drug discovery. It is also an effective tool to mitigate the risk of late-stage attrition and to optimize further screening. In this study, we built in silico prediction models of fraction unbound in human plasma with freely available software, aiming specifically to improve the accuracy in the low value ranges. We employed several machine learning techniques and built prediction models trained on the largest ever data set of 2738 experimental values. The classification model showed a high true positive rate of 0.826 for the low fraction unbound class on the test set. The strongly biased distribution of the fraction unbound in plasma was mitigated by a logarithmic transformation in the regression model, leading to improved accuracy at lower values. Overall, our models showed better performance than those of previously published methods, including commercial software. Our prediction tool can be used on its own or integrated into other pharmacokinetic modeling systems.

Binding of Small Molecule Drugs to Porcine Vitreous Humor

Pharmacokinetics in the posterior eye segment has therapeutic implications due to the importance of retinal diseases in ophthalmology. In principle, drug binding to the components of the vitreous, such as proteins, collagen, or glycosaminoglycans, could prolong ocular drug retention and modify levels of pharmacologically active free drug in the posterior eye segment. Since drug binding in the vitreous has been investigated only sparsely, we studied vitreal drug binding of 35 clinical small molecule drugs. Isolated homogenized porcine vitreous and the drugs were placed in a two-compartment dialysis system that was used to separate the bound and unbound drug. Free drug concentrations and binding percentages were quantitated using LC-MS/MS. Drug binding levels varied between 21 and 74% in the fresh vitreous and 0 and 64% in the frozen vitreous. The vitreal binding percentages did not correlate with those in plasma. Our data-based pharmacokinetic simulations suggest that vitreal binding of small molecule drugs has only a modest influence on the AUC of free drug or drug half-life in the vitreous. Therefore, it is likely that vitreal binding is not a major reason for interindividual variability in ocular drug responses or drug-drug interactions.

Synthesis, bioactivity, 3D-QSAR studies of novel dibenzofuran derivatives as PTP-MEG2 inhibitors

PTP-MEG2 plays a critical role in the diverse cell signalling processes, so targeting PTP-MEG2 is a promising strategy for various human diseases treatments. In this study, a series of novel dibenzofuran derivatives was synthesized and assayed for their PTP-MEG2 inhibitory activities. 10a with highest inhibitory activity (320 nM) exhibited significant selectivity for PTP-MEG2 over its close homolog SHP2, CDC25 (IC₅₀ > 50 μM). By means of the powerful “HipHop” technique, a 3D-QSAR study was carried out to explore structure activity relationship of these molecules. The generated pharmacophore model revealed that the one RA, three Hyd, and two HBA features play an important role in binding to the active site of the target protein-PTP-MEG2. Docking simulation study indicated that 10a achieved its potency and specificity for PTP-MEG2 by targeting unique nearby peripheral binding pockets and the active site. The absorption, distribution, metabolism and excretion (ADME) predictions showed that the 11 compounds hold high potential to be novel lead compounds for targeting PTP-MEG2. Our findings here can provide a new strategy or useful insights for designing the effective PTP-MEG2 inhibitors.

Probing the opportunities for designing anthelmintic leads by sub-structural topology-based QSAR modelling

A quantitative structure-activity (QSAR) model has been developed for enriched tubulin inhibitors, which were retrieved from sequence similarity searches and applicability domain analysis. Using partial least square (PLS) method and leave-one-out (LOO) validation approach, the model was generated with the correlation statistics of [Formula: see text] and [Formula: see text] of 0.68 and 0.69, respectively. The present study indicates that topological descriptors, viz. BIC, CH_3_C, IC, JX and Kappa_2 correlate well with biological activity. ADME and toxicity (or ADME/T) assessment showed that out of 260 molecules, 255 molecules successfully passed the ADME/T assessment test, wherein the drug-likeness attributes were exhibited. These results showed that topological indices and the colchicine binding domain directly influence the aetiology of helminthic infections. Further, we anticipate that our model can be applied for guiding and designing potential anthelmintic inhibitors.

The design of novel inhibitors for treating cancer by targeting CDC25B through disruption of CDC25B-CDK2/Cyclin A interaction using computational approaches

Cell division cycle 25B is a key cell cycle regulator and widely considered as potent clinical drug target for cancers. This research focused on identifying potential compounds in theory which are able to disrupt transient interactions between CDC25B and its CDK2/Cyclin A substrate.By using the method of ZDOCK and RDOCK, the most optimized 3D structure of CDK2/Cyclin A in complex with CDC25B was constructed and validated using two methods: 1) the superimposition of proteins; 2) analysis of the hydrogen bond distances of Arg 488(N1)-Asp 206(OD1), Arg 492(NE)-Asp 206(OD1), Arg 492(N1)-Asp 206(OD2) and Tyr 497(NE)-Asp 210(OD1). A series of new compounds was gained through searching the fragment database derived from ZINC based on the known inhibitor-compound 7 by the means of "replace fragment" technique. The compounds acquired via meeting the requirements of the absorption, distribution, metabolism, and excretion (ADME) predictions. Finally, 12 compounds with better binding affinity were identified. The comp#1, as a representative, was selected to be synthesized and assayed for their CDC25B inhibitory activities. The comp#1 exhibited mild inhibitory activities against human CDC25B with IC50 values at about 39.02 μM. Molecular Dynamic (MD) simulation revealed that the new inhibitor-comp#1 had favorable conformations for binding to CDC25B and disturbing the interactions between CDC25B and CDK2/Cyclin A.

Molecular activity prediction by means of supervised subspace projection based ensembles of classifiers

This paper proposes a method for molecular activity prediction in QSAR studies using ensembles of classifiers constructed by means of two supervised subspace projection methods, namely nonparametric discriminant analysis (NDA) and hybrid discriminant analysis (HDA). We studied the performance of the proposed ensembles compared to classical ensemble methods using four molecular datasets and eight different models for the representation of the molecular structure. Using several measures and statistical tests for classifier comparison, we observe that our proposal improves the classification results with respect to classical ensemble methods. Therefore, we show that ensembles constructed using supervised subspace projections offer an effective way of creating classifiers in cheminformatics.