In Silico Prediction of Compounds Binding to Human Plasma Proteins by QSAR Models

Machine learning models for predicting in-hospital mortality from acute pancreatitis in intensive care unit

BACKGROUND

Acute pancreatitis (AP) represents a critical medical condition where timely and precise prediction of in-hospital mortality is crucial for guiding optimal clinical management. This study focuses on the development of advanced machine learning (ML) models to accurately predict in-hospital mortality among AP patients admitted to intensive care unit (ICU).

METHOD

Our study utilized data from three distinct sources: the Medical Information Mart for Intensive Care III (MIMIC-III), MIMIC-IV databases, and Beijing Chaoyang Hospital. We systematically developed and evaluated 11 distinct machine learning (ML) models, employing a comprehensive set of evaluation metrics to assess model performance, including the area under the curve (AUC). To enhance interpretability and identify key predictive features, we implemented Shapley Additive Explanations (SHAP) analysis for the top-performing model. Furthermore, we developed a streamlined version of the model through strategic feature reduction, followed by rigorous hyperparameter optimization (HPO) to maximize predictive performance. To facilitate clinical implementation, we designed and deployed an intuitive web-based calculator, enabling convenient access and practical application of our optimized predictive model.

RESULT

The study analyzed 1802 AP patients, with 266 (14.8%) experiencing in-hospital mortality. A set of 27 features was utilized to construct various models, and among them, CatBoost demonstrated the highest performance in both the validation and test sets. To create a more concise model, we selected the top 13 features. After HPO, the AUC in the test set reached 0.835 (95% CI: 0.793-0.872), the AUC in the external validation from Beijing Chaoyang hospital was 0.782 (95% CI: 0.699-0.860).

CONCLUSION

ML models have shown promising reliability in predicting in-hospital mortality among patients with AP in the ICU. Among these models, the CatBoost model exhibits superior predictive performance, providing valuable assistance to clinical practitioners in identifying high-risk patients and facilitating early interventions to enhance prognosis. The development of a compact model and a web-based calculator further enhances the convenience of using these models in clinical practice.

Annonaceous acetogenins as promising DNA methylation inhibitors to prevent and treat leukemogenesis - an in silico approach

Leukemia is a haematological malignancy affecting blood and bone marrow, ranking 10th among the other common cancers. DNA methylation is an epigenetic dysregulation that plays a critical role in leukemogenesis. DNA methyltransferases (DNMTs) such as DNMT1, DNMT3A and DNMT3B are the key enzymes catalysing DNA methylation. Inhibition of DNMT1 with secondary metabolites from medicinal plants helps reverse DNA methylation. The present study focuses on inhibiting DNMT1 protein (PDB ID: 3PTA) with annonaceous acetogenins through in-silico studies. The docking and molecular dynamic (MD) simulation study was carried out using Schrödinger Maestro and Desmond, respectively. These compounds' drug likeliness, ADMET properties and bioactivity scores were analysed. About 76 different acetogenins were chosen for this study, among which 17 showed the highest binding energy in the range of -8.312 to -10.266 kcal/mol. The compounds with the highest negative binding energy were found to be annohexocin (-10.266 kcal/mol), isoannonacinone (-10.209 kcal/mol) and annonacin (-9.839 kcal/mol). MD simulation results reveal that annonacin remains stable throughout the simulation time of 100 ns and also binds to the catalytic domain of DNMT1 protein. From the above results, it can be concluded that annonacin has the potential to inhibit the DNA methylation process and prevent leukemogenesis.

In vitro and in silico evaluation of synthetic compounds derived from bi-triazoles against asexual and sexual forms of Plasmodium falciparum

BACKGROUND

Despite advances in malaria chemotherapy, the disease continues to claim thousands of lives annually. Addressing this issue requires the discovery of new compounds to counteract resistance threatening the current therapeutic arsenal. In this context, bi-triazoles are substances with diverse biological activities, showing promise as lead compound to fight malaria. Triazoles are heterocyclic structures composed of five members, including three nitrogen atoms and two double bonds. Bi-triazoles, the focus of this study, are derivatives of triazoles consisting of two triazole rings (nitrogen heterocyclic) with isolated nuclei lacking a spacer and two substituents at each end. The goal of the present study was to assess the in vitro and in silico, antimalarial activity of bi-triazole compounds 14c, 14d, 13c, and 13d against asexual and sexual forms of Plasmodium falciparum.

METHODS

For in silico predictions, the software OSIRIS, Molinspiration, and ADMETlab were employed. To determine the 50% inhibitory concentration (IC50) on the asexual forms, the W2 clone was used, while the strain NF54 was used to assess inhibition of sexual forms. Cytotoxicity was evaluated using the HepG2 cell line, and haemolysis tests were conducted. Additionally, the selectivity index (SI) of each compound was calculated.

RESULTS

In silico analyses of physicochemical properties revealed that all compounds have favorable potential for drug development. Pharmacokinetics predictions also provided important, novel insights into this chemical class. Antimalarial activity tests showed that compounds 14d and 13d exhibited promising activity, with IC50 values of 3.1 and 4.4 µM, respectively. Antimalarial activity of compounds 14d and 13d may be related to the presence of methyl acetate in substituent R2 conjugated to the bi-triazole. None of the compounds demonstrated cytotoxic or haemolytic activity, with SI values above 51 for the three most active compounds, highlighting their selectivity. For the sexual forms, compounds 14c and 14d were classified as having a high potential to block malaria transmission.

CONCLUSION

Overall, the in vitro and in silico results showed that bi-triazole compounds may guide new biological investigation for malaria, enabling the identification and development of more active and selective antimalarial agents.

