AI-Assisted Hypothesis Generation to Address Challenges in Cardiotoxicity Research: Simulation Study Using ChatGPT With GPT-4o (Preprint) DOI
Yilan Li,

Tengda Gu,

Chengyuan Yang

и другие.

Опубликована: Сен. 5, 2024

BACKGROUND Cardiotoxicity is a major concern in heart disease research because it can lead to severe cardiac damage, including failure and arrhythmias. OBJECTIVE This study aimed explore the ability of ChatGPT with GPT-4o generate innovative hypotheses address 5 challenges cardiotoxicity research: complexity mechanisms, variability among patients, lack detection sensitivity, reliable biomarkers, limitations animal models. METHODS was used multiple for each challenges. These were then independently evaluated by 3 experts novelty feasibility. subsequently selected most promising hypothesis from category provided detailed experimental plans, background, rationale, design, expected outcomes, potential pitfalls, alternative approaches. RESULTS generated 96 hypotheses, which 13 (14%) rated as highly novel 62 (65%) moderately novel. The average group score 3.85 indicated strong level innovation these hypotheses. Literature searching identified at least 1 relevant publication 28 (29%) included using single-cell RNA sequencing understand cellular heterogeneity, integrating artificial intelligence genetic profiles personalized risk prediction, applying machine learning electrocardiogram data enhanced multi-omics approaches biomarker discovery, developing 3D bioprinted tissues overcome Our group’s evaluation 30 dimensions plans revealed consistent strengths approaches, (20/30, 67%) receiving scores ≥4 areas. While generally well received, designs often deemed overly ambitious, highlighting need more practical considerations. CONCLUSIONS demonstrates that potentially impactful overcoming critical research. findings suggest intelligence–assisted generation could play crucial role advancing field cardiotoxicity, leading accurate predictions, earlier detection, better patient outcomes.

Язык: Английский

Artificial Intelligence (AI) Applications in Drug Discovery and Drug Delivery: Revolutionizing Personalized Medicine DOI Creative Commons
Dolores R. Serrano,

Francis C. Luciano,

Brayan J. Anaya

и другие.

Pharmaceutics, Год журнала: 2024, Номер 16(10), С. 1328 - 1328

Опубликована: Окт. 14, 2024

Artificial intelligence (AI) encompasses a broad spectrum of techniques that have been utilized by pharmaceutical companies for decades, including machine learning, deep and other advanced computational methods. These innovations unlocked unprecedented opportunities the acceleration drug discovery delivery, optimization treatment regimens, improvement patient outcomes. AI is swiftly transforming industry, revolutionizing everything from development to personalized medicine, target identification validation, selection excipients, prediction synthetic route, supply chain optimization, monitoring during continuous manufacturing processes, or predictive maintenance, among others. While integration promises enhance efficiency, reduce costs, improve both medicines health, it also raises important questions regulatory point view. In this review article, we will present comprehensive overview AI's applications in covering areas such as discovery, safety, more. By analyzing current research trends case studies, aim shed light on transformative impact industry its broader implications healthcare.

Язык: Английский

Процитировано

55
Pharmacology of Epitranscriptomic Modifications: Decoding the Therapeutic Potential of RNA Modifications in Drug Resistance DOI
Abdullah Alkhammash

European Journal of Pharmacology, Год журнала: 2025, Номер 994, С. 177397 - 177397

Опубликована: Фев. 18, 2025

Язык: Английский

Процитировано

0
A comprehensive review of neurotransmitter modulation via artificial intelligence: A new frontier in personalized neurobiochemistry DOI

Jaleh Bagheri Hamzyan Olia,

Arasu Raman, Chou‐Yi Hsu

и другие.

Computers in Biology and Medicine, Год журнала: 2025, Номер 189, С. 109984 - 109984

Опубликована: Март 14, 2025

Язык: Английский

Процитировано

0
Exploring Therapeutic Paradigm Focusing on Genes, Proteins, and Pathways to Combat Leprosy and Tuberculosis: A Network Medicine and Drug Repurposing Approach DOI Creative Commons
Mohd Imran, Ahmed Subeh Alshrari,

Md Golam Hafiz

и другие.

