Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks
Open accessThe DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.
Abstract
The purpose of this study was to develop a method of classifying cancers to specific diagnostic categories based on their gene expression signatures using artificial neural networks (ANNs). We trained the ANNs using the small, round blue-cell tumors (SRBCTs) as a model. These cancers belong to four distinct diagnostic categories and often present diagnostic dilemmas in clinical practice. The ANNs correctly classified all samples and identified the genes most relevant to the classification. Expression of several of these genes has been reported in SRBCTs, but most have not been associated with these cancers. To test the ability of the trained ANN models to recognize SRBCTs, we analyzed additional blinded samples that were not previously used for the training procedure, and correctly classified them in all cases. This study demonstrates the potential applications of these methods for tumor diagnosis and the identification of candidate targets for therapy.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Similar techniques have been used to diagnose cancer by Khan et al, where the inputs are the PCs estimated from 6567 genes and the outcomes are the tumour categories.34”
From Artificial intelligence in healthcare: past, present and future (2017) · cites this paper as [34]
Citations
Cites
Neural networks for pattern recognition
(1994) · Choice Reviews Online · doi:10.5860/choice.31-5500 · Cited by 18,538
Molecular portraits of human breast tumours
Perou, C. M., Sørlie, T., Eisen, M. B., van de Rijn, M., Jeffrey, S. S., Rees, C. A., Pollack, J. R., Ross, D. T., Johnsen, H., Akslen, L. A., et al. (2000) · Nature · doi:10.1038/35021093 · Cited by 16,261 · cited 1×
“Monitoring global gene-expression levels by cDNA microarrays provides an additional tool for elucidating tumor biology as well as the potential for molecular diagnostic classification of cance”
MethodCluster analysis and display of genome-wide expression patterns
Eisen, M. B., Spellman, P. T., Brown, P. O., & Botstein, D. (1998) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.95.25.14863 · Cited by 16,184
Nishimura, R., Osako, T., Nishiyama, Y., Tashima, R., Nakano, M., Fujisue, M., Toyozumi, Y., & Arima, N. (2013) · Oncology · doi:10.1159/000353099 · Cited by 13,166
Neural Networks for Pattern Recognition
Bishop, C. M. (1995) · doi:10.1093/oso/9780198538493.001.0001 · Cited by 12,287
Golub, T. R., Slonim, D. K., Tamayo, P., Huard, C., Gaasenbeek, M., Mesirov, J. P., Coller, H., Loh, M. L., Downing, J. R., Caligiuri, M. A., et al. (1999) · Science · doi:10.1126/science.286.5439.531 · Cited by 11,516 · cited 1×
“Once the models were calibrated they were used to rank the genes according to their importance for the classification (8).”
MethodDistinct types of diffuse large B-cell lymphoma identified by gene expression profiling
Alizadeh, A. A., Eisen, M. B., Davis, R. E., Ma, C., Lossos, I. S., Rosenwald, A., Boldrick, J. C., Sabet, H., Tran, T., Yu, X., et al. (2000) · Nature · doi:10.1038/35000501 · Cited by 9,925 · cited 1×
“This was repeated using each of the 3 groups for validation (6).”
MethodGoodall, C. (1988) · Technometrics · doi:10.1080/00401706.1988.10488412 · Cited by 8,675
Jolliffe, I. T. (1986) · Springer Series in Statistics · doi:10.1007/978-1-4757-1904-8 · Cited by 8,273
Elkablawy, M. A., Albasri, A. M., Mohammed, R. A., Hussainy, A. S., Nouh, M. M., & Alhujaily, A. S. (2016) · Saudi Medical Journal · doi:10.15537/smj.2016.2.12285 · Cited by 4,382
Cited by
Items 401–500 of 999
Towards knowledge-based gene expression data mining
Bellazzi, R., & Zupan, B. (2007) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2007.06.005 · Cited by 83
“, [39]).”
Null space based feature selection method for gene expression data
Sharma, A. K., Imoto, S., Miyano, S., & Sharma, V. (2011) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-011-0061-9 · Cited by 74
On Feature Selection through Clustering
Butterworth, R., Piatetsky-Shapiro, G., & Simovici, D. A. (2006) · Proceedings · doi:10.1109/icdm.2005.106 · Cited by 74
“Several approaches to feature selection have been explored, including wrapper techniques [12], support vector machines [6], neural networks [11] and prototypebased feature selection [9] that is close to our own approach.”
MethodPeptide functionalized nanoparticles for nonviral gene delivery
Levine, R. M., Scott, C. M., & Kokkoli, E. (2012) · Soft Matter · doi:10.1039/c2sm26633d · Cited by 75
Aziz, R. M., Verma, C. K., & Srivastava, N. (2018) · Annals of Data Science · doi:10.1007/s40745-018-0155-2 · Cited by 77
“Authors classify and predict cancers using small round blue cell tumors (SRBCT) with PCA as dimension reduction and train ANN models with no hidden layers for classification [12].”
