Computational and structural biotechnology journal最新文献

筛选
英文 中文
Integrating spatial mapping and metabolomics: A novel platform for bioactive compound discovery and saline land reclamation. 整合空间制图和代谢组学:生物活性化合物发现和盐碱地复垦的新平台。
IF 4.4 2区 生物学
Computational and structural biotechnology journal Pub Date : 2025-04-30 eCollection Date: 2025-01-01 DOI: 10.1016/j.csbj.2025.04.035
Tushar Andriyas, Nisa Leksungnoen, Pichaya Pongchaidacha, Arashaporn Uthairangsee, Suwimon Uthairatsamee, Peerapat Doomnil, Yongkriat Ku-Or, Chatchai Ngernsaengsaruay, Sanyogita Andriyas, Arerut Yarnvudhi, Rossarin Tansawat
{"title":"Integrating spatial mapping and metabolomics: A novel platform for bioactive compound discovery and saline land reclamation.","authors":"Tushar Andriyas, Nisa Leksungnoen, Pichaya Pongchaidacha, Arashaporn Uthairangsee, Suwimon Uthairatsamee, Peerapat Doomnil, Yongkriat Ku-Or, Chatchai Ngernsaengsaruay, Sanyogita Andriyas, Arerut Yarnvudhi, Rossarin Tansawat","doi":"10.1016/j.csbj.2025.04.035","DOIUrl":"10.1016/j.csbj.2025.04.035","url":null,"abstract":"<p><p>Saline lands pose significant environmental and agricultural challenges due to high soil salinity, which disrupts water uptake and ionic balances, limiting conventional crop productivity. Yet, certain endemic plants thrive under these conditions and may offer untapped bioactive compounds. This study proposes a novel platform that integrates species distribution modeling (SDM) and advanced metabolomics to screen for bioactive secondary metabolites, using <i>Buchanania siamensis</i>, a rare native species, as a case study. An ensemble SDM model incorporating environmental and soil parameters identified salinity as a critical factor influencing the species' distribution. Leaf samples were collected from naturally growing trees at both saline (SS) and non-saline (NS) sites. LC-QTOF metabolomic analysis annotated a total of 1106 metabolites across the leaf samples, with 175 found to be significantly different between the groups. Among them, 108 metabolites exhibited higher abundance in the SS group. Additionally, antioxidant assays including DPPH, FRAP, and total phenolic content tests, were conducted. Data were further analyzed using O-PLSR models to identify key metabolites most relevant to antioxidant properties. The results indicated that afzelin was the key metabolite responsible for the antioxidant properties of <i>B. siamensis</i>, with significantly higher levels in SS compared to NS samples (<i>p</i> < 0.05), as determined by peak area. By leveraging this multidisciplinary approach, we propose a framework to support both bioactive compound discovery and saline land reclamation, offering potential environmental and pharmaceutical benefits. This integrated platform may support pharmaceutical research, particularly in drug discovery efforts.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"1741-1753"},"PeriodicalIF":4.4,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12104716/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144149653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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
Single-cell and multi-omics integration reveals cholesterol biosynthesis as a synergistic target with HER2 in aggressive breast cancer. 单细胞和多组学整合揭示了胆固醇生物合成与HER2在侵袭性乳腺癌中的协同作用。
IF 4.4 2区 生物学
Computational and structural biotechnology journal Pub Date : 2025-04-24 eCollection Date: 2025-01-01 DOI: 10.1016/j.csbj.2025.04.030
Tzu-Yang Tseng, Chiao-Hui Hsieh, Jie-Yu Liu, Hsuan-Cheng Huang, Hsueh-Fen Juan
{"title":"Single-cell and multi-omics integration reveals cholesterol biosynthesis as a synergistic target with HER2 in aggressive breast cancer.","authors":"Tzu-Yang Tseng, Chiao-Hui Hsieh, Jie-Yu Liu, Hsuan-Cheng Huang, Hsueh-Fen Juan","doi":"10.1016/j.csbj.2025.04.030","DOIUrl":"10.1016/j.csbj.2025.04.030","url":null,"abstract":"<p><p>Breast cancer stands as one of the most prevalent malignancies affecting women. Alterations in molecular pathways in cancer cells represent key regulatory disruptions that drive malignancy, influencing cancer cell survival, proliferation, and potentially modulating therapeutic responsiveness. Therefore, decoding the intricate molecular mechanisms and identifying novel therapeutic targets through