Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases

The role of nanomedicine and artificial intelligence in cancer health care: individual applications and emerging integrations-a narrative review

Cancer remains one of the deadliest diseases globally, significantly impacting patients' quality of life. Addressing the rising incidence of cancer deaths necessitates innovative approaches such as nanomedicine and artificial intelligence (AI). The convergence of nanomedicine and AI represents a transformative frontier in cancer healthcare, promising unprecedented advancements in diagnosis, treatment, and patient management. This narrative review explores the distinct applications of nanomedicine and AI in oncology, alongside their synergistic potential. Nanomedicine leverages nanoparticles for targeted drug delivery, enhancing therapeutic efficacy while minimizing adverse effects. Concurrently, AI algorithms facilitate early cancer detection, personalized treatment planning, and predictive analytics, thereby optimizing clinical outcomes. Emerging integrations of these technologies could transform cancer care by facilitating precise, personalized, and adaptive treatment strategies. This review synthesizes current research, highlights innovative individual applications, and discusses the emerging integrations of nanomedicine and AI in oncology. The goal is to provide a comprehensive understanding of how these cutting-edge technologies can collaboratively improve cancer diagnosis, treatment, and patient prognosis.

Anti-cancer activity elucidation of geissolosimine as an MDM2-p53 interaction inhibitor: An in-silico study

For cancer treatment, Inhibition of murine double minute (MDM2) & p53 interaction is considered an attractive therapeutic approach. In this study, we performed an integrated virtual screening (i.e., QSAR, structural similarity, molecular docking, and molecular dynamic simulation) on the in-house building alkaloids library. Geissolosimine (i.e., an indole alkaloid) was predicted as a potential inhibitor for MDM2-p53 interaction. The predicted pIC50 value of Geissolosimine, was 7.013 M. Moreover, Geissolosimine showed 0.62% structural similarity to 'SAR405838' (i.e., a clinical trial inhibitor for MDM2-p53 interaction inhibition); and a docking score of -10.9 kcal/mol that was higher than the 'SAR405838'.100 ns molecular dynamics simulation (MDS) was performed to validate the docking result and it exhibited better binding stability to MDM2. The pharmacokinetic & drug-likeness analysis suggested that Geissolosimine had potential to be a drug-like compound. However, in vitro & in vivo assays will be required to validate this study.

Perspectives: Comparison of deep learning segmentation models on biophysical and biomedical data

Deep learning-based approaches are now widely used across biophysics to help automate a variety of tasks including image segmentation, feature selection, and deconvolution. However, the presence of multiple competing deep learning architectures, each with its own advantages and disadvantages, makes it challenging to select an architecture best suited for a specific application. As such, we present a comprehensive comparison of common models. Here, we focus on the task of segmentation assuming typical (often small) training dataset sizes available from biophysics experiments and compare the following four commonly used architectures: convolutional neural networks, U-Nets, vision transformers, and vision state space models. In doing so, we establish criteria for determining optimal conditions under which each model excels, thereby offering practical guidelines for researchers and practitioners in the field.

Machine Learning-Driven Discovery of Structurally Related Natural Products as Activators of the Cardiac Calcium Pump SERCA2a

A key molecular dysfunction in heart failure is the reduced activity of the cardiac sarcoplasmic reticulum Ca2+-ATPase (SERCA2a) in cardiac muscle cells. Reactivating SERCA2a improves cardiac function in heart failure models, making it a validated target and an attractive therapeutic approach for heart failure therapy. However, finding small-molecule SERCA2a activators is challenging. In this study, we used a machine learning-based virtual screening to identify SERCA2a activators among 57,423 natural products. The machine learning model identified ten structurally related natural products from Zingiber officinale, Aframomum melegueta, Alpinia officinarum, Alpinia oxyphylla, and Capsicum (chili peppers) as SERCA2a activators. Initial ATPase assays showed seven of these activate SERCA at low micromolar concentrations. Notably, two natural products, Yakuchinone A and Alpinoid D displayed robust concentration-dependent responses in primary ATPase activity assays, efficient lipid bilayer binding and permeation in atomistic simulations, and enhanced intracellular Ca2+ transport in adult mouse cardiac cells. While these natural products exert off-target effects on Ca2+ signaling, these compounds offer promising avenues for the design and optimization of lead compounds. In conclusion, this study increases the array of calcium pump effectors and provides new scaffolds for the development of novel SERCA2a activators as new therapies for heart failure.

Prediction of Adeno-Associated Virus Fitness with a Protein Language-Based Machine Learning Model

Adeno-associated virus (AAV)-based therapeutics have the potential to transform the lives of patients by delivering one-time treatments for a variety of diseases. However, a critical challenge to their widespread adoption and distribution is the high cost of goods. Reducing manufacturing costs by developing AAV capsids with improved yield, or fitness, is key to making gene therapies more affordable. AAV fitness is largely determined by the amino acid sequence of the capsid, however, engineered AAVs are rarely optimized for manufacturability. Here, we report a state-of-the art machine learning (ML) model that predicts the fitness of AAV2 capsid mutants based on the amino acid sequence of the capsid monomer. By combining a protein language model (PLM) and classical ML techniques, our model achieved a significantly high prediction accuracy (Pearson correlation = 0.818) for capsid fitness. Importantly, tests on completely independent datasets showed robustness and generalizability of our model, even for multimutant AAV capsids. Our accurate ML-based model can be used as a surrogate for laborious in vitro experiments, thus saving time and resources, and can be deployed to increase the fitness of clinical AAV capsids to make gene therapies economically viable for patients.

Computational Evaluation of Phytocompounds From Selective Medicinal Plants as Potential Antidiabetic Agents

The distinguishing characteristic of diabetes mellitus (DM), chronic hyperglycemia emphasizes the need for safer, more efficient antidiabetic treatments. This study employs computational approaches to explore the therapeutic potential of phytochemicals from medicinal plants as antidiabetic drugs. Molecular docking against phosphorylated insulin receptor (IR) tyrosine kinase and human dipeptidyl peptidase IV (DPP-IV) identified eriodictyol (-7.13 kcal/mol) and petunidin (-6.61 kcal/mol) as potent inhibitors. Molecular dynamics simulations confirmed the structural stability of these complexes, with root mean square deviation values stabilizing within 2.8-4.5 Å. Binding free energy calculations using Molecular Mechanics Generalized Born Surface Area evealed strong binding affinities of eriodictyol-IR (ΔGbinding = -44.63 ± 4.05 kcal/mol), and petunidin-DPP-IV complex (ΔGbinding = -49.86 ± 6.13 kcal/mol). Additionally, pharmacokinetic assessments showed that these compounds adhered to Lipinski's rule, with no significant hepatotoxicity or cytotoxicity. These findings underscore the potential of these phytocompounds as antidiabetic candidates, warranting further in vitro and in vivo investigations.

Discovery and Characterization of Novel Receptor-Interacting Protein Kinase 1 Inhibitors Using Deep Learning and Virtual Screening

Receptor-interacting protein kinase 1 (RIPK1) serves as a critical mediator of cell necroptosis and represents a promising therapeutic target for various human neurodegenerative diseases and inflammatory diseases. Nonetheless, the RIPK1 inhibitors currently reported are inadequate for clinical research due to suboptimal inhibitory activities or lack of selectivity. Consequently, there is a need for the discovery of novel RIPK1 kinase inhibitors. In this study, we integrated a deep learning model, specifically the fingerprint graph attention network (FP-GAT), with molecular docking-based virtual screening to identify potential RIPK1 inhibitors from a library comprising 13 million compounds. Out of 43 compounds procured, two compounds (designated as 24 and 41) demonstrated enzyme inhibition activity exceeding 50% at a concentration of 10 μM against RIPK1. The half-maximal inhibitory concentrations (IC50) for compounds 24 and 41 were determined to be 2.01 and 2.95 μM, respectively. Furthermore, these compounds exhibited protective effects in an HT-29 cell model of TSZ-induced necroptosis, with half-maximal effective concentrations (EC50) of 6.77 μM for compound 24 and 68.70 μM for compound 41. Finally, molecular dynamics simulations and binding free energy calculations were conducted to elucidate the molecular mechanism of compounds 24 and 41 binding to RIPK1. The results show that Met92, Met95, Ala155, and Asp156 are key residues for novel RIPK1 inhibitors. In summary, this work discovered two hit compounds targeting RIPK1, which can be further structurally modified to become promising lead compounds.