Classification of Individual Lung Cancer Cell Lines Based on DNA Methylation Markers
Marchevsky, A. M., Tsou, J. A., & Laird‐Offringa, I. A. (2004) · Journal of Molecular Diagnostics · doi:10.1016/s1525-1578(10)60488-6 · Cited by 75
Takahashi, M., Hayashi, H., Watanabe, Y., Sawamura, K., Fukui, N., Watanabe, J., Kitajima, T., Yamanouchi, Y., Iwata, N., Mizukami, K., et al. (2010) · Schizophrenia Research · doi:10.1016/j.schres.2009.12.024 · Cited by 75
“In cancer research, classification by gene expression signature is widely used to predict tumor classes, drug responses, and prognosis of individual subjects (Khan et al., 2001; Lin et al., 2007; O'Neill and Song, 2003).”
BackgroundMethodResultInfluentialSchaefer, K., Brachwitz, K., Wai, D., Braun, Y., Diallo, R. I., Korsching, E., Eisenacher, M., Voß, R., van Valen, F., Baer, C., et al. (2004) · Cancer Research · doi:10.1158/0008-5472.can-03-0809 · Cited by 74
Yu, Z., Chen, H., You, J., Wong, H., Liu, J., Li, L., & Han, G. (2014) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2014.2315996 · Cited by 77
Fast feature selection for interval-valued data through kernel density estimation entropy
Dai, J., Liu, Y., Chen, J., & Liu, X. (2020) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-020-01131-5 · Cited by 73
Wang, A., Liu, H., Yang, J., & Chen, G. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.105208 · Cited by 84
“The rapid development of microarray technology in the post-genome era enables us to simultaneous measure the expression profiles of thousands of genes [1 – 3].”
BackgroundMethodMChip: A Tool for Influenza Surveillance
Dawson, E. D., Moore, C. L., Smagala, J. A., Dankbar, D. M., Mehlmann, M., Townsend, M. B., Smith, C. B., Cox, N. J., Kuchta, R. D., & Rowlen, K. L. (2006) · Analytical Chemistry · doi:10.1021/ac061739f · Cited by 73
Statistical data processing in clinical proteomics
Smit, S., Hoefsloot, H. C. J., & Smilde, A. K. (2007) · Journal of Chromatography B · doi:10.1016/j.jchromb.2007.10.042 · Cited by 76
Development and validation of biomarker classifiers for treatment selection
Simon, R. M. (2007) · Journal of Statistical Planning and Inference · doi:10.1016/j.jspi.2007.06.010 · Cited by 78
“Some investigators have used linear combinations of gene expression values as predictors (Khan et al., 2001; West et al., 2001).”
BackgroundFeature Selection at the Discrete Limit
Zhang, M., Ding, C. H. Q., Zhang, Y., & Nie, F. (2014) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v28i1.8919 · Cited by 73
“…we apply it on three data sets: DNA dataset, which belongs to the Statlog collection and used in (Hsu and Lin 2002), and two publicly available microarray datasets: the small round blue cell tumors (SRBCT) dataset (Khan et al. 2001) and the malignant glioma (GLIOMA) dataset (Nutt et al. 2003).”
MethodPTPL1 is a direct transcriptional target of EWS-FLI1 and modulates Ewing's Sarcoma tumorigenesis
Abaan, O. D., Levenson, A. E., Khan, O. A., Furth, P. A., Üren, A., & Toretsky, J. A. (2005) · Oncogene · doi:10.1038/sj.onc.1208247 · Cited by 75
Expression analysis of pediatric solid tumor cell lines using oligonucleotide microarrays
Wai, D., Schaefer, K., Schramm, A. R., Korsching, E., van Valen, F., Ozaki, T., Boecker, W., Schweigerer, L., Dockhorn‐Dworniczak, B., & Poremba, C. (2002) · International Journal of Oncology · doi:10.3892/ijo.20.3.441 · Cited by 73
Detecting Outlier Samples in Microarray Data
Shieh, A. D., & Hung, Y. S. (2009) · Statistical Applications in Genetics and Molecular Biology · doi:10.2202/1544-6115.1426 · Cited by 74
MTar: a computational microRNA target prediction architecture for human transcriptome
S, V. C. S., Girijadevi, R., Nair, A. S., Pillai, S. S., & Pillai, R. M. (2010) · BMC Bioinformatics · doi:10.1186/1471-2105-11-s1-s2 · Cited by 76
A tail strength measure for assessing the overall univariate significance in a dataset
Taylor, J., & Tibshirani, R. (2005) · Biostatistics · doi:10.1093/biostatistics/kxj009 · Cited by 81
“The datasets ‘aud-over’ and ‘aud-sent’ are from an auditory functional magnetic resonance imaging study (Taylor and Worsley, 2005) with aud-over being overall activation and aud-sent a measure of hemodynamic delay (Liao et al., 2002) in response to different sentences. The dataset ‘dtiTS’ comes from a diffusion tensor…”
BackgroundPrognostic Value of the Human Kallikrein Gene 15 Expression in Ovarian Cancer
Yousef, G. M., Scorilas, A., Katsaros, D., Fracchioli, S., Iskander, L., Borgoño, C. A., de la Longrais, I. A. R., Puopolo, M., Massobrio, M., & Diamandis, E. P. (2003) · Journal of Clinical Oncology · doi:10.1200/jco.2003.09.111 · Cited by 71
New gene selection method for classification of cancer subtypes considering within‐class variation
Cho, J., Lee, D., Park, J. H., & Lee, I. (2003) · FEBS Letters · doi:10.1016/s0014-5793(03)00819-6 · Cited by 72
Gadekallu, T. R., & Khare, N. (2017) · International Journal of Fuzzy System Applications · doi:10.4018/ijfsa.2017040102 · Cited by 71
“…the tumor, along with Fisher Linear Discriminate analysis (Dudoit, Fridyand, & Speed, 2002), k-nearest neighbour (Li, Darden, Weinberg, Levine, & Pederson, 2001) decision tree, multilayer perceptron (Khan et al., 2001), and hold up vector machine (Jong, Mary, Cornuejols, Marchiori, & Sebag, 2004).”