systematic computational approaches are essential steps toward advancing effective breast cancer treatments. In this study, we developed an integrative computational framework that combines single-cell RNA sequencing (scRNA-seq) and multi-omics analyses to delineate the functional characteristics of malignant cell subsets in breast cancer patients. Our analyses revealed a significant correlation between cholesterol biosynthesis and HER2 expression in malignant breast cancer cells, supported by proteomics data, gene expression profiles, drug treatment scores, and cell-surface HER2 intensity measurements. Given previous evidence linking cholesterol biosynthesis to HER2 membrane dynamics, we proposed a combinatorial strategy targeting both pathways. Experimental validation through clonogenic and viability assays demonstrated that simultaneous inhibition of cholesterol biosynthesis (via statins) and HER2 (via Neratinib) synergistically reduced malignant breast cancer cells, even in HER2-negative contexts. Through systematic analysis of scRNA-seq and multi-omics data, our study computationally identified and experimentally validated cholesterol biosynthesis and HER2 as novel combinatorial therapeutic targets in breast cancer. This data-driven approach highlights the potential of leveraging multiple molecular profiling techniques to uncover previously unexplored treatment strategies.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"1719-1731"},"PeriodicalIF":4.4,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12088767/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144101546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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
Transfer learning towards predicting viral missense mutations: A case study on SARS-CoV-2. 迁移学习预测病毒错义突变:以SARS-CoV-2为例
IF 4.4 2区 生物学
Computational and structural biotechnology journal Pub Date : 2025-04-22 eCollection Date: 2025-01-01 DOI: 10.1016/j.csbj.2025.04.029
Shaylyn Govender, Emily Morgan, Rabelani Ramahala, Kevin Lobb, Nigel T Bishop, Özlem Tastan Bishop
{"title":"Transfer learning towards predicting viral missense mutations: A case study on SARS-CoV-2.","authors":"Shaylyn Govender, Emily Morgan, Rabelani Ramahala, Kevin Lobb, Nigel T Bishop, Özlem Tastan Bishop","doi":"10.1016/j.csbj.2025.04.029","DOIUrl":"https://doi.org/10.1016/j.csbj.2025.04.029","url":null,"abstract":"<p><p>Understanding viral evolution and predicting future mutations are crucial for overcoming drug resistance and developing long-lasting treatments. Previously, we established machine learning (ML) models using dynamic residue network (DRN) metric data and leveraging a vast amount of existing mutation data from the SARS-CoV-2 main protease (M<sup>pro</sup>). Here, we sought to assess the generalizability and robustness of the current models across other SARS-CoV-2 proteins. To achieve this, for the first time, we employed a transfer learning (TL) approach, allowing us to determine the extent to which M<sup>pro</sup> trained models could be applied to other SARS-CoV-2 proteins. The TL results were highly promising, with artificial neural network (ANN) and random forest (RF) correlation coefficients for M<sup>pro</sup> closely matching those of NSP10, NSP16, and PL<sup>pro</sup>. The ANN |R| value for M<sup>pro</sup> was 0.564, while NSP10, NSP16, and PL<sup>pro</sup> had values of 0.533, 0.527, and 0.464, respectively. Similarly, the RF |R| value for M<sup>pro</sup> was 0.673, compared to 0.457, 0.460, and 0.437 for NSP10, NSP16, and PL<sup>pro</sup>, respectively. Interestingly, we did not observe a strong correlation for the spike (S) protein monomer and its domains. The low p-values that are associated with the correlation |R| values show that the linear correlations between predicted and actual mutation frequencies are statistically significant. This indicates that TL may generalize well across structurally related viral proteins using DRN-derived ML model from M<sup>pro</sup>. Overall, we aim to develop a universal ML model for predicting missense mutation frequencies in viral proteins, and this study lays the foundation for that goal.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"1686-1692"},"PeriodicalIF":4.4,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12063013/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143986916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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
