IF 4.2 3区生物学

Methods Pub Date : 2025-03-18 DOI: 10.1016/j.ymeth.2025.03.010

Sichen Yi , Minzhu Xie

{"title":"DriverMEDS: Cancer driver gene identification using mutual exclusivity from embeded features and driver mutation scoring","authors":"Sichen Yi , Minzhu Xie","doi":"10.1016/j.ymeth.2025.03.010","DOIUrl":"10.1016/j.ymeth.2025.03.010","url":null,"abstract":"<div><div>Efficiently identifying cancer driver genes plays a key role in the cancer development, diagnosis and treatment. Current unsupervised driver gene identification methods typically integrate multi-omics data into gene function networks and employ network embedding algorithms to learn gene features. Additionally, they consider mutual exclusivity and mutation frequency as crucial concepts in identifying driver genes. However, existing approaches neglect the possible important implications of mutual exclusivity in the embedding space. Furthermore, they simply assume that all driver genes exhibit high mutation frequencies. Fortunately, we explored the mutual exclusivity implanted in the learned features and have verified that the Euclidean distances between learned features are strongly related to the mutual exclusivity and they can reveal more information for the mutual exclusivity. Thus, we designed an unsupervised driver gene predicting framework DriverMEDS based on the above idea and a novel driver mutation scoring strategy. First, we design a feature clustering algorithm to generate gene modules. In each module, the Euclidean distances of learned features are used to calculate a module importance score for each gene based on the related mutual exclusivity. Then, following the fact that most of driver genes have intermediate mutation frequencies, a driver mutation scoring function is designed for each gene to optimize the existing mutation frequency scoring strategy. Finally, the weighted sum of the module importance score and the driver mutation score is used to prioritize the genes. The experiment results and analysis show that DriverMEDS could detect novel cancer driver genes and relevant function modules, and outperforms other five state-of-the-art methods for cancer driver identification.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"239 ","pages":"Pages 22-29"},"PeriodicalIF":4.2,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143668679","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Iontophoresis impact on corneal properties using an ex vivo bovine eye model 离子导入对离体牛眼模型角膜特性的影响

IF 4.2 3区生物学

Methods Pub Date : 2025-03-16 DOI: 10.1016/j.ymeth.2025.03.011

Gabriela Fávero Galvão , Izabella Cristina Bernardo Maríngolo , Yugo Araújo Martins , Janette Bezebeth Villarruel Muñoz , Marina Zilio Fantucci , Ricardo Roberto da Silva , Eduardo Melani Rocha , Eloísa Berbel Manaia , Gilles Ponchel , Renata Fonseca Vianna Lopez

{"title":"Iontophoresis impact on corneal properties using an ex vivo bovine eye model","authors":"Gabriela Fávero Galvão , Izabella Cristina Bernardo Maríngolo , Yugo Araújo Martins , Janette Bezebeth Villarruel Muñoz , Marina Zilio Fantucci , Ricardo Roberto da Silva , Eduardo Melani Rocha , Eloísa Berbel Manaia , Gilles Ponchel , Renata Fonseca Vianna Lopez","doi":"10.1016/j.ymeth.2025.03.011","DOIUrl":"10.1016/j.ymeth.2025.03.011","url":null,"abstract":"<div><div>This study addresses the challenge of low drug bioavailability in topical ocular administration by developing and validating an ex vivo bovine eye model chamber to evaluate the effects of iontophoresis on drug delivery and corneal properties. Transepithelial electrical resistance (TEER) was assessed as a predictor of corneal epithelial integrity in dissected bovine eyes. TEER measurements were correlated with methylene blue permeation, confirming a threshold of 4.2 kOhm·cm2 as an indicator of epithelial integrity. The model chamber enabled the application of drug solutions around a defined area of the cornea without leakage, facilitating the placement of electrodes and the application of constant electric currents. Applying iontophoresis at 2 mA/cm2 for 6 min significantly increased rhodamine B penetration into the cornea by nearly sixfold compared to passive diffusion (approximately 1.3 µg/cm2 vs. 0.24 µg/cm2), allowing detectable drug levels in the aqueous humor (27.9 ± 0.5 ng/mL). Morphological analyses revealed temporary changes in the cornea, including a 2.3-fold increase in surface roughness (from 44.6 nm to 105.3 nm) and mild collagen disorganization in the stroma, while Bowman’s membrane remained intact. A significant increase in corneal stiffness was noted, with a 200 % rise in the area under the stress–strain curve after iontophoresis. These findings provide insights into iontophoresis-induced changes and highlight the model’s potential for optimizing ocular drug delivery systems. Additionally, the model aligns with the 3Rs principles and could be instrumental in advancing the understanding of anterior segment diseases driven by structural and biomechanical alterations.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"238 ","pages":"Pages 74-83"},"PeriodicalIF":4.2,"publicationDate":"2025-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Domain alignment method based on masked variational autoencoder for predicting patient anticancer drug response 基于掩模变分自编码器的区域对齐方法预测患者抗癌药物反应。