Decoding Drug Discovery: Exploring A-to-Z In Silico Methods for Beginners

The drug development process is a critical challenge in the pharmaceutical industry due to its time-consuming nature and the need to discover new drug potentials to address various ailments. The initial step in drug development, drug target identification, often consumes considerable time. While valid, traditional methods such as in vivo and in vitro approaches are limited in their ability to analyze vast amounts of data efficiently, leading to wasteful outcomes. To expedite and streamline drug development, an increasing reliance on computer-aided drug design (CADD) approaches has merged. These sophisticated in silico methods offer a promising avenue for efficiently identifying viable drug candidates, thus providing pharmaceutical firms with significant opportunities to uncover new prospective drug targets. The main goal of this work is to review in silico methods used in the drug development process with a focus on identifying therapeutic targets linked to specific diseases at the genetic or protein level. This article thoroughly discusses A-to-Z in silico techniques, which are essential for identifying the targets of bioactive compounds and their potential therapeutic effects. This review intends to improve drug discovery processes by illuminating the state of these cutting-edge approaches, thereby maximizing the effectiveness and duration of clinical trials for novel drug target investigation.

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.

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.

Prediction method of pharmacokinetic parameters of small molecule drugs based on GCN network model

CONTEXT

Accurately predicting plasma protein binding rate (PPBR) and oral bioavailability (OBA) helps to better reveal the absorption and distribution of drugs in the human body and subsequent drug design. Although machine learning models have achieved good results in prediction accuracy, they often suffer from insufficient accuracy when dealing with data with irregular topological structures.

METHODS

In view of this, this study proposes a pharmacokinetic parameter prediction framework based on graph convolutional networks (GCN), which predicts the PPBR and OBA of small molecule drugs. In the framework, GCN is first used to extract spatial feature information on the topological structure of drug molecules, in order to better learn node features and association information between nodes. Then, based on the principle of drug similarity, this study calculates the similarity between small molecule drugs, selects different thresholds to construct datasets, and establishes a prediction model centered on the GCN algorithm. The experimental results show that compared with traditional machine learning prediction models, the prediction model constructed based on the GCN method performs best on PPBR and OBA datasets with an inter-molecular similarity threshold of 0.25, with MAE of 0.155 and 0.167, respectively. In addition, in order to further improve the accuracy of the prediction model, GCN is combined with other algorithms. Compared to using a single GCN method, the distribution of the predicted values obtained by the combined model is highly consistent with the true values. In summary, this work provides a new method for improving the rate of early drug screening in the future.

An assessment of crucial structural contributors of HDAC6 inhibitors through fragment-based non-linear pattern recognition and molecular dynamics simulation approaches

Amidst the Zn2+-dependant isoforms of the HDAC family, HDAC6 has emerged as a potential target associated with an array of diseases, especially cancer and neuronal disorders like Rett's Syndrome, Alzheimer's disease, Huntington's disease, etc. Also, despite the availability of a handful of HDAC inhibitors in the market, their non-selective nature has restricted their use in different disease conditions. In this situation, the development of selective and potent HDAC6 inhibitors will provide efficacious therapeutic agents to treat different diseases. In this context, this study has been carried out to evaluate the potential structural contributors of quinazoline-cap-containing HDAC6 inhibitors via machine learning (ML), conventional classification-dependant QSAR, and MD simulation-based binding mode of interaction analysis toward HDAC6 binding. This combined conventional and modern molecular modeling study has revealed the significance of the quinazoline moiety, substitutions present at the quinazoline cap group, as well as the importance of molecular property, number of hydrogen bond donor-acceptor functions, carbon-chlorine distance that significantly affects the HDAC6 binding of these inhibitors, subsequently affecting their potency . Interestingly, the study also revealed that the substitutions such as the chloroethyl group, and bulky quinazolinyl cap group can affect the binding of the cap function with the amino acid residues present in the loops proximal to the catalytic site of HDAC6. Such contributions of cap groups can lead to both stabilization and destabilization of the cap function after occupying the hydrophobic catalytic site by the aryl hydroxamate linker-ZBG functions.

Computer-aided drug discovery of c-Abl kinase inhibitors from plant compounds against chronic myeloid leukemia

Chronic myeloid leukemia (CML) is a hematological malignancy characterized by the neoplastic transformation of hematopoietic stem cells, driven by the Philadelphia (Ph) chromosome resulting from a translocation between chromosomes 9 and 22. This Ph chromosome harbors the breakpoint cluster region (BCR) and the Abelson (ABL) oncogene (BCR-ABL1) which have a constitutive tyrosine kinase activity. However, the tyrosine kinase activity of BCR-ABL1 have been identified as a key player in CML initiation and maintenance through c-Abl kinase. Despite advancements in tyrosine kinase inhibitors, challenges such as efficacy, safety concerns, and recurring drug resistance persist. This study aims to discover potential c-Abl kinase inhibitors from plant compounds with anti-leukemic properties, employing drug-likeness assessment, molecular docking, in silico pharmacokinetics (ADMET) screening, density function theory (DFT), and molecular dynamics simulations (MDS). Out of 58 screened compounds for drug-likeness, 44 were docked against c-Abl kinase. The top hit compound (isovitexin) and nilotinib (control drug) were subjected to rigorous analyses, including ADMET profiling, DFT evaluation, and MDS for 100 ns. Isovitexin demonstrated a notable binding affinity (-15.492 kcal/mol), closely comparable to nilotinib (-16.826 kcal/mol), showcasing a similar binding pose and superior structural stability and reactivity. While these findings suggest isovitexin as a potential c-Abl kinase inhibitor, further validation through urgent in vitro and in vivo experiments is imperative. This research holds promise for providing an alternative avenue to address existing CML treatment and management challenges.

