<?xml version="1.1" encoding="utf-8"?>
<article xsi:noNamespaceSchemaLocation="http://jats.nlm.nih.gov/publishing/1.1/xsd/JATS-journalpublishing1-mathml3.xsd" dtd-version="1.1" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"><front><journal-meta><journal-id journal-id-type="publisher-id">MRP</journal-id><journal-title-group><journal-title>Medical Research and Practice</journal-title></journal-title-group><issn>2993-9690</issn><eissn>2993-9704</eissn><publisher><publisher-name>Art and Design</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.61369/MRP.2025120043</article-id><article-categories><subj-group subj-group-type="heading"><subject>Article</subject></subj-group></article-categories><title>基于最佳特征集肿瘤凝集素的分类研究</title><url>https://artdesignp.com/journal/MRP/3/12/10.61369/MRP.2025120043</url><author>周才貌,田明珠,黄玲娃</author><pub-date pub-type="publication-year"><year>2025</year></pub-date><volume>3</volume><issue>12</issue><history><date date-type="pub"><published-time>2025-12-20</published-time></date></history><abstract>肿瘤凝集素与癌症关联密切，可应用于临床诊断、治疗、药物输送及癌症靶向领域。因此，提升其分类准确性对疾病研究具有重要意义，能为深入理解和攻克癌症提供关键支持。本文构建了一种基于机器学习的肿瘤凝集素计算方法（ZTL_M），该方法通过 monoDiKGap 提取特征，经F-score筛选得到最优特征集，再利用多层感知器分类器完成识别。实验采用5倍交叉验证，结果显示 ZTL_M对肿瘤凝集素的识别准确率达96.3%，使用monoDiKGap可以提高模型识别肿瘤凝集素的能力，ZTL_M方法比一些现有方法具有更好的性能。</abstract><keywords>肿瘤集素,monoDiKGap方法,特征选择,多层感知器</keywords></article-meta></front><body/><back><ref-list><ref id="B1" content-type="article"><label>1</label><element-citation publication-type="journal"><p>[1]Sarhadi, V KArmengol G. Molecular biomarkers in cancer [J]. Biomolecules, 2022, 12(8): 1021.[2]Lin, H, Liu W X, He J, et al. Predicting cancerlectins by the optimal g-gap dipeptides [J]. Scientific Reports, 2015, 5(1): 16964.[3]Lavanya, V, Bommanabonia A K, Ahmed N, et al. Immunomodulatory effects of jacalin, a dietary plant lectin on the peripheral blood mononuclear cells (pbmcs) [J]. Applied Biochemistry and Biotechnology, 2022, 194(1): 587.[4]Shatz-Azoulay, H, Vinik Y, Isaac R, et al. The animal lectin galectin-8 promotes cytokine expression and metastatic tumor growth in mice [J]. Scientific Reports, 2020, 10(1): 7375.[5]Hern&amp;aacute;ndez, E, S&amp;aacute;nchez-Maldonado C, Ch&amp;aacute;vez M, et al. The therapeutic potential of galectin-1 and galectin-3 in the treatment of neurodegenerative diseases [J]. Expert Review of Neurotherapeutics, 2020, 20(1): 1.[6]Duan, L, Zangiabadi MZhao Y. Synthetic lectins for selective binding of glycoproteins in water [J]. Chemical Communications, 2020, 56(70).[7]Mane, V, Arakera S B, Pingle S, et al. Lectin as an anticancer therapeutic agent [M]. Handbook of research on natural products and their bioactive compounds as cancer therapeutics. IGI Global. 2022: 384.[8]Cummings, R D. The mannose receptor ligands and the macrophage glycome [J]. Current Opinion in Structural Biology, 2022, 75: 102394.[9]FREEMAN, H J. Role of lectins in gastrointestinal disorders [J]. Herbs, Spices, and Medicinal Plants for Human Gastrointestinal Disorders: Health Benefits and Safety, 2022.[10]Ali, F, Ghulam A, Maher Z A, et al. Deep-pcl: A deep learning model for prediction of cancerlectins and non cancerlectins using optimized integrated features [J]. Chemometrics and Intelligent Laboratory Systems, 2022, 221: 104484.[11]Kumar, R, Panwar B, Chauhan J S, et al. Analysis and prediction of cancerlectins using evolutionary and domain information [J]. Bmc Research Notes, 2011, 4(1): 237.[12]Qian, L, Wen YHan G. Identification of cancerlectins using support vector machines with fusion of g-gap dipeptide [J]. Frontiers in Genetics, 2020, 11.[13]Su, W, Liu M L, Yang Y H, et al. Ppd: A manually curated database for experimentally verified prokaryotic promoters [J]. Journal of Molecular Biology, 2021, 433(11): 166860.[14]Rafsanjani, Muhammod, Sajid, et al. Pyfeat: A python-based effective feature generation tool for DNA, rna, and protein sequences [J]. Bioinformatics, 2019.[15]Basith, S, Manavalan B, Shin T H, et al. Sdm6a: A web-based integrative machine-learning framework for predicting 6ma sites in the rice genome [J]. Molecular Therapy Nucleic Acids, 2019.[16]Hua, T, Ya-Wei Z, Ping Z, et al. Hbpred: A tool to identify growth hormone-binding proteins [J]. Int J Biol, 2018, 14(8): 957.[17]Ding, Y, Tang JGuo F. Identification of drug&amp;ndash;target interactions via fuzzy bipartite local model [J]. Neural Computing and Applications, 2020, 32(D1): 1.[18]Hong-Yan, Lai, Xin-Xin, et al. Sequence-based predictive modeling to identify cancerlectins [J]. Oncotarget, 2017.</p><pub-id pub-id-type="doi"/></element-citation></ref></ref-list></back></article>
