{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T12:36:52Z","timestamp":1765888612143,"version":"3.37.3"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,5,12]],"date-time":"2021-05-12T00:00:00Z","timestamp":1620777600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,5,12]],"date-time":"2021-05-12T00:00:00Z","timestamp":1620777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P30CA54174","1UL1RR025767-01","K99CA248944"],"award-info":[{"award-number":["P30CA54174","1UL1RR025767-01","K99CA248944"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004917","name":"CPRIT","doi-asserted-by":"crossref","award":["RP190346","RP160732","RP190346"],"award-info":[{"award-number":["RP190346","RP160732","RP190346"]}],"id":[{"id":"10.13039\/100004917","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>The state-of-the-art deep learning based cancer type prediction can only predict cancer types whose samples are available during the training where the sample size is commonly large. In this paper, we consider how to utilize the existing training samples to predict cancer types unseen during the training. We hypothesize the existence of a set of type-agnostic expression representations that define the similarity\/dissimilarity between samples of the same\/different types and propose a novel one-shot learning model called CancerSiamese to learn this common representation. CancerSiamese accepts a pair of query and support samples (gene expression profiles) and learns the representation of similar or dissimilar cancer types through two parallel convolutional neural networks joined by a similarity function.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>We trained CancerSiamese for cancer type prediction for primary and metastatic tumors using samples from the Cancer Genome Atlas (TCGA) and MET500. Network transfer learning was utilized to facilitate the training of the CancerSiamese models. CancerSiamese was tested for different <jats:italic>N<\/jats:italic>-way predictions and yielded an average accuracy improvement of 8% and 4% over the benchmark 1-Nearest Neighbor (1-NN) classifier for primary and metastatic tumors, respectively. Moreover, we applied the guided gradient saliency map and feature selection to CancerSiamese to examine 100 and 200 top marker-gene candidates for the prediction of primary and metastatic cancers, respectively. Functional analysis of these marker genes revealed several cancer related functions between primary and metastatic tumors.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusion<\/jats:title>\n                <jats:p>This work demonstrated, for the first time, the feasibility of predicting unseen cancer types whose samples are limited. Thus, it could inspire new and ingenious applications of one-shot and few-shot learning solutions for improving cancer diagnosis, prognostic, and our understanding of cancer.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12859-021-04157-w","type":"journal-article","created":{"date-parts":[[2021,5,12]],"date-time":"2021-05-12T20:02:28Z","timestamp":1620849748000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["CancerSiamese: one-shot learning for predicting primary and metastatic tumor types unseen during model training"],"prefix":"10.1186","volume":"22","author":[{"given":"Milad","family":"Mostavi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Chiao","family":"Chiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yidong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6268-5357","authenticated-orcid":false,"given":"Yufei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,12]]},"reference":[{"issue":"1","key":"4157_CR1","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.ccell.2019.12.004","volume":"37","author":"NJ Birkbak","year":"2020","unstructured":"Birkbak NJ, McGranahan N. Cancer genome evolutionary trajectories in metastasis. Cancer Cell. 2020;37(1):8\u201319.","journal-title":"Cancer Cell"},{"key":"4157_CR2","volume-title":"Molecular biology of cancer: mechanisms, targets, and therapeutics","author":"L Pecorino","year":"2012","unstructured":"Pecorino L. Molecular biology of cancer: mechanisms, targets, and therapeutics. Oxford: Oxford University Press; 2012."},{"key":"4157_CR3","doi-asserted-by":"crossref","unstructured":"Cancer Genome Atlas Research, N, et al., The Cancer Genome Atlas Pan-Cancer analysis project. Nat Genet. 2013;45(10):1113\u201320.","DOI":"10.1038\/ng.2764"},{"issue":"7667","key":"4157_CR4","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1038\/nature23306","volume":"548","author":"DR Robinson","year":"2017","unstructured":"Robinson DR, et al. Integrative clinical genomics of metastatic cancer. Nature. 