IF 4.2 3区生物学

Methods Pub Date : 2025-03-14 DOI: 10.1016/j.ymeth.2025.03.012

Wei Dai , Gong Chen , Wei Peng , Chuyue Chen , Xiaodong Fu , Li Liu , Lijun Liu , Ning Yu

{"title":"Domain alignment method based on masked variational autoencoder for predicting patient anticancer drug response","authors":"Wei Dai , Gong Chen , Wei Peng , Chuyue Chen , Xiaodong Fu , Li Liu , Lijun Liu , Ning Yu","doi":"10.1016/j.ymeth.2025.03.012","DOIUrl":"10.1016/j.ymeth.2025.03.012","url":null,"abstract":"<div><div>Predicting the patient’s response to anticancer drugs is essential in personalized treatment plans. However, due to significant distribution differences between cell line data and patient data, models trained well on cell line data may perform poorly on patient anticancer drug response predictions. Some existing methods use transfer learning strategies to implement domain feature alignment between cell lines and patient data and leverage knowledge from cell lines to predict patient anticancer drug responses. This study proposes a domain alignment method based on masked variational autoencoders, MVAEDA, to predict patient anticancer drug responses. The model constructs multiple variational autoencoders (VAEs) and mask predictors to extract specific and domain-invariant features of cell lines and patients. Then, it masks and reconstructs the gene expression matrix, using generative adversarial training to learn domain-invariant features from the cell line and patient domains. These domain-invariant features are then used to train a classifier. Finally, the final trained model predicts the anticancer drug response in the target domain. Our model is experimentally evaluated on the clinical dataset and the preclinical dataset. The results show that our method performs better than other state-of-the-art methods.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"238 ","pages":"Pages 61-73"},"PeriodicalIF":4.2,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143639353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Two minimally invasive strategies to implant guide cannulas for multiple injections in deep brain areas 两种微创方法植入导管用于脑深部多次注射。

IF 4.2 3区生物学

Methods Pub Date : 2025-03-08 DOI: 10.1016/j.ymeth.2025.03.005

Stefania Bartoletti , Federica Raimondi , Beatrice Casadei Garofani , Elisa Ren , Francesca Ciarpella , Arianna Capodiferro , Gemma Palazzolo , Antonietta Vilella , Giuseppina Leo , Michele Zoli , Ilaria Decimo , Giulia Curia

