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
Furey, T. S., Cristianini, N., Duffy, N., Bednarski, D. W., Schummer, M., & Haussler, D. (2000) · Bioinformatics · doi:10.1093/bioinformatics/16.10.906 · Cited by 2,443 · cited 1×
“Thus far, these other methods have not been fully explored to extract the genes or features that are most important for the classification performance and which also will be of interest to cancer biologist”
MethodKnowledge-based analysis of microarray gene expression data by using support vector machines
Brown, M. P. S., Grundy, W. N., Lin, D., Cristianini, N., Sugnet, C. W., Furey, T. S., Ares, M., & Haussler, D. (2000) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.97.1.262 · Cited by 2,308 · cited 1×
“Other approaches that share the parametric nature of ANNs and have been utilized to classify gene-expression profiles include Support Vector Machine”
MethodPrinciples and Practice of Pediatric Oncology
(1990) · Annals of Internal Medicine · doi:10.7326/0003-4819-112-8-636_3 · Cited by 2,027 · cited 1×
“The entire dataset of all 88 experiments was first quality filtered (1) and then the dimensionality was further reduced by principal component analysis (PCA) to 10 PCA projections (2), from the original 6567 expression values.”
MethodMolecular classification of cutaneous malignant melanoma by gene expression profiling
Bittner, M., Meltzer, P., Chen, Y., Jiang, Y., Seftor, E., Hendrix, M., Radmacher, M., Simon, R., Yakhini, Z., Ben-Dor, A., et al. (2000) · Nature · doi:10.1038/35020115 · Cited by 1,990 · cited 1×
“The samples were again randomly partitioned and the entire training process repeated (7).”
BackgroundSelf-citationUse of a cDNA microarray to analyse gene expression patterns in human cancer
(1996) · Nature Genetics · doi:10.1038/ng1296-457 · Cited by 1,951 · 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”
MethodSelf-citationGene-Expression Profiles in Hereditary Breast Cancer
Hedenfalk, I., Duggan, D., Chen, Y., Radmacher, M., Bittner, M., Simon, R., Meltzer, P., Gusterson, B., Esteller, M., Raffeld, M., et al. (2001) · New England Journal of Medicine · doi:10.1056/nejm200102223440801 · Cited by 1,733
Self-citationRatio-based decisions and the quantitative analysis of cDNA microarray images
Chen, Y. (1997) · Journal of Biomedical Optics · doi:10.1117/1.429838 · Cited by 637
Principles and Practice of Pediatric Oncology
Labotka, R. J. (1997) · JAMA: The Journal of the American Medical Association · doi:10.1001/jama.1997.03540480082049 · Cited by 630
Gene expression profiling of alveolar rhabdomyosarcoma with cDNA microarrays.
Khan, J. I., Simon, R., Bittner, M. L., Chen, Y., Leighton, S. B., Pohida, T. J., Smith, P. D., Jiang, Y. Y., Gooden, G. C., Trent, J. M., et al. (1998) · PubMed · Cited by 437
Self-citationKhan, J., Bittner, M. L., Saal, L. H., Teichmann, U., Azorsa, D. O., Gooden, G. C., Pavan, W. J., Trent, J. M., & Meltzer, P. S. (1999) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.96.23.13264 · Cited by 314
Self-citationHughes, S. E. (1997) · Journal of Histochemistry & Cytochemistry · doi:10.1177/002215549704500710 · Cited by 280
Experimental evidence for a neural origin of Ewing's sarcoma of bone.