Anti-leishmanial activity of Eleutherine plicata Herb. and predictions of isoeleutherin and its analogues

Introduction: Leishmaniasis is caused by protozoa of the genus Leishmania, classified as tegumentary and visceral. The disease treatment is still a serious problem, due to the toxic effects of available drugs, the costly treatment and reports of parasitic resistance, making the search for therapeutic alternatives urgent. This study assessed the in vitro anti-leishmanial potential of the extract, fractions, and isoeleutherin from Eleutherine plicata, as well as the in silico interactions of isoeleutherin and its analogs with Trypanothione Reductase (TR), in addition to predicting pharmacokinetic parameters. Methods: From the ethanolic extract of E. plicata (EEEp) the dichloromethane fraction (FDEp) was obtained, and isoeleutherin isolated. All samples were tested against promastigotes, and parasite viability was evaluated. Isoeleutherin analogues were selected based on similarity in databases (ZINK and eMolecules) to verify the impact on structural change. Results and Discussion: The extract and its fractions were not active against the promastigote form (IC50 > 200 μg/mL), while isoeleutherin was active (IC50 = 25 μg/mL). All analogues have high intestinal absorption (HIA), cell permeability was moderate in Caco2 and low to moderate in MDCK. Structural changes interfered with plasma protein binding and blood-brain barrier permeability. Regarding metabolism, all molecules appear to be CYP3A4 metabolized and inhibited 2-3 CYPs. Molecular docking and molecular dynamics assessed the interactions between the most stable configurations of isoeleutherin, analogue compound 17, and quinacrine (control drug). Molecular dynamics simulations demonstrated stability and favorable interactions with TR. In summary, fractionation contributed to antileishmanial activity and isoleutherin seems to be promising. Structural alterations did not contribute to improve pharmacokinetic aspects and analogue 17 proved to be more promising than isoeleutherin, presenting better stabilization in TR.

Machine-Learning- and Structure-Based Virtual Screening for Selecting Cinnamic Acid Derivatives as Leishmania major DHFR-TS Inhibitors

The critical enzyme dihydrofolate reductase-thymidylate synthase in Leishmania major (LmDHFR-TS) serves a dual-purpose role and is essential for DNA synthesis, a cornerstone of the parasite's reproductive processes. Consequently, the development of inhibitors against LmDHFR-TS is crucial for the creation of novel anti-Leishmania chemotherapies. In this study, we employed an in-house database containing 314 secondary metabolites derived from cinnamic acid that occurred in the Asteraceae family. We conducted a combined ligand/structure-based virtual screening to identify potential inhibitors against LmDHFR-TS. Through consensus analysis of both approaches, we identified three compounds, i.e., lithospermic acid (237), diarctigenin (306), and isolappaol A (308), that exhibited a high probability of being inhibitors according to both approaches and were consequently classified as promising hits. Subsequently, we expanded the binding mode examination of these compounds within the active site of the test enzyme through molecular dynamics simulations, revealing a high degree of structural stability and minimal fluctuations in its tertiary structure. The in silico predictions were then validated through in vitro assays to examine the inhibitory capacity of the top-ranked naturally occurring compounds against LmDHFR-TS recombinant protein. The test compounds effectively inhibited the enzyme with IC50 values ranging from 6.1 to 10.1 μM. In contrast, other common cinnamic acid derivatives (i.e., flavonoid glycosides) from the Asteraceae family, such as hesperidin, isovitexin 4'-O-glucoside, and rutin, exhibited low activity against this target. The selective index (SI) for all tested compounds was determined using HsDHFR with moderate inhibitory effect. Among these hits, lignans 306 and 308 demonstrated the highest selectivity, displaying superior SI values compared to methotrexate, the reference inhibitor of DHFR-TS. Therefore, continued research into the anti-leishmanial potential of these C6C3-hybrid butyrolactone lignans may offer a brighter outlook for combating this neglected tropical disease.

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.

Deep Learning for Drug Development: Using CNNs in MIA-QSAR to Predict Plasma Protein Binding of Drugs

Predicting plasma protein binding (PPB) is crucial in drug development due to its profound impact on drug efficacy and safety. In our study, we employed a convolutional neural network (CNN) as a tool to extract valuable information from the molecular structures of 100 different drugs. These extracted features were then used as inputs for a feedforward network to predict the PPB of each drug. Through this approach, we successfully obtained 10 specific numerical features from each drug's molecular structure, which represent fundamental aspects of their molecular composition. Leveraging the CNN's ability to capture these features significantly improved the precision of our predictions. Our modeling results revealed impressive accuracy, with an R2 train value of 0.89 for the training dataset, a [Formula: see text] of 0.98, a [Formula: see text] of 0.931 for the external validation dataset, and a low cross-validation mean squared error (CV-MSE) of 0.0213. These metrics highlight the effectiveness of our deep learning techniques in the fields of pharmacokinetics and drug development. This study makes a substantial contribution to the expanding body of research exploring the application of artificial intelligence (AI) and machine learning in drug development. By adeptly capturing and utilizing molecular features, our method holds promise for enhancing drug efficacy and safety assessments in pharmaceutical research. These findings underscore the potential for future investigations in this exciting and transformative field.

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.

A Quantitative Structure-Activity Relationship for Human Plasma Protein Binding: Prediction, Validation and Applicability Domain

Purpose

The purpose of this study was to develop a robust and externally predictive in silico QSAR-neural network model for predicting plasma protein binding of drugs. This model aims to enhance drug discovery processes by reducing the need for chemical synthesis and extensive laboratory testing.