DNA MICROARRAY TECHNOLOGY FOR TARGET IDENTIFICATION AND VALIDATION
Jayapal, M., & Melendez, A. J. (2006) · Clinical and Experimental Pharmacology and Physiology · doi:10.1111/j.1440-1681.2006.04398.x · Cited by 76
“Current supervised methods, among many others, include decision trees, Fischer linear discriminant, multilayer perceptrons, nearestneighbours’ classifiers and Parzen windows.(29) Another type of visualization tool as a means to predict data quality based on the parameters chosen is principal component analysis.”
MethodRandom forest for gene selection and microarray data classification
Moorthy, K., & Mohamad, M. S. (2011) · Bioinformation · doi:10.6026/97320630007142 · Cited by 71
“Dataset Name Genes Patients Classes Reference Adenocarcinoma 9868 76 2 [6] Brain 5597 42 5 [7] Breast2 4869 77 2 [8] Breast3 4869 95 3 [8] Colon 2000 62 2 [9] Leukemia 3051 38 2 [10] Lymphoma 4026 62 3 [11] NCI60 5244 61 8 [12] Prostate 6033 102 2 [13] SRBCT 2308 63 4 [14]”
Bayesian variable selection for disease classification using gene expression data
Ai-Jun, Y., & Song, X. (2009) · Bioinformatics · doi:10.1093/bioinformatics/btp638 · Cited by 71
Toxicogenomics in drug discovery: from preclinical studies to clinical trials
Yang, Y., Blomme, E. A. G., & Waring, J. F. (2004) · Chemico-Biological Interactions · doi:10.1016/j.cbi.2004.09.013 · Cited by 71
Peng, C., Wu, X., Yuan, W., Zhang, X., Zhang, Y., & Li, Y. (2019) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2019.2921961 · Cited by 79
“For the SRBCT dataset, MGRFE selected five genes and achieved 100 percent Acc in both 5-fold and 10-time 10-fold CV.”
InfluentialMixtures of Multivariate Power Exponential Distributions
Dang, U. J., Browne, R. P., & McNicholas, P. D. (2015) · Biometrics · doi:10.1111/biom.12351 · Cited by 68
“The srbct data contain gene expression microarray data from experiments on small round blue cell tumors (Khan et al., 2001).”
MethodLancashire, L., Powe, D. G., Reis-Filho, J. S., Rakha, E. A., Lemetre, C., Weigelt, B., Abdel-Fatah, T. M. A., Green, A. R., Mukta, R., Blamey, R. W., et al. (2009) · Breast Cancer Research and Treatment · doi:10.1007/s10549-009-0378-1 · Cited by 85
“Previous studies have shown the ability of microarrays [1] to successfully predict clinical outcome in a variety of malignancies [2–6].”
BackgroundResultHybrid genetic algorithm-neural network: Feature extraction for unpreprocessed microarray data
Tong, D. L., & Schierz, A. C. (2011) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2011.06.008 · Cited by 70
Ying, H., Suzuki, H., Furumoto, H., Walker, R. L., Meltzer, P. S., Willingham, M. C., & Cheng, S.-Y. (2003) · Carcinogenesis · doi:10.1093/carcin/bgg111 · Cited by 75
Tan, Y., Shi, L., Tong, W., & Wang, C. (2005) · Nucleic Acids Research · doi:10.1093/nar/gki144 · Cited by 71
Analyzing Array Data Using Supervised Methods
Ringnér, M., Peterson, C., & Khan, J. I. (2002) · Pharmacogenomics · doi:10.1517/14622416.3.3.403 · Cited by 70
“Secondly, the learning process can be carefully monitored using a cross-validation scheme to avoid overtraining [26].”