2017;548(7667):297\u2013303.","journal-title":"Nature"},{"issue":"7619","key":"4157_CR5","doi-asserted-by":"publisher","first-page":"S63","DOI":"10.1038\/537S63a","volume":"537","author":"V Prasad","year":"2016","unstructured":"Prasad V. Perspective: the precision-oncology illusion. Nature. 2016;537(7619):S63.","journal-title":"Nature"},{"key":"4157_CR6","doi-asserted-by":"crossref","unstructured":"Ahn, T., et al. Deep learning-based identification of cancer or normal tissue using gene expression data. In 2018 IEEE international conference on bioinformatics and biomedicine (BIBM). 2018. IEEE.","DOI":"10.1109\/BIBM.2018.8621108"},{"key":"4157_CR7","unstructured":"Joseph M, Devaraj M, Leung CK. DeepGx: deep learning using gene expression for cancer classification. In 2019 IEEE\/ACM international conference on advances in social networks analysis and mining (ASONAM). 2019. IEEE."},{"key":"4157_CR8","doi-asserted-by":"crossref","unstructured":"Lyu B, Haque A. Deep learning based tumor type classification using gene expression data. In: Proceedings of the 2018 ACM international conference on bioinformatics, computational biology, and health informatics. 2018.","DOI":"10.1145\/3233547.3233588"},{"key":"4157_CR9","unstructured":"Bazgir, O., et al. REFINED (REpresentation of Features as Images with NEighborhood Dependencies): a novel feature representation for convolutional neural networks. arXiv e-prints. arxXiv:1912.05687, 2019."},{"key":"4157_CR10","doi-asserted-by":"publisher","first-page":"4248","DOI":"10.1093\/bioinformatics\/btaa500","volume":"36","author":"N Fatima","year":"2020","unstructured":"Fatima N, Rueda L. iSOM-GSN: an integrative approach for transforming multi-omic data into gene similarity networks via self-organizing maps. Bioinformatics. 2020;36:4248\u201354.","journal-title":"Bioinformatics"},{"issue":"1","key":"4157_CR11","doi-asserted-by":"publisher","first-page":"11399","DOI":"10.1038\/s41598-019-47765-6","volume":"9","author":"A Sharma","year":"2019","unstructured":"Sharma A, et al. DeepInsight: a methodology to transform a non-image data to an image for convolution neural network architecture. Sci Rep. 2019;9(1):11399.","journal-title":"Sci Rep"},{"issue":"Suppl 5","key":"4157_CR12","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s12920-020-0677-2","volume":"13","author":"M Mostavi","year":"2020","unstructured":"Mostavi M, et al. Convolutional neural network models for cancer type prediction based on gene expression. BMC Med Genomics. 2020;13(Suppl 5):44.","journal-title":"BMC Med Genomics"},{"key":"4157_CR13","doi-asserted-by":"publisher","first-page":"2066","DOI":"10.1093\/bib\/bbz144","volume":"21","author":"YC Chiu","year":"2019","unstructured":"Chiu YC, et al. Deep learning of pharmacogenomics resources: moving towards precision oncology. Brief Bioinform. 2019;21:2066\u201383.","journal-title":"Brief Bioinform"},{"issue":"4","key":"4157_CR14","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1109\/TPAMI.2006.79","volume":"28","author":"L Fei-Fei","year":"2006","unstructured":"Fei-Fei L, Fergus R, Perona P. One-shot learning of object categories. IEEE Trans Pattern Anal Mach Intell. 2006;28(4):594\u2013611.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4157_CR15","unstructured":"Lake B, et al. One shot learning of simple visual concepts. In: Proceedings of the annual meeting of the cognitive science society. 2011."},{"issue":"24","key":"4157_CR16","doi-asserted-by":"publisher","first-page":"5249","DOI":"10.1093\/bioinformatics\/btz411","volume":"35","author":"M Jeon","year":"2019","unstructured":"Jeon M, et al. ReSimNet: drug response similarity prediction using Siamese neural networks. Bioinformatics. 2019;35(24):5249\u201356.","journal-title":"Bioinformatics"},{"issue":"11","key":"4157_CR17","doi-asserted-by":"publisher","first-page":"1820","DOI":"10.1093\/bioinformatics\/bty887","volume":"35","author":"W Zheng","year":"2019","unstructured":"Zheng W, et al. SENSE: Siamese neural network for sequence embedding and alignment-free comparison. Bioinformatics. 2019;35(11):1820\u20138.","journal-title":"Bioinformatics"},{"key":"4157_CR18","doi-asserted-by":"crossref","unstructured":"Koh W, Hoon SJB. MapCell: Learning a comparative cell type distance metric with Siamese neural nets with applications towards cell-types identification across experimental datasets. 2019. bioRxiv:828699.","DOI":"10.1101\/828699"},{"issue":"14","key":"4157_CR19","doi-asserted-by":"publisher","first-page":"i305","DOI":"10.1093\/bioinformatics\/btz328","volume":"35","author":"M Chen","year":"2019","unstructured":"Chen M, et al. Multifaceted protein-protein interaction prediction based on Siamese residual RCNN. Bioinformatics. 