Journal of Infection and Public Health, Год журнала: 2025, Номер unknown, С. 102763 - 102763

Опубликована: Март 1, 2025

Leprosy and tuberculosis caused by Mycobacterium leprae tuberculosis, respectively, are chronic infections with significant public health implications. While leprosy affects the skin peripheral nerves primarily targets lungs, both diseases involve systemic immune responses. This study integrates transcriptomic analysis cheminformatics molecular dynamics simulations to identify mechanisms potential therapeutic targets. Transcriptomic datasets were analyzed dysregulated genes pathways. Pathway enrichment tissue-specific bulk RNA-seq expression analyses provided biological context. System biology networks revealed regulatory hub docking studies evaluated CHEMBL compounds as therapeutics. Molecular (MD) assessed stability of top ligand-protein complexes through RMSD RMSF MM-GBSA free energy calculations. Gene identified 13 core genes, including HSP90AA1 MAPK8IP3 ZMPSTE24. Tissue-specific localized pivotal lung tissues cells highly expressed in alveolar macrophages epithelial cells. gene emerged a central 96 interactions involved stress response Docking CHEMBL3653862 CHEMBL3653884 strong binding affinities (-10.16 -12.69 kcal/mol) interacting Asp93 Tyr139. MD confirmed fluctuations within 2.1-3.5 Å values supporting stability. identifies drug target tuberculosis. Findings support host-directed therapy approaches highlight importance computational modeling accelerating discovery. The provides foundation for future experimental validation, vitro vivo testing advance repurposing strategies these infections.

Язык: Английский

Процитировано

0
Graph-Theoretic and Computational Analysis of QSAR Molecular Descriptors for Single Chain Diamond Silicates DOI Creative Commons
Sajeev Erangu Purath Mohankumar, Ponnurengam Malliappan Sivakumar,

S. Priyatharshni

и другие.

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Март 28, 2025

Abstract This study presents a comprehensive graph-theoretic and computational analysis of Quantitative Structure-Activity Relationship (QSAR) molecular descriptors for Single Chain Diamond Silicates (CSn), crucial class silicate structures defined by their unique connectivity SiO₄ tetrahedra. Various descriptors, including the Atom Bond Connectivity (ABC) Index, Sum (ABS) Augmented Zagreb Index (AZI), (SZI), Geometric Arithmetic (GAI), (AGI), are examined to assess structural, electronic, thermodynamic properties. Through mathematical formulations modelling, this quantifies complexity, stability, patterns CSn, enhancing predictive capabilities QSAR models. The findings underscore significance in characterising networks, with applications spanning materials science, catalysis, geochemistry.

Язык: Английский

Процитировано

0
A Review of In Silico and In Vitro Approaches in the Fight Against Carbapenem‐Resistant Enterobacterales DOI Creative Commons

Muhammad Absar,

Abdul Rahman Zaidah, Amer Mahmood

и другие.

Journal of Clinical Laboratory Analysis, Год журнала: 2025, Номер unknown

Опубликована: Апрель 9, 2025

ABSTRACT Objectives The rise in carbapenem‐resistant Enterobacterales (CRE) has reinforced the global quest for developing effective therapeutics. Traditional drug discovery approaches have been inadequate overcoming this challenge due to their resource and time constraints. Methods English literature was searched by structured queries related our review between January 1, 2020, December 31, 2024. Results key resistance mechanisms CRE, such as enzymatic hydrolysis, decreased permeability, efflux pump overexpression, examined review. Computational technologies become pivotal discovering novel antimicrobial agents with improved accuracy efficiency. Besides this, highlights advances structure‐ ligand‐based identifying potential drugs against CRE. Recent studies demonstrating use of silico techniques develop targeted CRE also explored. Moreover, underscores significance integrating both vitro counter Enterobacterales, supported latest studies. However, these promising computational a few major drawbacks, lack standardized parameterization, potentially false positives, complexity clinical translations. regulatory barriers restrict progress new antimicrobials market approval. Conclusion inhibitor is gaining popularity, it can be expedited refining them reliable validation. innovative hybrid need hour tackle mitigate threat resistance.

Язык: Английский

Процитировано

0
Peptide Property Prediction for Mass Spectrometry Using AI: An Introduction to State of the Art Models DOI Creative Commons

Jesse Angelis,

Eva Ayla Schröder, Zixuan Xiao

и другие.

PROTEOMICS, Год журнала: 2025, Номер unknown

Опубликована: Апрель 10, 2025

ABSTRACT This review explores state of the art machine learning and deep models for peptide property prediction in mass spectrometry‐based proteomics, including, but not limited to, predicting digestibility, retention time, charge distribution, collisional cross section, fragmentation ion intensities, detectability. The combination these enables only silico generation spectral libraries also finds many additional use cases design targeted assays or data‐driven rescoring. serves as both an introduction newcomers update experienced researchers aiming to develop accessible reproducible predictions. Key limitations current models, including difficulties handling diverse post‐translational modifications instrument variability, highlight need large‐scale, harmonized datasets, standardized evaluation metrics benchmarking.

Язык: Английский

Процитировано

0
Exploring Gingerol Substructures as Potential SARS‐CoV‐2 RBD Inhibitors: An Integrated Machine Learning and In Silico Approach DOI
D. R. Sherin,

S. R. Linda,

A. Akhila

и другие.

