Background: In recent years, researchers have made significant strides in understanding the heterogeneity of breast cancer and its various subtypes. However, the wealth of genomic and proteomic data available today necessitates efficient frameworks, instruments, and computational tools for meaningful analysis. Despite its success as a prognostic tool, the PAM50 gene signature's reliance on many genes presents challenges in terms of cost and complexity. Consequently, there is a need for more efficient methods to classify breast cancer subtypes using a reduced gene set accurately.
Results: This study explores the potential of achieving precise breast cancer subtype categorization using a reduced gene set derived from the PAM50 gene signature. By employing a "Few-Shot Genes Selection" method, we randomly select smaller subsets from PAM50 and evaluate their performance using metrics and a linear model, specifically the Support Vector Machine (SVM) classifier. In addition, we aim to assess whether a more compact gene set can maintain performance while simplifying the classification process. Our findings demonstrate that certain reduced gene subsets can perform comparable or superior to the full PAM50 gene signature.
Conclusions: The identified gene subsets, with 36 genes, have the potential to contribute to the development of more cost-effective and streamlined diagnostic tools in breast cancer research and clinical settings.
Multilevel classification framework for breast cancer cell selection and its integration with advanced disease models
School of Electronics and Computer Science, University of Southampton(南安普顿大学电子与计算机科学学院);Institute for Life Sciences, University of Southampton(南安普顿大学生命科学研究所);Department of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa(里斯本大学高等技术学院生物工程系);Institute for Health and Bioeconomy, Instituto Superior Técnico, Universidade de Lisboa(里斯本大学高等技术学院健康与生物经济研究所);Centre for Mechanical Technology and Automation (TEMA), University of Aveiro(阿维罗大学机械技术与自动化中心(TEMA));Intelligent Systems Associate Laboratory (LASI)(智能系统联合实验室(LASI));Department of Pharmacy, University of Naples “Federico II”(那不勒斯费德里科二世大学药学系);Department of Life Sciences, Imperial College London(伦敦帝国理工学院生命科学系)
A Multicentric Dataset for Training and Benchmarking Breast Cancer Segmentation in H&E Slides
Department of Pathology, Radboud University Medical Center(病理学系,拉德堡德大学医学中心);Fondazione Bruno Kessler(布鲁诺·凯塞勒基金会);Department of Cellular, Computational and Integrative Biology, University of Trento(细胞、计算与整合生物学系,特伦托大学);Biopticka Laboratory Ltd.(Biopticka实验室有限公司);Department of Pathology, Faculty of Medicine in Pilsen, Charles University(病理学系,皮尔森医学院,查尔斯大学);University of Washington Medical Center(华盛顿大学医学中心);Department of Surgical Pathology, Santa Chiara Hospital, APSS(外科病理学系,圣查理医院,APSS);CISMed - Centre for Medical Sciences, University of Trento(CISMed医学研究中心,特伦托大学);Pathology Unit, University and Hospital Trust of Verona(病理学部,韦罗纳大学与医院信托);IRCCS Sacro Cuore Don Calabria Hospital(IRCCS圣心多玛利亚医院)
BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images
National Cancer Institute – IRCCS – Fondazione Pascale(国家癌症研究所——IRCCS——帕斯卡尔基金会);IBM Research – Zurich(IBM研究院——苏黎世);ETH Zurich(苏黎世联邦理工学院);Institute for High Performance Computing and Networking of the Research Council of Italy, ICAR-CNR(意大利研究理事会高性能计算与网络研究所,ICAR-CNR);University of Naples Federico II(那不勒斯费德里科二世大学);EPFL Lausanne(洛桑联邦理工学院)
Convolutional neural network models for cancer type prediction based on gene expression
Greehey Children’s Cancer Research Institute(格里希儿童癌症研究所);University of Texas Health Science Center at San Antonio(德克萨斯大学圣安东尼奥健康科学中心);University of Texas at San Antonio(德克萨斯大学圣安东尼奥分校)
Gene-SGAN: a method for discovering disease subtypes with imaging and genetic signatures via multi-view weakly-supervised deep clustering
University of Pennsylvania(宾夕法尼亚大学);University of Southern California(南加州大学);Lausanne University Hospital (CHUV) and University of Lausanne(洛桑大学医院(CHUV)和洛桑大学);University of Texas San Antonio Health Science Center(德克萨斯大学圣安东尼奥健康科学中心);The University of Melbourne(墨尔本大学);CSIRO(澳大利亚联邦科学与工业研究组织);National Institute on Aging, National Institutes of Health(美国国立卫生研究院国家老龄化研究所);Johns Hopkins University(约翰霍普金斯大学);University of Wisconsin(威斯康星大学);Washington University in St. Louis(圣路易斯华盛顿大学);National Institute on Aging(国家老龄化研究所)
Unsupervised Feature Selection for Tumor Profiles using Autoencoders and Kernel Methods
Universite de Technologie de Troyes(特鲁瓦技术大学);Instituto de Investigacion en Biomedicina de Buenos Aires (IBioBA)—CONICET Partner Institute of the Max Planck Society(布宜诺斯艾利斯生物医学研究所(IBioBA)—马克斯·普朗克学会合作研究所)