A review on machine learning approaches and trends in drug discovery

Integrated ML-Based Strategy Identifies Drug Repurposing for Idiopathic Pulmonary Fibrosis

Idiopathic pulmonary fibrosis (IPF) affects an estimated global population of around 3 million individuals. IPF is a medical condition with an unknown cause characterized by the formation of scar tissue in the lungs, leading to progressive respiratory disease. Currently, there are only two FDA-approved small molecule drugs specifically for the treatment of IPF and this has created a demand for the rapid development of drugs for IPF treatment. Moreover, denovo drug development is time and cost-intensive with less than a 10% success rate. Drug repurposing currently is the most feasible option for rapidly making the drugs to market for a rare and sporadic disease. Normally, the repurposing of drugs begins with a screening of FDA-approved drugs using computational tools, which results in a low hit rate. Here, an integrated machine learning-based drug repurposing strategy is developed to significantly reduce the false positive outcomes by introducing the predock machine-learning-based predictions followed by literature and GSEA-assisted validation and drug pathway prediction. The developed strategy is deployed to 1480 FDA-approved drugs and to drugs currently in a clinical trial for IPF to screen them against "TGFB1", "TGFB2", "PDGFR-a", "SMAD-2/3", "FGF-2", and more proteins resulting in 247 total and 27 potentially repurposable drugs. The literature and GSEA validation suggested that 72 of 247 (29.14%) drugs have been tried for IPF, 13 of 247 (5.2%) drugs have already been used for lung fibrosis, and 20 of 247 (8%) drugs have been tested for other fibrotic conditions such as cystic fibrosis and renal fibrosis. Pathway prediction of the remaining 142 drugs was carried out resulting in 118 distinct pathways. Furthermore, the analysis revealed that 29 of 118 pathways were directly or indirectly involved in IPF and 11 of 29 pathways were directly involved. Moreover, 15 potential drug combinations are suggested for showing a strong synergistic effect in IPF. The drug repurposing strategy reported here will be useful for rapidly developing drugs for treating IPF and other related conditions.

Predicting blood-brain barrier permeability of molecules with a large language model and machine learning

Predicting the blood-brain barrier (BBB) permeability of small-molecule compounds using a novel artificial intelligence platform is necessary for drug discovery. Machine learning and a large language model on artificial intelligence (AI) tools improve the accuracy and shorten the time for new drug development. The primary goal of this research is to develop artificial intelligence (AI) computing models and novel deep learning architectures capable of predicting whether molecules can permeate the human blood-brain barrier (BBB). The in silico (computational) and in vitro (experimental) results were validated by the Natural Products Research Laboratories (NPRL) at China Medical University Hospital (CMUH). The transformer-based MegaMolBART was used as the simplified molecular input line entry system (SMILES) encoder with an XGBoost classifier as an in silico method to check if a molecule could cross through the BBB. We used Morgan or Circular fingerprints to apply the Morgan algorithm to a set of atomic invariants as a baseline encoder also with an XGBoost classifier to compare the results. BBB permeability was assessed in vitro using three-dimensional (3D) human BBB spheroids (human brain microvascular endothelial cells, brain vascular pericytes, and astrocytes). Using multiple BBB databases, the results of the final in silico transformer and XGBoost model achieved an area under the receiver operating characteristic curve of 0.88 on the held-out test dataset. Temozolomide (TMZ) and 21 randomly selected BBB permeable compounds (Pred scores = 1, indicating BBB-permeable) from the NPRL penetrated human BBB spheroid cells. No evidence suggests that ferulic acid or five BBB-impermeable compounds (Pred scores < 1.29423E-05, which designate compounds that pass through the human BBB) can pass through the spheroid cells of the BBB. Our validation of in vitro experiments indicated that the in silico prediction of small-molecule permeation in the BBB model is accurate. Transformer-based models like MegaMolBART, leveraging the SMILES representations of molecules, show great promise for applications in new drug discovery. These models have the potential to accelerate the development of novel targeted treatments for disorders of the central nervous system.

Explainable artificial intelligence in the design of selective carbonic anhydrase I-II inhibitors via molecular fingerprinting

Inhibiting the enzymes carbonic anhydrase I (CA I) and carbonic anhydrase II (CA II) presents a potential avenue for addressing nervous system ailments such as glaucoma and Alzheimer's disease. Our study explored harnessing explainable artificial intelligence (XAI) to unveil the molecular traits inherent in CA I and CA II inhibitors. The PubChem molecular fingerprints of these inhibitors, sourced from the ChEMBL database, were subjected to detailed XAI analysis. The study encompassed training 10 regression models using IC50 values, and their efficacy was gauged using metrics including R2, RMSE, and time taken. The Decision Tree Regressor algorithm emerged as the optimal performer (R2: 0.93, RMSE: 0.43, time-taken: 0.07). Furthermore, the PFI method unveiled key molecular features for CA I inhibitors, notably PubChemFP432 (C(O)N) and PubChemFP6978 (C(O)O). The SHAP analysis highlighted the significance of attributes like PubChemFP539 (C(O)NCC), PubChemFP601 (C(O)OCC), and PubChemFP432 (C(O)N) in CA I inhibitiotable n. Likewise, features for CA II inhibitors encompassed PubChemFP528(C(O)OCCN), PubChemFP791 (C(O)OCCC), PubChemFP696 (C(O)OCCCC), PubChemFP335 (C(O)NCCN), PubChemFP580 (C(O)NCCCN), and PubChemFP180 (C(O)NCCC), identified through SHAP analysis. The sulfonamide group (S), aromatic ring (A), and hydrogen bonding group (H) exert a substantial impact on CA I and CA II enzyme activities and IC50 values through the XAI approach. These insights into the CA I and CA II inhibitors are poised to guide future drug discovery efforts, serving as a beacon for innovative therapeutic interventions.

scDrug+: predicting drug-responses using single-cell transcriptomics and molecular structure

Predicting drug responses based on individual transcriptomic profiles holds promise for refining prognosis and advancing precision medicine. Although many studies have endeavored to predict the responses of known drugs to novel transcriptomic profiles, research into predicting responses for newly discovered drugs remains sparse. In this study, we introduce scDrug+, a comprehensive pipeline that seamlessly integrates single-cell analysis with drug-response prediction. Importantly, scDrug+ is equipped to predict the response of new drugs by analyzing their molecular structures. The open-source tool is available as a Docker container, ensuring ease of deployment and reproducibility. It can be accessed at https://github.com/ailabstw/scDrugplus.

A Review of Machine Learning and QSAR/QSPR Predictions for Complexes of Organic Molecules with Cyclodextrins

Cyclodextrins are macrocyclic rings composed of glucose residues. Due to their remarkable structural properties, they can form host-guest inclusion complexes, which is why they are frequently used in the pharmaceutical, cosmetic, and food industries, as well as in environmental and analytical chemistry. This review presents the reports from 2011 to 2023 on the quantitative structure-activity/property relationship (QSAR/QSPR) approach, which is primarily employed to predict the thermodynamic stability of inclusion complexes. This article extensively discusses the significant developments related to the size of available experimental data, the available sets of descriptors, and the machine learning (ML) algorithms used, such as support vector machines, random forests, artificial neural networks, and gradient boosting. As QSAR/QPR analysis only requires molecular structures of guests and experimental values of stability constants, this approach may be particularly useful for predicting these values for complexes with randomly substituted cyclodextrins, as well as for estimating their dependence on pH. This work proposes solutions on how to effectively use this knowledge, which is especially important for researchers who will deal with this topic in the future. This review also presents other applications of ML in relation to CD complexes, including the prediction of physicochemical properties of CD complexes, the development of analytical methods based on complexation with CDs, and the optimisation of experimental conditions for the preparation of the complexes.

Identification of SARS-CoV-2 Mpro inhibitors through deep reinforcement learning for de novo drug design and computational chemistry approaches

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a global pandemic of coronavirus disease (COVID-19) since its emergence in December 2019. As of January 2024, there has been over 774 million reported cases and 7 million deaths worldwide. While vaccination efforts have been successful in reducing the severity of the disease and decreasing the transmission rate, the development of effective therapeutics against SARS-CoV-2 remains a critical need. The main protease (Mpro) of SARS-CoV-2 is an essential enzyme required for viral replication and has been identified as a promising target for drug development. In this study, we report the identification of novel Mpro inhibitors, using a combination of deep reinforcement learning for de novo drug design with 3D pharmacophore/shape-based alignment and privileged fragment match count scoring components followed by hit expansions and molecular docking approaches. Our experimentally validated results show that 3 novel series exhibit potent inhibitory activity against SARS-CoV-2 Mpro, with IC50 values ranging from 1.3 μM to 2.3 μM and a high degree of selectivity. These findings represent promising starting points for the development of new antiviral therapies against COVID-19.