BackgroundMethodInfluentialSelf-citationMicroarrays—the 21st century divining rod?
He, Y. D., & Friend, S. H. (2001) · Nature Medicine · doi:10.1038/89022 · Cited by 70
Computational intelligence approaches for pattern discovery in biological systems
Fogel, G. B. (2008) · Briefings in Bioinformatics · doi:10.1093/bib/bbn021 · Cited by 69
Shukla, A. K., Singh, P., & Vardhan, M. (2018) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2018.10.009 · Cited by 68
Altered expression of cell cycle genes distinguishes aggressive neuroblastoma
Krasnoselsky, A. L., Whiteford, C. C., Wei, J. S., Bilke, S., Westermann, F., Chen, Q., & Khan, J. I. (2004) · Oncogene · doi:10.1038/sj.onc.1208341 · Cited by 69
Self-citationGlobal Analysis of Gene Expression: Methods, Interpretation, and Pitfalls
Fryer, R. M., Randall, J., Yoshida, T., Hsiao, L., Blumenstock, J. E., Jensen, K. E., Dimofte, T., Jensen, R. V., & Gullans, S. R. (2002) · Nephron Experimental Nephrology · doi:10.1159/000049901 · Cited by 80
MULTICLASS CANCER CLASSIFICATION USING GENE EXPRESSION PROFILING AND PROBABILISTIC NEURAL NETWORKS
Berrar, D., Downes, C. S., & Dubitzky, W. (2002) · Pacific Symposium on Biocomputing (PSB) · doi:10.1142/9789812776303_0002 · Cited by 69
“used an artificial neural network approach for the classification of microarray data, including both tissue biopsy material and cell lines [9].”
BackgroundMethodEvolving connectionist systems for knowledge discovery from gene expression data of cancer tissue
Futschik, M. E., Reeve, A. E., & Kasabov, N. K. (2003) · Artificial Intelligence in Medicine · doi:10.1016/s0933-3657(03)00063-0 · Cited by 69
“The classification of cancer types was achieved by using statistical as well as machine learning techniques [8,13].”
MethodHan, F., Yang, C., Wu, Y., Zhu, J., Ling, Q.-H., Song, Y., & Huang, D.-S. (2015) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2015.2465906 · Cited by 74
Hidden Markov models for cancer classification using gene expression profiles
Nguyen, T. T., Khosravi, A., Creighton, D., & Nahavandi, S. (2015) · Information Sciences · doi:10.1016/j.ins.2015.04.012 · Cited by 68
“In order to train as many examples as possible, the leave one out cross validation (LOOCV) [16,13] is employed.”
MethodAge-specific profiles of tissue-level composition and mechanical properties in murine cortical bone
Raghavan, M., Sahar, N. D., Kohn, D. H., & Morris, M. D. (2012) · Bone · doi:10.1016/j.bone.2011.12.026 · Cited by 73
“Further, the visualizations directly use the original variables, unlike multidimensional scaling or partial least squares approaches that use their computed combinations [51,52].”
MethodThe three M’s: melanoma, microphthalmia‐associated transcription factor and microRNA
Bell, R. E., & Levy, C. (2011) · Pigment Cell & Melanoma Research · doi:10.1111/j.1755-148x.2011.00931.x · Cited by 68
“, 2005), predicting responses to therapy (Khan et al., 2001; Winnepenninckx et al., 2006), and constructing and calibrating network models of genes that are co-regulated or involved in the same cellular processes (Schäfer and Strimmer, 2005; Segal et al.”
BackgroundMao, Y., Zhou, X., Pi, D., Sun, Y., & Wong, S. T. C. (2005) · BioMed Research International · doi:10.1155/jbb.2005.160 · Cited by 68
“In this experiment, we consider the small round blue-cell tumors (SRBCTs) of childhood, which include neuroblastoma (NB), rhabdomyosarcoma (RMS), nonHodgkin lymphoma (NHL), and the Ewing sarcoma (EWS) in [25].”