{"title":"Two minimally invasive strategies to implant guide cannulas for multiple injections in deep brain areas","authors":"Stefania Bartoletti , Federica Raimondi , Beatrice Casadei Garofani , Elisa Ren , Francesca Ciarpella , Arianna Capodiferro , Gemma Palazzolo , Antonietta Vilella , Giuseppina Leo , Michele Zoli , Ilaria Decimo , Giulia Curia","doi":"10.1016/j.ymeth.2025.03.005","DOIUrl":"10.1016/j.ymeth.2025.03.005","url":null,"abstract":"<div><div>Temporal lobe epilepsy (TLE) is characterized by seizures that originate in temporal structures and that are pharmacoresistant in ∼ 40 % of patients. In the context of a preclinical study aimed at developing an innovative therapy to treat TLE, we needed to perform multiple intracranial injections in the rat ventral CA3 (vCA3). To reduce invasiveness and to increase the precision reproducibility when multiple injections are performed over time, we opted for the implantation of guide cannulas.</div><div>In the conventional approach, the guide cannula is implanted close to the target zone damaging the brain tissue along the route of the cannula insertion. This is a particularly relevant issue in our study because vCA3 is situated deep in the rat brain. The damage caused by the standard procedure would severely compromise the integrity of the hippocampal tissue necessary for the effectiveness of the therapeutic intervention.</div><div>To overcome this problem, we developed, in TLE adult rats, two novel approaches to implant guide cannulas more superficially: the “above dentate gyrus (DG)” and the “above hippocampus (HPC)” strategies. The target brain area was then reached with the thinner infusion needle, resulting in minimally invasive approaches. We demonstrated by immunofluorescence that both novel surgical approaches enable injections of different agents into the ventral hippocampus with excellent precision and reproducibility. Being this aspect comparable between the two approaches, we concluded that the “above HPC” strategy must be preferred due to its lower invasiveness. Behavioral tests confirmed that memory, locomotion and anxiety level were not affected by the cannula-induced damage.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"238 ","pages":"Pages 27-39"},"PeriodicalIF":4.2,"publicationDate":"2025-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143595959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Milking mesenchymal stem cells: Updated protocols for cell lysate, secretome, and exosome extraction, and comparative analysis of their therapeutic potential 挤奶间充质干细胞：细胞裂解液、分泌组和外泌体提取的更新方案，以及它们治疗潜力的比较分析。

IF 4.2 3区生物学

Methods Pub Date : 2025-03-07 DOI: 10.1016/j.ymeth.2025.03.004

Sepideh Zununi Vahed , Seyyedeh Mina Hejazian , William Ndjidda Bakari , Rebecca Landon , Virginie Gueguen , Anne Meddahi-Pellé , Fani Anagnostou , Abolfazl Barzegari , Graciela Pavon-Djavid

{"title":"Milking mesenchymal stem cells: Updated protocols for cell lysate, secretome, and exosome extraction, and comparative analysis of their therapeutic potential","authors":"Sepideh Zununi Vahed , Seyyedeh Mina Hejazian , William Ndjidda Bakari , Rebecca Landon , Virginie Gueguen , Anne Meddahi-Pellé , Fani Anagnostou , Abolfazl Barzegari , Graciela Pavon-Djavid","doi":"10.1016/j.ymeth.2025.03.004","DOIUrl":"10.1016/j.ymeth.2025.03.004","url":null,"abstract":"<div><div>The potential of the cell lysate, secretome, and extracellular vesicles (EVs) of mesenchymal stem cells (MSCs) to modulate the immune response and promote tissue regeneration has positioned them as a promising option for cell-free therapy. Currently, many clinical trials in stem cells-derived EVs and secretome are in progress various diseases and sometimes the results are failing. The major challenge on this roadmap is the lack of a standard extraction method for exosome, secretome, and lysate. The most optimal method for obtaining the secretome of MSCs for clinical utilization involves a comprehensive approach that includes non-destructive collection methods, time optimization, multiple collection rounds, optimization of culture conditions, and quality control measures. Further research and clinical studies are warranted to validate and refine these methods for safe and effective utilization of the MSC exosome, secretome, and lysate in various clinical applications. To address these challenges, it is imperative to establish a standardized and unified methodology to ensure reliable evaluation of these extractions in clinical trials. This review seeks to outline the pros and cons of methods for the preparation of MSCs-derived exosome, and secretome/lysate, and comparative analysis of their therapeutic potential.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"238 ","pages":"Pages 40-60"},"PeriodicalIF":4.2,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143584146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

OmniClust: A versatile clustering toolkit for single-cell and spatial transcriptomics data OmniClust：用于单细胞和空间转录组学数据的多功能聚类工具包。

IF 4.2 3区生物学

Methods Pub Date : 2025-03-06 DOI: 10.1016/j.ymeth.2025.03.007

Yaxuan Cui , Yang Cui , Yi Ding , Kenta Nakai , Leyi Wei , Yuyin Le , Xiucai Ye , Tetsuya Sakurai