Intelligent detection for Polycystic Ovary Syndrome (PCOS): Taxonomy, datasets and detection tools. 多囊卵巢综合征(PCOS)的智能检测:分类、数据集和检测工具。
IF 4.4 2区 生物学
Computational and structural biotechnology journal Pub Date : 2025-04-17 eCollection Date: 2025-01-01 DOI: 10.1016/j.csbj.2025.04.011
Meng Li, Zanxiang He, Liyun Shi, Mengyuan Lin, Minge Li, Yanjun Cheng, Hongwei Liu, Lei Xue, Kabir Sulaiman Said, Murtala Yusuf, Hadiza Shehu Galadanci, Liming Nie
{"title":"Intelligent detection for Polycystic Ovary Syndrome (PCOS): Taxonomy, datasets and detection tools.","authors":"Meng Li, Zanxiang He, Liyun Shi, Mengyuan Lin, Minge Li, Yanjun Cheng, Hongwei Liu, Lei Xue, Kabir Sulaiman Said, Murtala Yusuf, Hadiza Shehu Galadanci, Liming Nie","doi":"10.1016/j.csbj.2025.04.011","DOIUrl":"https://doi.org/10.1016/j.csbj.2025.04.011","url":null,"abstract":"<p><p>Recent research on Polycystic Ovary Syndrome (PCOS) detection increasingly employs intelligent algorithms to assist gynecologists in more accurate and efficient diagnoses. However, intelligent PCOS detection faces notable challenges: absence of standardized feature taxonomies, limited research on available datasets, and insufficient understanding of existing detection tools' capabilities. This paper addresses these gaps by introducing a novel analytical framework for PCOS diagnostic research and developing a comprehensive taxonomy comprising 108 features across 8 categories. Furthermore, we analyzed available datasets and assessed current intelligent detection tools. Our findings reveal that 12 publicly accessible datasets cover only 54% of the 108 features identified in our taxonomy. These datasets frequently lack multimodal integration, regular updates, and clear license information-constraints that potentially limit detection tool development. Additionally, our analysis of 42 detection tools identifies several limitations: high computational resource requirements, inadequate multimodal data processing, insufficient longitudinal analysis capabilities, and limited clinical validation. Based on these observations, we highlight critical challenges and future research directions for advancing intelligent PCOS detection tools.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"1578-1599"},"PeriodicalIF":4.4,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12032871/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143984478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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
A molecular dynamics study of membrane positioning for 7-transmembrane RGS proteins to modulate G-protein-mediated signaling in plants. 7-跨膜RGS蛋白在植物中调节g蛋白介导信号的分子动力学研究。
IF 4.4 2区 生物学
Computational and structural biotechnology journal Pub Date : 2025-04-11 eCollection Date: 2025-01-01 DOI: 10.1016/j.csbj.2025.04.013
Celio Cabral Oliveira, Eduardo Bassi Simoni, Mariana Abrahão Bueno Morais, Elizabeth Pacheco Batista Fontes, Pedro A Braga Dos Reis, Daisuke Urano, Alan M Jones
{"title":"A molecular dynamics study of membrane positioning for 7-transmembrane RGS proteins to modulate G-protein-mediated signaling in plants.","authors":"Celio Cabral Oliveira, Eduardo Bassi Simoni, Mariana Abrahão Bueno Morais, Elizabeth Pacheco Batista Fontes, Pedro A Braga Dos Reis, Daisuke Urano, Alan M Jones","doi":"10.1016/j.csbj.2025.04.013","DOIUrl":"https://doi.org/10.1016/j.csbj.2025.04.013","url":null,"abstract":"<p><p>Protein phosphorylation regulates G protein signaling in plants. AtRGS1 primarily modulates AtGPA1, the canonical Gα subunit in the heterotrimeric G protein complex. AtRGS1 possesses both a seven-transmembrane (7TM) domain connected to a cytoplasmic Regulator of G Protein Signaling domain (RGS box domain) by a flexible linker region. This study presents the novel function of a highly conserved, known phosphorylation site, Ser278, within this linker region utilizing molecular dynamics (MD) simulations with <i>in vivo</i> experimental validation. We show that phosphorylation at Ser278 is crucial for establishing specific AtRGS1 interactions with AtGPA1, primarily by stabilizing