AI and ML-based risk assessment of chemicals: predicting carcinogenic risk from chemical-induced genomic instability

Advances in pharmacological research on myocardial remodeling agents: A decade in review

Myocardial remodeling, a complex adaptive response to pathological stimuli, plays a pivotal role in the progression of various cardiovascular diseases, including arrhythmias and heart failure. Significant progress has been made in understanding the molecular mechanisms of myocardial remodeling and exploring the efficacy of single and multicomponent agents. Myocardial remodeling entails a complex signaling network that incorporates certain identified critical "bridge nodes," which are also significant drug targets in classical pharmacological approaches. Nonetheless, some multicomponent drugs that have undergone clinical trials, such as Qili Qiangxin capsules, may suggest the presence of a new and feasible drug development path. The potential of multicomponent agents lies in their ability to achieve a synergistic effect through the coordinated regulation of multiple up- and downstream molecules in signaling pathways involved in myocardial remodeling. However, the development of multicomponent agents presents several challenges, such as identifying active compounds, defining their mechanisms of action, and determining the optimal proportions of each component. Delving deeper into the synergistic, multitarget effects of multicomponent agents in the realm of future research holds the promise to chart a new course toward the development of more effective and safer therapeutic strategies for managing myocardial remodeling and its associated cardiovascular diseases.

Explicating the transformative role of artificial intelligence in designing targeted nanomedicine

INTRODUCTION

Artificial intelligence (AI) has emerged as a transformative force in nanomedicine, revolutionizing drug delivery, diagnostics, and personalized treatment. While nanomedicine offers precise targeted drug delivery and reduced toxic effects, its clinical translation is hindered by biological complexity, unpredictable in vivo behavior, and inefficient trial-and-error approaches.

AREAS COVERED

This review covers the application of AI and Machine Learning (ML) across the nanomedicine development pipeline, starting from drug and target identification to nanoparticle design, toxicity prediction, and personalized dosing. Different AI/ML models like QSAR, MTK-QSBER, and Alchemite, along with data sources and high-throughput screening methods, have been explored. Real-world applications are critically discussed, including AI-assisted drug repurposing, controlled-release formulations, and cancer-specific delivery systems.

EXPERT OPINION

AI has emerged as an essential component in designing next-generation nanomedicine. Efficiently handling multidimensional datasets, optimizing formulations, and personalizing treatment regimens, it has sped up the innovation process. However, challenges like data heterogeneity, model transparency, and regulatory gaps remain. Addressing these hurdles through interdisciplinary efforts and emerging innovations like explainable AI and federated learning will pave the way for the clinical translation of AI-driven nanomedicine.

Transforming beef quality through healthy breeding: a strategy to reduce carcinogenic compounds and enhance human health: a review

The presence of carcinogenic substances in beef poses a significant risk to public health, with far-reaching implications for consumer safety and the meat production industry. Despite advancements in food safety measures, traditional breeding methods have proven inadequate in addressing these risks, revealing a substantial gap in knowledge. This review aims to fill this gap by evaluating the potential of healthy breeding techniques to significantly reduce the levels of carcinogenic compounds in beef. We focus on elucidating the molecular pathways that contribute to the formation of key carcinogens, such as heterocyclic amines (HCAs) and polycyclic aromatic hydrocarbons (PAHs), while exploring the transformative capabilities of advanced genomic technologies. These technologies include genomic selection, CRISPR/Cas9, base editing, prime editing, and artificial intelligence-driven predictive models. Additionally, we examine multi-omics approaches to gain new insights into the genetic and environmental factors influencing carcinogen formation. Our findings suggest that healthy breeding strategies could markedly enhance meat quality, thereby offering a unique opportunity to improve public health outcomes. The integration of these innovative technologies into breeding programs not only provides a pathway to safer beef production but also fosters sustainable livestock management practices. The improvement of these strategies, along with careful consideration of ethical and regulatory challenges, will be crucial for their effective implementation and broader impact.

Association between hemoglobin glycation index and the risk of cardiovascular disease in early-stage cardiovascular-kidney-metabolic syndrome: evidence from the China health and retirement longitudinal study

Background

Cardiovascular-kidney-metabolic (CKM) syndrome reflects the interplay among metabolic risk factors, chronic kidney disease, and cardiovascular disease (CVD). While the hemoglobin glycation index (HGI) has demonstrated prognostic value for cardiovascular events, its clinical utility remains unexplored in early-stage CKM syndrome.