Cavazzana, A. O., Miser, J., Jefferson, J., & Triche, T. J. (1987) · PubMed Central · Cited by 263
El‐Badry, O. M., Minniti, C. P., Kohn, E. C., Houghton, P. J., Daughaday, W. H., & Helman, L. J. (1990) · PubMed · Cited by 249
Song, W. K. (1992) · The Journal of Cell Biology · doi:10.1083/jcb.117.3.643 · Cited by 238
Neuroblastoma and the differential diagnosis of small-, round-, blue-cell tumors
Finegold, M. J., Triche, T. J., & Askin, F. B. (1983) · Human Pathology · doi:10.1016/s0046-8177(83)80202-0 · Cited by 222 · cited 1×
“In clinical practice, several techniques are used for diagnosis, including immunohistochemistr”
MethodKumar, S., Perlman, E., Harris, C. A., Raffeld, M., & Tsokos, M. (2000) · Modern Pathology · doi:10.1038/modpathol.3880179 · Cited by 218
Kovar, H., Dworzak, M. N., Strehl, S., Schnell, E., Ambros, I. M., Ambros, P. F., & Gadner, H. (1990) · PubMed · Cited by 188
Acute Myocardial Infarction Detected in the 12-Lead ECG by Artificial Neural Networks
Hedén, B., Öhlin, H., Rittner, R., & Edenbrandt, L. (1997) · Circulation · doi:10.1161/01.cir.96.6.1798 · Cited by 174 · cited 1×
“ANNs have been recently applied to clinical problems such as diagnosing myocardial infarct”
MethodSavchenko, V. L., McKanna, J. A., Nikonenko, I. R., & Skibo, G. G. (2000) · Neuroscience · doi:10.1016/s0306-4522(99)00538-2 · Cited by 168
Amplification of fgfr4 gene in human breast and gynecological cancers
Jaakkola, S., Salmikangas, P., Nylund, S. J., Lehtovirta, P., Nevanlinna, H. A., Partanen, J. M., Armstrong, E., & Pyrhönen, S. O. (1993) · International Journal of Cancer · doi:10.1002/ijc.2910540305 · Cited by 142 · cited 1×
“but not in adult muscle, and is of interest because of its potential role in tumor growt”
BackgroundExpression of the Fgf6 gene is restricted to developing skeletal muscle in the mouse embryo
deLapeyrière, O., Ollendorff, V., Planche, J., Ott, M. O., Pizette, S., Coulier, F., & Birnbaum, D. (1993) · Development · doi:10.1242/dev.118.2.601 · Cited by 136
Fibroblast growth factor receptors display both common and distinct signaling pathways.
Shaoul, E., Reich‐Slotky, R., Berman, B., & Ron, D. (1995) · PubMed · Cited by 124
Green, B. N., Jones, S. B., Streck, R. D., Wood, T. L., Rotwein, P. S., & Pintar, J. E. (1994) · Endocrinology · doi:10.1210/endo.134.2.7507840 · Cited by 108 · cited 1×
“Twenty genes were highly expressed only in RMS, including eight specific for muscle tissue and five ( FGFR4 , IGF2 , MYL4 , ITGA7 and IGFBP5”
BackgroundSequence of an expressed human β-tubulin gene containing tenAlufamily members
Lee, M. G.-S., Loomis, C. A., & Cowan, N. J. (1984) · Nucleic Acids Research · doi:10.1093/nar/12.14.5823 · Cited by 95
Ashizawa, K., Ishida, T., MacMahon, H., Vyborny, C. J., Katsuragawa, S., & Doi, K. (1999) · Academic Radiology · doi:10.1016/s1076-6332(99)80055-5 · Cited by 94 · cited 1×
“and interpreting radiographs and magnetic resonance image”
Taylor, C. J., Patel, K. S., Jones, T. A., Kiely, F., Stavola, B. L. D., & Sheer, D. (1993) · British Journal of Cancer · doi:10.1038/bjc.1993.22 · Cited by 77 · cited 1×
“Next, the 25 test experiments were set aside and the 63 training experiments were randomly partitioned into 3 groups (3).”