2019;35(14):i305\u201314.","journal-title":"Bioinformatics"},{"key":"4157_CR20","doi-asserted-by":"crossref","unstructured":"Nourani E, Asgari E, McHardy AC, Mofrad MR. TripletProt: Deep representation learning of proteins based on siamese networks. 2020. bioRxiv:2020.05.11.088237.","DOI":"10.1101\/2020.05.11.088237"},{"key":"4157_CR21","unstructured":"Chung YA, Weng WH. Learning deep representations of medical images using siamese CNNs with application to content-based image retrieval. 2017. arXiv preprint arXiv:1711.08490."},{"key":"4157_CR22","doi-asserted-by":"crossref","unstructured":"Ma T, Zhang A. AffinityNet: semi-supervised few-shot learning for disease type prediction. In: Proceedings of the AAAI conference on artificial intelligence. 2019.","DOI":"10.1609\/aaai.v33i01.33011069"},{"key":"4157_CR23","unstructured":"Koch G, Zemel R, Salakhutdinov R. Siamese neural networks for one-shot image recognition. In: ICML deep learning workshop. 2015."},{"key":"4157_CR24","unstructured":"Chollet, F., keras. 2015."},{"issue":"2","key":"4157_CR25","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1016\/j.molonc.2007.03.005","volume":"1","author":"M Suzuki","year":"2007","unstructured":"Suzuki M, Tarin D. Gene expression profiling of human lymph node metastases and matched primary breast carcinomas: clinical implications. Mol Oncol. 2007;1(2):172\u201380.","journal-title":"Mol Oncol"},{"issue":"1","key":"4157_CR26","doi-asserted-by":"publisher","first-page":"13343","DOI":"10.1038\/s41598-019-50099-y","volume":"9","author":"T Iwamoto","year":"2019","unstructured":"Iwamoto T, et al. Distinct gene expression profiles between primary breast cancers and brain metastases from pair-matched samples. Sci Rep. 2019;9(1):13343.","journal-title":"Sci Rep"},{"issue":"3","key":"4157_CR27","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1093\/annonc\/mdw652","volume":"28","author":"TH Ho","year":"2017","unstructured":"Ho TH, et al. Differential gene expression profiling of matched primary renal cell carcinoma and metastases reveals upregulation of extracellular matrix genes. Ann Oncol. 2017;28(3):604\u201310.","journal-title":"Ann Oncol"},{"issue":"1","key":"4157_CR28","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.compeleceng.2013.11.024","volume":"40","author":"G Chandrashekar","year":"2014","unstructured":"Chandrashekar G, Sahin FJC, Engineering E. A survey on feature selection methods. Comput Electr Eng. 2014;40(1):16\u201328.","journal-title":"Comput Electr Eng"},{"issue":"1","key":"4157_CR29","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/nprot.2008.211","volume":"4","author":"W da Huang","year":"2009","unstructured":"da Huang W, Sherman BT, Lempicki RA. Systematic and integrative analysis of large gene lists using DAVID bioinformatics resources. Nat Protoc. 2009;4(1):44\u201357.","journal-title":"Nat Protoc"},{"issue":"1","key":"4157_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/nar\/gkn923","volume":"37","author":"W da Huang","year":"2009","unstructured":"da Huang W, Sherman BT, Lempicki RA. Bioinformatics enrichment tools: paths toward the comprehensive functional analysis of large gene lists. Nucleic Acids Res. 2009;37(1):1\u201313.","journal-title":"Nucleic Acids Res"},{"issue":"3","key":"4157_CR31","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1093\/carcin\/21.3.485","volume":"21","author":"SW Lowe","year":"2000","unstructured":"Lowe SW, Lin AW. Apoptosis in cancer. Carcinogenesis. 2000;21(3):485\u201395.","journal-title":"Carcinogenesis"},{"issue":"7","key":"4157_CR32","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.3390\/ijms18071544","volume":"18","author":"SK Saha","year":"2017","unstructured":"Saha SK, et al. Correlation between oxidative stress, nutrition, and cancer initiation. Int J Mol Sci. 2017;18(7):1544.","journal-title":"Int J Mol Sci"},{"issue":"1","key":"4157_CR33","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.arr.2012.10.004","volume":"12","author":"V Sosa","year":"2013","unstructured":"Sosa V, et al. Oxidative stress and cancer: an overview. Ageing Res Rev. 2013;12(1):376\u201390.","journal-title":"Ageing Res Rev"},{"issue":"114","key":"4157_CR34","first-page":"125","volume":"21","author":"C Voena","year":"2016","unstructured":"Voena C, Chiarle R. Advances in cancer immunology and cancer immunotherapy. Discov Med. 2016;21(114):125\u201333.","journal-title":"Discov Med"},{"key":"4157_CR35","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.12688\/f1000research.15064.2","volume":"7","author":"JL Chitty","year":"2018","unstructured":"Chitty JL, et al. Recent advances in understanding the complexities of metastasis. F1000Res. 2018;7:1169.","journal-title":"F1000Res"},{"issue":"1","key":"4157_CR36","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1186\/s13046-017-0619-9","volume":"36","author":"MZ Han","year":"2017","unstructured":"Han MZ, et al. TAGLN2 is a candidate prognostic biomarker promoting tumorigenesis in human gliomas. J Exp Clin Cancer Res. 2017;36(1):155.","journal-title":"J Exp Clin Cancer Res"},{"issue":"4","key":"4157_CR37","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1002\/path.4021","volume":"228","author":"S Meding","year":"2012","unstructured":"Meding S, et al. Tissue-based proteomics reveals FXYD3, S100A11 and GSTM3 as novel markers for regional lymph node metastasis in colon cancer. J Pathol. 