{"title":"OmniClust: A versatile clustering toolkit for single-cell and spatial transcriptomics data","authors":"Yaxuan Cui , Yang Cui , Yi Ding , Kenta Nakai , Leyi Wei , Yuyin Le , Xiucai Ye , Tetsuya Sakurai","doi":"10.1016/j.ymeth.2025.03.007","DOIUrl":"10.1016/j.ymeth.2025.03.007","url":null,"abstract":"<div><div>In recent years, RNA transcriptome sequencing technology has been continuously evolving, ranging from single-cell transcriptomics to spatial transcriptomics. Although these technologies are all based on RNA sequencing, each sequencing technology has its own unique characteristics, and there is an urgent need to develop an algorithmic toolkit that integrates both sequencing techniques. To address this, we have developed OmniClust, a toolkit based on single-cell RNA sequencing (scRNA-seq) and spatial transcriptomics data. OmniClust employs deep learning algorithms for feature learning and clustering of spatial transcriptomics data, while utilizing machine learning algorithms for clustering scRNA-seq data. OmniClust was tested on 12 spatial transcriptomics benchmark datasets, demonstrating high clustering accuracy across multiple clustering evaluation metrics. It was also evaluated on four scRNA-seq benchmark datasets, achieving high clustering accuracy based on various clustering evaluation metrics. Furthermore, we applied OmniClust to downstream analyses of spatial transcriptomics and single-cell RNA breast cancer data, showcasing its potential to uncover and interpret the biological significance of cancer transcriptome data. In summary, OmniClust is a clustering tool designed for both single-cell transcriptomics and spatial transcriptomics data, demonstrating outstanding performance.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"238 ","pages":"Pages 84-94"},"PeriodicalIF":4.2,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143584151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating a multi-omics strategy framework to screen potential targets in cognitive impairment-related epilepsy 整合多组学策略框架筛选认知障碍相关癫痫的潜在靶点

IF 4.2 3区生物学

Methods Pub Date : 2025-03-04 DOI: 10.1016/j.ymeth.2025.03.003

Chao Xu , Zijun Zhu , Xinyu Chen , Minke Lu , Chao Wang , Sainan Zhang , Lei Shi , Liang Cheng , Xue Zhang

{"title":"Integrating a multi-omics strategy framework to screen potential targets in cognitive impairment-related epilepsy","authors":"Chao Xu , Zijun Zhu , Xinyu Chen , Minke Lu , Chao Wang , Sainan Zhang , Lei Shi , Liang Cheng , Xue Zhang","doi":"10.1016/j.ymeth.2025.03.003","DOIUrl":"10.1016/j.ymeth.2025.03.003","url":null,"abstract":"<div><div>Epilepsy is a prevalent neurological disorder that affects over 70 million individuals worldwide and is often associated with cognitive impairments. Despite the widespread impact of epilepsy and cognitive impairments, the genetic basis and causal relationships underlying these conditions remain uncertain, prompting us to conduct a comprehensive investigation into the molecular mechanisms involved. In this study, we utilized statistical data from the third National Health and Nutrition Examination Survey (NHANES III) to evaluate correlation and large-scale pan-phenotype genome-wide association study (GWAS) data to establish genetic correlation and causality. Leveraging multi-omics datasets, we performed a comprehensive post-analysis that included variant prioritization, gene analysis, tissue and cell type enrichment, and pathway annotation. An integrated strategy—multi-trait analysis of GWAS (MTAG), transcriptome-wide association study (TWAS), summary-data-based Mendelian Randomization (SMR), and protein quantitative trait locus (pQTL)-MR—was performed to investigate the shared genetic architecture. Based on multiple orthogonal lines of evidence, we thereby identified 40 single nucleotide polymorphisms (SNPs) and 85 genes common to both conditions. Additionally, we optimized candidate genes such as <em>GNAQ</em>, <em>FADS1</em>, and <em>PTK2</em> by single-cell expression analysis and molecular pathway mechanisms, thereby highlighting potential shared genetic pathways. These findings elucidate the genetic interplay and co-occurring mechanisms between epilepsy and cognitive impairments, providing crucial insights for future research and therapeutic strategies.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"237 ","pages":"Pages 34-44"},"PeriodicalIF":4.2,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143549398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Leveraging protein language models for robust antimicrobial peptide detection 利用蛋白质语言模型进行稳健的抗菌肽检测。