Methods

Participants with early-stage CKM syndrome (stage 0-3) were recruited from the China Health and Retirement Longitudinal Study (CHARLS) database. Using k-means clustering analysis, the participants were classified according to the values of HGI measured at baseline and 3 years later, respectively. The primary outcome was self-reported CVD during the follow-up of at least 3 years. Extreme gradient boosting (XGBoost) algorithm was applied, with the Shapley additive explanation (SHAP) method used to determine feature importance. Multivariable logistics proportional regression analysis the association between HGI and CVD, and restricted cubic spline (RCS) regression assessed potential nonlinear relationships.

Results

A total of 4676 eligible participants were included in the final analysis, with 944 (20.19%) progressed to CVD within 10 years. Among the baseline clinical features, HGI ranked the second for the impact on the occurrence of CVD. According to the changes of HGI values, the participants were clustered into 4 classes. Compared to the class 1 with lower level of HGI, higher risk of CVD was observed in class 3 (adjusted OR: 1.34, 95% CI: 1.06-1.69, P = 0.013) and class 4 (adjusted OR: 1.65, 95% CI: 1.01-2.45, P = 0.025) with higher and rapidly increasing level of HGI. RCS analysis showed cumulative HGI and the risk of CVD were linearly related (P for nonlinearity = 0.967). Subgroup analyses confirmed the stability of the association. Additionally, the SHAP plot revealed that HGI were the more important features than traditional risk factors such as FBG for predicting CVD.

Conclusion

HGI is associated with an elevated risk of CVD in participants with early-stage CKM syndrome. HGI can serve as an independent biomarker for guiding clinical decision-making and managing patient outcomes.

Do Gut Microbiomes Shift After Bariatric Surgery? A Literature Review

The human gastrointestinal tract is estimated to be populated by 38 trillion bacteria from almost 1000 different species. The dominant phyla are Firmicutes, Bacteroidetes, Actinobacteria, and Proteobacteria. However, the diversity and amount of gut microbiota depends on various factors. The importance of gut microbiota is increasingly noticed due to the influence of bacteria on energy homeostasis, the immune system, general health, and metabolism. Bariatric surgery is the mainstay treatment for patients with obesity. Two of the most common mechanisms are reducing gastric volume and decreasing ghrelin secretion. This literature review aims to depict the diverse impact of different bariatric procedures on gut microbiota. The original research papers were collected from the PubMed, Cochrane, and Elsevier databases. This literature review is focused on human studies. However, several references include animal models, specifically rats and germ-free mice. The findings suggest that bariatric surgery causes changes in the diversity of gut microbiota. However, the specificity of the changes depends on the type of bariatric surgery. The Firmicutes/Bacteroidetes ratio is elevated in the groups of patients with obesity compared to lean individuals. Bariatric surgery lowers the ratios impact on metabolism and energy absorption. Gut microbiota produces short-chain fatty acids, of which butyrate is responsible for strengthening the gut barrier, and acetate is correlated with fat deposition and lipogenesis. Moreover, changes in short-chain fatty acids influence insulin resistance and inflammation. In conclusion, bariatric surgery impacts gut microbiota, resulting in metabolic changes in patients, and the need for further study regarding long-term microbiota alterations post-operation is notable.

Predicting biomolecule adsorption on nanomaterials: a hybrid framework of molecular simulations and machine learning

The adsorption of biomolecules on the surface of nanomaterials (NMs) is a critical determinant of their behavior, toxicity, and efficacy in biological systems. Experimental testing of these phenomena is often costly or complicated. Computational approaches, particularly the integrating methods of various theoretical levels, can provide essential insights into nano-bio interactions and bio-corona formation, facilitating the efficient design of nanomaterials for biomedical applications. This study presents a hybrid, meta-modeling approach that integrates physics-based molecular modeling with machine learning algorithms to predict the interaction energy between NMs and biomolecules extracted from the potential of mean force (PMF). Novel descriptors for the surface properties of NMs are developed and combined with structural descriptors of biomolecules to derive quantitative structure-property relationships (QSPRs). The developed QSPR model (training set: R2 = 0.84, RMSE = 1.52, Rcv2 = 0.83, and RMSEcv = 1.34; validation set: R2 = 0.70, RMSE = 1.94, and Rcv2 = 0.72, RMSEcv = 1.88) helps in understanding and predicting the interactions between NMs (including carbon-based materials, metals, metal oxides, metalloids, and cadmium selenide) and biomolecules (including amino acids and amino acid derivatives). The model facilitates safe and sustainable design of nanomaterials for various applications, particularly for nanomedicine, by providing insight into nano-bio interactions, identification of toxicity risk and optimizing functionalization for safety according to the risk mitigation policy of regulatory authorities. Additionally, a dedicated application has been developed and is available on GitHub, enabling researchers to analyze the surface properties of nanomaterials belonging to the above-mentioned groups of NMs.