BackgroundMethodDas, S., Das, T., & Chakraborty, S. K. (2005) · Sensors and Actuators B Chemical · doi:10.1016/j.snb.2005.08.012 · Cited by 67
Mixture models for assessing differential expression in complex tissues using microarray data
Ghosh, D. (2004) · Bioinformatics · doi:10.1093/bioinformatics/bth139 · Cited by 71
Genomics and proteomics: Emerging technologies in clinical cancer research
Chung, C. H., Levy, S., Chaurand, P., & Carbone, D. P. (2006) · Critical Reviews in Oncology/Hematology · doi:10.1016/j.critrevonc.2006.06.005 · Cited by 74
A kernel-based clustering method for gene selection with gene expression data
Chen, H., Zhang, Y., & Gutman, İ. (2016) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2016.05.007 · Cited by 68
Carr, K. M., Rosenblatt, K. P., Petricoin, E. F., & Liotta, L. A. (2004) · Human Genomics · doi:10.1186/1479-7364-1-2-134 · Cited by 65
“Specifically, the use of DNA microarrays has created robust molecular phenotypes for many tumours, including brain,(1,2) breast, colon,(11,12) gastric,(13) kidney,(14) leukaemia, lymphoma, lung, melanoma,(24) ovary, prostate and small, round blue-cell tumours of childhood.(33) In a subset of these studies, the gene ex…”
BackgroundDabba, A., Tari, A., & Meftali, S. (2020) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-020-02434-9 · Cited by 68
Hybrid clustering solution selection strategy
Yu, Z., Li, L., Gao, Y., You, J., Liu, J., Wong, H., & Han, G. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.04.005 · Cited by 66
“Table 2 provides a summary of the five cancer gene expression profiles, which includes the Lymphoma cancer dataset (Lymphoma [59]), the dataset for the small, round blue-cell tumors (SRBCT [60]), the Gliomas cancer dataset (Gliomas [61]), the dataset for the embryonal tumours of the central nervous system (ET-CNS [62]…”
BackgroundKovar, H. (2014) · Expert Opinion on Therapeutic Targets · doi:10.1517/14728222.2014.947963 · Cited by 72
PTPL1: a large phosphatase with a split personality
Abaan, O. D., & Toretsky, J. A. (2008) · Cancer and Metastasis Reviews · doi:10.1007/s10555-008-9114-2 · Cited by 66
Gibbs, I., Leavey, K., Benton, S. J., Grynspan, D., Bainbridge, S. A., & Cox, B. (2018) · American Journal of Obstetrics and Gynecology · doi:10.1016/j.ajog.2018.10.003 · Cited by 70
SGL-SVM: A novel method for tumor classification via support vector machine with sparse group Lasso
Huo, Y., Xin, L., Kang, C., Wang, M., Ma, Q., & Yu, B. (2019) · Journal of Theoretical Biology · doi:10.1016/j.jtbi.2019.110098 · Cited by 73
Breast cancer prognosis by combinatorial analysis of gene expression data
Alexe, G., Alexe, S., Axelrod, D. E., Bonates, T. O., Lozina, I., Reiß, M., & Hammer, P. L. (2006) · Breast Cancer Research · doi:10.1186/bcr1512 · Cited by 66
“Numerous statistical and machine learning methods have been successfully applied to the analysis of microarray datasets; these methods include cluster analysis (hierarchical clustering [4-7], self-organizing maps [8-10], and two-way clustering [11]), regression analysis [12], nearest neighborhood methods [14], decisio…”
MethodMcArdle, L. (2004) · Carcinogenesis · doi:10.1093/carcin/bgh173 · Cited by 66
“, (12), who demonstrated that different small round blue cell tumors, including neuroblastoma, rhabdomyosarcoma, non-Hodgkin lymphoma and Ewing tumors, could be distinguished on the basis of their patterns of gene expression.”
BackgroundMissing-value estimation using linear and non-linear regression with Bayesian gene selection
Zhou, X., Wang, X., & Dougherty, E. R. (2003) · Bioinformatics · doi:10.1093/bioinformatics/btg323 · Cited by 66
“We test our proposed methods on breast cancer data (Hedenfalk et al., 2001) and small round blue-cell tumor data (Khan et al., 2001).”
BackgroundMethodCheng, S., Cheng, L., Qin, S., Zhang, L., Liu, P., Liu, L., Xu, Z., & Wang, Q. (2022) · Water Resources Research · doi:10.1029/2021wr031412 · Cited by 67
“…understanding of underlying mechanisms, interpretable ML methods (called “explainable artificial intelligence”) have recently been used to explain what the ML models are learning (Miller, 2019), and to extract new insights from complex natural systems (Guidotti et al., 2019; Khan et al., 2001).”
BackgroundLee, Z.-J. (2007) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2007.09.004 · Cited by 65
“Recently, there aremany methods such as feature selection, correlation methods, nonparametric scoring approach, and Bayesian variable selection approach that are proposed to select informative genes from microarray data [7,11—23].”
MethodRAPTT: An Exact Two-Sample Test in High Dimensions Using Random Projections
Srivastava, R., Li, P., & Ruppert, D. (2015) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2015.1062771 · Cited by 93
“For example, van der Laan and Bryan (2001), Kosorok and Ma (2007), Kuelbs and Vidyashankar (2010), Clemencon, Depecker, and Vayatis (2009), Jacob, Neuvial, and Dudoit (2012), and Lu et al.”