IF 4.2 3区生物学

Methods Pub Date : 2025-03-04 DOI: 10.1016/j.ymeth.2025.03.002

Lichao Zhang , Shuwen Xiong , Lei Xu , Junwei Liang , Xuehua Zhao , Honglai Zhang , Xu Tan

引用次数: 0

Detection of hypochlorous acid fluctuation via a near-infrared fluorescent probe in Parkinson’s disease cells and mouse models 用近红外荧光探针检测帕金森病细胞和小鼠模型中的次氯酸波动。

IF 4.2 3区生物学

Methods Pub Date : 2025-03-04 DOI: 10.1016/j.ymeth.2025.03.006

Xumei Wang , Ke Wu , Ruixin Liu , Kai Wang , Wenyu Xie , Xinyuan Zhai , Shangshen Yang , Xiaoming Wang , Zhixin Tang

{"title":"Detection of hypochlorous acid fluctuation via a near-infrared fluorescent probe in Parkinson’s disease cells and mouse models","authors":"Xumei Wang , Ke Wu , Ruixin Liu , Kai Wang , Wenyu Xie , Xinyuan Zhai , Shangshen Yang , Xiaoming Wang , Zhixin Tang","doi":"10.1016/j.ymeth.2025.03.006","DOIUrl":"10.1016/j.ymeth.2025.03.006","url":null,"abstract":"<div><div>Parkinson’s disease (PD) is a neurodegenerative disorder caused by excessive reactive halogen species leading to the death of dopaminergic (DA) neurons, which disrupts the coordination of normal physiological structures and functions. Hypochlorous acid (HOCl) is a reactive halogen species whose overproduction is associated with the death of DA neurons. Herein, overproduction of HOCl may be a neurotoxin substance in the pathogenesis of PD. Therefore, it is essential to understand the disease of HOCl in PD model. However, early detection HOCl in PD model remains lacking of effective methods. In this study, a high sensitivity off–on near-infrared probe (MB-HOCl) was designed and synthesized. MB-HOCl showed a quantitative response toward HOCl (0–100 μM) with detection limit of 0.32 μM. Importantly, MB-HOCl was capable of selectively and specially detecting exogenous and endogenous HOCl in PC-12 cells and was successfully used for imaging in PD mice models. All results demonstrate that the probe (MB-HOCl) holds great promise for understanding the disease and diagnosis of HOCl-mediated PD models.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"238 ","pages":"Pages 11-18"},"PeriodicalIF":4.2,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143571761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MGDM: Molecular generation using a multinomial diffusion model MGDM：使用多项扩散模型的分子生成。

IF 4.2 3区生物学

Methods Pub Date : 2025-03-04 DOI: 10.1016/j.ymeth.2025.03.001

Sisi Yuan , Chen Zhao , Lin Liu , Guifei Zhou

{"title":"MGDM: Molecular generation using a multinomial diffusion model","authors":"Sisi Yuan , Chen Zhao , Lin Liu , Guifei Zhou","doi":"10.1016/j.ymeth.2025.03.001","DOIUrl":"10.1016/j.ymeth.2025.03.001","url":null,"abstract":"<div><div>Accurate analysis of molecular structures and the rapid generation of valid molecules remain significant challenges in De Novo drug design. In this study, we propose the <u>M</u>ultinomial <u>G</u>enerated <u>D</u>iffusion <u>M</u>odel (MGDM) for molecular generation. This model leverages a multinomial diffusion framework to process discrete data, with a focus on learning the multinomial distribution inherent in the dataset. During the generation process, the model progressively denoises molecules, transitioning from a uniform noise distribution to ultimately produce valid molecular structures. Initially, we generate molecules unconditionally to expand the compound library. In the next phase, we focus on generating molecules with specific properties to assess the model’s capacity for conditional generation. For this, we implement a classifier-free guidance strategy, which directs the diffusion model’s task without the need for training separate classifier models. To validate the effectiveness of our framework, we conducted experiments using the Molecular Sets (MOSES) dataset. The results demonstrate that, compared to several state-of-the-art methods, MGDM generates valid molecules while achieving superior or comparable performance in terms of novelty and diversity.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"239 ","pages":"Pages 1-9"},"PeriodicalIF":4.2,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143571840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Methods最新文献