Phytochemical composition, anti-microbial, anti-oxidant and anti-diabetic effects of Solanum elaeagnifolium Cav. leaves: in vitro and in silico assessments

The aim of this study was to screen the chemical components of Solanum elaeagnifolium leaves and assess their therapeutic attributes with regard to their antioxidant, antibacterial, and antidiabetic activities. The antidiabetic effects were explored to determine the α-amylase and α-glucosidase inhibitory potential of the leaf extract. To identify the active antidiabetic drugs from the extracts, the GC-MS-screened molecules were docked with diabetes-related proteins using the glide module in the Schrodinger Tool. In addition, molecular dynamics (MD) simulations were performed for 100 ns to evaluate the binding stability of the docked complex using the Desmond module. The ethyl acetate had a significant total phenolic content (TPC), with a value of 79.04 ± 0.98 mg/g GAE. The ethanol extract was tested for its minimum inhibitory concentration (MIC) for its bacteriostatic properties. It suppressed the growth of B. subtilis, E. coli, P. vulgaris, R. equi and S. epidermis at a dosage of 118.75 µg/mL. Moreover, the IC50 values of the ethanol extract were determined to be 17.78 ± 2.38 in the α-amylase and and 27.90 ± 5.02 µg/mL in α-glucosidase. The in-silico investigation revealed that cyclolaudenol achieved docking scores of -7.94 kcal/mol for α-amylase. Likewise, the α-tocopherol achieved the docking scores of -7.41 kcal/mol for glycogen phosphorylase B and -7.21 kcal/mol for phosphorylase kinase. In the MD simulations, the cyclolaudenol and α-tocopherol complexes exhibited consistently stable affinities with diabetic proteins throughout the trajectory. Based on these findings, we conclude that this plant could be a good source for the development of novel antioxidant, antibacterial, and antidiabetic agents.

Advances in AI-based strategies and tools to facilitate natural product and drug development

Natural products and their derivatives have been important for treating diseases in humans, animals, and plants. However, discovering new structures from natural sources is still challenging. In recent years, artificial intelligence (AI) has greatly aided the discovery and development of natural products and drugs. AI facilitates to: connect genetic data to chemical structures or vice-versa, repurpose known natural products, predict metabolic pathways, and design and optimize metabolites biosynthesis. More recently, the emergence and improvement in neural networks such as deep learning and ensemble automated web based bioinformatics platforms have sped up the discovery process. Meanwhile, AI also improves the identification and structure elucidation of unknown compounds from raw data like mass spectrometry and nuclear magnetic resonance. This article reviews these AI-driven methods and tools, highlighting their practical applications and guide for efficient natural product discovery and drug development.

Artificial intelligence accelerates the identification of nature-derived potent LOXL2 inhibitors

The role of LOXL2 in cancer has been widely demonstrated, but current therapies targeting LOXL2 are not yet fully developed. We believe that selective nature-derived inhibition of LOXL2 may provide a better therapeutic approach for the treatment of cancer. Therefore, we adopted a comprehensive approach combining deep learning and traditional computer-aided drug design methods to screen LOXL2 selective inhibitors. Bioactivity and affinity of the potential LOXL2 inhibitors were determined by molecular docking and virtual screening. At the same time, we experimentally tested the effect of potential LOXL2 inhibitors on cancer cells. Validation showed that it could inhibit proliferation and migration, promote apoptosis of CT26 cells, and reduce the expression level of LOXL2 protein. As a result, we identified a potent LOXL2 inhibitor: the natural product Forsythoside A, and demonstrated that Forsythoside A has an inhibitory effect on tumors.

Fine-Tuned Deep Transfer Learning Models for Large Screenings of Safer Drugs Targeting Class A GPCRs

G protein-coupled receptors (GPCRs) remain a focal point of research due to their critical roles in cell signaling and their prominence as drug targets. However, directly linking drug efficacy to the receptor-mediated activation of specific intracellular transducers and the resulting physiological outcomes remains challenging. It is unclear whether the enhanced therapeutic window of certain drugs─defined as the dose range that provides effective therapy with minimal side effects─stems from their low intrinsic efficacy across all signaling pathways or ligand bias, wherein specific transducer subtypes are preferentially activated in a given cellular system compared to a reference ligand. Accurately predicting safer compounds, through either low intrinsic efficacy or ligand bias, would greatly advance drug development. While AI models hold promise for such predictions, the development of deep learning models capable of reliably forecasting GPCR ligands with defined bioactivities remains challenging, largely due to the limited availability of high-quality data. To address this, we pretrained a model on receptor sequences and ligand data sets across all class A GPCRs and then refined it to predict low-efficacy compounds or biased agonists for individual class A GPCRs. This was achieved using transfer learning and a neural network incorporating natural language processing of target sequences and receptor mutation effects on signaling. These two fine-tuned models─one for low-efficacy agonists and one for biased agonists─are available on demand for each class A GPCR and enable virtual screening of large chemical libraries, thereby facilitating the discovery of compounds with potentially improved safety profiles.

Enhancing Drug Repositioning Through Local Interactive Learning With Bilinear Attention Networks

Drug repositioning has emerged as a promising strategy for identifying new therapeutic applications for existing drugs. In this study, we present DRGBCN, a novel computational method that integrates heterogeneous information through a deep bilinear attention network to infer potential drugs for specific diseases. DRGBCN involves constructing a comprehensive drug-disease network by incorporating multiple similarity networks for drugs and diseases. Firstly, we introduce a layer attention mechanism to effectively learn the embeddings of graph convolutional layers from these networks. Subsequently, a bilinear attention network is constructed to capture pairwise local interactions between drugs and diseases. This combined approach enhances the accuracy and reliability of predictions. Finally, a multi-layer perceptron module is employed to evaluate potential drugs. Through extensive experiments on three publicly available datasets, DRGBCN demonstrates better performance over baseline methods in 10-fold cross-validation, achieving an average area under the receiver operating characteristic curve (AUROC) of 0.9399. Furthermore, case studies on bladder cancer and acute lymphoblastic leukemia confirm the practical application of DRGBCN in real-world drug repositioning scenarios. Importantly, our experimental results from the drug-disease network analysis reveal the successful clustering of similar drugs within the same community, providing valuable insights into drug-disease interactions. In conclusion, DRGBCN holds significant promise for uncovering new therapeutic applications of existing drugs, thereby contributing to the advancement of precision medicine.

Identification of active compounds as novel dipeptidyl peptidase-4 inhibitors through machine learning and structure-based molecular docking simulations

The enzyme dipeptidyl peptidase 4 (DPP4) is a potential therapeutic target for type 2 diabetes (T2DM). Many synthetic anti-DPP4 medications are available to treat T2DM. The need for secure and efficient medicines has been unmet due to the adverse side effects of existing DPP4 medications. The present study implemented a combined approach to machine learning and structure-based virtual screening to identify DPP4 inhibitors. Two ML models were trained based on DPP4 IC50 datasets. The ML models random forest (RF) and multilayer perceptron (MLP) neural network showed good accuracy, with the area under the curve being 0.93 and 0.91, respectively. The natural compound library was screened through ML models, and 1% (217) of compounds were selected for further screening. Structure-based virtual screening was performed along with positive control sitagliptin to obtain more specific and selective leads for DPP4. Based on binding affinity, drug-likeness properties, and interaction with DPP4, Z-614 and Z-997 compounds showed high binding affinity and specificity in the catalytic pocket of DPP4. Finally, the stability conformation of the DPP4 enzyme complex was checked by a molecular dynamics (MD) simulation. The MD simulation showed that both compounds bind better in the catalytic pocket, but the Z-614 compound altered the DPP4 native conformation. Therefore, Z-614 showed a high deviation in the backbone. This combined approach (ML and structure-based) study reported that Z-997 binds most stably to DPP4 in their catalytic pocket with a binding free energy of -70.3 kJ/mol, suggesting its therapeutic potential as a treatment option for T2DM disease.Communicated by Ramaswamy H. Sarma.