BackgroundLancashire, L., Schmid, O., Shah, H., & Ball, G. (2005) · Computer applications in the biosciences · doi:10.1093/bioinformatics/bti368 · Cited by 66
“Their uses range from the prediction of outcome in acute lower-gastrointestinal haemorrhages (Das et al., 2003), the diagnosis of cancers (Khan et al., 2001; Batuello et al., 2001; Anagnostou et al., 2003; Peterson and Ringnér, 2003), to the identification of environmental influences on plant…”
BackgroundPredicting cancer type from tumour DNA signatures
Soh, K. P., Szczurek, E., Sakoparnig, T., & Beerenwinkel, N. (2017) · Genome Medicine · doi:10.1186/s13073-017-0493-2 · Cited by 69
Age and gender classification using brain–computer interface
Kaur, B., Singh, D., & Roy, P. P. (2018) · Neural Computing and Applications · doi:10.1007/s00521-018-3397-1 · Cited by 72
“Here, ANN feed-forward model was trained with two hidden layers and Sigmoid activation function.”
MethodInfluentialSelective Usage of D-Type Cyclins by Ewing’s Tumors and Rhabdomyosarcomas
Zhang, J., Hu, S., Schofield, D. E., Sorensen, P. H. B., & Triche, T. J. (2004) · Cancer Research · doi:10.1158/0008-5472.can-03-2594 · Cited by 68
“Gene expression profiling of ET, RMS, neuroblastoma, and Burkitt lymphoma cell lines as well as primary tumors with cDNA microarray further demonstrated high levels of cyclin D1 expression in ET and neuroblastoma but not in RMS or Burkitt lymphoma (16).”
BackgroundIntroduction to Scientific Computing
Holmes, M. H. (2016) · Texts in computational science and engineering · doi:10.1007/978-3-319-30256-0_1 · Cited by 65
Catto, J. W. F., Abbod, M., Wild, P. J., Linkens, D. A., Pilarsky, C. P., Rehman, I., Rosario, D. J., Denzinger, S., Burger, M., Stoehr, R., et al. (2009) · European Urology · doi:10.1016/j.eururo.2009.10.029 · Cited by 64
“A panel with 11 genes has a similar error to that with 158 genes (NFM) or 140 genes (ANN).”
BackgroundInfluentialMining gene expression data by interpreting principal components
Roden, J., King, B., Trout, D. E., Mortazavi, A., Wold, B. J., & Hart, C. E. (2006) · BMC Bioinformatics · doi:10.1186/1471-2105-7-194 · Cited by 67
“PCA is most commonly used in as a means of dimensionality reduction prior to clustering [7,17] or prior to classification [18,19].”
MethodClassification of asthma using artificial neural network
Badnjević, A., Gurbeta, L., Cifrek, M., & Marjanović, D. (2016) · International Convention on Information and Communication Technology, Electronics and Microelectronics · doi:10.1109/mipro.2016.7522173 · Cited by 64
“According to the application experts, the linear feed forward (FF) neural network are mostly used for classification task [16-20].”
MethodA tailored smart home for dementia care
Amiribesheli, M., & Bouchachia, H. (2017) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-017-0645-7 · Cited by 77
“About health monitoring in SHs, ANNs were used to diagnose and monitor chronic diseases as well to build medical decision support systems (Er et al., 2010; Khan et al., 2001; Lisboa and Taktak, 2006).”
MethodSteroid Hormone Regulation and Prognostic Value of the Human Kallikrein Gene 14 in Ovarian Cancer
Yousef, G. M., Fracchioli, S., Scorilas, A., Borgoño, C. A., Iskander, L., Puopolo, M., Massobrio, M., Diamandis, E. P., & Katsaros, D. (2003) · American Journal of Clinical Pathology · doi:10.1309/0ua57mnayv0mce9u · Cited by 64
“30‡ Serous (n = 70) 39 (56) 31 (44) Endometrioid (n = 28) 9 (32) 19 (68) Mucinous (n = 15) 10 (67) 5 (33) Clear cell (n = 16) 10 (63) 6 (38) Undifferentiated (n = 24) 11 (46) 13 (54) Status unknown (n = 2) — — Residual tumor (cm) .”
Beeksma, M., Verberne, S., van den Bosch, A. P. J., Das, E., Hendrickx, I., & Groenewoud, S. (2019) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-019-0775-2 · Cited by 73
Al-Batah, M. S., Zaqaibeh, B. M., Alomari, S. A., & Alzboon, M. S. (2019) · International Journal of Online and Biomedical Engineering (iJOE) · doi:10.3991/ijoe.v15i08.10617 · Cited by 63
“Nowadays, various kinds of machine learning and statistical approaches are used to classify tumour cells accurate such as support vector machines [15], k-nearest neighbor [30], and neural network techniques [24].”
BackgroundTraining multi-layer perceptron with artificial algae algorithm
Türkoğlu, B., & Kaya, E. (2020) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2020.07.001 · Cited by 63
Deep learning to infer eddy heat fluxes from sea surface height patterns of mesoscale turbulence
George, T. M., Manucharyan, G. E., & Thompson, A. F. (2021) · Nature Communications · doi:10.1038/s41467-020-20779-9 · Cited by 78
One-Versus-One and One-Versus-All Multiclass SVM-RFE for Gene Selection in Cancer Classification
Duan, K.-B., Rajapakse, J. C., & Nguyen, M. N. (2007) · Springer eBooks · doi:10.1007/978-3-540-71783-6_5 · Cited by 76
“SRBCT dataset is about small, round, blue cell tumors of childhood.”