MethodMcManus, A. P., Gusterson, B. A., Pinkerton, R., & SHIPLEY, J. M. (1996) · The Journal of Pathology · Cited by 75
Differentially expressed olfactomedin-related glycoproteins (Pancortins) in the brain
Nagano, T., Nakamura, A., Mori, Y., Maeda, M., Takami, T., Shiosaka, S., Takagi, H., & Sato, M. (1998) · Molecular Brain Research · doi:10.1016/s0169-328x(97)00271-4 · Cited by 63 · cited 1×
“Of the 14 genes that have not yet been reported to be highly expressed in EWS, 4 ( TUBB5, ANXA1, NOE1 and GSTM5”
BackgroundTakahashi, Y., Campbell, E., Hirata, Y., Takayama, T., & Listowsky, I. (1993) · Journal of Biological Chemistry · doi:10.1016/s0021-9258(18)52957-4 · Cited by 62
Human Fetal Muscle and Cultured Myotubes Derived from It Contain a Fetal-Specific Myosin Light Chain
Strohman, R. C., Micou-Eastwood, J., Glass, C. A., & Matsuda, R. (1983) · Science · doi:10.1126/science.6879193 · Cited by 43 · cited 1×
“Twenty genes were highly expressed only in RMS, including eight specific for muscle tissue and five ( FGFR4 , IGF2 , MYL4 , ITGA7 and IGFBP5”
BackgroundCharacterization of Human Glycogenin-2, a Self-glucosylating Initiator of Liver Glycogen Metabolism
Mu, J., & Roach, P. J. (1998) · Journal of Biological Chemistry · doi:10.1074/jbc.273.52.34850 · Cited by 43 · cited 1×
“Of the 16 genes highly expressed only in EWS, two ( MIC2 and GYG2 ) have been previously describe”
BackgroundZeng, L., Takeya, M., & Takahashi, K. (1996) · The Journal of Pathology · doi:10.1002/(sici)1096-9896(199602)178:2<221::aid-path441>3.0.co;2-w · Cited by 34
Silipo, R., Gori, M., Taddei, A., Varanini, M., & Marchesi, C. (1995) · Computers and Biomedical Research · doi:10.1006/cbmr.1995.1021 · Cited by 30 · cited 2×
“t(11;22)(q24;q12) in EWS, and the PAX3-FKHR; t(2;13)(q35;q14) in alveolar rhabdomyosarcoma(1) (ARMS).”
BackgroundMethodNeural network analysis of breast cancer from MRI findings.
Abdolmaleki, P., Buadu, L. D., Murayama, S., Murakami, J., Hashiguchi, N., Yabuuchi, H., & Masuda, K. (1997) · PubMed · Cited by 27
Holtrich, U., Bräuninger, A., Strebhardt, K., & Rübsamen‐Waigmann, H. (1991) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.88.23.10411 · Cited by 26 · cited 1×
“Although the high expression of FGFR4 in most cases of RMS indicates that it may be relevant to the biology of this tumor, it is also expressed in some other cancer”
BackgroundMcKarney, L. A., Overall, M. L., & Dziadek, M. A. (1997) · The International Journal of Developmental Biology · doi:10.1387/ijdb.9240565 · Cited by 21
Cited by
Gene expression profiling predicts clinical outcome of breast cancer
van 't Veer, L. J., Dai, H., van de Vijver, M. J., He, Y. D., Hart, A. A. M., Mao, M., Peterse, H. L., van der Kooy, K., Marton, M. J., Witteveen, A. T., et al. (2002) · Nature · doi:10.1038/415530a · Cited by 9,536
Survey of Clustering Algorithms
Xu, R., & WunschII, D. (2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2005.845141 · Cited by 6,197
“and 5 non-SRBCT samples [164].”
Management of Hepatocellular Carcinoma *
Bruix, J., & Sherman, M. (2005) · Hepatology · doi:10.1002/hep.20933 · Cited by 5,857
Artificial intelligence in healthcare: past, present and future
Jiang, F., Jiang, Y., Zhi, H., Dong, Y., Li, H., Ma, S., Wang, Y., Dong, Q., Shen, H., & Wang, Y. (2017) · Stroke and Vascular Neurology · doi:10.1136/svn-2017-000101 · Cited by 4,837
mixOmics: An R package for ‘omics feature selection and multiple data integration
Rohart, F., Gautier, B., Singh, A., & Lê Cao, K.-A. (2017) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1005752 · Cited by 4,056
“The study investigates Small Round Blue Cell Tumors (SRBCT, [35]) of 63 tumour samples with the expression levels of 2,308 genes.”
BackgroundMethod
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.