Methods

A dataset of 277 drugs was used to develop the QSAR-neural network model. The model was constructed using a Filter method to select 55 molecular descriptors. The validation set's external accuracy was assessed through the predictive squared correlation coefficient Q2 and the root mean squared error (RMSE).

Results

The developed QSAR-neural network model demonstrated robustness and good applicability domain. The external accuracy of the validation set was high, with a predictive squared correlation coefficient Q2 of 0.966 and a root mean squared error (RMSE) of 0.063. Comparatively, this model outperformed previously published models in the literature.

Conclusion

The study successfully developed an advanced QSAR-neural network model capable of predicting plasma protein binding in human plasma for a diverse set of 277 drugs. This model's accuracy and robustness make it a valuable tool in drug discovery, potentially reducing the need for resource-intensive chemical synthesis and laboratory testing.

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.

Machine Learning-Enabled Genome Mining and Bioactivity Prediction of Natural Products

Natural products (NPs) produced by microorganisms and plants are a major source of drugs, herbicides, and fungicides. Thanks to recent advances in DNA sequencing, bioinformatics, and genome mining tools, a vast amount of data on NP biosynthesis has been generated over the years, which has been increasingly exploited to develop machine learning (ML) tools for NP discovery. In this review, we discuss the latest advances in developing and applying ML tools for exploring the potential NPs that can be encoded by genomic language and predicting the types of bioactivities of NPs. We also examine the technical challenges associated with the development and application of ML tools for NP research.

Identification of potential human pancreatic α-amylase inhibitors from natural products by molecular docking, MM/GBSA calculations, MD simulations, and ADMET analysis

Human pancreatic α-amylase (HPA), which works as a catalyst for carbohydrate hydrolysis, is one of the viable targets to control type 2 diabetes. The inhibition of α-amylase lowers blood glucose levels and helps to alleviate hyperglycemia complications. Herein, we systematically screened the potential HPA inhibitors from a library of natural products by molecular modeling. The modeling encompasses molecular docking, MM/GBSA binding energy calculations, MD simulations, and ADMET analysis. This research identified newboulaside B, newboulaside A, quercetin-3-O-β-glucoside, and sasastilboside A as the top four potential HPA inhibitors from the library of natural products, whose Glide docking scores and MM/GBSA binding energies range from -9.191 to -11.366 kcal/mol and -19.38 to -77.95 kcal/mol, respectively. Based on the simulation, among them, newboulaside B was found as the best HPA inhibitor. Throughout the simulation, with the deviation of 3Å (acarbose = 3Å), it interacted with ASP356, ASP300, ASP197, THR163, ARG161, ASP147, ALA106, and GLN63 via hydrogen bonding. Additionally, the comprehensive ADMET analysis revealed that it has good pharmacokinetic properties having not acutely toxic, moderately bioavailable, and non-inhibitor nature toward cytochrome P450. All the results suggest that newboulaside B might be a promising candidate for drug discovery against type 2 diabetes.

Opportunities and challenges in application of artificial intelligence in pharmacology

Artificial intelligence (AI) is a machine science that can mimic human behaviour like intelligent analysis of data. AI functions with specialized algorithms and integrates with deep and machine learning. Living in the digital world can generate a huge amount of medical data every day. Therefore, we need an automated and reliable evaluation tool that can make decisions more accurately and faster. Machine learning has the potential to learn, understand and analyse the data used in healthcare systems. In the last few years, AI is known to be employed in various fields in pharmaceutical science especially in pharmacological research. It helps in the analysis of preclinical (laboratory animals) and clinical (in human) trial data. AI also plays important role in various processes such as drug discovery/manufacturing, diagnosis of big data for disease identification, personalized treatment, clinical trial research, radiotherapy, surgical robotics, smart electronic health records, and epidemic outbreak prediction. Moreover, AI has been used in the evaluation of biomarkers and diseases. In this review, we explain various models and general processes of machine learning and their role in pharmacological science. Therefore, AI with deep learning and machine learning could be relevant in pharmacological research.

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.

In Silico Identification of Anti-SARS-CoV-2 Medicinal Plants Using Cheminformatics and Machine Learning

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the causative pathogen of COVID-19, is spreading rapidly and has caused hundreds of millions of infections and millions of deaths worldwide. Due to the lack of specific vaccines and effective treatments for COVID-19, there is an urgent need to identify effective drugs. Traditional Chinese medicine (TCM) is a valuable resource for identifying novel anti-SARS-CoV-2 drugs based on the important contribution of TCM and its potential benefits in COVID-19 treatment. Herein, we aimed to discover novel anti-SARS-CoV-2 compounds and medicinal plants from TCM by establishing a prediction method of anti-SARS-CoV-2 activity using machine learning methods. We first constructed a benchmark dataset from anti-SARS-CoV-2 bioactivity data collected from the ChEMBL database. Then, we established random forest (RF) and support vector machine (SVM) models that both achieved satisfactory predictive performance with AUC values of 0.90. By using this method, a total of 1011 active anti-SARS-CoV-2 compounds were predicted from the TCMSP database. Among these compounds, six compounds with highly potent activity were confirmed in the anti-SARS-CoV-2 experiments. The molecular fingerprint similarity analysis revealed that only 24 of the 1011 compounds have high similarity to the FDA-approved antiviral drugs, indicating that most of the compounds were structurally novel. Based on the predicted anti-SARS-CoV-2 compounds, we identified 74 anti-SARS-CoV-2 medicinal plants through enrichment analysis. The 74 plants are widely distributed in 68 genera and 43 families, 14 of which belong to antipyretic detoxicate plants. In summary, this study provided several medicinal plants with potential anti-SARS-CoV-2 activity, which offer an attractive starting point and a broader scope to mine for potentially novel anti-SARS-CoV-2 drugs.