Recent Developments in Machine Learning for Mass Spectrometry

Statistical analysis and modeling of mass spectrometry (MS) data have a long and rich history with several modern MS-based applications using statistical and chemometric methods. Recently, machine learning (ML) has experienced a renaissance due to advents in computational hardware and the development of new algorithms for artificial neural networks (ANN) and deep learning architectures. Moreover, recent successes of new ANN and deep learning architectures in several areas of science, engineering, and society have further strengthened the ML field. Importantly, modern ML methods and architectures have enabled new approaches for tasks related to MS that are now widely adopted in several popular MS-based subdisciplines, such as mass spectrometry imaging and proteomics. Herein, we aim to provide an introductory summary of the practical aspects of ML methodology relevant to MS. Additionally, we seek to provide an up-to-date review of the most recent developments in ML integration with MS-based techniques while also providing critical insights into the future direction of the field.

Machine-learning-based models assist the prediction of pulmonary embolism in autoimmune diseases: A retrospective, multicenter study

BACKGROUND

Pulmonary embolism (PE) is a severe and acute cardiovascular syndrome with high mortality among patients with autoimmune inflammatory rheumatic diseases (AIIRDs). Accurate prediction and timely intervention play a pivotal role in enhancing survival rates. However, there is a notable scarcity of practical early prediction and risk assessment systems of PE in patients with AIIRD.

METHODS

In the training cohort, 60 AIIRD with PE cases and 180 age-, gender-, and disease-matched AIIRD non-PE cases were identified from 7254 AIIRD cases in Tongji Hospital from 2014 to 2022. Univariable logistic regression (LR) and least absolute shrinkage and selection operator (LASSO) were used to select the clinical features for further training with machine learning (ML) methods, including random forest (RF), support vector machines (SVM), neural network (NN), logistic regression (LR), gradient boosted decision tree (GBDT), classification and regression trees (CART), and C5.0 models. The performances of these models were subsequently validated using a multicenter validation cohort.

RESULTS

In the training cohort, 24 and 13 clinical features were selected by univariable LR and LASSO strategies, respectively. The five ML models (RF, SVM, NN, LR, and GBDT) showed promising performances, with an area under the receiver operating characteristic (ROC) curve (AUC) of 0.962-1.000 in the training cohort and 0.969-0.999 in the validation cohort. CART and C5.0 models achieved AUCs of 0.850 and 0.932, respectively, in the training cohort. Using D-dimer as a pre-screening index, the refined C5.0 model achieved an AUC exceeding 0.948 in the training cohort and an AUC above 0.925 in the validation cohort. These results markedly outperformed the use of D-dimer levels alone.

CONCLUSION

ML-based models are proven to be precise for predicting the onset of PE in patients with AIIRD exhibiting clinical suspicion of PE.

TRIAL REGISTRATION

Chictr.org.cn: ChiCTR2200059599.

In Silico Design and In Vitro Assessment of Bicyclic Trifluoromethylated Pyrroles as New Antibacterial and Antifungal Agents

QSAR studies on the number of compounds tested as S. aureus inhibitors were performed using an interactive Online Chemical Database and Modeling Environment (OCHEM) web platform. The predictive ability of the developed consensus QSAR model was q2=0.79±0.02. The consensus prediction for the external evaluation set afforded high predictive power (q2=0.82±0.03). The models were applied to screen a virtual chemical library with anti-S. aureus activity. Six promising new bicyclic trifluoromethylated pyrroles were identified, synthesized and evaluated in vitro against S. aureus, E. coli, and A. baumannii for their antibacterial activity and against C. albicans, C. krusei and C. glabrata for their antifungal activity. The synthesized compounds were characterized by 1H, 19F, and 13C NMR and elemental analysis. The antimicrobial activity assessment indicated that trifluoromethylated pyrroles 9 and 11 demonstrated the greatest antibacterial and antifungal effects against all the tested pathogens, especially against multidrug-resistant strains. The acute toxicity of the compounds to Daphnia magna ranged from 1.21 to 33.39 mg/L (moderately and slightly toxic). Based on the docking results, it can be suggested that the antibacterial and antifungal effects of the compounds can be explained by the inhibition of bacterial wall component synthesis.

Exploring machine learning for untargeted metabolomics using molecular fingerprints

BACKGROUND

Metabolomics, the study of substrates and products of cellular metabolism, offers valuable insights into an organism's state under specific conditions and has the potential to revolutionise preventive healthcare and pharmaceutical research. However, analysing large metabolomics datasets remains challenging, with available methods relying on limited and incompletely annotated metabolic pathways.

METHODS

This study, inspired by well-established methods in drug discovery, employs machine learning on metabolite fingerprints to explore the relationship of their structure with responses in experimental conditions beyond known pathways, shedding light on metabolic processes. It evaluates fingerprinting effectiveness in representing metabolites, addressing challenges like class imbalance, data sparsity, high dimensionality, duplicate structural encoding, and interpretable features. Feature importance analysis is then applied to reveal key chemical configurations affecting classification, identifying related metabolite groups.

RESULTS

The approach is tested on two datasets: one on Ataxia Telangiectasia and another on endothelial cells under low oxygen. Machine learning on molecular fingerprints predicts metabolite responses effectively, and feature importance analysis aligns with known metabolic pathways, unveiling new affected metabolite groups for further study.

CONCLUSION

In conclusion, the presented approach leverages the strengths of drug discovery to address critical issues in metabolomics research and aims to bridge the gap between these two disciplines. This work lays the foundation for future research in this direction, possibly exploring alternative structural encodings and machine learning models.

Current perspectives and trend of computer-aided drug design: a review and bibliometric analysis

AIM

Computer-aided drug design (CADD) is a drug design technique for computing ligand-receptor interactions and is involved in various stages of drug development. To better grasp the frontiers and hotspots of CADD, we conducted a review analysis through bibliometrics.

METHODS

A systematic review of studies published between 2000 and 20 July 2023 was conducted following the PRISMA guidelines. Literature on CADD was selected from the Web of Science Core Collection. General information, publications, output trends, countries/regions, institutions, journals, keywords, and influential authors were visually analyzed using software such as Excel, VOSviewer, RStudio, and CiteSpace.

RESULTS

A total of 2031 publications were included. These publications primarily originated from 99 countries or regions led by the U.S. and China. Among the contributors, MacKerell AD had the highest number of articles and the greatest influence. The Journal of Medicinal Chemistry was the most cited journal, whereas the Journal of Chemical Information and Modeling had the highest number of publications.

CONCLUSIONS

Influential authors in the field were identified. Current research shows active collaboration between countries, institutions, and companies. CADD technologies such as homology modeling, pharmacophore modeling, quantitative conformational relationships, molecular docking, molecular dynamics simulation, binding free energy prediction, and high-throughput virtual screening can effectively improve the efficiency of new drug discovery. Artificial intelligence-assisted drug design and screening based on CADD represent key topics that will influence future development. Furthermore, this paper will be helpful in better understanding the frontiers and hotspots of CADD.

Metabolome-Wide Mendelian Randomization Assessing the Causal Role of Serum and Cerebrospinal Metabolites in Traumatic Brain Injury

Previous studies have identified metabolites as biomarkers or potential therapeutic targets for traumatic brain injury (TBI). However, the causal association between them remains unknown. Therefore, we investigated the causal effect of serum metabolites and cerebrospinal fluid (CSF) metabolites on TBI susceptibility through Mendelian randomization (MR). Genetic variants related to metabolites and TBI were extracted from a corresponding genome-wide association study (GWAS). Causal effects were estimated through the inverse variance weighted approach, supplemented by a weighted median, weight mode, and the MR-Egger test. In addition, sensitivity analyses were further performed to evaluate the stability of the MR results, including the MR-Egger intercept, leave-one-out analysis, Cochrane's Q-test, and the MR-PRESSO global test. Metabolic pathway analysis was applied to uncover the underlying pathways of the significant metabolites in TBI. In blood metabolites, substances such as 4-acetaminophen sulfate and kynurenine showed positive links, whereas beta-hydroxyisovalerate and creatinine exhibited negative correlations. CSF metabolites such as N-formylanthranilic acid were positively related, while kynurenate showed negative associations. The metabolic pathway analysis highlighted the potential biological pathways involved in TBI. Of these 16 serum metabolites, 11 CSF metabolites and metabolic pathways may serve as useful circulating biomarkers in clinical screening and prevention, and may be candidate molecules for the exploration of mechanisms and drug targets.