Innovative nanoparticle strategies for treating oral cancers

Conventional therapies for oral squamous cell carcinoma (OSCC), a serious worldwide health problem, are frequently constrained by inadequate targeting and serious side effects. Drug delivery systems (DDS) based on nanoparticles provide a possible substitute by improving drug stability, target accuracy, and lowering toxicity. By addressing issues like irregular vasculature and thick tumor matrices, these methods allow for more effective medication administration. For instance, the delivery of cisplatin via liposomes, as opposed to free drug formulations, results in a 40% improvement in tumor suppression. Likewise, compared to traditional techniques, poly (lactic-co-glycolic acid) (PLGA) nanoparticles can produce up to 2.3 times more intertumoral drug accumulation. These platforms have effectively administered natural substances like curcumin and chemotherapeutics like paclitaxel, enhancing therapeutic results while reducing adverse effects. Despite their promise, several types of nanoparticles have drawbacks. For example, PLGA nanoparticles have scaling issues because of their complicated production, whereas liposomes are quickly removed from circulation. In preclinical investigations, functionalized nanoparticles-like EGFR-targeted gold nanoparticles-improve selectivity and effectiveness by obtaining up to 90% receptor binding. By preferentially accumulating in tumors via the increased permeability and retention (EPR) effect, nanoparticles also improve immunotherapy and radiation. Mechanistically, they increase the death of cancer cells by causing DNA damage, interfering with cell division, and producing reactive oxygen species (ROS). There are still issues with toxicity (such as the buildup of metallic nanoparticles in the liver) and large-scale manufacturing. Nevertheless, developments in multifunctional platforms and stimuli-responsive nanoparticles show promise for getting over these obstacles. These developments open the door to more individualized and successful OSCC therapies.

Nanoimmunotherapy: the smart trooper for cancer therapy

Immunotherapy has gathered significant attention and is now a widely used cancer treatment that uses the body's immune system to fight cancer. Despite initial successes, its broader clinical application is hindered by limitations such as heterogeneity in patient response and challenges associated with the tumor immune microenvironment. Recent advancements in nanotechnology have offered innovative solutions to these barriers, providing significant enhancements to cancer immunotherapy. Nanotechnology-based approaches exhibit multifaceted mechanisms, including effective anti-tumor immune responses during tumorigenesis and overcoming immune suppression mechanisms to improve immune defense capacity. Nanomedicines, including nanoparticle-based vaccines, liposomes, immune modulators, and gene delivery systems, have demonstrated the ability to activate immune responses, modulate tumor microenvironments, and target specific immune cells. Success metrics in preclinical and early clinical studies, such as improved survival rates, enhanced tumor regression, and elevated immune activation indices, highlight the promise of these technologies. Despite these achievements, several challenges remain, including scaling up manufacturing, addressing off-target effects, and navigating regulatory complexities. The review emphasizes the need for interdisciplinary approaches to address these barriers, ensuring broader clinical adoption. It also provides insights into interdisciplinary approaches, advancements, and the transformative potential of nano-immunotherapy and promising results in checkpoint inhibitor delivery, nanoparticle-mediated photothermal therapy, immunomodulation as well as inhibition by nanoparticles and cancer vaccines.

An interpreting machine learning models to predict amputation risk in patients with diabetic foot ulcers: a multi-center study

Background

Diabetic foot ulcers (DFUs) constitute a significant complication among individuals with diabetes and serve as a primary cause of nontraumatic lower-extremity amputation (LEA) within this population. We aimed to develop machine learning (ML) models to predict the risk of LEA in DFU patients and used SHapley additive explanations (SHAPs) to interpret the model.

Methods

In this retrospective study, data from 1,035 patients with DFUs at Sun Yat-sen Memorial Hospital were utilized as the training cohort to develop the ML models. Data from 297 patients across multiple tertiary centers were used for external validation. We then used least absolute shrinkage and selection operator analysis to identify predictors of amputation. We developed five ML models [logistic regression (LR), support vector machine (SVM), random forest (RF), k-nearest neighbors (KNN) and extreme gradient boosting (XGBoost)] to predict LEA in DFU patients. The performance of these models was evaluated using several metrics, including the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), precision, recall, accuracy, and F1 score. Finally, the SHAP method was used to ascertain the significance of the features and to interpret the model.