MethodInfluentialFu, L., Jia, H., Dong, Q., Wu, J., Zhao, Y., Zhou, H.-J., Ren, N., Ye, Q.-H., & Qin, L. (2009) · BMC Cancer · doi:10.1186/1471-2407-9-49 · Cited by 63
“Based on one of the tumorigenesis and metastasis theories that genes favoring metastasis progression are initiated in the primary tumors [22,23], it is becoming a routine strategy to compare gene expression levels in tumor samples with different prognostic outcomes: cancer with- and without- metastasis [24-27], to fin…”
BackgroundDetection of Somatic Mutations by High-Resolution DNA Melting (HRM) Analysis in Multiple Cancers
Bosquet, J. G., Calcei, J. G., Wei, J. S., García‐Closas, M., Sherman, M. E., Hewitt, S. M., Vockley, J. G., Lissowska, J., Yang, H., Khan, J. I., et al. (2011) · PLoS ONE · doi:10.1371/journal.pone.0014522 · Cited by 60
“Neuroblastoma cell lines and their culture conditions are described elsewhere [22].”
BackgroundSelf-citationA multi-objective heuristic algorithm for gene expression microarray data classification
Lv, J., Peng, Q., Chen, X., & Sun, Z. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.04.020 · Cited by 61
Early diagnosis of gastrointestinal cancer by using case-based and rule-based reasoning
Saraiva, R., Perkusich, M., Silva, L. C. E., de Almeida, H. O., Siebra, C., & Perkusich, Â. (2016) · Expert Systems with Applications · doi:10.1016/j.eswa.2016.05.026 · Cited by 63
“Finally, Khan et al. (2001) focused on the small, round blue cell tumors (SRBCTs).”
BackgroundNikolaou, Z. M., Chrysostomou, C., Vervisch, L., & Cant, S. (2019) · Flow Turbulence and Combustion · doi:10.1007/s10494-019-00028-w · Cited by 71
“Despite numerous breakthrough applications of machine-learning in a wide range of areas such as gene-profiling [23], speech recognition [24], text-translation [25], decision-making [26, 27] etc. such methods have seen limited use for closure modelling in LES, with the few studies in the literature…”
MethodBicciato, S., Pandin, M., Didone, G., & Bello, C. D. (2002) · Biotechnology and Bioengineering · doi:10.1002/bit.10505 · Cited by 63
Binarization of microarray data on the basis of a mixture model.
Zhou, X., Wang, X., & Dougherty, E. R. (2003) · PubMed · Cited by 62
Ward, D. G., Cheng, Y., Nkontchou, G., Thar, T. T., Barget, N., Wei, W., Billingham, L. J., Martin, A., Beaugrand, M., & Johnson, P. J. (2006) · British Journal of Cancer · doi:10.1038/sj.bjc.6602923 · Cited by 64
“In the procedure of training a committee model, a 10-fold cross-validation approach was used to reduce the risk of ‘over fit’ (Khan et al, 2001).”
MethodRomualdi, C. (2003) · Human Molecular Genetics · doi:10.1093/hmg/ddg093 · Cited by 63
“Two experimental gene expression datasets were used to compare the selected discriminant analyses: (i) the NCI60 dataset—in a project of the National Cancer Institute for the screening of anti-cancer drugs, a cDNA array with 5519 genes was used to study the expression profiles of 60 human cell lines derived from nine…”
BackgroundMethodInfluentialResampling methods improve the predictive power of modeling in class-imbalanced datasets
Lee, P. (2014) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph110909776 · Cited by 62
“As the use of automated classifiers like decision trees, support vector machines (see [14] for example) and artificial neural networks (see [15] for example) are becoming much more popular in the medical literature, the use of resampling methods should be promoted as it apply on all these statistical models that targe…”
MethodUnsupervised Feature Selection With Weighted and Projected Adaptive Neighbors
Li, Z., Nie, F., Wu, D., Hu, Z., & Li, X. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3087632 · Cited by 64
“2) AR [35]; and 3) CMU-PIE [36] and three bioinformatics datasets: 1) SRBCT [37]; 2) LEU [38]; and 3) PROSTATE [39].”
MethodInfluentialArtificial intelligence in clinical research of cancers
Shao, D., Dai, Y., Li, N., Cao, X., Zhao, W., Li, C., Rong, Z., Huang, L., Wang, Y., & Zhao, J. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab523 · Cited by 71
“Some popular high-dimensional cancer microarray datasets, such as the small round blue cell tumor (SRBCT) dataset [58] and diffuse large B-cell lymphoma (DLBCL) [59], contain large number of experimental samples with corresponding genes expressions.”