Peptide-based drug discovery through artificial intelligence: towards an autonomous design of therapeutic peptides

With their diverse biological activities, peptides are promising candidates for therapeutic applications, showing antimicrobial, antitumour and hormonal signalling capabilities. Despite their advantages, therapeutic peptides face challenges such as short half-life, limited oral bioavailability and susceptibility to plasma degradation. The rise of computational tools and artificial intelligence (AI) in peptide research has spurred the development of advanced methodologies and databases that are pivotal in the exploration of these complex macromolecules. This perspective delves into integrating AI in peptide development, encompassing classifier methods, predictive systems and the avant-garde design facilitated by deep-generative models like generative adversarial networks and variational autoencoders. There are still challenges, such as the need for processing optimization and careful validation of predictive models. This work outlines traditional strategies for machine learning model construction and training techniques and proposes a comprehensive AI-assisted peptide design and validation pipeline. The evolving landscape of peptide design using AI is emphasized, showcasing the practicality of these methods in expediting the development and discovery of novel peptides within the context of peptide-based drug discovery.

Modeling of Effectiveness of N3-Substituted Amidrazone Derivatives as Potential Agents against Gram-Positive Bacteria

Prediction of the antibacterial activity of new chemical compounds is an important task, due to the growing problem of bacterial drug resistance. Generalized linear models (GLMs) were created using 85 amidrazone derivatives based on the results of antimicrobial activity tests, determined as the minimum inhibitory concentration (MIC) against Gram-positive bacteria: Staphylococcus aureus, Enterococcus faecalis, Micrococcus luteus, Nocardia corallina, and Mycobacterium smegmatis. For the analysis of compounds characterized by experimentally measured MIC values, we included physicochemical properties (e.g., molecular weight, number of hydrogen donors and acceptors, topological polar surface area, compound percentages of carbon, nitrogen, and oxygen, melting points, and lipophilicity) as potential predictors. The presence of R1 and R2 substituents, as well as interactions between melting temperature and R1 or R2 substituents, were also considered. The set of potential predictors also included possible biological effects (e.g., antibacterial, antituberculotic) of tested compounds calculated with the PASS (Prediction of Activity Spectra for Substances) program. Using GLMs with least absolute shrinkage and selection (LASSO), least-angle regression, and stepwise selection, statistically significant models with the optimal value of the adjusted determination coefficient and of seven fit criteria were chosen, e.g., Akaike's information criterion. The most often selected variables were as follows: molecular weight, PASS_antieczematic, PASS_anti-inflam, squared melting temperature, PASS_antitumor, and experimental lipophilicity. Additionally, relevant to the bacterial strain, the interactions between melting temperature and R1 or R2 substituents were selected, indicating that the relationship between MIC and melting temperature depends on the type of R1 or R2 substituent.

Alnustone promotes megakaryocyte differentiation and platelet production via the interleukin-17A/interleukin-17A receptor/Src/RAC1/MEK/ERK signaling pathway

OBJECTIVES

Thrombocytopenia is a disease in which the number of platelets in the peripheral blood decreases. It can be caused by multiple genetic factors, and numerous challenges are associated with its treatment. In this study, the effects of alnustone on megakaryocytes and platelets were investigated, with the aim of developing a new therapeutic approach for thrombocytopenia.

METHODS

Random forest algorithm was used to establish a drug screening model, and alnustone was identified as a natural active compound that could promote megakaryocyte differentiation. The effect of alnustone on megakaryocyte activity was determined using cell counting kit-8. The effect of alnustone on megakaryocyte differentiation was determined using flow cytometry, Giemsa staining, and phalloidin staining. A mouse model of thrombocytopenia was established by exposing mice to X-rays at 4 Gy and was used to test the bioactivity of alnustone in vivo. The effect of alnustone on platelet production was determined using zebrafish. Network pharmacology was used to predict targets and signaling pathways. Western blotting and immunofluorescence staining determined the expression levels of proteins.

RESULTS

Alnustone promoted the differentiation and maturation of megakaryocytes in vitro and restored platelet production in thrombocytopenic mice and zebrafish. Network pharmacology and western blotting showed that alnustone promoted the expression of interleukin-17A and enhanced its interaction with its receptor, and thereby regulated downstream MEK/ERK signaling and promoted megakaryocyte differentiation.

CONCLUSIONS

Alnustone can promote megakaryocyte differentiation and platelet production via the interleukin-17A/interleukin-17A receptor/Src/RAC1/MEK/ERK signaling pathway and thus provides a new therapeutic strategy for the treatment of thrombocytopenia.

Image2InChI: Automated Molecular Optical Image Recognition

The accurate identification and analysis of chemical structures in molecular images are prerequisites of artificial intelligence for drug discovery. It is important to efficiently and automatically convert molecular images into machine-readable representations. Therefore, in this paper, we propose an automated molecular optical image recognition model based on deep learning, called Image2InChI. Additionally, the proposed Image2InChI introduces a novel feature fusion network with attention to integrate image patch and InChI prediction. The improved SwinTransformer as an encoder and the Transformer Decoder as a decoder with patch embedding are applied to predict the image features for the corresponding InChI. The experimental results showed that the Image2InChI model achieves an accuracy of InChI (InChI acc) of 99.8%, a Morgan FP of 94.1%, an accuracy of maximum common structures (MCS acc) of 94.8%, and an accuracy of longest common subsequence (LCS acc) of 96.2%. The experiments demonstrated that the proposed Image2InChI model improves the accuracy and efficiency of molecular image recognition and provided a valuable reference about optical chemical structure recognition for InChI.

Prediction of cytochrome P450-mediated bioactivation using machine learning models and in vitro validation

Cytochrome P450 (P450)-mediated bioactivation, which can lead to the hepatotoxicity through the formation of reactive metabolites (RMs), has been regarded as the major problem of drug failures. Herein, we purposed to establish machine learning models to predict the bioactivation of P450. On the basis of the literature-derived bioactivation dataset, models for Benzene ring, Nitrogen heterocycle and Sulfur heterocycle were developed with machine learning methods, i.e., Random Forest, Random Subspace, SVM and Naïve Bayes. The models were assessed by metrics like "Precision", "Recall", "F-Measure", "AUC" (Area Under the Curve), etc. Random Forest algorithms illustrated the best predictability, with nice AUC values of 0.949, 0.973 and 0.958 for the test sets of Benzene ring, Nitrogen heterocycle and Sulfur heterocycle models, respectively. 2D descriptors like topological indices, 2D autocorrelations and Burden eigenvalues, etc. contributed most to the models. Furthermore, the models were applied to predict the occurrence of bioactivation of an external verification set. Drugs like selpercatinib, glafenine, encorafenib, etc. were predicted to undergo bioactivation into toxic RMs. In vitro, IC50 shift experiment was performed to assess the potential of bioactivation to validate the prediction. Encorafenib and tirbanibulin were observed of bioactivation potential with shifts of 3-6 folds or so. Overall, this study provided a reliable and robust strategy to predict the P450-mediated bioactivation, which will be helpful to the assessment of adverse drug reactions (ADRs) in clinic and the design of new candidates with lower toxicities.

Advances in machine intelligence-driven virtual screening approaches for big-data

Virtual screening (VS) is an integral and ever-evolving domain of drug discovery framework. The VS is traditionally classified into ligand-based (LB) and structure-based (SB) approaches. Machine intelligence or artificial intelligence has wide applications in the drug discovery domain to reduce time and resource consumption. In combination with machine intelligence algorithms, VS has emerged into revolutionarily progressive technology that learns within robust decision orders for data curation and hit molecule screening from large VS libraries in minutes or hours. The exponential growth of chemical and biological data has evolved as "big-data" in the public domain demands modern and advanced machine intelligence-driven VS approaches to screen hit molecules from ultra-large VS libraries. VS has evolved from an individual approach (LB and SB) to integrated LB and SB techniques to explore various ligand and target protein aspects for the enhanced rate of appropriate hit molecule prediction. Current trends demand advanced and intelligent solutions to handle enormous data in drug discovery domain for screening and optimizing hits or lead with fewer or no false positive hits. Following the big-data drift and tremendous growth in computational architecture, we presented this review. Here, the article categorized and emphasized individual VS techniques, detailed literature presented for machine learning implementation, modern machine intelligence approaches, and limitations and deliberated the future prospects.