KinasePred: A Computational Tool for Small-Molecule Kinase Target Prediction

Protein kinases are key regulators of cellular processes and critical therapeutic targets in diseases like cancer, making them a focal point for drug discovery efforts. In this context, we developed KinasePred, a robust computational workflow that combines machine learning and explainable artificial intelligence to predict the kinase activity of small molecules while providing detailed insights into the structural features driving ligand-target interactions. Our kinase-family predictive tool demonstrated significant performance, validated through virtual screening, where it successfully identified six kinase inhibitors. Target-focused operational models were subsequently developed to refine target-specific predictions, enabling the identification of molecular determinants of kinase selectivity. This integrated framework not only accelerates the screening and identification of kinase-targeting compounds but also supports broader applications in target identification, polypharmacology studies, and off-target effect analysis, providing a versatile tool for streamlining the drug discovery process.

Integrated analysis of gene expressions and targeted mirnas for explaining crosstalk between oral and esophageal squamous cell carcinomas through an interpretable machine learning approach

This study explores the bidirectional relation of esophageal squamous cell carcinoma (ESCC) and oral squamous cell carcinoma (OSCC), examining shared risk factors and underlying molecular mechanisms. By employing random forest (RF) classifier, enhanced with interpretable machine learning (IML) through SHapley Additive exPlanations (SHAP), we analyzed gene expression from two GEO datasets (GSE30784 and GSE44021). The GSE30784 dataset comprises 167 OSCC samples and 45 control group, whereas the GSE44021 dataset encompasses 113 ESCC samples and 113 control group. Our analysis led to identification of 20 key genes, such as XBP1, VGLL1, and RAD1, which are significantly associated with development of ESCC and OSCC. Further investigations were conducted using tools like NetworkAnalyst 3.0, Single Cell Portal, and miRNET 2.0, which highlighted complex interactions between these genes and specific miRNA targets including hsa-mir-124-3p and hsa-mir-1-3p. Our model achieved high precision in identifying genes linked to crucial processes like programmed cell death and cancer pathways, suggesting new avenues for diagnosis and treatment. This study confirms the bidirectional relationship between OSCC and ESCC, laying groundwork for targeted therapeutic approaches. This study helps to identify shared biological pathways and genetic factors of these conditions for designing personalized medicine strategies and to improve disease management.

Comparison of new secondgeneration H1 receptor blockers with some molecules; a study involving DFT, molecular docking, ADMET, biological target and activity

Although the antiallergic properties of compounds such as CAPE, Melatonin, Curcumin, and Vitamin C have been poorly discussed by experimental studies, the antiallergic properties of these famous molecules have never been discussed with calculations. The histamine-1 receptor (H1R) belongs to the family of rhodopsin-like G-protein-coupled receptors expressed in cells that mediate allergies and other pathophysiological diseases. In this study, pharmacological activities of FDA-approved second generation H1 antihistamines (Levocetirizine, desloratadine and fexofenadine) and molecules such as CAPE, Melatonin, Curcumin, Vitamin C, ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) profiles, density functional theory (DFT), molecular docking, biological targets and activities were compared by calculating. Since drug development is an extremely risky, costly and time-consuming process, the data obtained in this study will facilitate and guide future studies. It will also enable researchers to focus on the most promising compounds, providing an effective design strategy. Their pharmacological activity was carried out using computer-based computational techniques including DFT, molecular docking, ADMET analysis, biological targeting, and activity methods. The best binding sites of Desloratadine, Levocetirizine, Fexofenadine, CAPE, Quercetin, Melatonin, curcumin, Vitamin C ligands to Desmoglein 1, Human Histamine H1 receptor, IgE and IL13 protons were determined by molecular docking method and binding energy and interaction states were analyzed. Fexofenadine and Quercetin ligand showed the most effective binding affinity. Melatonin had the best Caco-2 permeability PPB values of Quercetin, CAPE and Curcumin were at optimal levels. On the OATP1B1 and OATP1B3 of curcumin and CAPE, Quercetin was found to have strong inhibition effects on BCRP. Melatonin and CAPE were found to have the highest inhibition values on CYP1A2, while CAPE had the highest inhibition values on CYP2C19 and CYP2C9. Vitamin C and Quercetin were found to be safer in terms of cardiac toxicity and mutagenic risks, while Desloratadine and Levocetirizine carried high risks of neurotoxicity and hematotoxicity, while CAPE was noted for its high enzyme inhibitory activities and low toxicity profiles, while the hERG blockade, DILI, and cytotoxicity values of other compounds pointed to various safety concerns. This study demonstrated the potential of machine learning methods in understanding and discovering H1 receptor blockers. The results obtained provide important clues in the development of important strategies in the clinical use of H1 receptor blockers. In the light of these data, CAPE and Quercetin are remarkable molecules.

Deep learning-based discovery of compounds for blood pressure lowering effects

The hypotensive side effects caused by drugs during their use have been a vexing issue. Recent studies have found that deep learning can effectively predict the biological activity of compounds by mining patterns and rules in the data, providing a potential solution for identifying drug side effects. In this study, we established a deep learning-based predictive model, utilizing a data set comprised of compounds known to either elevate or lower blood pressure. Subsequently, the trained model was used to predict the blood pressure-lowering effects of 26,000 compounds. Based on the predicted results, we randomly selected 50 molecules for validation and compared them with literature reports. The results showed that the predictions for 30 molecules were consistent with literature reports, with known antihypertensive drugs such as reserpine, guanethidine, and mecamylamine ranking at the top. We further selected 10 of these molecules and 3 related protein targets for molecular docking, and the docking results indirectly confirmed the model's accuracy. Ultimately, we discovered and validated that salaprinol significantly inhibits ACE1 activity and lowers canine blood pressure. In summary, we have established a highly accurate activity prediction model and confirmed its accuracy in predicting potential blood pressure-lowering compounds, which is expected to help patients avoid hypotensive side effects during clinical medication and also provide significant assistance in the discovery of antihypertensive drugs.

Predicting drug protein interactions based on improved support vector data description in unbalanced data

Introduction

Predicting drug-protein interactions is critical in drug discovery, but traditional laboratory methods are expensive and time-consuming. Computational approaches, especially those leveraging machine learning, are increasingly popular. This paper introduces VASVDD, a multi-step method to predict drug-protein interactions. First, it extracts features from amino acid sequences in proteins and drug structures. To address the challenge of unbalanced datasets, a Support Vector Data Description (SVDD) approach is employed, outperforming standard techniques like SMOTE and ENN in balancing data. Subsequently, dimensionality reduction using a Variational Autoencoder (VAE) reduces features from 1074 to 32, improving computational efficiency and predictive performance.

Methods

The proposed method was evaluated on four datasets related to enzymes, G-protein-coupled receptors, ion channels, and nuclear receptors. Without preprocessing, the Gradient Boosting Classifier showed bias towards the majority class. However, balancing and dimensionality reduction significantly improved accuracy, sensitivity, specificity, and F1 scores. VASVDD demonstrated superior performance compared to other dimensionality reduction methods, such as kernel principal component analysis (kernel PCA) and Principal Component Analysis (PCA), and was validated across multiple classifiers, achieving higher AUROC values than existing techniques.

Results

The results highlight VASVDD's effectiveness and generalizability in predicting drug-target interactions. The method outperforms state-of-the-art techniques in terms of accuracy, robustness, and efficiency, making it a promising tool in bioinformatics for drug discovery.

Conclusion

The datasets analyzed during the current study are not publicly available but are available from the corresponding author upon reasonable request and source code are available on GitHub: https://github.com/alirezakhorramfard/vasvdd.

Preparation, Characterization, and Leishmanicidal Assessment of Silver- and Dapsone-Loaded Niosomes Co-administration: In Silico and In Vitro Study

Purpose

Currently, there is a crucial need for alternative strategies to control leishmaniasis, which threatens more than 1 billion people worldwide. The simultaneous use of combination therapy and nanostructured lipid carriers aimed to assess the leishmanicidal activity of silver and dapsone niosomes co-administration in vitro and in silico.