the positioning and orientation of the RGS domain within the membrane. Phosphorylation at Ser278 enhances the formation of stable hydrogen bonds between phosphorylated Ser278 and conserved residues within the RGS box domain, influencing the flexibility of RGS domain mobility and thus modulating its interface to AtGPA1. Consistent with the MD simulations, <i>in vivo</i> assays demonstrated that this phosphorylation reduced the binding of AtRGS1 to AtGPA1 and conferred changes in physiology. Specifically, the non-phosphorylation mutation of Ser278 decreased both plant immune responses and AtRGS1 endocytosis evoked by the bacterial effector, flg22. MD simulations and sequence analysis of diverse plant 7TM-RGS proteins suggest conservation of this mechanism across land plants, emphasizing the critical role of this previously overlooked linker region.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"1529-1537"},"PeriodicalIF":4.4,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12017998/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143983707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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
Advancements in one-dimensional protein structure prediction using machine learning and deep learning. 基于机器学习和深度学习的一维蛋白质结构预测研究进展。
IF 4.4 2区 生物学
Computational and structural biotechnology journal Pub Date : 2025-04-03 eCollection Date: 2025-01-01 DOI: 10.1016/j.csbj.2025.04.005
Wafa Alanazi, Di Meng, Gianluca Pollastri
{"title":"Advancements in one-dimensional protein structure prediction using machine learning and deep learning.","authors":"Wafa Alanazi, Di Meng, Gianluca Pollastri","doi":"10.1016/j.csbj.2025.04.005","DOIUrl":"https://doi.org/10.1016/j.csbj.2025.04.005","url":null,"abstract":"<p><p>The accurate prediction of protein structures remains a cornerstone challenge in structural bioinformatics, essential for understanding the intricate relationship between protein sequence, structure, and function. Recent advancements in Machine Learning (ML) and Deep Learning (DL) have revolutionized this field, offering innovative approaches to tackle one- dimensional (1D) protein structure annotations, including secondary structure, solvent accessibility, and intrinsic disorder. This review highlights the evolution of predictive methodologies, from early machine learning models to sophisticated deep learning frameworks that integrate sequence embeddings and pretrained language models. Key advancements, such as AlphaFold's transformative impact on structure prediction and the rise of protein language models (PLMs), have enabled unprecedented accuracy in capturing sequence-structure relationships. Furthermore, we explore the role of specialized datasets, benchmarking competitions, and multimodal integration in shaping state-of-the-art prediction models. By addressing challenges in data quality, scalability, interpretability, and task-specific optimization, this review underscores the transformative impact of ML, DL, and PLMs on 1D protein prediction while providing insights into emerging trends and future directions in this rapidly evolving field.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"1416-1430"},"PeriodicalIF":4.4,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12002955/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143987973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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
Next-Generation Sequencing: a powerful multi-purpose tool in cell line development for biologics production 下一代测序:一个强大的多用途的工具,在细胞系开发的生物制剂生产
IF 4.4 2区 生物学
Computational and structural biotechnology journal Pub Date : 2025-04-03 DOI: 10.1016/j.csbj.2025.04.006
Luigi Grassi, Claire Harris, Jie Zhu, Diane Hatton, Sarah Dunn