Discovery of novel SOS1 inhibitors using machine learning

Overactivation of the rat sarcoma virus (RAS) signaling is responsible for 30% of all human malignancies. Son of sevenless 1 (SOS1), a crucial node in the RAS signaling pathway, could modulate RAS activation, offering a promising therapeutic strategy for RAS-driven cancers. Applying machine learning (ML)-based virtual screening (VS) on small-molecule databases, we selected a random forest (RF) regressor for its robustness and performance. Screening was performed with the L-series and EGFR-related datasets, and was extended to the Chinese National Compound Library (CNCL) with more than 1.4 million compounds. In addition to a series of documented SOS1-related molecules, we uncovered nine compounds that have an unexplored chemical framework and displayed inhibitory activity, with the most potent achieving more than 50% inhibition rate in the KRAS G12C/SOS1 PPI assay and an IC50 value in the proximity of 20 μg mL-1. Compared with the manner that known inhibitory agents bind to the target, hit compounds represented by CL01545365 occupy a unique pocket in molecular docking. An in silico drug-likeness assessment suggested that the compound has moderately favorable drug-like properties and pharmacokinetic characteristics. Altogether, our findings strongly support that, characterized by the distinctive binding modes, the recognition of novel skeletons from the carboxylic acid series could be candidates for developing promising SOS1 inhibitors.

Gap-Δenergy, a New Metric of the Bond Energy State, Assisting to Predict Molecular Toxicity

Molecular toxicity is a critical feature of drug development. It is thus very important to develop computational models to evaluate the toxicity of small molecules. The accuracy of toxicity prediction largely depends on the quality of molecular representation; however, current methods for this purpose do not address this issue well. Here, we introduce a new metric, gap-Δenergy, which is designed to quantify the intermolecular bond energy difference with atom distance. We next find significant variations in the gap-Δenergy distribution among different types of molecules. Moreover, we show that this metric is able to distinguish the toxic small molecules. We collected data sets of toxic and exogenous small molecules and presented a novel index, namely, global toxicity, to evaluate the overall toxicity of molecules. Based on molecular descriptors and the proposed gap-Δenergy metric, we further constructed machine learning models that were trained with 7816 small molecules. The XGBoost-based model achieved the best performance with an AUC score of 0.965 and an F1 score of 0.849 on the test set (1954 small molecules), which outperformed the model that did not use gap-Δenergy features, with a sensitivity score increase of 3.2%.

Novel insights into immune-related genes associated with type 2 diabetes mellitus-related cognitive impairment

BACKGROUND

The cognitive impairment in type 2 diabetes mellitus (T2DM) is a multifaceted and advancing state that requires further exploration to fully comprehend. Neuroinflammation is considered to be one of the main mechanisms and the immune system has played a vital role in the progression of the disease.

AIM

To identify and validate the immune-related genes in the hippocampus associated with T2DM-related cognitive impairment.

METHODS

To identify differentially expressed genes (DEGs) between T2DM and controls, we used data from the Gene Expression Omnibus database GSE125387. To identify T2DM module genes, we used Weighted Gene Co-Expression Network Analysis. All the genes were subject to Gene Set Enrichment Analysis. Protein-protein interaction network construction and machine learning were utilized to identify three hub genes. Immune cell infiltration analysis was performed. The three hub genes were validated in GSE152539 via receiver operating characteristic curve analysis. Validation experiments including reverse transcription quantitative real-time PCR, Western blotting and immunohistochemistry were conducted both in vivo and in vitro. To identify potential drugs associated with hub genes, we used the Comparative Toxicogenomics Database (CTD).

RESULTS

A total of 576 DEGs were identified using GSE125387. By taking the intersection of DEGs, T2DM module genes, and immune-related genes, a total of 59 genes associated with the immune system were identified. Afterward, machine learning was utilized to identify three hub genes (H2-T24, Rac3, and Tfrc). The hub genes were associated with a variety of immune cells. The three hub genes were validated in GSE152539. Validation experiments were conducted at the mRNA and protein levels both in vivo and in vitro, consistent with the bioinformatics analysis. Additionally, 11 potential drugs associated with RAC3 and TFRC were identified based on the CTD.

CONCLUSION

Immune-related genes that differ in expression in the hippocampus are closely linked to microglia. We validated the expression of three hub genes both in vivo and in vitro, consistent with our bioinformatics results. We discovered 11 compounds associated with RAC3 and TFRC. These findings suggest that they are co-regulatory molecules of immunometabolism in diabetic cognitive impairment.

Deciphering Ferroptosis: From Molecular Pathways to Machine Learning-Guided Therapeutic Innovation

Ferroptosis is a unique form of cell death reliant on iron and lipid peroxidation. It disrupts redox balance, causing cell death by damaging the plasma membrane, with inducers acting through enzymatic pathways or transport systems. In cancer treatment, suppressing ferroptosis or circumventing it holds significant promise. Beyond cancer, ferroptosis affects aging, organs, metabolism, and nervous system. Understanding ferroptosis mechanisms holds promise for uncovering novel therapeutic strategies across a spectrum of diseases. However, detection and regulation of this regulated cell death are still mired with challenges. The dearth of cell, tissue, or organ-specific biomarkers muted the pharmacological use of ferroptosis. This review covers recent studies on ferroptosis, detailing its properties, key genes, metabolic pathways, and regulatory networks, emphasizing the interaction between cellular signaling and ferroptotic cell death. It also summarizes recent findings on ferroptosis inducers, inhibitors, and regulators, highlighting their potential therapeutic applications across diseases. The review addresses challenges in utilizing ferroptosis therapeutically and explores the use of machine learning to uncover complex patterns in ferroptosis-related data, aiding in the discovery of biomarkers, predictive models, and therapeutic targets. Finally, it discusses emerging research areas and the importance of continued investigation to harness the full therapeutic potential of targeting ferroptosis.

Finding new analgesics: Computational pharmacology faces drug discovery challenges

Despite the worldwide prevalence and huge burden of pain, pain is an undertreated phenomenon. Currently used analgesics have several limitations regarding their efficacy and safety. The discovery of analgesics possessing a novel mechanism of action has faced multiple challenges, including a limited understanding of biological processes underpinning pain and analgesia and poor animal-to-human translation. Computational pharmacology is currently employed to face these challenges. In this review, we discuss the theory, methods, and applications of computational pharmacology in pain research. Computational pharmacology encompasses a wide variety of theoretical concepts and practical methodological approaches, with the overall aim of gaining biological insight through data acquisition and analysis. Data are acquired from patients or animal models with pain or analgesic treatment, at different levels of biological organization (molecular, cellular, physiological, and behavioral). Distinct methodological algorithms can then be used to analyze and integrate data. This helps to facilitate the identification of biological molecules and processes associated with pain phenotype, build quantitative models of pain signaling, and extract translatable features between humans and animals. However, computational pharmacology has several limitations, and its predictions can provide false positive and negative findings. Therefore, computational predictions are required to be validated experimentally before drawing solid conclusions. In this review, we discuss several case study examples of combining and integrating computational tools with experimental pain research tools to meet drug discovery challenges.

Exploring novel lead scaffolds for SGLT2 inhibitors: Insights from machine learning and molecular dynamics simulations

Sodium-glucose cotransporter 2 (SGLT2) plays a pivotal role in mediating glucose reabsorption within the renal filtrate, representing a well-known target in type 2 diabetes and heart failure. Recent emphasis has been directed toward designing SGLT2 inhibitors, with C-glycoside inhibitors emerging as front-runners. The architecture of SGLT2 has been successfully resolved using cryo-electron microscopy. However, comprehension of the pharmacophores within the binding site of SGLT2 remains unclear. Here, we use machine learning and molecular dynamics simulations on SGLT2 bound with its inhibitors in preclinical or clinical development to shed light on this issue. Our dataset comprises 1240 SGLT2 inhibitors amalgamated from diverse sources, forming the basis for constructing machine learning models. SHapley Additive exPlanation (SHAP) elucidates the crucial fragments that contribute to inhibitor activity, specifically Morgan_3, 162, 310, 325, 366, 470, 597, 714, 926, and 975. Furthermore, the computed binding free energies and per-residue contributions for SGLT2-inhibitor complexes unveil crucial fragments of inhibitors that interact with residues Asn-75, His-80, Val-95, Phe-98, Val-157, Leu-274, and Phe-453 in the binding site of SGLT2. This comprehensive investigation enhances understanding of the binding mechanism for SGLT2 inhibitors, providing a robust framework for evaluating and discovering novel lead scaffolds within this domain.