Methods

After preparing the niosomal formulations of dapsone and silver using the film hydration method, Span 40 and Tween 40/cholesterol with a 7/3 molar ratio was selected as the optimal formulation. Consequently, the arrays of experimental approaches were conducted to compare the anti-leishmaniasis efficacy of ready niosomes with amphotericin B and obtain a deeper understanding of their possible mechanisms of action.

Results

Our findings showed higher potency of silver-loaded and dapsone-loaded niosomes co-administration compared to amphotericin B as a positive control group. The results of isobologram and combination index (CI) analyses confirmed the synergic potential of this mixture. This combination triggered anti-leishmanial pathways of macrophages, which promoted the expression level of Th1 cell-related genes, and the downregulated expression of the phenotypes related to Th2 cells. Furthermore, a high level of antioxidant and apoptotic profiles against the parasite provides a rational basis and potential drug combination for cutaneous leishmaniasis. Moreover, the outcomes of the molecular docking showed a high binding affinity between dapsone and iNOS, stimulating the immune response in Th1 direction.

Conclusion

In general, the multifunctional leishmanicidal activity of dapsone and silver-niosomes co-administration should be considered for further in vivo and clinical studies.

Fine-Tuned Deep Transfer Learning Models for Large Screenings of Safer Drugs Targeting Class A GPCRs

G protein-coupled receptors (GPCRs) remain a focal point of research due to their critical roles in cell signaling and their prominence as drug targets. However, directly linking drug efficacy to receptor-mediated activation of specific intracellular transducers and the resulting physiological outcomes remains challenging. It is unclear whether the enhanced therapeutic window of certain drugs - defined as the dose range that provides effective therapy with minimal side effects - stems from their low intrinsic efficacy across all signaling pathways or ligand bias, wherein specific transducer subtypes are preferentially activated in a given cellular system compared to a reference ligand. Accurately predicting safer compounds, whether through low intrinsic efficacy or ligand bias, would greatly advance drug development. While AI models hold promise for such predictions, the development of deep learning models capable of reliably forecasting GPCR ligands with defined bioactivities remains challenging, largely due to the limited availability of high-quality data. To address this, we pre-trained a model on receptor sequences and ligand datasets across all class A GPCRs, and then refined it to predict low-efficacy compounds or biased agonists for individual class A GPCRs. This was achieved using transfer learning and a neural network incorporating natural language processing of target sequences and receptor mutation effects on signaling. These two fine-tuned models-one for low-efficacy agonists and one for biased agonists-are available on demand for each class A GPCR and enable virtual screening of large chemical libraries, thereby facilitating the discovery of compounds with potentially improved safety profiles.

Utilizing artificial intelligence for precision exploration of N protein targeting phenanthridine sars-cov-2 inhibitors: A novel approach

The persistent mutation of the novel coronavirus presents a continual threat of infections and associated illnesses. While considerable research efforts have concentrated on the functional proteins of SARS-CoV-2 in the development of anti-COVID-19 therapeutics, the structural proteins, particularly the N protein, have received comparatively less attention. This study focuses on the N protein, a critical structural component of the virus, and employs advanced deep learning models, including EMPIRE and DeepFrag, to optimize the structures of phenanthridine-based compounds. More than 10,000 small molecules, derived through deep learning, underwent high-throughput virtual screening, resulting in the synthesis of 44 compounds. Compound 38 showed a binding potential energy of -8.2 kcal/mol in molecular docking. Surface Plasmon Resonance (SPR) and Microscale Thermophoresis (MST) validation yielded dissociation constants of 353 nM and 726 nM, confirming strong binding to the N protein. Compound 38 demonstrated antiviral activity in vitro and exhibited anti-COVID-19 effects by interfering with the binding of N proteins to RNA. This research underscores the potential of targeting the SARS-CoV-2 N protein for therapeutic intervention and illustrates the efficacy of deep learning model in the design of lead compounds. The application of these deep learning models represents a promising approach for accelerating the discovery and development of antiviral agents.

FragGen: towards 3D geometry reliable fragment-based molecular generation

3D structure-based molecular generation is a successful application of generative AI in drug discovery. Most earlier models follow an atom-wise paradigm, generating molecules with good docking scores but poor molecular properties (like synthesizability and drugability). In contrast, fragment-wise generation offers a promising alternative by assembling chemically viable fragments. However, the co-design of plausible chemical and geometrical structures is still challenging, as evidenced by existing models. To address this, we introduce the Deep Geometry Handling protocol, which decomposes the entire geometry into multiple sets of geometric variables, looking beyond model architecture design. Drawing from a newly defined six-category taxonomy, we propose FragGen, a novel hybrid strategy as the first geometry-reliable, fragment-wise molecular generation method. FragGen significantly enhances both the geometric quality and synthesizability of the generated molecules, overcoming major limitations of previous models. Moreover, FragGen has been successfully applied in real-world scenarios, notably in designing type II kinase inhibitors at the ∼nM level, establishing it as the first validated 3D fragment-based drug design algorithm. We believe that this concept-algorithm-application cycle will not only inspire researchers working on other geometry-centric tasks to move beyond architecture designs but also provide a solid example of how generative AI can be customized for drug design.

Sequence-Activity Relationship of Angiotensin-Converting Enzyme Inhibitory Peptides Derived from Food Proteins, Based on a New Deep Learning Model

Food-derived peptides are usually safe natural drug candidates that can potentially inhibit the angiotensin-converting enzyme (ACE). The wet experiments used to identify ACE inhibitory peptides (ACEiPs) are time-consuming and costly, making it important and urgent to reduce the scope of experimental validation through bioinformatics methods. Here, we construct an ACE inhibitory peptide predictor (ACEiPP) using optimized amino acid descriptors (AADs) and long- and short-term memory neural networks. Our results show that combined-AAD models exhibit more efficient feature transformation ability than single-AAD models, especially the training model with the optimal descriptors as the feature inputs, which exhibits the highest predictive ability in the independent test (Acc = 0.9479 and AUC = 0.9876), with a significant performance improvement compared to the existing three predictors. The model can effectively characterize the structure-activity relationship of ACEiPs. By combining the model with database mining, we used ACEiPP to screen four ACEiPs with multiple reported functions. We also used ACEiPP to predict peptides from 21,249 food-derived proteins in the Database of Food-derived Bioactive Peptides (DFBP) and construct a library of potential ACEiPs to facilitate the discovery of new anti-ACE peptides.

Improved Ensemble Model for Insecticide Recognition by Incorporating Insect Toxicity Data

Pesticide molecules, such as insecticides, play a critical role in modern agricultural production. Traditional pesticide development methods are often inefficient and expensive, while data-driven artificial intelligence (AI) techniques have emerged as a useful tool to facilitate drug discovery. However, currently available commercial pesticide data is limited, which makes the trained models unsatisfactory in terms of performance and generalization. From a domain knowledge perspective, insect toxicity data were incorporated to improve the insecticide recognition of AI models. Compared to the models trained with the original data set, the new models performed better in the external validation, and their generalization was more desirable. In addition, by integrating different types of individual models, we obtained an ensemble model with better performance. Based on this, an online platform was developed to provide researchers with free access to insecticide screening (https://dpai.ccnu.edu.cn/InsectiVS/). Finally, two potential insecticide molecules with insecticidal activity against Plutella xylostella were successfully identified in a real-world scenario. In conclusion, this idea connects the fields of AI and agricultural chemistry and is expected to have wide application in pesticide research.

Progress in the application of artificial intelligence in molecular generation models based on protein structure

The molecular generation models based on protein structures represent a cutting-edge research direction in artificial intelligence-assisted drug discovery. This article aims to comprehensively summarize the research methods and developments by analyzing a series of novel molecular generation models predicated on protein structures. Initially, we categorize the molecular generation models based on protein structures and highlight the architectural frameworks utilized in these models. Subsequently, we detail the design and implementation of protein structure-based molecular generation models by introducing different specific examples. Lastly, we outline the current opportunities and challenges encountered in this field, intending to offer guidance and a referential framework for developing and studying new models in related fields in the future.