Results

In the final cohort comprising 1332 individuals, 600 patients underwent amputation. Following hyperparameter optimization, the XGBoost model achieved the best amputation prediction performance with an accuracy of 0.94, a precision of 0.96, an F1 score of 0.94 and an AUC of 0.93 for the internal validation set on the basis of the 17 features. For the external validation set, the model attained an accuracy of 0.78, a precision of 0.93, an F1 score of 0.78, and an AUC of 0.83. Through SHAP analysis, we identified white blood cell counts, lymphocyte counts, and blood urea nitrogen levels as the model's main predictors.

Conclusion

The XGBoost algorithm-based prediction model can be used to dynamically estimate the risk of LEA in DFU patients, making it a valuable tool for preventing the progression of DFUs to amputation.

Influence of experimental variables on spheroid attributes

The adoption of three-dimensional (3D) cell culture systems represents a critical advancement in biomedical research, better mimicking complex 3D tissue environments than traditional two-dimensional (2D) models. However, variability in experimental outcomes has limited their reproducibility and clinical translation. Here, we systematically analyzed 32,000 spheroid images to identify key parameters influencing 3D model reliability. Our large-scale analysis revealed that oxygen levels significantly affect spheroid size and necrosis, while media composition (e.g., glucose and calcium concentrations) and serum levels (0-20%) critically regulate cell viability and structural integrity. For instance, spheroids cultured in 3% oxygen exhibited reduced dimensions and increased necrosis, whereas serum concentrations above 10% promoted dense spheroid formation with distinct necrotic and proliferative zones. By integrating single-cell RNA sequencing and automated image analysis, we uncovered dynamic gene expression patterns linked to spheroid maturation and hypoxia. These findings provide actionable guidelines for standardizing 3D culture protocols, addressing critical reproducibility challenges. Our work establishes a robust framework to enhance the reliability of 3D models in drug testing, personalized medicine, and tumor biology, facilitating their broader adoption in translational research.

Large Language Models as Tools for Molecular Toxicity Prediction: AI Insights into Cardiotoxicity

The importance of drug toxicity assessment lies in ensuring the safety and efficacy of the pharmaceutical compounds. Predicting toxicity is crucial in drug development and risk assessment. This study compares the performance of GPT-4 and GPT-4o with traditional deep-learning and machine-learning models, WeaveGNN, MorganFP-MLP, SVC, and KNN, in predicting molecular toxicity, focusing on bone, neuro, and reproductive toxicity. The results indicate that GPT-4 is comparable to deep-learning and machine-learning models in certain areas. We utilized GPT-4 combined with molecular docking techniques to study the cardiotoxicity of three specific targets, examining traditional Chinese medicinal materials listed as both food and medicine. This approach aimed to explore the potential cardiotoxicity and mechanisms of action. The study found that components in Black Sesame, Ginger, Perilla, Sichuan Pagoda Tree Fruit, Galangal, Turmeric, Licorice, Chinese Yam, Amla, and Nutmeg exhibit toxic effects on cardiac target Cav1.2. The docking results indicated significant binding affinities, supporting the hypothesis of potential cardiotoxic effects.This research highlights the potential of ChatGPT in predicting molecular properties and its significance in medicinal chemistry, demonstrating its facilitation of a new research paradigm: with a data set, high-accuracy learning models can be generated without requiring computational knowledge or coding skills, making it accessible and easy to use.

Unveiling the Broad-Spectrum Efficacy of Volatile Terpenes to Fight Against SARS-COV-2-Associated Mucormycosis

Mucormycosis, a life-threatening fungal infection caused by Mucorales, affects immunocompromised patients, especially SARS-CoV-2 ones. Existing antifungal therapies, like amphotericin B, have serious health risks. The current study reviews the literature regarding an overview of SARS-CoV-2-associated mucormycosis, along with different terpenes from diverse edible sources, such as basil, ginger, and clove, which are detected till June 2024. The antifungal potential of collected terpenes, their classifications, mechanisms of action, minimum inhibitory concentration (MIC) values, and future perspectives are discussed here. The search identified 89 fungicidal volatile terpenes, belonging to about 26 families, from which 45 were selected for further in silico analysis. The results highlighted oryzalexin B (60), oryzalexin D (62), carvacrol (4), mansorin B (66), muzigadial (86), and lubimin (80) as potential antifungal agents against lanosterol 14α-demethylase, CotH3, and mucoricin as potential targets in Mucorales. CotH3 is crucial for activating GRP-78, a host co-receptor for ACE2, which is essential for SARS-CoV-2 pathogenesis. Additionally, carvacrol was in vitro investigated against Mucor racemosus via the agar diffusion method, giving an MIC value of 1 mg/mL, compared to 0.1 mg/mL of ketoconazole. This study suggests promising potential for volatile terpenes in combating SARS-CoV-2-associated mucormycosis, with the need for further refined in vitro and in vivo studies to establish clinical efficacy.