ChemistrySelect, Год журнала: 2025, Номер 10(15)

Опубликована: Апрель 1, 2025

Abstract The ongoing COVID‐19 pandemic has underscored the urgent need for effective antiviral therapies. This study presents a novel approach that integrates machine learning (ML) and in silico techniques to identify potential inhibitors targeting receptor‐binding domain (RBD) of SARS‐CoV‐2. A Random Forest (RF) regression model achieved an R 2 value 0.82, accurately predicting Vina scores 988 gingerol substructures. Subsequent virtual screening using PyRx identified 14 promising candidates with docking lower than reference compound, arbidol. Pharmacokinetic analysis via BOILED‐Egg Bioavailability Radar revealed four compounds‐ G4 , G5 G11 G13 exhibit favorable human intestinal absorption (HIA) drug‐like properties, as P‐glycoprotein (P‐gp) non‐substrate. Docking studies indicated significant interactions characterized by hydrogen bonding hydrophobic contacts. Molecular dynamics (MD) simulations demonstrated stability ligand‐protein complexes, showing maximum root mean square deviation (RMSD) 3 Å low fluctuation (RMSF) values 1.5 across interacting residues, highlighting robustness each ligand within RBD binding pocket. Additionally, electrostatic (ESP) plots highly electronegative regions around oxygen atoms, likely engage stabilizing positively charged or polar residues. Furthermore, assessments against mutated RBDs SARS‐CoV‐2, ranging from −7.7 −8.8 kcal mol −1 indicate strong affinity protein, suggesting these compounds remain various mutations. Our provides streamlined methodology identifying inhibitors, paving way further experimental validation.

Язык: Английский

Процитировано

0
Advances in Oral Solid Drug Delivery Systems: Quality by Design Approach in Development of Controlled Release Tablets DOI Creative Commons

Prachi Atre,

Syed A. A. Rizvi

BioChem, Год журнала: 2025, Номер 5(2), С. 9 - 9

Опубликована: Апрель 25, 2025

Oral solid drug delivery continues to be the gold standard in pharmaceutical formulations, owing its cost-effectiveness, ease of administration, and high patient compliance. Tablets, most widely used dosage form, are favored for their precise dosing, simplicity, economic advantages. Among these, controlled release (CR) tablets stand out ability maintain consistent levels, enhance therapeutic efficacy, reduce dosing frequency, thereby improving adherence treatment outcomes. A well-designed CR system ensures a sustained targeted supply, optimizing performance while minimizing side effects. This review delves into latest advancements with particular focus on hydrophilic matrix systems, which regulate through mechanisms such as swelling, diffusion, erosion. These systems rely variety polymers drug-retarding agents achieve tailored profiles. Recent breakthroughs crystal engineering polymer science have further enhanced solubility bioavailability, addressing critical challenges associated poorly soluble drugs. In terms manufacturing, direct compression has emerged efficient method producing tablets, streamlining production ensuring release. The integration Quality by Design framework been instrumental product systematically linking formulation process variables patient-centric quality attributes. advent cutting-edge technologies artificial intelligence 3D printing is revolutionizing field formulations. AI enables predictive modeling data-driven optimization profiles, facilitates development personalized medicines highly customizable kinetics. innovations paving way more patient-specific therapies. However, regulatory hurdles, patent constraints, need robust vivo validation remain significant barriers widespread adoption these advanced technologies. succinct underscores synergistic traditional emerging strategies tablets. It highlights potential co-crystal particularly those produced via compression, improve adherence, deliver superior By bridging gap between established practices innovative approaches, this poised address unmet clinical needs advance future oral delivery.

Язык: Английский

Процитировано

0
Computational Approaches for PPARγ Inhibitor Development: Recent Advances and Perspectives DOI Creative Commons
Ayanda M. Magwenyane, Hezekiel M. Kumalo

ChemistryOpen, Год журнала: 2025, Номер unknown

Опубликована: Май 6, 2025

The development of peroxisome proliferator‐activated receptor gamma (PPARγ) inhibitors has attracted significant interest for treating metabolic disorders, cancer, and inflammatory diseases. This review highlights the crucial role computational modelling in advancing PPARγ inhibitor development, emphasizing how these techniques streamline identification, optimization, evaluation new drug candidates. Key methods include molecular docking, QSAR, dynamics simulations, which enhance efficiency accuracy design. Computational deepened our understanding binding mechanisms conformational dynamics, allowing researchers to predict optimize ligand‐receptor complex stability. Despite advancements, challenges remain, such as improving predictions pharmacokinetic properties (ADME) evaluate drug‐like qualities. In conclusion, significantly enhanced discovery offering opportunities address Continued refinement models, combined with experimental validation emerging technologies, is overcoming current limitations achieving successful clinical outcomes.

Язык: Английский

Процитировано

0