Computer-Aided Drug Design and Drug Discovery: A Prospective Analysis

Pharmaceuticals, Год журнала: 2023, Номер 17(1), С. 22 - 22

Опубликована: Дек. 22, 2023

In the dynamic landscape of drug discovery, Computer-Aided Drug Design (CADD) emerges as a transformative force, bridging realms biology and technology. This paper overviews CADDs historical evolution, categorization into structure-based ligand-based approaches, its crucial role in rationalizing expediting discovery. As CADD advances, incorporating diverse biological data ensuring privacy become paramount. Challenges persist, demanding optimization algorithms robust ethical frameworks. Integrating Machine Learning Artificial Intelligence amplifies predictive capabilities, yet considerations scalability challenges linger. Collaborative efforts global initiatives, exemplified by platforms like Open-Source Malaria, underscore democratization The convergence with personalized medicine offers tailored therapeutic solutions, though dilemmas accessibility concerns must be navigated. Emerging technologies quantum computing, immersive technologies, green chemistry promise to redefine future CADD. trajectory CADD, marked rapid advancements, anticipates accuracy, addressing biases AI, sustainability metrics. concludes highlighting need for proactive measures navigating ethical, technological, educational frontiers shape healthier, brighter

Язык: Английский

---

Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening

Journal of Chemical Information and Modeling, Год журнала: 2025, Номер unknown

Опубликована: Янв. 17, 2025

Molecular Docking is a critical task in structure-based virtual screening. Recent advancements have showcased the efficacy of diffusion-based generative models for blind docking tasks. However, these do not inherently estimate protein–ligand binding strength thus cannot be directly applied to screening Protein–ligand scoring functions serve as fast and approximate computational methods evaluate between protein ligand. In this work, we introduce normalized mixture density network (NMDN) score, deep learning (DL)-based function probability distribution distances residues ligand atoms. The NMDN score addresses limitations observed existing DL performs robustly both pose selection Additionally, incorporate an interaction module predict experimental affinity fully utilize learned representations. Finally, present end-to-end protocol named DiffDock-NMDN. For each pair, employ DiffDock sample multiple poses, followed by utilizing select optimal pose, estimating using functions. Our achieves average enrichment factor 4.96 on LIT-PCBA data set, proving effective real-world drug discovery scenarios where binder information limited. This work only presents robust DL-based with superior capabilities but also offers benchmarks guide future development.

Язык: Английский

---

Emerging Trends in Bioinspired Superhydrophobic and Superoleophobic Sustainable Surfaces

Advanced Materials, Год журнала: 2025, Номер unknown

Опубликована: Фев. 18, 2025

Abstract Inspired by nature's ability to master materials for performance and sustainability, biomimicry has enabled the creation of bioinspired structural color, superadhesion, hydrophobicity hydrophilicity, among many others. This review summarizes emerging trends in novel sustainable fluorocarbon‐free designs creating superhydrophobic superoleophobic surfaces. It discusses methods, challenges, future directions, alongside impact computational modeling artificial intelligence accelerating experimental development more surface materials. While significant progress is made materials, surfaces remain a challenge. However, bioinspiration techniques supported platforms are paving way new renewable biodegradable repellent that meet environmental standards without sacrificing performance. Nevertheless, despite concerns, policies, several still continue apply fluorination other environmentally harmful achieve required standard repellency. As discussed this critical review, paradigm integrates advanced characterization, nanotechnology, additive manufacturing, modeling, coming, generate with tailored superhydrophobicity superoleophobicity while adhering standards.

Язык: Английский

---

Harnessing omics data for drug discovery and development in ovarian aging

Human Reproduction Update, Год журнала: 2025, Номер unknown

Опубликована: Фев. 20, 2025

Ovarian aging occurs earlier than the of many other organs and has a lasting impact on women's overall health well-being. However, effective interventions to slow ovarian remain limited, primarily due an incomplete understanding underlying molecular mechanisms drug targets. Recent advances in omics data resources, combined with innovative computational tools, are offering deeper insight into complexities aging, paving way for new opportunities discovery development. This review aims synthesize expanding multi-omics data, spanning genome, transcriptome, proteome, metabolome, microbiome, related from both tissue-level single-cell perspectives. We will specially explore how analysis these emerging datasets can be leveraged identify novel targets guide therapeutic strategies slowing reversing aging. conducted comprehensive literature search PubMed database using range relevant keywords: age at natural menopause, premature insufficiency (POI), diminished reserve (DOR), genomics, transcriptomics, epigenomics, DNA methylation, RNA modification, histone proteomics, metabolomics, lipidomics, single-cell, genome-wide association studies (GWAS), whole-exome sequencing, phenome-wide (PheWAS), Mendelian randomization (MR), epigenetic target, machine learning, artificial intelligence (AI), deep multi-omics. The was restricted English-language articles published up September 2024. Multi-omics have uncovered key driving including damage repair deficiencies, inflammatory immune responses, mitochondrial dysfunction, cell death. By integrating researchers critical regulatory factors across various biological levels, leading potential Notable examples include genetic such as BRCA2 TERT, like Tet FTO, metabolic sirtuins CD38+, protein BIN2 PDGF-BB, transcription FOXP1. advent cutting-edge technologies, especially technologies spatial provided valuable insights guiding treatment decisions become powerful tool aimed mitigating or As technology advances, integration AI models holds more accurately predict candidate convergence offers promising avenues personalized medicine precision therapies, tailored Not applicable.