A new workflow for the effective curation of membrane permeability data from open ADME information

Membrane permeability is an in vitro parameter that represents the apparent permeability (Papp) of a compound, and is a key absorption, distribution, metabolism, and excretion parameter in drug development. Although the Caco-2 cell lines are the most used cell lines to measure Papp, other cell lines, such as the Madin-Darby Canine Kidney (MDCK), LLC-Pig Kidney 1 (LLC-PK1), and Ralph Russ Canine Kidney (RRCK) cell lines, can also be used to estimate Papp. Therefore, constructing in silico models for Papp estimation using the MDCK, LLC-PK1, and RRCK cell lines requires collecting extensive amounts of in vitro Papp data. An open database offers extensive measurements of various compounds covering a vast chemical space; however, concerns were reported on the use of data published in open databases without the appropriate accuracy and quality checks. Ensuring the quality of datasets for training in silico models is critical because artificial intelligence (AI, including deep learning) was used to develop models to predict various pharmacokinetic properties, and data quality affects the performance of these models. Hence, careful curation of the collected data is imperative. Herein, we developed a new workflow that supports automatic curation of Papp data measured in the MDCK, LLC-PK1, and RRCK cell lines collected from ChEMBL using KNIME. The workflow consisted of four main phases. Data were extracted from ChEMBL and filtered to identify the target protocols. A total of 1661 high-quality entries were retained after checking 436 articles. The workflow is freely available, can be updated, and has high reusability. Our study provides a novel approach for data quality analysis and accelerates the development of helpful in silico models for effective drug discovery. Scientific Contribution: The cost of building highly accurate predictive models can be significantly reduced by automating the collection of reliable measurement data. Our tool reduces the time and effort required for data collection and will enable researchers to focus on constructing high-performance in silico models for other types of analysis. To the best of our knowledge, no such tool is available in the literature.

Photocatalytic degradation of drugs and dyes using a maching learning approach

The waste management industry uses an increasing number of mathematical prediction models to accurately forecast the behavior of organic pollutants during catalytic degradation. With the increasing quantity of waste generated, these models are critical for reinforcing the efficiency of wastewater treatment strategies. The application of machine-learning techniques in recent years has notably improved predictive models for waste management, which are essential for mitigating the impact of toxic commercial waste on global water supply. Organic contaminants, dyes, pesticides, surfactants, petroleum by-products, and prescription drugs pose risks to human health. Because traditional techniques face challenges in ensuring water quality, modern strategies are vital. Machine learning has emerged as a valuable tool for predicting the photocatalytic degradation of medicinal drugs and dyes, providing a promising avenue for addressing urgent demands in removing organic pollutants from wastewater. This research investigates the synergistic application of photocatalysis and machine learning for pollutant degradation, showcasing a sustainable solution with promising effects on environmental remediation and computational efficiency. This study contributes to green chemistry by providing a clever framework for addressing present-day water pollution challenges and achieving era-driven answers.

Learning self-supervised molecular representations for drug-drug interaction prediction

Drug-drug interactions (DDI) are a critical concern in healthcare due to their potential to cause adverse effects and compromise patient safety. Supervised machine learning models for DDI prediction need to be optimized to learn abstract, transferable features, and generalize to larger chemical spaces, primarily due to the scarcity of high-quality labeled DDI data. Inspired by recent advances in computer vision, we present SMR-DDI, a self-supervised framework that leverages contrastive learning to embed drugs into a scaffold-based feature space. Molecular scaffolds represent the core structural motifs that drive pharmacological activities, making them valuable for learning informative representations. Specifically, we pre-trained SMR-DDI on a large-scale unlabeled molecular dataset. We generated augmented views for each molecule via SMILES enumeration and optimized the embedding process through contrastive loss minimization between views. This enables the model to capture relevant and robust molecular features while reducing noise. We then transfer the learned representations for the downstream prediction of DDI. Experiments show that the new feature space has comparable expressivity to state-of-the-art molecular representations and achieved competitive DDI prediction results while training on less data. Additional investigations also revealed that pre-training on more extensive and diverse unlabeled molecular datasets improved the model's capability to embed molecules more effectively. Our results highlight contrastive learning as a promising approach for DDI prediction that can identify potentially hazardous drug combinations using only structural information.

Direct K-Ras Inhibitors to Treat Cancers: Progress, New Insights, and Approaches to Treat Resistance

Here we discuss approaches to K-Ras inhibition and drug resistance scenarios. A breakthrough offered a covalent drug against K-RasG12C. Subsequent innovations harnessed same-allele drug combinations, as well as cotargeting K-RasG12C with a companion drug to upstream regulators or downstream kinases. However, primary, adaptive, and acquired resistance inevitably emerge. The preexisting mutation load can explain how even exceedingly rare mutations with unobservable effects can promote drug resistance, seeding growth of insensitive cell clones, and proliferation. Statistics confirm the expectation that most resistance-related mutations are in cis, pointing to the high probability of cooperative, same-allele effects. In addition to targeted Ras inhibitors and drug combinations, bifunctional molecules and innovative tri-complex inhibitors to target Ras mutants are also under development. Since the identities and potential contributions of preexisting and evolving mutations are unknown, selecting a pharmacologic combination is taxing. Collectively, our broad review outlines considerations and provides new insights into pharmacology and resistance.

Explainable artificial intelligence-assisted virtual screening and bioinformatics approaches for effective bioactivity prediction of phenolic cyclooxygenase-2 (COX-2) inhibitors using PubChem molecular fingerprints

Cyclooxygenase-2 (COX-2) inhibitors are nonsteroidal anti-inflammatory drugs that treat inflammation, pain and fever. This study determined the interaction mechanisms of COX-2 inhibitors and the molecular properties needed to design new drug candidates. Using machine learning and explainable AI methods, the inhibition activity of 1488 molecules was modelled, and essential properties were identified. These properties included aromatic rings, nitrogen-containing functional groups and aliphatic hydrocarbons. They affected the water solubility, hydrophobicity and binding affinity of COX-2 inhibitors. The binding mode, stability and ADME properties of 16 ligands bound to the Cyclooxygenase active site of COX-2 were investigated by molecular docking, molecular dynamics simulation and MM-GBSA analysis. The results showed that ligand 339,222 was the most stable and effective COX-2 inhibitor. It inhibited prostaglandin synthesis by disrupting the protein conformation of COX-2. It had good ADME properties and high clinical potential. This study demonstrated the potential of machine learning and bioinformatics methods in discovering COX-2 inhibitors.

Machine learning and deep learning-based approach in smart healthcare: Recent advances, applications, challenges and opportunities

In recent years, machine learning (ML) and deep learning (DL) have been the leading approaches to solving various challenges, such as disease predictions, drug discovery, medical image analysis, etc., in intelligent healthcare applications. Further, given the current progress in the fields of ML and DL, there exists the promising potential for both to provide support in the realm of healthcare. This study offered an exhaustive survey on ML and DL for the healthcare system, concentrating on vital state of the art features, integration benefits, applications, prospects and future guidelines. To conduct the research, we found the most prominent journal and conference databases using distinct keywords to discover scholarly consequences. First, we furnished the most current along with cutting-edge progress in ML-DL-based analysis in smart healthcare in a compendious manner. Next, we integrated the advancement of various services for ML and DL, including ML-healthcare, DL-healthcare, and ML-DL-healthcare. We then offered ML and DL-based applications in the healthcare industry. Eventually, we emphasized the research disputes and recommendations for further studies based on our observations.

Improving ADMET Prediction Accuracy for Candidate Drugs: Factors to Consider in QSPR Modeling Approaches

Quantitative Structure-Property Relationship (QSPR) employs mathematical and statistical methods to reveal quantitative correlations between the pharmacokinetics of compounds and their molecular structures, as well as their physical and chemical properties. QSPR models have been widely applied in the prediction of drug absorption, distribution, metabolism, excretion, and toxicity (ADMET). However, the accuracy of QSPR models for predicting drug ADMET properties still needs improvement. Therefore, this paper comprehensively reviews the tools employed in various stages of QSPR predictions for drug ADMET. It summarizes commonly used approaches to building QSPR models, systematically analyzing the advantages and limitations of each modeling method to ensure their judicious application. We provide an overview of recent advancements in the application of QSPR models for predicting drug ADMET properties. Furthermore, this review explores the inherent challenges in QSPR modeling while also proposing a range of considerations aimed at enhancing model prediction accuracy. The objective is to enhance the predictive capabilities of QSPR models in the field of drug development and provide valuable reference and guidance for researchers in this domain.