Towards the prediction of drug solubility in binary solvent mixtures at various temperatures using machine learning

Drug solubility is an important parameter in the drug development process, yet it is often tedious and challenging to measure, especially for expensive drugs or those available in small quantities. To alleviate these challenges, machine learning (ML) has been applied to predict drug solubility as an alternative approach. However, the majority of existing ML research has focused on the predictions of aqueous solubility and/or solubility at specific temperatures, which restricts the model applicability in pharmaceutical development. To bridge this gap, we compiled a dataset of 27,000 solubility datapoints, including solubility of small molecules measured in a range of binary solvent mixtures under various temperatures. Next, a panel of ML models were trained on this dataset with their hyperparameters tuned using Bayesian optimization. The resulting top-performing models, both gradient boosted decision trees (light gradient boosting machine and extreme gradient boosting), achieved mean absolute errors (MAE) of 0.33 for LogS (S in g/100 g) on the holdout set. These models were further validated through a prospective study, wherein the solubility of four drug molecules were predicted by the models and then validated with in-house solubility experiments. This prospective study demonstrated that the models accurately predicted the solubility of solutes in specific binary solvent mixtures under different temperatures, especially for drugs whose features closely align within the solutes in the dataset (MAE < 0.5 for LogS). To support future research and facilitate advancements in the field, we have made the dataset and code openly available. Scientific contribution Our research advances the state-of-the-art in predicting solubility for small molecules by leveraging ML and a uniquely comprehensive dataset. Unlike existing ML studies that predominantly focus on solubility in aqueous solvents at fixed temperatures, our work enables prediction of drug solubility in a variety of binary solvent mixtures over a broad temperature range, providing practical insights on the modeling of solubility for realistic pharmaceutical applications. These advancements along with the open access dataset and code support significant steps in the drug development process including new molecule discovery, drug analysis and formulation.

Piperine exerts anti-inflammatory effects and antagonises the properties of celecoxib and ketoprofen: in vivo and molecular docking studies

This study evaluates the anti-inflammatory effects of a natural product, piperine (PPN), using in vivo and in silico methodologies. In the in vivo segment, inflammation was induced in the right hind paw of young chicks via a formalin (50 μL) injection. PPN was orally administered at doses of 25 and 50 mg/kg with or without celecoxib (CXB) and/or ketoprofen (KPN) (42 mg/kg). The vehicle acted as the negative control group (NC). The in silico analysis predicted the drug-likeness, pharmacokinetics, and toxicity profile of PPN, along with evaluating its binding affinity and ligand-receptor interactions. Results indicate that PPN significantly (p < 0.05) reduced licking frequency and paw edoema in a dose-dependent manner. However, in combination therapy, PPN diminished the effects of both CXB and KPN. PPN showed high affinity (-8.6 kcal/mol) towards the COX-2 enzyme. Therefore, PPN exerts anti-inflammatory effects in chicks through COX-2 inhibition pathways and antagonises CXB and KPN activities.

Improving Molecule Generation and Drug Discovery with a Knowledge-enhanced Generative Model

Recent advancements in generative models have established state-of-the-art benchmarks in the generation of molecules and novel drug candidates. Despite these successes, a significant gap persists between generative models and the utilization of extensive biomedical knowledge, often systematized within knowledge graphs, whose potential to inform and enhance generative processes has not been realized. In this paper, we present a novel approach that bridges this divide by developing a framework for knowledge-enhanced generative models called KARL. We develop a scalable methodology to extend the functionality of knowledge graphs while preserving semantic integrity, and incorporate this contextual information into a generative framework to guide a diffusion-based model. The integration of knowledge graph embeddings with our generative model furnishes a robust mechanism for producing novel drug candidates possessing specific characteristics while ensuring validity and synthesizability. KARL outperforms state-of-the-art generative models on both unconditional and targeted generation tasks.

DockingGA: enhancing targeted molecule generation using transformer neural network and genetic algorithm with docking simulation

Generative molecular models generate novel molecules with desired properties by searching chemical space. Traditional combinatorial optimization methods, such as genetic algorithms, have demonstrated superior performance in various molecular optimization tasks. However, these methods do not utilize docking simulation to inform the design process, and heavy dependence on the quality and quantity of available data, as well as require additional structural optimization to become candidate drugs. To address this limitation, we propose a novel model named DockingGA that combines Transformer neural networks and genetic algorithms to generate molecules with better binding affinity for specific targets. In order to generate high quality molecules, we chose the Self-referencing Chemical Structure Strings to represent the molecule and optimize the binding affinity of the molecules to different targets. Compared to other baseline models, DockingGA proves to be the optimal model in all docking results for the top 1, 10 and 100 molecules, while maintaining 100% novelty. Furthermore, the distribution of physicochemical properties demonstrates the ability of DockingGA to generate molecules with favorable and appropriate properties. This innovation creates new opportunities for the application of generative models in practical drug discovery.

GraphEGFR: Multi-task and transfer learning based on molecular graph attention mechanism and fingerprints improving inhibitor bioactivity prediction for EGFR family proteins on data scarcity

The proteins within the human epidermal growth factor receptor (EGFR) family, members of the tyrosine kinase receptor family, play a pivotal role in the molecular mechanisms driving the development of various tumors. Tyrosine kinase inhibitors, key compounds in targeted therapy, encounter challenges in cancer treatment due to emerging drug resistance mutations. Consequently, machine learning has undergone significant evolution to address the challenges of cancer drug discovery related to EGFR family proteins. However, the application of deep learning in this area is hindered by inherent difficulties associated with small-scale data, particularly the risk of overfitting. Moreover, the design of a model architecture that facilitates learning through multi-task and transfer learning, coupled with appropriate molecular representation, poses substantial challenges. In this study, we introduce GraphEGFR, a deep learning regression model designed to enhance molecular representation and model architecture for predicting the bioactivity of inhibitors against both wild-type and mutant EGFR family proteins. GraphEGFR integrates a graph attention mechanism for molecular graphs with deep and convolutional neural networks for molecular fingerprints. We observed that GraphEGFR models employing multi-task and transfer learning strategies generally achieve predictive performance comparable to existing competitive methods. The integration of molecular graphs and fingerprints adeptly captures relationships between atoms and enables both global and local pattern recognition. We further validated potential multi-targeted inhibitors for wild-type and mutant HER1 kinases, exploring key amino acid residues through molecular dynamics simulations to understand molecular interactions. This predictive model offers a robust strategy that could significantly contribute to overcoming the challenges of developing deep learning models for drug discovery with limited data and exploring new frontiers in multi-targeted kinase drug discovery for EGFR family proteins.

Current strategies to address data scarcity in artificial intelligence-based drug discovery: A comprehensive review

Artificial intelligence (AI) has played a vital role in computer-aided drug design (CADD). This development has been further accelerated with the increasing use of machine learning (ML), mainly deep learning (DL), and computing hardware and software advancements. As a result, initial doubts about the application of AI in drug discovery have been dispelled, leading to significant benefits in medicinal chemistry. At the same time, it is crucial to recognize that AI is still in its infancy and faces a few limitations that need to be addressed to harness its full potential in drug discovery. Some notable limitations are insufficient, unlabeled, and non-uniform data, the resemblance of some AI-generated molecules with existing molecules, unavailability of inadequate benchmarks, intellectual property rights (IPRs) related hurdles in data sharing, poor understanding of biology, focus on proxy data and ligands, lack of holistic methods to represent input (molecular structures) to prevent pre-processing of input molecules (feature engineering), etc. The major component in AI infrastructure is input data, as most of the successes of AI-driven efforts to improve drug discovery depend on the quality and quantity of data, used to train and test AI algorithms, besides a few other factors. Additionally, data-gulping DL approaches, without sufficient data, may collapse to live up to their promise. Current literature suggests a few methods, to certain extent, effectively handle low data for better output from the AI models in the context of drug discovery. These are transferring learning (TL), active learning (AL), single or one-shot learning (OSL), multi-task learning (MTL), data augmentation (DA), data synthesis (DS), etc. One different method, which enables sharing of proprietary data on a common platform (without compromising data privacy) to train ML model, is federated learning (FL). In this review, we compare and discuss these methods, their recent applications, and limitations while modeling small molecule data to get the improved output of AI methods in drug discovery. Article also sums up some other novel methods to handle inadequate data.