Язык: Английский

---

Ensemble deep learning model for protein secondary structure prediction using NLP metrics and explainable AI

Results in Engineering, Год журнала: 2024, Номер unknown, С. 103435 - 103435

Опубликована: Ноя. 1, 2024

Язык: Английский

---

MolFeSCue: enhancing molecular property prediction in data-limited and imbalanced contexts using few-shot and contrastive learning

Bioinformatics, Год журнала: 2024, Номер 40(4)

Опубликована: Фев. 29, 2024

Abstract Motivation Predicting molecular properties is a pivotal task in various scientific domains, including drug discovery, material science, and computational chemistry. This problem often hindered by the lack of annotated data imbalanced class distributions, which pose significant challenges developing accurate robust predictive models. Results study tackles these issues employing pretrained models within few-shot learning framework. A novel dynamic contrastive loss function utilized to further improve model performance situation imbalance. The proposed MolFeSCue framework not only facilitates rapid generalization from minimal samples, but also employs extract meaningful representations datasets. Extensive evaluations comparisons state-of-the-art algorithms have been conducted on multiple benchmark datasets, experimental demonstrate our algorithm’s effectiveness its broad applicability across Our findings underscore MolFeSCues potential accelerate advancements discovery. Availability implementation We made all source code this publicly accessible via GitHub at http://www.healthinformaticslab.org/supp/ or https://github.com/zhangruochi/MolFeSCue. (MolFeSCue-v1-00) available as supplementary file paper.

Язык: Английский

---

Accurate Prediction of NMR Chemical Shifts: Integrating DFT Calculations with Three-Dimensional Graph Neural Networks

Journal of Chemical Theory and Computation, Год журнала: 2024, Номер 20(12), С. 5250 - 5258

Опубликована: Июнь 6, 2024

Computer prediction of NMR chemical shifts plays an increasingly important role in molecular structure assignment and elucidation for organic molecule studies. Density functional theory (DFT) gauge-including atomic orbital (GIAO) have established a framework to predict but often at significant computational expense with limited accuracy. Recent advancements deep learning methods, especially graph neural networks (GNNs), shown promise improving the accuracy predicting experimental shifts, either by using 2D topological features or 3D conformational representation. This study presents new GNN model 1H 13C CSTShift, that combines DFT-calculated shielding tensor descriptors, capturing both isotropic anisotropic effects. Utilizing NMRShiftDB2 data set conducting DFT optimization GIAO calculations B3LYP/6-31G(d) level, we prepared NMRShiftDB2-DFT high-quality structures tensors corresponding experimentally measured shifts. The developed CSTShift models achieve state-of-the-art performance on test external CHESHIRE set. Further case studies identifying correct from two groups constitutional isomers show its capability elucidation. source code are accessible https://yzhang.hpc.nyu.edu/IMA.

Язык: Английский

---

Artificial Intelligence–Driven Computational Approaches in the Development of Anticancer Drugs

Cancers, Год журнала: 2024, Номер 16(22), С. 3884 - 3884

Опубликована: Ноя. 20, 2024

The integration of AI has revolutionized cancer drug development, transforming the landscape discovery through sophisticated computational techniques. AI-powered models and algorithms have enhanced computer-aided design (CADD), offering unprecedented precision in identifying potential anticancer compounds. Traditionally, been a complex, resource-intensive process, but introduces new opportunities to accelerate discovery, reduce costs, optimize efficiency. This manuscript delves into transformative applications AI-driven methodologies predicting developing drugs, critically evaluating their reshape future therapeutics while addressing challenges limitations.

Язык: Английский

---

Towards the “Eldorado” of pKa Determination: A Reliable and Rapid DFT Model

Molecules, Год журнала: 2024, Номер 29(6), С. 1255 - 1255

Опубликована: Март 12, 2024

The selection of a “perfect tool” for the theoretical determination acid-base dissociation constants (Ka) is still puzzling. Recently, we developed user-friendly model exploiting CAM-B3LYP determining pKa with impressive reliability. Herein, new challenge faced, examining panel functionals belonging to different rungs “Jacob’s ladder” organization, which classifies according their level theory. Specifically, meta-generalized gradient approximations (GGAs), hybrid-GGAs, and more complex range-separated hybrid (RSH)-GGAs were investigated in predicting differently substituted carboxylic acids. Therefore, CAM-B3LYP, WB97XD, B3PW91, PBE1PBE, PBEPBE TPSSTPSS used, 6-311G+(d,p) as basis set solvation based on density (SMD). showed lowest mean absolute error value (MAE = 0.23) relatively high processing time. PBE1PBE B3PW91 provided satisfactory predictions 0.34 0.38, respectively) moderate computational time cost, while PBEPBE, WB97XD led unreliable results > 1). These findings validate reliability our acids pKa, MAE well below 0.5 units, using simplistic low-cost approach.

Язык: Английский

---

Innovative Mamba and graph transformer framework for superior protein-ligand affinity prediction

Microchemical Journal, Год журнала: 2024, Номер 206, С. 111444 - 111444

Опубликована: Авг. 15, 2024

Язык: Английский

---