Integrating biocomputational techniques for Breast cancer drug discovery via the HER-2, BCRA, VEGF and ER protein targets

Computational modelling remains an indispensable technique in drug discovery. With myriad of high computing resources, and improved modelling algorithms, there has been a high-speed in the drug development cycle with promising success rate compared to the traditional route. For example, lapatinib; a well-known anticancer drug with clinical applications was discovered with computational drug design techniques. Similarly, molecular modelling has been applied to various disease areas ranging from cancer to neurodegenerative diseases. The techniques ranges from high-throughput virtual screening, molecular mechanics with generalized Born and surface area solvation (MM/GBSA) to molecular dynamics simulation. This review focuses on the application of computational modelling tools in the identification of drug candidates for Breast cancer. First, we begin with a succinct overview of molecular modelling in the drug discovery process. Next, we take note of special efforts on the developments and applications of combining these techniques with particular emphasis on possible breast cancer therapeutic targets such as estrogen receptor (ER), human epidermal growth factor receptor 2 (HER2), vascular endothelial growth factor (VEGF), breast cancer gene 1 (BRCA1), and breast cancer gene 2 (BRCA2). Finally, we discussed the search for covalent inhibitors against these receptors using computational techniques, advances, pitfalls, possible solutions, and future perspectives.

Developing a Prognostic Model for Primary Biliary Cholangitis Based on a Random Survival Forest Model

Background: Primary biliary cholangitis (PBC) is a rare autoimmune liver disease with few effective treatments and a poor prognosis, and its incidence is on the rise. There is an urgent need for more targeted treatment strategies to accurately identify high-risk patients. The use of stochastic survival forest models in machine learning is an innovative approach to constructing a prognostic model for PBC that can improve the prognosis by identifying high-risk patients for targeted treatment. Method: Based on the inclusion and exclusion criteria, the clinical data and follow-up data of patients diagnosed with PBC-associated cirrhosis between January 2011 and December 2021 at Taizhou Hospital of Zhejiang Province were retrospectively collected and analyzed. Data analyses and random survival forest model construction were based on the R language. Result: Through a Cox univariate regression analysis of 90 included samples and 46 variables, 17 variables with p-values <0.1 were selected for initial model construction. The out-of-bag (OOB) performance error was 0.2094, and K-fold cross-validation yielded an internal validation C-index of 0.8182. Through model selection, cholinesterase, bile acid, the white blood cell count, total bilirubin, and albumin were chosen for the final predictive model, with a final OOB performance error of 0.2002 and C-index of 0.7805. Using the final model, patients were stratified into high- and low-risk groups, which showed significant differences with a P value <0.0001. The area under the curve was used to evaluate the predictive ability for patients in the first, third, and fifth years, with respective results of 0.9595, 0.8898, and 0.9088. Conclusion: The present study constructed a prognostic model for PBC-associated cirrhosis patients using a random survival forest model, which accurately stratified patients into low- and high-risk groups. Treatment strategies can thus be more targeted, leading to improved outcomes for high-risk patients.

Integrated virtual screening and MD simulation approaches toward discovering potential inhibitors for targeting BRPF1 bromodomain in hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is one of the most aggressive and life-threatening cancers. Although multiple treatment options are available, the prognosis of HCC patients is poor due to metastasis and drug resistance. Hence, discovering novel targets is essential for better therapeutic development for HCC. In this study, we used the cancer genome atlas (TCGA) dataset to analyze the expression of bromodomain-containing proteins in HCC, as bromodomains are emerging attractive therapeutic targets. Our analysis identified BRPF1 as the most highly upregulated gene in HCC among the 43 bromodomain-containing genes. Upregulation of BRPF1 was significantly associated with poorer patient survival. Therefore, targeting BRPF1 may be an approach for HCC treatment. Previously, several potential inhibitors of BRPF1 bromodomain have been discovered. However, due to the limited clinical success of the current inhibitors, we aim to search for new inhibitors with high affinity and specificity for the BRPF1 bromodomain. In this study, we utilized high-throughput virtual screening methods to screen synthetic and natural compound databases against the BRPF1 bromodomain. In addition, we used machine learning-based QSAR modeling to predict the IC50 values of the selected BRPF1 bromodomain inhibitors. Extensive MD simulations were used to calculate the binding free energies of BRPF1 bromodomain and inhibitor complexes. Using this approach, we identified four lead scaffolds with a similar or better binding affinity towards the BRPF1 bromodomain than the previously reported inhibitors. Overall, this study discovered some promising compounds that have the potential to act as potent BRPF1 bromodomain inhibitors.

Exploring the Role of Chemoinformatics in Accelerating Drug Discovery: A Computational Approach

Cheminformatics and its role in drug discovery is expected to be the privileged approach in handling large number of chemical datasets. This approach contributes toward the pharmaceutical development and assessment of chemical compounds at a faster rate efficiently. Additionally, as technological advancement impacts research, cheminformatics is being used more and more in the field of health science. This chapter describes the concepts of cheminformatics along with its involvement in drug discovery with a case study.

From cancer big data to treatment: Artificial intelligence in cancer research

In recent years, developing the idea of "cancer big data" has emerged as a result of the significant expansion of various fields such as clinical research, genomics, proteomics and public health records. Advances in omics technologies are making a significant contribution to cancer big data in biomedicine and disease diagnosis. The increasingly availability of extensive cancer big data has set the stage for the development of multimodal artificial intelligence (AI) frameworks. These frameworks aim to analyze high-dimensional multi-omics data, extracting meaningful information that is challenging to obtain manually. Although interpretability and data quality remain critical challenges, these methods hold great promise for advancing our understanding of cancer biology and improving patient care and clinical outcomes. Here, we provide an overview of cancer big data and explore the applications of both traditional machine learning and deep learning approaches in cancer genomic and proteomic studies. We briefly discuss the challenges and potential of AI techniques in the integrated analysis of omics data, as well as the future direction of personalized treatment options in cancer.

Extensive prediction of drug response in mutation-subtype-specific LUAD with machine learning approach

Background

Lung cancer is the most prevalent cancer diagnosis and the leading cause of cancer death worldwide. Therapeutic failure in lung cancer (LUAD) is heavily influenced by drug resistance. This challenge stems from the diverse cell populations within the tumor, each having unique genetic, epigenetic, and phenotypic profiles. Such variations lead to varied therapeutic responses, thereby contributing to tumor relapse and disease progression.

Methods

The Genomics of Drug Sensitivity in Cancer (GDSC) database was used in this investigation to obtain the mRNA expression dataset, genomic mutation profile, and drug sensitivity information of NSCLS. Machine Learning (ML) methods, including Random Forest (RF), Artificial Neurol Network (ANN), and Support Vector Machine (SVM), were used to predict the response status of each compound based on the mRNA and mutation characteristics determined using statistical methods. The most suitable method for each drug was proposed by comparing the prediction accuracy of different ML methods, and the selected mRNA and mutation characteristics were identified as molecular features for the drug-responsive cancer subtype. Finally, the prognostic influence of molecular features on the mutational subtype of LUAD in publicly available datasets.

Results

Our analyses yielded 1,564 gene features and 45 mutational features for 46 drugs. Applying the ML approach to predict the drug response for each medication revealed an upstanding performance for SVM in predicting Afuresertib drug response (area under the curve [AUC] 0.875) using CIT, GAS2L3, STAG3L3, ATP2B4-mut, and IL15RA-mut as molecular features. Furthermore, the ANN algorithm using 9 mRNA characteristics demonstrated the highest prediction performance (AUC 0.780) in Gefitinib with CCL23-mut.

Conclusion

This work extensively investigated the mRNA and mutation signatures associated with drug response in LUAD using a machine-learning approach and proposed a priority algorithm to predict drug response for different drugs.

Current implications and challenges of artificial intelligence technologies in therapeutic intervention of colorectal cancer

Irrespective of men and women, colorectal cancer (CRC), is the third most common cancer in the population with more than 1.85 million cases annually. Fewer than 20% of patients only survive beyond five years from diagnosis. CRC is a highly preventable disease if diagnosed at the early stage of malignancy. Several screening methods like endoscopy (like colonoscopy; gold standard), imaging examination [computed tomographic colonography (CTC)], guaiac-based fecal occult blood (gFOBT), immunochemical test from faeces, and stool DNA test are available with different levels of sensitivity and specificity. The available screening methods are associated with certain drawbacks like invasiveness, cost, or sensitivity. In recent years, computer-aided systems-based screening, diagnosis, and treatment have been very promising in the early-stage detection and diagnosis of CRC cases. Artificial intelligence (AI) is an enormously in-demand, cost-effective technology, that uses various tools machine learning (ML), and deep learning (DL) to screen, diagnose, and stage, and has great potential to treat CRC. Moreover, different ML algorithms and neural networks [artificial neural network (ANN), k-nearest neighbors (KNN), and support vector machines (SVMs)] have been deployed to predict precise and personalized treatment options. This review examines and summarizes different ML and DL models used for therapeutic intervention in CRC cancer along with the gap and challenges for AI.