Isopropyl Gallate, a Gallic Acid Derivative: In Silico and In Vitro Investigation of Its Effects on Leishmania major

Isopropyl gallate (IPG) is a polyphenol obtained from alterations in the gallic acid molecule via acid catalysis with previously reported leishmanicidal and trypanocidal activities. The present study aims to evaluate in silico binding activity towards some targets for antileishmanial chemotherapy against Leishmania major species, and ADMET parameters for IPG, as well as in vitro antileishmanial and cytotoxic effects. Molecular docking was performed using AutoDockVina and BIOVIA Discovery Studio software, whereas in silico analysis used SwissADME, PreADMET and admetSAR software. In vitro antileishmanial activity on promastigotes and amastigotes of Leishmania major, cytotoxicity and macrophages activation were assessed. IPG exhibited affinity for pteridine reductase (PTR1; -8.2 kcal/mol) and oligopeptidase B (OPB; -8.0 kcal/mol) enzymes. ADMET assays demonstrated good lipophilicity, oral bioavailability, and skin permeability, as well as non-mutagenic, non-carcinogenic properties and low risk of cardiac toxicity for IPG. Moreover, IPG inhibited the in vitro growth of promastigotes (IC₅₀ = 90.813 µM), presented significant activity against amastigotes (IC₅₀ = 13.45 μM), promoted low cytotoxicity in macrophages (CC₅₀ = 1260 μM), and increased phagocytic capacity. These results suggest IPG is more selectively toxic to the parasite than to mammalian cells. IPG demonstrated acceptable in silico pharmacokinetics parameters, and reduced infection and infectivity in parasitized macrophages, possibly involving macrophage activation pathways and inhibition of leishmania enzymes.

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.

An open-source framework for fast-yet-accurate calculation of quantum mechanical features

We present the open-source framework kallisto that enables the efficient and robust calculation of quantum mechanical features for atoms and molecules. For a benchmark set of 49 experimental molecular polarizabilities,...

Comparative Study for Prediction of Low and High Plasma Protein Binding Drugs by Various Machine Learning-Based Classification Algorithms

<p>In the drug discovery path, most drug candidates failed at the early stages due to their pharmacokinetic behavior in the system. Early prediction of pharmacokinetic properties and screening methods can reduce the time and investment for lead discoveries. Plasma protein binding is one of these properties which has a vital role in drug discovery and development. The focus of the current study is to develop a computational model for the classification of Low Plasma Protein Binding (LPPB) and High Plasma Protein Binding (HPPB) drugs using machine learning methods for early screening of molecules through WEKA. Plasma protein binding drugs data was collated from the Drug Bank database where 617 drug candidates were found to interact with plasma proteins, out of which an equal proportion of high and low plasma protein binding drugs were extracted to build a training set of ~300 drugs. The machine learning algorithms were trained with a training set and evaluated by a test set. We also compared various machine learning-based classification algorithms i.e., the Naïve Bayes algorithm, Instance-Based Learner (IBK), multilayer perceptron, and random forest to determine the best model based on accuracy. It was observed that the random forest algorithm-based model outperforms with an accuracy of 99.67% and 0.9933 kappa value on training set and on test set as compared to other classification methods and can predict drug plasma binding capacity in the given data set using the WEKA tool.</p>

Artificial Intelligence, Machine Learning, and Deep Learning in Real-Life Drug Design Cases

The discovery and development of drugs is a long and expensive process with a high attrition rate. Computational drug discovery contributes to ligand discovery and optimization, by using models that describe the properties of ligands and their interactions with biological targets. In recent years, artificial intelligence (AI) has made remarkable modeling progress, driven by new algorithms and by the increase in computing power and storage capacities, which allow the processing of large amounts of data in a short time. This review provides the current state of the art of AI methods applied to drug discovery, with a focus on structure- and ligand-based virtual screening, library design and high-throughput analysis, drug repurposing and drug sensitivity, de novo design, chemical reactions and synthetic accessibility, ADMET, and quantum mechanics.

Plasma protein binding prediction focusing on residue-level features and circularity of cyclic peptides by deep learning

MOTIVATION

In recent years, cyclic peptide drugs have been receiving increasing attention because they can target proteins that are difficult to be tackled by conventional small-molecule drugs or antibody drugs. Plasma protein binding rate (%PPB) is a significant pharmacokinetic property of a compound in drug discovery and design. However, due to structural differences, previous computational prediction methods developed for small-molecule compounds cannot be successfully applied to cyclic peptides, and methods for predicting the PPB rate of cyclic peptides with high accuracy are not yet available.

RESULTS

Cyclic peptides are larger than small molecules, and their local structures have a considerable impact on PPB; thus, molecular descriptors expressing residue-level local features of cyclic peptides, instead of those expressing the entire molecule, as well as the circularity of the cyclic peptides should be considered. Therefore, we developed a prediction method named CycPeptPPB using deep learning that considers both factors. First, the macrocycle ring of cyclic peptides was decomposed residue by residue. The residue-based descriptors were arranged according to the sequence information of the cyclic peptide. Furthermore, the circular data augmentation method was used, and the circular convolution method CyclicConv was devised to express the cyclic structure. CycPeptPPB exhibited excellent performance, with mean absolute error (MAE) of 4.79% and correlation coefficient (R) of 0.92 for the public drug dataset, compared to the prediction performance of the existing PPB rate prediction software (MAE=15.08%, R=0.63).