P.O.L.A.R. Star: A New Framework Developed and Applied by One Mid-Sized Pharmaceutical Company to Drive Digital Transformation in R&D

Digital transformation has become a cornerstone of innovation in pharmaceutical research and development (R&D). Pharmaceutical companies now have an imperative to embrace transformation, including mid-sized and small-sized companies despite resource limitations that do not allow economies of scale compared with larger organizations. This article describes the journey undertaken by Chiesi to develop an efficient framework to drive digital transformation along its R&D value chain with the objective of building and refreshing a clear roadmap and relevant priorities, together with identifying and enabling new digital capabilities and skills within R&D, defining tools and processes that will guide Chiesi activities in the space up to mid-long term. This work has led so far to five main achievements, which align with the steps in the framework: a strategically aligned roadmap with key focus areas for digital transformation and a dedicated team to lead the effort; a common language for data across the R&D value chain; an internal mindset that's open to innovation and participation in key external networks and consortia; a set of quick-win use cases for the new framework; and a defined set of Key Performance Indicators (KPIs) and monitoring tools for digital transformation. The work presented here demonstrates that R&D digital transformation should represent an ongoing process to enable cross-functional collaboration and integration within complex corporate environments that face an ever-growing volume of diverse data, to efficiently support business needs, and to ensure a positive impact on patient care.

In Silico Screening of Therapeutic Targets as a Tool to Optimize the Development of Drugs and Nutraceuticals in the Treatment of Diabetes mellitus: A Systematic Review

The Target-Based Virtual Screening approach is widely employed in drug development, with docking or molecular dynamics techniques commonly utilized for this purpose. This systematic review (SR) aimed to identify in silico therapeutic targets for treating Diabetes mellitus (DM) and answer the question: What therapeutic targets have been used in in silico analyses for the treatment of DM? The SR was developed following the guidelines of the Preferred Reporting Items Checklist for Systematic Review and Meta-Analysis, in accordance with the protocol registered in PROSPERO (CRD42022353808). Studies that met the PECo strategy (Problem, Exposure, Context) were included using the following databases: Medline (PubMed), Web of Science, Scopus, Embase, ScienceDirect, and Virtual Health Library. A total of 20 articles were included, which not only identified therapeutic targets in silico but also conducted in vivo analyses to validate the obtained results. The therapeutic targets most frequently indicated in in silico studies were GLUT4, DPP-IV, and PPARγ. In conclusion, a diversity of targets for the treatment of DM was verified through both in silico and in vivo reassessment. This contributes to the discovery of potential new allies for the treatment of DM.

From Deep Learning to the Discovery of Promising VEGFR-2 Inhibitors

Vascular endothelial growth factor receptor 2 (VEGFR-2) stands as a prominent therapeutic target in oncology, playing a critical role in angiogenesis, tumor growth, and metastasis. FDA-approved VEGFR-2 inhibitors are associated with diverse side effects. Thus, finding novel and more effective inhibitors is of utmost importance. In this study, a deep learning (DL) classification model was first developed and then employed to select putative active VEGFR-2 inhibitors from an in-house chemical library including 187 druglike compounds. A pool of 18 promising candidates was shortlisted and screened against VEGFR-2 by using molecular docking. Finally, two compounds, RHE-334 and EA-11, were prioritized as promising VEGFR-2 inhibitors by employing PLATO, our target fishing and bioactivity prediction platform. Based on this rationale, we prepared RHE-334 and EA-11 and successfully tested their anti-proliferative potential against MCF-7 human breast cancer cells with IC50 values of 26.78±4.02 and 38.73±3.84 μM, respectively. Their toxicities were instead challenged against the WI-38. Interestingly, expression studies indicated that, in the presence of RHE-334, VEGFR-2 was equal to 0.52±0.03, thus comparable to imatinib equal to 0.63±0.03. In conclusion, this workflow based on theoretical and experimental approaches demonstrates effective in identifying VEGFR-2 inhibitors and can be easily adapted to other medicinal chemistry goals.

Computational Methodologies in Synthesis, Preparation and Application of Antimicrobial Polymers, Biomolecules, and Nanocomposites

The design and optimization of antimicrobial materials (polymers, biomolecules, or nanocomposites) can be significantly advanced by computational methodologies like molecular dynamics (MD), which provide insights into the interactions and stability of the antimicrobial agents within the polymer matrix, and machine learning (ML) or design of experiment (DOE), which predicts and optimizes antimicrobial efficacy and material properties. These innovations not only enhance the efficiency of developing antimicrobial polymers but also enable the creation of materials with tailored properties to meet specific application needs, ensuring safety and longevity in their usage. Therefore, this paper will present the computational methodologies employed in the synthesis and application of antimicrobial polymers, biomolecules, and nanocomposites. By leveraging advanced computational techniques such as MD, ML, or DOE, significant advancements in the design and optimization of antimicrobial materials are achieved. A comprehensive review on recent progress, together with highlights of the most relevant methodologies' contributions to state-of-the-art materials science will be discussed, as well as future directions in the field will be foreseen. Finally, future possibilities and opportunities will be derived from the current state-of-the-art methodologies, providing perspectives on the potential evolution of polymer science and engineering of novel materials.

The Art of Finding the Right Drug Target: Emerging Methods and Strategies

Drug targets are specific molecules in biological tissues and body fluids that interact with drugs. Drug target discovery is a key component of drug discovery and is essential for the development of new drugs in areas such as cancer therapy and precision medicine. Traditional in vitro or in vivo target discovery methods are time-consuming and labor-intensive, limiting the pace of drug discovery. With the development of modern discovery methods, the discovery and application of various emerging technologies have greatly improved the efficiency of drug discovery, shortened the cycle time, and reduced the cost. This review provides a comprehensive overview of various emerging drug target discovery strategies, including computer-assisted approaches, drug affinity response target stability, multiomics analysis, gene editing, and nonsense-mediated mRNA degradation, and discusses the effectiveness and limitations of the various approaches, as well as their application in real cases. Through the review of the aforementioned contents, a general overview of the development of novel drug targets and disease treatment strategies will be provided, and a theoretical basis will be provided for those who are engaged in pharmaceutical science research. SIGNIFICANCE STATEMENT: Target-based drug discovery has been the main approach to drug discovery in the pharmaceutical industry for the past three decades. Traditional drug target discovery methods based on in vivo or in vitro validation are time-consuming and costly, greatly limiting the development of new drugs. Therefore, the development and selection of new methods in the drug target discovery process is crucial.

Identification of novel NLRP3 inhibitors as therapeutic options for epilepsy by machine learning-based virtual screening, molecular docking and biomolecular simulation studies

The NOD-Like Receptor Protein-3 (NLRP3) inflammasome is a key therapeutic target for the treatment of epilepsy and has been reported to regulate inflammation in several neurological diseases. In this study, a machine learning-based virtual screening strategy has investigated candidate active compounds that inhibit the NLRP3 inflammasome. As machine learning-based virtual screening has the potential to accurately predict protein-ligand binding and reduce false positives outcomes compared to traditional virtual screening. Briefly, classification models were created using Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbor (KNN) machine learning methods. To determine the most crucial features of a molecule's activity, feature selection was carried out. By utilizing 10-fold cross-validation, the created models were analyzed. Among the generated models, the RF model obtained the best results as compared to others. Therefore, the RF model was used as a screening tool against the large chemical databases. Molecular operating environment (MOE) and PyRx software's were applied for molecular docking. Also, using the Amber Tools program, molecular dynamics (MD) simulation of potent inhibitors was carried out. The results showed that the KNN, SVM, and RF accuracy was 0.911 %, 0.906 %, and 0.946 %, respectively. Moreover, the model has shown sensitivity of 0.82 %, 0.78 %, and 0.86 % and specificity of 0.95 %, 0.96 %, and 0.98 % respectively. By applying the model to the ZINC and South African databases, we identified 98 and 39 compounds, respectively, potentially possessing anti-NLRP3 activity. Also, a molecular docking analysis produced ten ZINC and seven South African compounds that has comparable binding affinities to the reference drug. Moreover, MD analysis of the two complexes revealed that the two compounds (ZINC000009601348 and SANC00225) form stable complexes with varying amounts of binding energy. The in-silico studies indicate that both compounds most likely display their inhibitory effect by inhibiting the NLRP3 protein.