{"title":"Next-Generation Sequencing: a powerful multi-purpose tool in cell line development for biologics production","authors":"Luigi Grassi,&nbsp;Claire Harris,&nbsp;Jie Zhu,&nbsp;Diane Hatton,&nbsp;Sarah Dunn","doi":"10.1016/j.csbj.2025.04.006","DOIUrl":"10.1016/j.csbj.2025.04.006","url":null,"abstract":"<div><div>Within the biopharmaceutical industry, the cell line development (CLD) process generates recombinant mammalian cell lines for the expression of therapeutic proteins. Analytical methods for the extensive characterisation of the protein product are well established; however, over recent years, next-generation sequencing (NGS) technologies have rapidly become an integral part of the CLD workflow. NGS can be used for different applications to characterise the genome, epigenome and transcriptome of cell lines. The resulting extensive datasets, especially when integrated with systems biology models, can give comprehensive insights that can be applied to optimize cell lines, media, and fermentation processes. NGS also provides comprehensive methods to monitor genetic variability during CLD. High coverage NGS experiments can indeed be used to ensure the integrity of plasmids, identify integration sites, and verify monoclonality of the cell lines. This review summarises the role of NGS in advancing biopharmaceutical production to ensure safety and efficacy of therapeutic proteins.</div></div>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143807784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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
Fantastic genes and where to find them expressed in CHO 奇妙的基因在CHO中表达
IF 4.4 2区 生物学
Computational and structural biotechnology journal Pub Date : 2025-04-02 DOI: 10.1016/j.csbj.2025.03.050
Markus Riedl, Caterina Ruggeri, Nicolas Marx, Nicole Borth
{"title":"Fantastic genes and where to find them expressed in CHO","authors":"Markus Riedl,&nbsp;Caterina Ruggeri,&nbsp;Nicolas Marx,&nbsp;Nicole Borth","doi":"10.1016/j.csbj.2025.03.050","DOIUrl":"10.1016/j.csbj.2025.03.050","url":null,"abstract":"<div><div>The transcriptome of Chinese hamster ovary (CHO) cells plays a crucial role in determining cellular characteristics that are essential for biopharmaceutical applications. RNA-sequencing has been extensively used to profile gene expression patterns, aiming to gain a better understanding of intracellular behavior and mechanisms. Individual datasets, however, do not provide a comprehensive overview and characterisation of the CHO cell's transcriptome, such that the fundamental structure of the transcriptome remains unknown. Using 15 RNA-sequencing datasets, encompassing almost 300 samples of various experimental setups, conditions and cell lines, we explore and classify the protein-coding transcriptome of CHO cells. Differences in cell line lineages are found to be the primary source of variation in transcribed genes. By employing a novel approach, we identified the core transcriptome that is ubiquitously expressed in all cell lines and culture conditions, as well as genes that remain entirely non-expressed. Additionally, we identified a set of genes that may be active or inactive depending on different conditions, which are linked to biological processes including translation as well as immune and stress response. Lastly, by integrating chromatin states derived from histone modifications, we provided additional context on the epigenetic level that supports our protein-coding gene classification. Our study offers a comprehensive insight into the CHO cell transcriptome and lays the foundation for future research into cellular adaptation to changing conditions and the development of phenotypes.</div></div>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143776246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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
ToxDL 2.0: Protein toxicity prediction using a pretrained language model and graph neural networks. 使用预训练语言模型和图神经网络的蛋白质毒性预测。
IF 4.4 2区 生物学
Computational and structural biotechnology journal Pub Date : 2025-04-02 eCollection Date: 2025-01-01 DOI: 10.1016/j.csbj.2025.04.002
Lin Zhu, Yi Fang, Shuting Liu, Hong-Bin Shen, Wesley De Neve, Xiaoyong Pan