AVAILABILITY AND IMPLEMENTATION

The data underlying this article are available in the online supplementary material. The source code of CycPeptPPB is available at https://github.com/akiyamalab/cycpeptppb.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A Novel Method for Predicting the Human Inherent Clearance and Its Application in the Study of the Pharmacokinetics and Drug-Drug Interaction between Azidothymidine and Fluconazole Mediated by UGT Enzyme

In order to improve the benefit–risk ratio of pharmacokinetic (PK) research in the early development of new drugs, in silico and in vitro methods were constructed and improved. Models of intrinsic clearance rate (CL_int) were constructed based on the quantitative structure–activity relationship (QSAR) of 7882 collected compounds. Moreover, a novel in vitro metabolic method, the Bio-PK dynamic metabolic system, was constructed and combined with a physiology-based pharmacokinetic model (PBPK) model to predict the metabolism and the drug–drug interaction (DDI) of azidothymidine (AZT) and fluconazole (FCZ) mediated by the phase II metabolic enzyme UDP-glycosyltransferase (UGT) in humans. Compared with the QSAR models reported previously, the goodness of fit of our CL_int model was slightly improved (determination coefficient (R²) = 0.58 vs. 0.25–0.45). Meanwhile, compared with the predicted clearance of 61.96 L/h (fold error: 2.95–3.13) using CL_int (8 µL/min/mg) from traditional microsomal experiment, the predicted clearance using CL_int (25 μL/min/mg) from Bio-PK system was increased to 143.26 L/h (fold error: 1.27–1.36). The predicted C_max and AUC (the area under the concentration–time curve) ratio were 1.32 and 1.84 (fold error: 1.36 and 1.05) in a DDI study with an inhibition coefficient (Ki) of 13.97 μM from the Bio-PK system. The results indicate that the Bio-PK system more truly reflects the dynamic metabolism and DDI of AZT and FCZ in the body. In summary, the novel in silico and in vitro method may provide new ideas for the optimization of drug metabolism and DDI research methods in early drug development.

Machine learning methods to predict the cultivation age of Panacis Quinquefolii Radix

Background

American ginseng (AG) is a valuable medicine widely consumed as a herbal remedy throughout the world. Huge price difference among AG with different growth years leads to intentional adulteration for higher profits. Thus, developing reliable approaches to authenticate the cultivation ages of AG products is of great use in preventing age falsification.

Methods

A total of 106 batches of AG samples along with their 9 physicochemical features were collected and measured from experiments, which was then split into a training set and two test sets (test set 1 and 2) according to the cultivation regions. Principle component analysis (PCA) was carried out to examine the distribution of the three data sets. Four machine learning (ML) algorithms, namely elastic net, k-nearest neighbors, support vector machine and multi-layer perception (MLP) were employed to construct predictive models using the features as inputs and their growth years as outputs. In addition, a similarity-based applicability domain (AD) was defined for these models to ensure the reliability of the predictive results for AG samples produced in different regions.

Results

A positive correlation was observed between the several features and the growth years. PCA revealed diverse distributions among different cultivation regions. The most accurate model derived from MLP shows good prediction power for the fivefold cross validation and the test set 1 with mean square error (MSE) of 0.017 and 0.016 respectively, but a higher MSE value of 1.260 for the test set 2. After applying the AD, all models showed much lower prediction errors for the test samples within AD (IDs) than those outside the AD (ODs). MLP remains the best predictive model with an MSE value of 0.030 for the IDs.

Conclusion

Cultivation years have a close relationship with bioactive components of AG. The constructed models and AD are also able to predict the cultivation years and discriminate samples that have inaccurate prediction results. The AD-equipped models used in this study provide useful tools for determining the age of AG in the market and are freely available at https://github.com/dreadlesss/Panax_age_predictor.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13020-021-00511-5.

In Silico Prediction of CYP2C8 Inhibition with Machine-Learning Methods

Cytochrome P450 2C8 (CYP2C8) is a major drug-metabolizing enzyme in humans and is responsible for the metabolism of ∼5% drugs in clinical use. Thus, inhibition of CYP2C8, which causes potential adverse drug events, cannot be neglected. The in vitro drug interaction studies guidelines for industry issued by the FDA also point out that it needs to be determined whether investigated drugs are CYP2C8 inhibitors before clinical trials. However, current studies mainly focus on predicting the inhibitors of other major P450 enzymes, and the importance of CYP2C8 inhibition has been overlooked. Therefore, there is a need to develop models for identifying potential CYP2C8 inhibition. In this study, in silico classification models for predicting CYP2C8 inhibition were built by five machine-learning methods combined with nine molecular fingerprints. The performance of the models built was evaluated by test and external validation sets. The best model had AUC values of 0.85 and 0.90 for the test and external validation sets, respectively. The applicability domain was analyzed based on the molecular similarity and exhibited an impact on the improvement of prediction accuracy. Furthermore, several representative privileged substructures such as 1H-benzo[d]imidazole, 1-phenyl-1H-pyrazole, and quinoline were identified by information gain and substructure frequency analysis. Overall, our results would be helpful for the prediction of CYP2C8 inhibition.

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.

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.