Drug repositioning based on residual attention network and free multiscale adversarial training

BACKGROUND

Conducting traditional wet experiments to guide drug development is an expensive, time-consuming and risky process. Analyzing drug function and repositioning plays a key role in identifying new therapeutic potential of approved drugs and discovering therapeutic approaches for untreated diseases. Exploring drug-disease associations has far-reaching implications for identifying disease pathogenesis and treatment. However, reliable detection of drug-disease relationships via traditional methods is costly and slow. Therefore, investigations into computational methods for predicting drug-disease associations are currently needed.

RESULTS

This paper presents a novel drug-disease association prediction method, RAFGAE. First, RAFGAE integrates known associations between diseases and drugs into a bipartite network. Second, RAFGAE designs the Re_GAT framework, which includes multilayer graph attention networks (GATs) and two residual networks. The multilayer GATs are utilized for learning the node embeddings, which is achieved by aggregating information from multihop neighbors. The two residual networks are used to alleviate the deep network oversmoothing problem, and an attention mechanism is introduced to combine the node embeddings from different attention layers. Third, two graph autoencoders (GAEs) with collaborative training are constructed to simulate label propagation to predict potential associations. On this basis, free multiscale adversarial training (FMAT) is introduced. FMAT enhances node feature quality through small gradient adversarial perturbation iterations, improving the prediction performance. Finally, tenfold cross-validations on two benchmark datasets show that RAFGAE outperforms current methods. In addition, case studies have confirmed that RAFGAE can detect novel drug-disease associations.

CONCLUSIONS

The comprehensive experimental results validate the utility and accuracy of RAFGAE. We believe that this method may serve as an excellent predictor for identifying unobserved disease-drug associations.

Construction of IRAK4 inhibitor activity prediction model based on machine learning

Interleukin-1 receptor-associated kinase 4 (IRAK4) is a crucial serine/threonine protein kinase that belongs to the IRAK family and plays a pivotal role in Toll-like receptor (TLR) and Interleukin-1 receptor (IL-1R) signaling pathways. Due to IRAK4's significant role in immunity, inflammation, and malignancies, it has become an intriguing target for discovering and developing potent small-molecule inhibitors. Consequently, there is a pressing need for rapid and accurate prediction of IRAK4 inhibitor activity. Leveraging a comprehensive dataset encompassing activity data for 1628 IRAK4 inhibitors, we constructed a prediction model using the LightGBM algorithm and molecular fingerprints. This model achieved an R2 of 0.829, an MAE of 0.317, and an RMSE of 0.460 in independent testing. To further validate the model's generalization ability, we tested it on 90 IRAK4 inhibitors collected in 2023. Subsequently, we applied the model to predict the activity of 13,268 compounds with docking scores less than - 9.503 kcal/mol. These compounds were initially screened from a pool of 1.6 million molecules in the chemdiv database through high-throughput molecular docking. Among these, 259 compounds with predicted pIC50 values greater than or equal to 8.00 were identified. We then performed ADMET predictions on these selected compounds. Finally, through a rigorous screening process, we identified 34 compounds that adhere to the four complementary drug-likeness rules, making them promising candidates for further investigation. Additionally, molecular dynamics simulations confirmed the stable binding of the screened compounds to the IRAK4 protein. Overall, this work presents a machine learning model for accurate prediction of IRAK4 inhibitor activity and offers new insights for subsequent structure-guided design of novel IRAK4 inhibitors.

Artificial intelligence for small molecule anticancer drug discovery

INTRODUCTION

The transition from conventional cytotoxic chemotherapy to targeted cancer therapy with small-molecule anticancer drugs has enhanced treatment outcomes. This approach, which now dominates cancer treatment, has its advantages. Despite the regulatory approval of several targeted molecules for clinical use, challenges such as low response rates and drug resistance still persist. Conventional drug discovery methods are costly and time-consuming, necessitating more efficient approaches. The rise of artificial intelligence (AI) and access to large-scale datasets have revolutionized the field of small-molecule cancer drug discovery. Machine learning (ML), particularly deep learning (DL) techniques, enables the rapid identification and development of novel anticancer agents by analyzing vast amounts of genomic, proteomic, and imaging data to uncover hidden patterns and relationships.

AREA COVERED

In this review, the authors explore the important landmarks in the history of AI-driven drug discovery. They also highlight various applications in small-molecule cancer drug discovery, outline the challenges faced, and provide insights for future research.

EXPERT OPINION

The advent of big data has allowed AI to penetrate and enable innovations in almost every stage of medicine discovery, transforming the landscape of oncology research through the development of state-of-the-art algorithms and models. Despite challenges in data quality, model interpretability, and technical limitations, advancements promise breakthroughs in personalized and precision oncology, revolutionizing future cancer management.

Application progress of deep generative models in de novo drug design

The deep molecular generative model has recently become a research hotspot in pharmacy. This paper analyzes a large number of recent reports and reviews these models. In the central part of this paper, four compound databases and two molecular representation methods are compared. Five model architectures and applications for deep molecular generative models are emphatically introduced. Three evaluation metrics for model evaluation are listed. Finally, the limitations and challenges in this field are discussed to provide a reference and basis for developing and researching new models published in future.

Efficient prediction of anticancer peptides through deep learning

Background

Cancer remains one of the leading causes of mortality globally, with conventional chemotherapy often resulting in severe side effects and limited effectiveness. Recent advancements in bioinformatics and machine learning, particularly deep learning, offer promising new avenues for cancer treatment through the prediction and identification of anticancer peptides.

Objective

This study aimed to develop and evaluate a deep learning model utilizing a two-dimensional convolutional neural network (2D CNN) to enhance the prediction accuracy of anticancer peptides, addressing the complexities and limitations of current prediction methods.

Methods

A diverse dataset of peptide sequences with annotated anticancer activity labels was compiled from various public databases and experimental studies. The sequences were preprocessed and encoded using one-hot encoding and additional physicochemical properties. The 2D CNN model was trained and optimized using this dataset, with performance evaluated through metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC).

Results

The proposed 2D CNN model achieved superior performance compared to existing methods, with an accuracy of 0.87, precision of 0.85, recall of 0.89, F1-score of 0.87, and an AUC-ROC value of 0.91. These results indicate the model's effectiveness in accurately predicting anticancer peptides and capturing intricate spatial patterns within peptide sequences.

Conclusion

The findings demonstrate the potential of deep learning, specifically 2D CNNs, in advancing the prediction of anticancer peptides. The proposed model significantly improves prediction accuracy, offering a valuable tool for identifying effective peptide candidates for cancer treatment.

Future Work

Further research should focus on expanding the dataset, exploring alternative deep learning architectures, and validating the model's predictions through experimental studies. Efforts should also aim at optimizing computational efficiency and translating these predictions into clinical applications.

Where developmental toxicity meets explainable artificial intelligence: state-of-the-art and perspectives

INTRODUCTION

The application of Artificial Intelligence (AI) to predictive toxicology is rapidly increasing, particularly aiming to develop non-testing methods that effectively address ethical concerns and reduce economic costs. In this context, Developmental Toxicity (Dev Tox) stands as a key human health endpoint, especially significant for safeguarding maternal and child well-being.

AREAS COVERED

This review outlines the existing methods employed in Dev Tox predictions and underscores the benefits of utilizing New Approach Methodologies (NAMs), specifically focusing on eXplainable Artificial Intelligence (XAI), which proves highly efficient in constructing reliable and transparent models aligned with recommendations from international regulatory bodies.

EXPERT OPINION

The limited availability of high-quality data and the absence of dependable Dev Tox methodologies render XAI an appealing avenue for systematically developing interpretable and transparent models, which hold immense potential for both scientific evaluations and regulatory decision-making.

