{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T01:03:28Z","timestamp":1778634208712,"version":"3.51.4"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006,3,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: Multilayer perceptrons (MLP) represent one of the widely used and effective machine learning methods currently applied to diagnostic classification based on high-dimensional genomic data. Since the dimensionalities of the existing genomic data often exceed the available sample sizes by orders of magnitude, the MLP performance may degrade owing to the curse of dimensionality and over-fitting, and may not provide acceptable prediction accuracy.<\/jats:p>\n               <jats:p>Results: Based on Fisher linear discriminant analysis, we designed and implemented an MLP optimization scheme for a two-layer MLP that effectively optimizes the initialization of MLP parameters and MLP architecture. The optimized MLP consistently demonstrated its ability in easing the curse of dimensionality in large microarray datasets. In comparison with a conventional MLP using random initialization, we obtained significant improvements in major performance measures including Bayes classification accuracy, convergence properties and area under the receiver operating characteristic curve (Az).<\/jats:p>\n               <jats:p>Supplementary information: The Supplementary information is available on<\/jats:p>\n               <jats:p>Contact: \u00a0yuewang@vt.edu<\/jats:p>","DOI":"10.1093\/bioinformatics\/btk036","type":"journal-article","created":{"date-parts":[[2006,1,11]],"date-time":"2006-01-11T01:18:22Z","timestamp":1136942302000},"page":"755-761","source":"Crossref","is-referenced-by-count":25,"title":["Optimized multilayer perceptrons for molecular classification and diagnosis using genomic data"],"prefix":"10.1093","volume":"22","author":[{"given":"Zuyi","family":"Wang","sequence":"first","affiliation":[{"name":"Center for Genetic Medicine, Children's National Medical Center 1 \u00a0 1 \u00a0 \u00a0 Washington, DC 20010, USA"},{"name":"Department of Electrical Engineering and Computer Science, The Catholic University of America 2 \u00a0 2 \u00a0 \u00a0 Washington, DC 20064, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"The Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University 3 \u00a0 3 \u00a0 \u00a0 Arlington, VA 22203, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Xuan","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, The Catholic University of America 2 \u00a0 2 \u00a0 \u00a0 Washington, DC 20064, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibin","family":"Dong","sequence":"additional","affiliation":[{"name":"The Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University 3 \u00a0 3 \u00a0 \u00a0 Arlington, VA 22203, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marina","family":"Bakay","sequence":"additional","affiliation":[{"name":"Center for Genetic Medicine, Children's National Medical Center 1 \u00a0 1 \u00a0 \u00a0 Washington, DC 20010, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanjian","family":"Feng","sequence":"additional","affiliation":[{"name":"The Bradley Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University 3 \u00a0 3 \u00a0 \u00a0 Arlington, VA 22203, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Clarke","sequence":"additional","affiliation":[{"name":"Departments of Oncology, Physiology and Biophysics, Lombardi Comprehensive Cancer Center, Georgetown University 4 \u00a0 4 \u00a0 \u00a0 Washington, DC 20007, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eric P.","family":"Hoffman","sequence":"additional","affiliation":[{"name":"Center for Genetic Medicine, Children's National Medical Center 1 \u00a0 1 \u00a0 \u00a0 Washington, DC 20010, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2006,1,10]]},"reference":[{"key":"2023012408541044800_b1","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1038\/35020115","article-title":"Molecular classification of cutaneous malignant melanoma by gene expression profiling","volume":"406","author":"Bittner","year":"2000","journal-title":"Nature"},{"key":"2023012408541044800_b2","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1073\/pnas.97.1.262","article-title":"Knowledge-based analysis of microarray gene expression data by using support vector machines","volume":"97","author":"Brown","year":"2000","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023012408541044800_b3","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1126\/science.286.5439.531","article-title":"Molecular classification of cancer: class discovery and class prediction by gene expression monitoring","volume":"286","author":"Golub","year":"1999","journal-title":"Science"},{"key":"2023012408541044800_b4","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1023\/A:1010920819831","article-title":"A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems","volume":"45","author":"Hand","year":"2001","journal-title":"Machine Learning"},{"key":"2023012408541044800_b5","volume-title":"Neural Networks: a Comprehensive Foundation","author":"Haykin","year":"1999","edition":"2nd edn"},{"key":"2023012408541044800_b6","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/34.824819","article-title":"Statistical pattern recognition: a review","volume":"22","author":"Jain","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2023012408541044800_b7","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1038\/89044","article-title":"Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks","volume":"7","author":"Khan","year":"2001","journal-title":"Nat. Med."