Identification of New GSK3β Inhibitors through a Consensus Machine Learning-Based Virtual Screening

Glycogen synthase kinase-3 beta (GSK3β) is a serine/threonine kinase that plays key roles in glycogen metabolism, Wnt/β-catenin signaling cascade, synaptic modulation, and multiple autophagy-related signaling pathways. GSK3β is an attractive target for drug discovery since its aberrant activity is involved in the development of neurodegenerative diseases such as Alzheimer's and Parkinson's disease. In the present study, multiple machine learning models aimed at identifying novel GSK3β inhibitors were developed and evaluated for their predictive reliability. The most powerful models were combined in a consensus approach, which was used to screen about 2 million commercial compounds. Our consensus machine learning-based virtual screening led to the identification of compounds G1 and G4, which showed inhibitory activity against GSK3β in the low-micromolar and sub-micromolar range, respectively. These results demonstrated the reliability of our virtual screening approach. Moreover, docking and molecular dynamics simulation studies were employed for predicting reliable binding modes for G1 and G4, which represent two valuable starting points for future hit-to-lead and lead optimization studies.

A deep learning model for predicting multidrug-resistant organism infection in critically ill patients

BACKGROUND

This study aimed to apply the backpropagation neural network (BPNN) to develop a model for predicting multidrug-resistant organism (MDRO) infection in critically ill patients.

METHODS

This study collected patient information admitted to the intensive care unit (ICU) of the Affiliated Hospital of Qingdao University from August 2021 to January 2022. All patients enrolled were divided randomly into a training set (80%) and a test set (20%). The least absolute shrinkage and selection operator and stepwise regression analysis were used to determine the independent risk factors for MDRO infection. A BPNN model was constructed based on these factors. Then, we externally validated this model in patients from May 2022 to July 2022 over the same center. The model performance was evaluated by the calibration curve, the area under the curve (AUC), sensitivity, specificity, and accuracy.

RESULTS

In the primary cohort, 688 patients were enrolled, including 109 (15.84%) MDRO infection patients. Risk factors for MDRO infection, as determined by the primary cohort, included length of hospitalization, length of ICU stay, long-term bed rest, antibiotics use before ICU, acute physiology and chronic health evaluation II, invasive operation before ICU, quantity of antibiotics, chronic lung disease, and hypoproteinemia. There were 238 patients in the validation set, including 31 (13.03%) MDRO infection patients. This BPNN model yielded good calibration. The AUC of the training set, the test set and the validation set were 0.889 (95% CI 0.852-0.925), 0.919 (95% CI 0.856-0.983), and 0.811 (95% CI 0.731-0.891), respectively.

CONCLUSIONS

This study confirmed nine independent risk factors for MDRO infection. The BPNN model performed well and was potentially used to predict MDRO infection in ICU patients.

Usage of model combination in computational toxicology

New Approach Methodologies (NAMs) have ushered in a new era in the field of toxicology, aiming to replace animal testing. However, despite these advancements, they are not exempt from the inherent complexities associated with the study's endpoint. In this review, we have identified three major groups of complexities: mechanistic, chemical space, and methodological. The mechanistic complexity arises from interconnected biological processes within a network that are challenging to model in a single step. In the second group, chemical space complexity exhibits significant dissimilarity between compounds in the training and test series. The third group encompasses algorithmic and molecular descriptor limitations and typical class imbalance problems. To address these complexities, this work provides a guide to the usage of a combination of predictive Quantitative Structure-Activity Relationship (QSAR) models, known as metamodels. This combination of low-level models (LLMs) enables a more precise approach to the problem by focusing on different sub-mechanisms or sub-processes. For mechanistic complexity, multiple Molecular Initiating Events (MIEs) or levels of information are combined to form a mechanistic-based metamodel. Regarding the complexity arising from chemical space, two types of approaches were reviewed to construct a fragment-based chemical space metamodel: those with and without structure sharing. Metamodels with structure sharing utilize unsupervised strategies to identify data patterns and build low-level models for each cluster, which are then combined. For situations without structure sharing due to pharmaceutical industry intellectual property, the use of prediction sharing, and federated learning approaches have been reviewed. Lastly, to tackle methodological complexity, various algorithms are combined to overcome their limitations, diverse descriptors are employed to enhance problem definition and balanced dataset combinations are used to address class imbalance issues (methodological-based metamodels). Remarkably, metamodels consistently outperformed classical QSAR models across all cases, highlighting the importance of alternatives to classical QSAR models when faced with such complexities.

Utilizing Heteroatom Types and Numbers from Extensive Ligand Libraries to Develop Novel hERG Blocker QSAR Models Using Machine Learning-Based Classifiers

The human ether-à-go-go-related gene (hERG) channel plays a crucial role in membrane repolarization. Any disruptions in its function can lead to severe cardiovascular disorders such as long QT syndrome (LQTS), which increases the risk of serious cardiovascular problems such as tachyarrhythmia and sudden cardiac death. Drug-induced LQTS is a significant concern and has resulted in drug withdrawals from the market in the past. The main objective of this study is to pinpoint crucial heteroatoms present in ligands that initiate interactions leading to the effective blocking of the hERG channel. To achieve this aim, ligand-based quantitative structure-activity relationships (QSAR) models were constructed using extensive ligand libraries, considering the heteroatom types and numbers, and their associated hERG channel blockage pIC50 values. Machine learning-assisted QSAR models were developed to analyze the key structural components influencing compound activity. Among the various methods, the KPLS method proved to be the most efficient, allowing the construction of models based on eight distinct fingerprints. The study delved into investigating the influence of heteroatoms on the activity of hERG blockers, revealing their significant role. Furthermore, by quantifying the effect of heteroatom types and numbers on ligand activity at the hERG channel, six compound pairs were selected for molecular docking. Subsequent molecular dynamics simulations and per residue MM/GBSA calculations were performed to comprehensively analyze the interactions of the selected pair compounds.

Can machine learning 'transform' peptides/peptidomimetics into small molecules? A case study with ghrelin receptor ligands

There has been considerable interest in transforming peptides into small molecules as peptide-based molecules often present poorer bioavailability and lower metabolic stability. Our studies looked into building machine learning (ML) models to investigate if ML is able to identify the 'bioactive' features of peptides and use the features to accurately discriminate between binding and non-binding small molecules. The ghrelin receptor (GR), a receptor that is implicated in various diseases, was used as an example to demonstrate whether ML models derived from a peptide library can be used to predict small molecule binders. ML models based on three different algorithms, namely random forest, support vector machine, and extreme gradient boosting, were built based on a carefully curated dataset of peptide/peptidomimetic and small molecule GR ligands. The results indicated that ML models trained with a dataset exclusively composed of peptides/peptidomimetics provide limited predictive power for small molecules, but that ML models trained with a diverse dataset composed of an array of both peptides/peptidomimetics and small molecules displayed exceptional results in terms of accuracy and false rates. The diversified models can accurately differentiate the binding small molecules from non-binding small molecules using an external validation set with new small molecules that we synthesized previously. Structural features that are the most critical contributors to binding activity were extracted and are remarkably consistent with the crystallography and mutagenesis studies.

Hub gene identification and molecular subtype construction for Helicobacter pylori in gastric cancer via machine learning methods and NMF algorithm

Helicobacter pylori (HP) is a gram-negative and spiral-shaped bacterium colonizing the human stomach and has been recognized as the risk factor of gastritis, peptic ulcer disease, and gastric cancer (GC). Moreover, it was recently identified as a class I carcinogen, which affects the occurrence and progression of GC via inducing various oncogenic pathways. Therefore, identifying the HP-related key genes is crucial for understanding the oncogenic mechanisms and improving the outcomes of GC patients. We retrieved the list of HP-related gene sets from the Molecular Signatures Database. Based on the HP-related genes, unsupervised non-negative matrix factorization (NMF) clustering method was conducted to stratify TCGA-STAD, GSE15459, GSE84433 samples into two clusters with distinct clinical outcomes and immune infiltration characterization. Subsequently, two machine learning (ML) strategies, including support vector machine-recursive feature elimination (SVM-RFE) and random forest (RF), were employed to determine twelve hub HP-related genes. Beyond that, receiver operating characteristic and Kaplan-Meier curves further confirmed the diagnostic value and prognostic significance of hub genes. Finally, expression of HP-related hub genes was tested by qRT-PCR array and immunohistochemical images. Additionally, functional pathway enrichment analysis indicated that these hub genes were implicated in the genesis and progression of GC by activating or inhibiting the classical cancer-associated pathways, such as epithelial-mesenchymal transition, cell cycle, apoptosis, RAS/MAPK, etc. In the present study, we constructed a novel HP-related tumor classification in different datasets, and screened out twelve hub genes via performing the ML algorithms, which may contribute to the molecular diagnosis and personalized therapy of GC.