Gene Selection Using Locality Sensitive Laplacian Score
Liao, B., Jiang, Y., Liang, W., Zhu, W., Cai, L., & Cao, Z. (2014) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2014.2328334 · Cited by 64
“In addition, MLLLeukemia and SRBCT are two multi-classi.cation problems.”
InfluentialA Kernel-Based Multivariate Feature Selection Method for Microarray Data Classification
Sun, S., Peng, Q., & Shakoor, A. (2014) · PLoS ONE · doi:10.1371/journal.pone.0102541 · Cited by 64
“Source: http://llmpp.nih.gov/ lymphoma; N SRBCT(SR)([34]).”
Abdi, M. J., Hosseini, S. M., & Rezghi, M. (2012) · Computational and Mathematical Methods in Medicine · doi:10.1155/2012/320698 · Cited by 62
“Various clustering, classification, and prediction techniques have been utilized to analyze, classify, and understand the gene expression data such as Fisher discriminant analysis [1], artificial neural networks [2], and support vector machines (SVM) [3].”
MethodLaplacian Linear Discriminant Analysis Approach to Unsupervised Feature Selection
Niijima, S., & Okuno, Y. (2009) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2007.70257 · Cited by 63
“For the SRBCT data set, the expression profiles already preprocessed following [17] were used.”
MethodInfluentialWang, W., Wang, J., Zhang, X., & Liu, G. (2019) · OncoTargets and Therapy · doi:10.2147/ott.s220700 · Cited by 64
Classification algorithms for phenotype prediction in genomics and proteomics
Habtom, W. R. (2007) · Frontiers in bioscience · doi:10.2741/2712 · Cited by 72
“(37) used an ANN-classifier approach to select a subset of genes for the multiclass prediction of small round blue cell tumors (SRBCTs).”
MethodChagas‐Paula, D. A., Oliveira, T. B., Zhang, T., Edrada‐Ebel, R., & Costa, F. B. D. (2015) · Planta Medica · doi:10.1055/s-0034-1396206 · Cited by 68
Chu, C., Yao, C., Chang, Y.-T., Chou, H., Chou, Y., Chen, K., Terng, H.-J., Huang, C.-S., Lee, C., Su, S., et al. (2014) · Disease Markers · doi:10.1155/2014/634123 · Cited by 61
Dissimilarity based ensemble of extreme learning machine for gene expression data classification
Lu, H., An, C., Zheng, E., & Lu, Y. (2013) · Neurocomputing · doi:10.1016/j.neucom.2013.02.052 · Cited by 65
Borjabad, A., Brooks, A. I., & Volsky, D. J. (2009) · Journal of Neuroimmune Pharmacology · doi:10.1007/s11481-009-9167-1 · Cited by 62
“…of disease states has been applied with great success to identification of complex molecular pathways in carcinogenesis and more precise classification, detection, and prognosis of some cancers (Golub et al. 1999; Khan et al. 2001; Martin et al. 2001; Ramaswamy et al. 2003; Parmigiani et al. 2004).”
Metadata
- Authors
- Khan, J., Wei, J. S., Ringnér, M., Saal, L. H., Ladanyi, M., Westermann, F., Berthold, F., Schwab, M., Antonescu, C. R., Peterson, C., & Meltzer, P. S.
- Affiliations
- National Institutes of Health (US)
- Memorial Sloan Kettering Cancer Center (US)
- German Cancer Research Center (DE)
- University of Cologne (DE)
- Lund University (SE)
- Corresponding author
- Khan, Javed
- Meltzer, Paul S.
- ORCID
- Venue
- Nature Medicine
- Published
- 2001-06
- Volume
- 7
- Issue
- 6
- Pages
- 673-679
- ISSN
- 1078-8956 (ISSN-L)
- 1546-170X
- PMC
- PMC1282521
- OpenAlex
- W1727290854
- Cited by
- 2,644
- References
- 46
- Citations by year
- 2026: 24 · 2025: 42 · 2024: 47 · 2023: 84 · 2022: 82 · 2021: 84 · 2020: 112 · 2019: 123 · 2018: 83 · 2017: 93 · 2016: 92 · 2015: 96 · 2014: 126 · 2013: 98 · 2012: 109
- FWCI
- 47.48
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Licence
- www.springer.com/tdm (tdm)
- Locations
- Nature Medicine (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Lund University Publications (Lund University) (submittedVersion)
- Funders
- National Cancer Institute (Z01SC010366)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Breast Cancer Treatment Studies
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Keywords
- cancer classification, gene expression profiling, artificial neural networks, small round cell tumor, diagnostic prediction, tumor diagnosis, gene expression signatures, drug target identification
- MeSH terms
- Burkitt Lymphoma, Data Interpretation, Statistical, Humans, Models, Biological, Neoplasms, Neuroblastoma, Rhabdomyosarcoma, Sarcoma, Ewing, Tumor Cells, Cultured, Neural Networks, Computer, Oligonucleotide Array Sequence Analysis, Gene Expression Profiling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.