},{"key":"2023012408541044800_b8","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1038\/sj.leu.2403167","article-title":"Pediatric acute lymphoblastic leukemia (ALL) gene expression signature classify an independent cohort of adult ALL patients","volume":"18","author":"Kohlmann","year":"2004","journal-title":"Leukemia"},{"key":"2023012408541044800_b9","doi-asserted-by":"crossref","first-page":"3544","DOI":"10.1093\/bioinformatics\/bth441","article-title":"The \u2018subsequent artificial neural network\u2019 (SANN) approach might bring more classificatory power to ANN-based DNA microarray analyses","volume":"20","author":"Linder","year":"2004","journal-title":"Bioinformatics"},{"key":"2023012408541044800_b10","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1109\/34.935849","article-title":"Multiclass linear dimension reduction by weighted pairwise Fisher criteria","volume":"23","author":"Loog","year":"2001","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2023012408541044800_b11","first-page":"365","article-title":"Statistical analysis of ROC data in evaluating diagnostic performance","author":"Metz","year":"1986","journal-title":"Mult. Regression Anal."},{"key":"2023012408541044800_b12","doi-asserted-by":"crossref","first-page":"2051","DOI":"10.1126\/science.293.5537.2051","article-title":"Machine learning for science: state of the art and future prospects","volume":"293","author":"Mjolsness","year":"2001","journal-title":"Science"},{"key":"2023012408541044800_b13","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/1471-2105-4-13","article-title":"Neural network analysis of lymphoma microarray data: prognosis and diagnosis near-perfect","volume":"4","author":"O'Neill","year":"2003","journal-title":"BMC Bioinformatics"},{"key":"2023012408541044800_b14","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/415436a","article-title":"Prediction of central nervous system embryonal tumour outcome based on gene expression","volume":"415","author":"Pomeroy","year":"2002","journal-title":"Nature"},{"key":"2023012408541044800_b15","doi-asserted-by":"crossref","first-page":"15149","DOI":"10.1073\/pnas.211566398","article-title":"Multiclass cancer diagnosis using tumor gene expression signatures","volume":"98","author":"Ramaswamy","year":"2001","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023012408541044800_b16","first-page":"62","article-title":"Accuracy of feature selection and extraction in statistical and neural net pattern classification","volume":"2","author":"Raudys","year":"1992","journal-title":"Proc. Int. Conf. Pattern Recogn."},{"key":"2023012408541044800_b17","first-page":"287","article-title":"Why do multilayer perceptrons have favorable small sample properties?","volume-title":"Pattern Recognition in Practice IV, Elsevier Science B. V","author":"Raudys","year":"1994"},{"key":"2023012408541044800_b18","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1109\/34.601254","article-title":"On dimensionality, sample size, and classification error of nonparametric linear classification algorithms","volume":"19","author":"Raudys","year":"1997","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2023012408541044800_b19","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1109\/34.75512","article-title":"Small sample size effects in statistical pattern recognition: recommendations for practitioners","volume":"13","author":"Raudys","year":"1991","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2023012408541044800_b20","first-page":"343","article-title":"The role of the number of training samples on weight initialisation of artificial neural net classifier","volume":"1","author":"Raudys","year":"1992","journal-title":"RNNS\/IEEE Symp. Neuroinform. Neurocomput."},{"key":"2023012408541044800_b21","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511812651","volume-title":"Pattern Recognition and Neural Networks","author":"Ripley","year":"1996"},{"key":"2023012408541044800_b22","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1038\/nm0102-68","article-title":"Diffuse large B-cell lymphoma outcome prediction by gene-expression profiling and supervised machine learning","volume":"8","author":"Shipp","year":"2002","journal-title":"Nat. Med."},{"key":"2023012408541044800_b23","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1093\/bioinformatics\/bti033","article-title":"A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis","volume":"21","author":"Statnikov","year":"2005","journal-title":"Bioinformatics"},{"key":"2023012408541044800_b24","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1038\/415530a","article-title":"Gene expression profiling predicts clinical outcome of breast cancer","volume":"415","author":"van't Veer","year":"2002","journal-title":"Nature"},{"key":"2023012408541044800_b25","first-page":"273","article-title":"Optimizing multilayer perceptrons by discriminatory component analysis","author":"Wang","year":"2004","journal-title":"Proc. IEEE Workshop on Machine Learning for Signal Processing"},{"key":"2023012408541044800_b26","doi-asserted-by":"crossref","first-page":"6883","DOI":"10.1158\/0008-5472.CAN-04-0695","article-title":"Prediction of clinical outcome using gene expression profiling and artificial neural networks for patients with neuroblastoma [Erratum (2005) Cancer Res., 65, 374.]","volume":"64","author":"Wei","year":"2004","journal-title":"Cancer Res."},{"key":"2023012408541044800_b27","doi-asserted-by":"crossref","first-page":"11462","DOI":"10.1073\/pnas.201162998","article-title":"Predicting the clinical status of human breast cancer by using gene expression profiles","volume":"98","author":"West","year":"2001","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"2023012408541044800_b28","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1109\/ICPR.2004.1334170","article-title":"Robust feature selection by weighted fisher criterion for multiclass prediction in gene expression profiling","volume":"2","author":"Xuan","year":"2004","journal-title":"Proc. Int. Conf. Pattern Recogn."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/22\/6\/755\/48840517\/bioinformatics_22_6_755.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/22\/6\/755\/48840517\/bioinformatics_22_6_755.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T09:35:48Z","timestamp":1674552948000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/22\/6\/755\/296044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,1,10]]},"references-count":28,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2006,3,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btk036","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2006,3,15]]},"published":{"date-parts":[[2006,1,10]]}}}