Machine learning in pharmacometrics: Opportunities and challenges

The explosive growth in medical devices, imaging and diagnostics, computing, and communication and information technologies in drug development and healthcare has created an ever-expanding data landscape that the pharmacometrics (PMX) research community must now traverse. The tools of machine learning (ML) have emerged as a powerful computational approach in other data-rich disciplines but its effective utilization in the pharmaceutical sciences and PMX modelling is in its infancy. ML-based methods can complement PMX modelling by enabling the information in diverse sources of big data, e.g. population-based public databases and disease-specific clinical registries, to be harnessed because they are capable of efficiently identifying salient variables associated with outcomes and delineating their interdependencies. ML algorithms are computationally efficient, have strong predictive capabilities and can enable learning in the big data setting. ML algorithms can be viewed as providing a computational bridge from big data to complement PMX modelling. This review provides an overview of the strengths and weaknesses of ML approaches vis-à-vis population methods, assesses current research into ML applications in the pharmaceutical sciences and provides perspective for potential opportunities and strategies for the successful integration and utilization of ML in PMX.

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.

Artificial Intelligence in Drug Discovery: A Comprehensive Review of Data-driven and Machine Learning Approaches

As expenditure on drug development increases exponentially, the overall drug discovery process requires a sustainable revolution. Since artificial intelligence (AI) is leading the fourth industrial revolution, AI can be considered as a viable solution for unstable drug research and development. Generally, AI is applied to fields with sufficient data such as computer vision and natural language processing, but there are many efforts to revolutionize the existing drug discovery process by applying AI. This review provides a comprehensive, organized summary of the recent research trends in AI-guided drug discovery process including target identification, hit identification, ADMET prediction, lead optimization, and drug repositioning. The main data sources in each field are also summarized in this review. In addition, an in-depth analysis of the remaining challenges and limitations will be provided, and proposals for promising future directions in each of the aforementioned areas.

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.

Metabolic stability studies of lead compounds supported by separation techniques and chemometrics analysis

With metabolism being one of the main routes of drug elimination from the body (accounting for removal of around 75% of known drugs), it is crucial to understand and study metabolic stability of drug candidates. Metabolically unstable compounds are uncomfortable to administer (requiring repetitive dosage during therapy), while overly stable drugs increase risk of adverse drug reactions. Additionally, biotransformation reactions can lead to formation of toxic or pharmacologically active metabolites (either less-active than parent drug, or even with different action). There were numerous approaches in estimating metabolic stability, including in vitro, in vivo, in silico, and high-throughput screening to name a few. This review aims at describing separation techniques used in in vitro metabolic stability estimation, as well as chemometric techniques allowing for creation of predictive models which enable high-throughput screening approach for estimation of metabolic stability. With a very low rate of drug approval, it is important to understand in silico methods that aim at supporting classical in vitro approach. Predictive models that allow assessment of certain biological properties of drug candidates allow for cutting not only cost, but also time required to synthesize compounds predicted to be unstable or inactive by in silico models.

Organizing mechanism-related information on chemical interactions using a framework based on the aggregate exposure and adverse outcome pathways

This paper presents a framework for organizing and accessing mechanistic data on chemical interactions. The framework is designed to support the assessment of risks from combined chemical exposures. The framework covers interactions between chemicals that occur over the entire source-to-outcome continuum including interactions that are studied in the fields of chemical transport, environmental fate, exposure assessment, dosimetry, and individual and population-based adverse outcomes. The framework proposes to organize data using a semantic triple of a chemical (subject), has impact (predicate), and a causal event on the source-to-outcome continuum of a second chemical (object). The location of the causal event on the source-to-outcome continuum and the nature of the impact are used as the basis for a taxonomy of interactions. The approach also builds on concepts from the Aggregate Exposure Pathway (AEP) and Adverse Outcome Pathway (AOP). The framework proposes the linking of AEPs of multiple chemicals and the AOP networks relevant to those chemicals to form AEP-AOP networks that describe chemical interactions that cannot be characterized using AOP networks alone. Such AEP-AOP networks will aid the construction of workflows for both experimental design and the systematic review or evaluation performed in risk assessments. Finally, the framework is used to link the constructs of existing component-based approaches for mixture toxicology to specific categories in the interaction taxonomy.

In Silico Prediction of Human Renal Clearance of Compounds Using Quantitative Structure-Pharmacokinetic Relationship Models

Renal clearance (CLr) plays an essential role in the elimination of drugs. In this study, 636 compounds were obtained from various sources to develop in silico models for the prediction of CLr. Stepwise multiple linear regression and random forest regression methods were employed to build global models and local models according to ionization state or net elimination pathways. The local models toward compounds undergoing different net elimination pathways showed good predictive power: the geometric mean fold error was close to 2, indicating the clearance of most compounds could be predicted within a 2-fold error range. Six classification methods were used to construct classification models. However, the performance of these classification models was less than satisfactory, and the mean accuracy of the top five models in test sets was 0.65. Moreover, qualitative analysis of physicochemical profiles between compounds undergoing different net elimination pathways revealed that compounds with higher lipophilicity tended to be reabsorbed more easily and showed lower CLr, while compounds with higher values of polar descriptors tended to secrete more easily and showed higher CLr.