Datasets Construction and Development of QSAR Models for Predicting Micronucleus In Vitro and In Vivo Assay Outcomes

In silico (quantitative) structure-activity relationship modeling is an approach that provides a fast and cost-effective alternative to assess the genotoxic potential of chemicals. However, one of the limiting factors for model development is the availability of consolidated experimental datasets. In the present study, we collected experimental data on micronuclei in vitro and in vivo, utilizing databases and conducting a PubMed search, aided by text mining using the BioBERT large language model. Chemotype enrichment analysis on the updated datasets was performed to identify enriched substructures. Additionally, chemotypes common for both endpoints were found. Five machine learning models in combination with molecular descriptors, twelve fingerprints and two data balancing techniques were applied to construct individual models. The best-performing individual models were selected for the ensemble construction. The curated final dataset consists of 981 chemicals for micronuclei in vitro and 1309 for mouse micronuclei in vivo, respectively. Out of 18 chemotypes enriched in micronuclei in vitro, only 7 were found to be relevant for in vivo prediction. The ensemble model exhibited high accuracy and sensitivity when applied to an external test set of in vitro data. A good balanced predictive performance was also achieved for the micronucleus in vivo endpoint.

MAVEN: compound mechanism of action analysis and visualisation using transcriptomics and compound structure data in R/Shiny

BACKGROUND

Understanding the Mechanism of Action (MoA) of a compound is an often challenging but equally crucial aspect of drug discovery that can help improve both its efficacy and safety. Computational methods to aid MoA elucidation usually either aim to predict direct drug targets, or attempt to understand modulated downstream pathways or signalling proteins. Such methods usually require extensive coding experience and results are often optimised for further computational processing, making them difficult for wet-lab scientists to perform, interpret and draw hypotheses from.

RESULTS

To address this issue, we in this work present MAVEN (Mechanism of Action Visualisation and Enrichment), an R/Shiny app which allows for GUI-based prediction of drug targets based on chemical structure, combined with causal reasoning based on causal protein-protein interactions and transcriptomic perturbation signatures. The app computes a systems-level view of the mechanism of action of the input compound. This is visualised as a sub-network linking predicted or known targets to modulated transcription factors via inferred signalling proteins. The tool includes a selection of MSigDB gene set collections to perform pathway enrichment on the resulting network, and also allows for custom gene sets to be uploaded by the researcher. MAVEN is hence a user-friendly, flexible tool for researchers without extensive bioinformatics or cheminformatics knowledge to generate interpretable hypotheses of compound Mechanism of Action.

CONCLUSIONS

MAVEN is available as a fully open-source tool at https://github.com/laylagerami/MAVEN with options to install in a Docker or Singularity container. Full documentation, including a tutorial on example data, is available at https://laylagerami.github.io/MAVEN .

CBPDdb: a curated database of compounds derived from Coumarin-Benzothiazole-Pyrazole

The present article describes the building of a small-molecule web server, CBPDdb, employing R-shiny. For the generation of the web server, three compounds were chosen, namely coumarin, benzothiazole and pyrazole, and their derivatives were curated from the literature. The two-dimensional (2D) structures were drawn using ChemDraw, and the .sdf file was created employing Discovery Studio Visualizer v2017. These compounds were read on the R-shiny app using ChemmineR, and the dataframe consisting of a total of 1146 compounds was generated and manipulated employing the dplyr package. The web server is provided with JSME 2D sketcher. The descriptors of the compounds are obtained using propOB with a filter. The users can download the filtered data in the .csv and .sdf formats, and the entire dataset of a compound can be downloaded in .sdf format. This web server facilitates the researchers to screen plausible inhibitors for different diseases. Additionally, the method used in building the web server can be adapted for developing other small-molecule databases (web servers) in RStudio. Database URL: https://srampogu.shinyapps.io/CBPDdb_Revised/.

Revolutionizing Medicinal Chemistry: The Application of Artificial Intelligence (AI) in Early Drug Discovery

Artificial intelligence (AI) has permeated various sectors, including the pharmaceutical industry and research, where it has been utilized to efficiently identify new chemical entities with desirable properties. The application of AI algorithms to drug discovery presents both remarkable opportunities and challenges. This review article focuses on the transformative role of AI in medicinal chemistry. We delve into the applications of machine learning and deep learning techniques in drug screening and design, discussing their potential to expedite the early drug discovery process. In particular, we provide a comprehensive overview of the use of AI algorithms in predicting protein structures, drug-target interactions, and molecular properties such as drug toxicity. While AI has accelerated the drug discovery process, data quality issues and technological constraints remain challenges. Nonetheless, new relationships and methods have been unveiled, demonstrating AI's expanding potential in predicting and understanding drug interactions and properties. For its full potential to be realized, interdisciplinary collaboration is essential. This review underscores AI's growing influence on the future trajectory of medicinal chemistry and stresses the importance of ongoing synergies between computational and domain experts.

Comparative antioxidant activity and untargeted metabolomic analyses of cherry extracts of two Chinese cherry species based on UPLC-QTOF/MS and machine learning algorithms

P. pseudocerasus and P. tomentosa are the two native Chinese cherry species of high economic and ornamental worths. Little is known about the metabolic information of P. pseudocerasus and P. tomentosa. Effective means are lacking for distinguishing these two similar species. In this study, the differences in total phenolic content (TPC), total flavonoid content (TFC), and in vitro antioxidant activities in 21 batches of two species of cherries were compared. A comparative UPLC-QTOF/MS-based metabolomics coupled with three machine learning algorithms was established for differentiating the cherry species. The results demonstrated that P. tomentosa had higher TPC and TFC with average content differences of 12.07 times and 39.30 times, respectively, and depicted better antioxidant activity. Total of 104 differential compounds were identified by UPLC-QTOF/MS metabolomics. The major differential compounds were flavonoids, organooxygen compounds, and cinnamic acids and derivatives. Correlation analysis revealed differences in flavonoids content such as procyanidin B1 or isomer and (Epi)catechin. They could be responsible for differences in antioxidant activities between the two species. Among three machine learning algorithms, the prediction accuracy of support vector machine (SVM) was 85.7%, and those of random forest (RF) and back propagation neural network (BPNN) were 100%. BPNN exhibited better classification performance and higher prediction rate for all testing set samples than those of RF. The study herein found that P. tomentosa had higher nutritional value and biological functions, and thus considered for usage in health products. Machine models based on untargeted metabolomics can be effective tools for distinguishing these two species.

3DDPDs: describing protein dynamics for proteochemometric bioactivity prediction. A case for (mutant) G protein-coupled receptors

Proteochemometric (PCM) modelling is a powerful computational drug discovery tool used in bioactivity prediction of potential drug candidates relying on both chemical and protein information. In PCM features are computed to describe small molecules and proteins, which directly impact the quality of the predictive models. State-of-the-art protein descriptors, however, are calculated from the protein sequence and neglect the dynamic nature of proteins. This dynamic nature can be computationally simulated with molecular dynamics (MD). Here, novel 3D dynamic protein descriptors (3DDPDs) were designed to be applied in bioactivity prediction tasks with PCM models. As a test case, publicly available G protein-coupled receptor (GPCR) MD data from GPCRmd was used. GPCRs are membrane-bound proteins, which are activated by hormones and neurotransmitters, and constitute an important target family for drug discovery. GPCRs exist in different conformational states that allow the transmission of diverse signals and that can be modified by ligand interactions, among other factors. To translate the MD-encoded protein dynamics two types of 3DDPDs were considered: one-hot encoded residue-specific (rs) and embedding-like protein-specific (ps) 3DDPDs. The descriptors were developed by calculating distributions of trajectory coordinates and partial charges, applying dimensionality reduction, and subsequently condensing them into vectors per residue or protein, respectively. 3DDPDs were benchmarked on several PCM tasks against state-of-the-art non-dynamic protein descriptors. Our rs- and ps3DDPDs outperformed non-dynamic descriptors in regression tasks using a temporal split and showed comparable performance with a random split and in all classification tasks. Combinations of non-dynamic descriptors with 3DDPDs did not result in increased performance. Finally, the power of 3DDPDs to capture dynamic fluctuations in mutant GPCRs was explored. The results presented here show the potential of including protein dynamic information on machine learning tasks, specifically bioactivity prediction, and open opportunities for applications in drug discovery, including oncology.