2012;228(4):459\u201370.","journal-title":"J Pathol"},{"issue":"6","key":"4157_CR38","first-page":"1287","volume":"11","author":"M Mori","year":"2004","unstructured":"Mori M, et al. S100A11 gene identified by in-house cDNA microarray as an accurate predictor of lymph node metastases of gastric cancer. Oncol Rep. 2004;11(6):1287\u201393.","journal-title":"Oncol Rep"},{"issue":"10","key":"4157_CR39","doi-asserted-by":"publisher","first-page":"3031","DOI":"10.1016\/j.jprot.2011.11.033","volume":"75","author":"C Greenwood","year":"2012","unstructured":"Greenwood C, et al. Stat1 and CD74 overexpression is co-dependent and linked to increased invasion and lymph node metastasis in triple-negative breast cancer. J Proteomics. 2012;75(10):3031\u201340.","journal-title":"J Proteomics"},{"issue":"1","key":"4157_CR40","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s13058-016-0785-2","volume":"19","author":"X Zhang","year":"2017","unstructured":"Zhang X, et al. Thymosin beta 10 is a key regulator of tumorigenesis and metastasis and a novel serum marker in breast cancer. Breast Cancer Res. 2017;19(1):15.","journal-title":"Breast Cancer Res"},{"issue":"1","key":"4157_CR41","first-page":"305","volume":"12","author":"R Xiao","year":"2019","unstructured":"Xiao R, et al. TMSB10 promotes migration and invasion of cancer cells and is a novel prognostic marker for renal cell carcinoma. Int J Clin Exp Pathol. 2019;12(1):305\u201312.","journal-title":"Int J Clin Exp Pathol"},{"issue":"1","key":"4157_CR42","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.canlet.2016.01.054","volume":"374","author":"S Ji","year":"2016","unstructured":"Ji S, et al. ALDOA functions as an oncogene in the highly metastatic pancreatic cancer. Cancer Lett. 2016;374(1):127\u201335.","journal-title":"Cancer Lett"},{"issue":"Suppl 8","key":"4157_CR43","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1186\/s12918-018-0642-2","volume":"12","author":"HH Chen","year":"2018","unstructured":"Chen HH, et al. GSAE: an autoencoder with embedded gene-set nodes for genomics functional characterization. BMC Syst Biol. 2018;12(Suppl 8):142.","journal-title":"BMC Syst Biol"},{"key":"4157_CR44","doi-asserted-by":"publisher","first-page":"203","DOI":"10.3389\/fphy.2020.00203","volume":"8","author":"R Ramirez","year":"2020","unstructured":"Ramirez R, et al. Classification of cancer types using graph convolutional neural networks. Front Phys. 2020;8:203.","journal-title":"Front Phys"},{"key":"4157_CR45","doi-asserted-by":"publisher","DOI":"10.3389\/fphy.2020.00196","author":"S Salekin","year":"2020","unstructured":"Salekin S, et al. Predicting sites of epitranscriptome modifications using unsupervised representation learning based on generative adversarial networks. Front Phys. 2020. https:\/\/doi.org\/10.3389\/fphy.2020.00196.","journal-title":"Front. Phys."},{"key":"4157_CR46","doi-asserted-by":"crossref","unstructured":"Mostavi M, Salekin S, Huang Y. Deep-2'-O-Me: predicting 2'-O-methylation sites by convolutional neural networks. In 2018 40th annual international conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2018. IEEE.","DOI":"10.1109\/EMBC.2018.8512780"},{"key":"4157_CR47","unstructured":"Springenberg JT, et al. Striving for simplicity: the all convolutional net. arXiv preprint arxXiv:1412.6806. 2014."}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04157-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-021-04157-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-021-04157-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,12]],"date-time":"2021-05-12T20:03:09Z","timestamp":1620849789000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-021-04157-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,12]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["4157"],"URL":"https:\/\/doi.org\/10.1186\/s12859-021-04157-w","relation":{},"ISSN":["1471-2105"],"issn-type":[{"type":"electronic","value":"1471-2105"}],"subject":[],"published":{"date-parts":[[2021,5,12]]},"assertion":[{"value":"9 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"244"}}