Drug Concentration Asymmetry in Tissues and Plasma for Small Molecule-Related Therapeutic Modalities

The well accepted "free drug hypothesis" for small-molecule drugs assumes that only the free (unbound) drug concentration at the therapeutic target can elicit a pharmacologic effect. Unbound (free) drug concentrations in plasma are readily measurable and are often used as surrogates for the drug concentrations at the site of pharmacologic action in pharmacokinetic-pharmacodynamic analysis and clinical dose projection in drug discovery. Furthermore, for permeable compounds at pharmacokinetic steady state, the free drug concentration in tissue is likely a close approximation of that in plasma; however, several factors can create and maintain disequilibrium between the free drug concentration in plasma and tissue, leading to free drug concentration asymmetry. These factors include drug uptake and extrusion mechanisms involving the uptake and efflux drug transporters, intracellular biotransformation of prodrugs, membrane receptor-mediated uptake of antibody-drug conjugates, pH gradients, unique distribution properties (covalent binders, nanoparticles), and local drug delivery (e.g., inhalation). The impact of these factors on the free drug concentrations in tissues can be represented by K p,uu, the ratio of free drug concentration between tissue and plasma at steady state. This review focuses on situations in which free drug concentrations in tissues may differ from those in plasma (e.g., K p,uu > or <1) and discusses the limitations of the surrogate approach of using plasma-free drug concentration to predict free drug concentrations in tissue. This is an important consideration for novel therapeutic modalities since systemic exposure as a driver of pharmacologic effects may provide limited value in guiding compound optimization, selection, and advancement. Ultimately, a deeper understanding of the relationship between free drug concentrations in plasma and tissues is needed.

Intercorrelation Limits in Molecular Descriptor Preselection for QSAR/QSPR

QSAR/QSPR (quantitative structure-activity/property relationship) modeling has been a prevalent approach in various, overlapping sub-fields of computational, medicinal and environmental chemistry for decades. The generation and selection of molecular descriptors is an essential part of this process. In typical QSAR workflows, the starting pool of molecular descriptors is rationalized based on filtering out descriptors which are (i) constant throughout the whole dataset, or (ii) very strongly correlated to another descriptor. While the former is fairly straightforward, the latter involves a level of subjectivity when deciding what exactly is considered to be a strong correlation. Despite that, most QSAR modeling studies do not report on this step. In this study, we examine in detail the effect of various possible descriptor intercorrelation limits on the resulting QSAR models. Statistical comparisons are carried out based on four case studies from contemporary QSAR literature, using a combined methodology based on sum of ranking differences (SRD) and analysis of variance (ANOVA).

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.

In Silico Prediction of Endocrine Disrupting Chemicals Using Single-Label and Multilabel Models

Endocrine disruption (ED) has become a serious public health issue and also poses a significant threat to the ecosystem. Due to complex mechanisms of ED, traditional in silico models focusing on only one mechanism are insufficient for detection of endocrine disrupting chemicals (EDCs), let alone offering an overview of possible action mechanisms for a known EDC. To remove these limitations, in this study both single-label and multilabel models were constructed across six ED targets, namely, AR (androgen receptor), ER (estrogen receptor alpha), TR (thyroid receptor), GR (glucocorticoid receptor), PPARg (peroxisome proliferator-activated receptor gamma), and aromatase. Two machine learning methods were used to build the single-label models, with multiple random under-sampling combining voting classification to overcome the challenge of data imbalance. Four methods were explored to construct the multilabel models that can predict the interaction of one EDC against multiple targets simultaneously. The single-label models of all the six targets have achieved reasonable performance with balanced accuracy (BA) values from 0.742 to 0.816. Each top single-label model was then joined to predict the multilabel test set with BA values from 0.586 to 0.711. The multilabel models could offer a significant boost over the single-label baselines with BA values for the multilabel test set from 0.659 to 0.832. Therefore, we concluded that single-label models could be employed for identification of potential EDCs, while multilabel ones are preferable for prediction of possible mechanisms of known EDCs.

Development of QSAR machine learning-based models to forecast the effect of substances on malignant melanoma cells

SK-MEL-5 is a human melanoma cell line that has been used in various studies to explore new therapies against melanoma in different in vitro experiments. Based on this study we report on the development of quantitative structure-activity relationship (QSAR) models able to predict the cytotoxic effect of diverse chemical compounds on this cancer cell line. The dataset of cytotoxic and inactive compounds were downloaded from the PubChem database. It contains the data for all chemical compounds for which cytotoxicity results expressed by GI₅₀ was recorded. In total 13 blocks of molecular descriptors were computed and used, after appropriate pre-processing in building QSAR models with four machine learning classifiers: Random forest (RF), gradient boosting, support vector machine and random k-nearest neighbors. Among the 186 models reported none had a positive predictive value (PPV) higher than 0.90 in both nested cross-validation and on an external dataset testing, but 7 models had a PPV higher than 0.85 in both evaluations, all seven using the RFs algorithm as a classifier, and topological descriptors, information indices, 2D-autocorrelation descriptors, P-VSA-like descriptors, and edge-adjacency descriptors as sets of features used for classification. The y-scrambling test was associated with considerably worse performance (confirming the non-random character of the models) and the applicability domain was assessed through three different methods.

Application of Multivariate Adaptive Regression Splines (MARSplines) for Predicting Hansen Solubility Parameters Based on 1D and 2D Molecular Descriptors Computed from SMILES String

A new method of Hansen solubility parameters (HSPs) prediction was developed by combining the multivariate adaptive regression splines (MARSplines) methodology with a simple multivariable regression involving 1D and 2D PaDEL molecular descriptors. In order to adopt the MARSplines approach to QSPR/QSAR problems, several optimization procedures were proposed and tested. The effectiveness of the obtained models was checked via standard QSPR/QSAR internal validation procedures provided by the QSARINS software and by predicting the solubility classification of polymers and drug-like solid solutes in collections of solvents. By utilizing information derived only from SMILES strings, the obtained models allow for computing all of the three Hansen solubility parameters including dispersion, polarization, and hydrogen bonding. Although several descriptors are required for proper parameters estimation, the proposed procedure is simple and straightforward and does not require a molecular geometry optimization. The obtained HSP values are highly correlated with experimental data, and their application for solving solubility problems leads to essentially the same quality as for the original parameters. Based on provided models, it is possible to characterize any solvent and liquid solute for which HSP data are unavailable.

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.