{"title":"ToxDL 2.0: Protein toxicity prediction using a pretrained language model and graph neural networks.","authors":"Lin Zhu, Yi Fang, Shuting Liu, Hong-Bin Shen, Wesley De Neve, Xiaoyong Pan","doi":"10.1016/j.csbj.2025.04.002","DOIUrl":"https://doi.org/10.1016/j.csbj.2025.04.002","url":null,"abstract":"<p><strong>Motivation: </strong>Assessing the potential toxicity of proteins is crucial for both therapeutic and agricultural applications. Traditional experimental methods for protein toxicity evaluation are time-consuming, expensive, and labor-intensive, highlighting the requirement for efficient computational approaches. Recent advancements in language models and deep learning have significantly improved protein toxicity prediction, yet current models often lack the ability to integrate evolutionary and structural information, which is crucial for accurate toxicity assessment of proteins.</p><p><strong>Results: </strong>In this study, we present ToxDL 2.0, a novel multimodal deep learning model for protein toxicity prediction that integrates both evolutionary and structural information derived from a pretrained language model and AlphaFold2. ToxDL 2.0 consists of three key modules: (1) a Graph Convolutional Network (GCN) module for generating protein graph embeddings based on AlphaFold2-predicted structures, (2) a domain embedding module for capturing protein domain representations, and (3) a dense module that combines these embeddings to predict the toxicity. After constructing a comprehensive toxicity benchmark dataset, we obtained experimental results on both an original non-redundant test set (comprising pre-2022 protein sequences) and an independent non-redundant test set (a holdout set of post-2022 protein sequences), demonstrating that ToxDL 2.0 outperforms existing state-of-the-art methods. Additionally, we utilized Integrated Gradients to discover known toxic motifs associated with protein toxicity. A web server for ToxDL 2.0 is publicly available at www.csbio.sjtu.edu.cn/bioinf/ToxDL2/.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"1538-1549"},"PeriodicalIF":4.4,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12018212/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143986917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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
NMR-based metabolomic approach to estimate chemical and sensorial profiles of olive oil. 基于核磁共振的代谢组学方法估计橄榄油的化学和感官特征。
IF 4.4 2区 生物学
Computational and structural biotechnology journal Pub Date : 2025-03-29 eCollection Date: 2025-01-01 DOI: 10.1016/j.csbj.2025.03.045
Gaia Meoni, Leonardo Tenori, Francesca Di Cesare, Stefano Brizzolara, Pietro Tonutti, Chiara Cherubini, Laura Mazzanti, Claudio Luchinat
{"title":"NMR-based metabolomic approach to estimate chemical and sensorial profiles of olive oil.","authors":"Gaia Meoni, Leonardo Tenori, Francesca Di Cesare, Stefano Brizzolara, Pietro Tonutti, Chiara Cherubini, Laura Mazzanti, Claudio Luchinat","doi":"10.1016/j.csbj.2025.03.045","DOIUrl":"https://doi.org/10.1016/j.csbj.2025.03.045","url":null,"abstract":"<p><p>This study investigates the potential of <sup>1</sup>H NMR spectroscopy for predicting key chemical and sensory attributes in olive oil. By integrating NMR data with traditional chemical analyses and sensory evaluation, we developed multivariate models to evaluate the predictive power of NMR spectra coupled with machine learning algorithms for 50 distinct olive oil quality parameters, including physicochemical properties, fatty acid composition, total polyphenols, tocopherols, and sensory attributes. We applied Random Forest regression models to correlate NMR spectra with these parameters, achieving promising results, particularly for predicting major fatty acids, total polyphenols, and tocopherols. We have also found the collected data to be highly effective in classifying olive cultivars and the years of harvest. Our findings highlight the potential of NMR spectroscopy as a rapid, non-destructive, and environmentally friendly tool for olive oil quality assessment. This study introduces a novel approach that combines machine learning with <sup>1</sup>H NMR spectral analysis to correlate analytical data for predicting essential qualitative parameters in olive oil. By leveraging <sup>1</sup>H NMR spectra as predictive proxies, this methodology offers a promising alternative to traditional assessment techniques, enabling rapid determination of several parameters related to chemical composition, sensory attributes, and geographical origin of olive oil samples.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"1359-1369"},"PeriodicalIF":4.4,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11999361/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143988862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信