A Hierarchical Graph Neural Network Framework for Predicting Protein-Protein Interaction Modulators With Functional Group Information and Hypergraph Structure

Accurate prediction of small molecule modulators targeting protein-protein interactions (PPIMs) remains a significant challenge in drug discovery. Existing machine learning-based models rely on manual feature engineering, which is tedious and task-specific. Recently, deep learning models based on graph neural networks have made remarkable progress in molecular representation learning. However, many graph-based approaches ignore molecular hierarchical structure modeling guided by domain knowledge. In chemistry, the functional groups of a molecule determine its interaction with specific targets. Therefore, we propose a hierarchical graph neural network framework (called HiGPPIM) for predicting PPIMs by integrating atom-level and functional group-level features of molecules. HiGPPIM constructs atom-level and functional group-level graphs based on chemical knowledge and learns graph representations using graph attention networks. Furthermore, a hypergraph attention network is designed in HiGPPIM to aggregate and transform two-level graph information. We evaluate the performance of HiGPPIM on eight PPI families and two prediction tasks, namely PPIM identification and potency prediction. Experimental results demonstrate that HiGPPIM achieves state-of-the-art performance on both tasks and that using functional group information to guide PPIM prediction is effective.

Investigating molecular descriptors in cell-penetrating peptides prediction with deep learning: Employing N, O, and hydrophobicity according to the Eisenberg scale

Cell-penetrating peptides comprise a group of molecules that can naturally cross the lipid bilayer membrane that protects cells, sharing physicochemical and structural properties, and having several pharmaceutical applications, particularly in drug delivery. Investigations of molecular descriptors have provided not only an improvement in the performance of classifiers but also less computational complexity and an enhanced understanding of membrane permeability. Furthermore, the employment of new technologies, such as the construction of deep learning models using overfitting treatment, promotes advantages in tackling this problem. In this study, the descriptors nitrogen, oxygen, and hydrophobicity on the Eisenberg scale were investigated, using the proposed ConvBoost-CPP composed of an improved convolutional neural network with overfitting treatment and an XGBoost model with adjusted hyperparameters. The results revealed favorable to the use of ConvBoost-CPP, having as input nitrogen, oxygen, and hydrophobicity together with ten other descriptors previously investigated in this research line, showing an increase in accuracy from 88% to 91.2% in cross-validation and 82.6% to 91.3% in independent test.

DEAttentionDTA: protein-ligand binding affinity prediction based on dynamic embedding and self-attention

MOTIVATION

Predicting protein-ligand binding affinity is crucial in new drug discovery and development. However, most existing models rely on acquiring 3D structures of elusive proteins. Combining amino acid sequences with ligand sequences and better highlighting active sites are also significant challenges.

RESULTS

We propose an innovative neural network model called DEAttentionDTA, based on dynamic word embeddings and a self-attention mechanism, for predicting protein-ligand binding affinity. DEAttentionDTA takes the 1D sequence information of proteins as input, including the global sequence features of amino acids, local features of the active pocket site, and linear representation information of the ligand molecule in the SMILE format. These three linear sequences are fed into a dynamic word-embedding layer based on a 1D convolutional neural network for embedding encoding and are correlated through a self-attention mechanism. The output affinity prediction values are generated using a linear layer. We compared DEAttentionDTA with various mainstream tools and achieved significantly superior results on the same dataset. We then assessed the performance of this model in the p38 protein family.

AVAILABILITY AND IMPLEMENTATION

The resource codes are available at https://github.com/whatamazing1/DEAttentionDTA.

Protein family annotation for the Unified Human Gastrointestinal Proteome by DPCfam clustering

Technological advances in massively parallel sequencing have led to an exponential growth in the number of known protein sequences. Much of this growth originates from metagenomic projects producing new sequences from environmental and clinical samples. The Unified Human Gastrointestinal Proteome (UHGP) catalogue is one of the most relevant metagenomic datasets with applications ranging from medicine to biology. However, the low levels of sequence annotation may impair its usability. This work aims to produce a family classification of UHGP sequences to facilitate downstream structural and functional annotation. This is achieved through the release of the DPCfam-UHGP50 dataset containing 10,778 putative protein families generated using DPCfam clustering, an unsupervised pipeline grouping sequences into single or multi-domain architectures. DPCfam-UHGP50 considerably improves family coverage at protein and residue levels compared to the manually curated repository Pfam. In the hope that DPCfam-UHGP50 will foster future discoveries in the field of metagenomics of the human gut, we release a FAIR-compliant database of our results that is easily accessible via a searchable web server and Zenodo repository.

Feature engineered embeddings for classification of molecular data

The classification of molecules is of particular importance to the drug discovery process and several other use cases. Data in this domain can be partitioned into structural and sequence/text data. Several techniques such as deep learning are able to classify molecules and predict their functions using both types of data. Molecular structure and encoded chemical information are sufficient to classify a characteristic of a molecule. However, the use of a molecule's structural information typically requires large amounts of computational power with deep learning models that take a long time to train. In this study, we present an alternative approach to molecule classification that addresses the limitations of other techniques. This approach uses natural language processing techniques in the form of count vectorisation, term frequency-inverse document frequency, word2vec and Latent Dirichlet Allocation to feature engineer molecular text data. Through this approach, we aim to make a robust and easily reproducible embedding that is fast to implement and solely dependent on chemical (text) data such as the sequence of a protein. Further, we investigate the usefulness of these embeddings for machine learning models. We apply the techniques to two different types of molecular text data: FASTA sequence data and Simplified Molecular Input Line Entry Specification data. We show that these embeddings provide excellent performance for classification.

Sustainable methods for the carboxymethylation and methylation of ursolic acid with dimethyl carbonate under mild and acidic conditions

Ursolic acid is a triterpene plant extract that exhibits significant potential as an anti-cancer, anti-tumour, and anti-inflammatory agent. Its direct use in the pharmaceutical industry is hampered by poor uptake of ursolic acid in the human body coupled with rapid metabolism causing a decrease in bioactivity. Modification of ursolic acid can overcome such issues, however, use of toxic reagents, unsustainable synthetic routes and poor reaction metrics have limited its potential. Herein, we demonstrate the first reported carboxymethylation and/or methylation of ursolic acid with dimethyl carbonate (DMC) as a green solvent and sustainable reagent under acidic conditions. The reaction of DMC with ursolic acid, in the presence of PTSA, ZnCl2, or H2SO4-SiO2 yielded the carboxymethylation product 3β-[[methoxy]carbonyl]oxyurs-12-en-28-oic acid, the methylation product 3β-methoxyurs-12-en-28-oic acid and the dehydration product urs-2,12-dien-28-oic acid. PTSA demonstrated high conversion and selectivity towards the previously unreported carboxymethylation of ursolic acid, while the application of formic acid in the system led to formylation of ursolic acid (3β-formylurs-12-en-28-oic acid) in quantitative yields via esterification, with DMC acting solely as a solvent. Meanwhile, the methylation product of ursolic acid, 3β-methoxyurs-12-en-28-oic acid, was successfully synthesised with FeCl3, demonstrating exceptional conversion and selectivity, >99% and 99%, respectively. Confirmed with the use of qualitative and quantitative green metrics, this result represents a significant improvement in conversion, selectivity, safety, and sustainability over previously reported methods of ursolic acid modification. It was demonstrated that these methods could be applied to other triterpenoids, including corosolic acid. The study also explored the potential pharmaceutical applications of ursolic acid, corosolic acid, and their derivatives, particularly in anti-inflammatory, anti-cancer, and anti-tumour treatments, using molecular ADMET and docking methods. The methods developed in this work have led to the synthesis of novel molecules, thus creating opportunities for the future investigation of biological activity and the modification of a wide range of triterpenoids applying acidic DMC systems to deliver novel active pharmaceutical intermediates.

Paradigm shift required for translational research on the brain

Biomedical research on the brain has led to many discoveries and developments, such as understanding human consciousness and the mind and overcoming brain diseases. However, historical biomedical research on the brain has unique characteristics that differ from those of conventional biomedical research. For example, there are different scientific interpretations due to the high complexity of the brain and insufficient intercommunication between researchers of different disciplines owing to the limited conceptual and technical overlap of distinct backgrounds. Therefore, the development of biomedical research on the brain has been slower than that in other areas. Brain biomedical research has recently undergone a paradigm shift, and conducting patient-centered, large-scale brain biomedical research has become possible using emerging high-throughput analysis tools. Neuroimaging, multiomics, and artificial intelligence technology are the main drivers of this new approach, foreshadowing dramatic advances in translational research. In addition, emerging interdisciplinary cooperative studies provide insights into how unresolved questions in biomedicine can be addressed. This review presents the in-depth aspects of conventional biomedical research and discusses the future of biomedical research on the brain.