RNA-seq is gradually becoming the dominating technique employed to access the global gene expression in biological samples, allowing more flexible protocols and robust analysis. However, the nature of RNA-seq results imposes new data-handling challenges when it comes to computational analysis. With the increasing employment of machine learning (ML) techniques in biomedical sciences, databases that could provide curated data sets treated with state-of-the-art approaches already adapted to ML protocols, become essential for testing new algorithms. In this study, we present the Benchmarking of ARtificial intelligence Research: Curated RNA-seq Database (BARRA:CuRDa). BARRA:CuRDa was built exclusively for cancer research and is composed of 17 handpicked RNA-seq data sets for Homo sapiens that were gathered from the Gene Expression Omnibus, using rigorous filtering criteria. All data sets were individually submitted to sample quality analysis, removal of low-quality bases and artifacts from the experimental process, removal of ribosomal RNA, and estimation of transcript-level abundance. Moreover, all data sets were tested using standard approaches in the field, which allows them to be used as benchmark to new ML approaches. A feature selection analysis was also performed on each data set to investigate the biological accuracy of basic techniques. Results include genes already related to their specific tumoral tissue a large amount of long noncoding RNA and pseudogenes. BARRA:CuRDa is available at http://sbcb.inf.ufrgs.br/barracurda.
Get full access to this article
View all access options for this article.
References
1.
Aguirre-PortolésC., FeliuJ., RegleroG., et al.2018. Abca1 overexpression worsens colorectal cancer prognosis by facilitating tumour growth and caveolin-1-dependent invasiveness, and these effects can be ameliorated using the bet inhibitor apabetalone. Mol. Oncolgy. 12, 1735–1752.
2.
ArcherT.C., FertigE.J., GoslineS.J., et al.2016. Systems approaches to cancer biology. Cancer Res. 76, 6774–6777.
3.
BlalockE.M.2003. A Beginner's Guide to Microarrays. Springer: Boston, Massachusetts, USA.
4.
BlohmD. and Guiseppi-ElieA.2001. New developments in microarray technology. Curr. Opin. Biotechnol. 12, 41–47.
5.
BolgerA.M., LohseM., and UsadelB.2014. Trimmomatic: A flexible trimmer for illumina sequence data. Bioinformatics. 30, 2114–2120.
6.
Bolón-CanedoV., Sánchez-MaroñoN., and Alonso-BetanzosA.2016. Feature selection for high-dimensional data. Progr. Artif. Intell. 5, 65–75.
7.
BreimanL.2001. Random forests. Mach. Learn. 45, 5–32.
8.
CaoX., LiY., LuoR.-Z., et al.2015. Expression of cystatin sn significantly correlates with recurrence, metastasis, and survival duration in surgically resected non-small cell lung cancer patients. Sci. Rep. 5, 8230.
9.
CeramiE., GaoJ., DogrusozU., et al.2012. The cbio cancer genomics portal: An open platform for exploring multidimensional cancer genomics data. Cancer Discov. 2, 401–404.
10.
ChanJ.J. and TayY.2018. Noncoding RNA: RNA regulatory networks in cancer. Int. J. Mol. Sci. 19, 1310.
11.
ChawlaN.V., BowyerK.W., HallL.O., et al.2002. Smote: Synthetic minority over-sampling technique. J. Artif. Int. Res. 16, 321–357.
12.
ChiY., WangD., WangJ., et al.2019. Long non-coding RNA in the pathogenesis of cancers. Cells. 8, 1015.
13.
CortesC. and VapnikV.1995. Support-vector networks. Mach. Learn. 20, 273–297.
14.
DaiD.-n., LiY., ChenB., et al.2017. Elevated expression of cst1 promotes breast cancer progression and predicts a poor prognosis. J. Mol. Med. 95, 873–886.
15.
DavisS. and MeltzerP.2007. Geoquery: A bridge between the gene expression omnibus (GEO) and bioconductor. Bioinformatics. 14, 1846–1847.
16.
De MartinoM., ForzatiF., ArraC., et al.2016. Hmga1-pseudogenes and cancer. Oncotarget. 7, 28724.
FarynaM., KonermannC., AulmannS., et al.2012. Genome-wide methylation screen in low-grade breast cancer identifies novel epigenetically altered genes as potential biomarkers for tumor diagnosis. FASEB J. 26, 4937–4950.
20.
FeltesB.C., ChandelierE.B., GrisciB.I., et al.2019. Cumida: An extensively curated microarray database for benchmarking and testing of machine learning approaches in cancer research. J. Comput. Biol. 26, 376–386.
21.
FrancoH.L., NagariA., MalladiV.S., et al.2018. Enhancer transcription reveals subtype-specific gene expression programs controlling breast cancer pathogenesis. Genome Res. 28, 159–170.
22.
FrankE., HallM.A., and WittenI.H.2016. The WEKA Workbench. Online Appendix for “Data Mining: Practical Machine Learning Tools and Techniques.” Morgan Kaufmann, 4th edition.
23.
GeisserS.1975. The predictive sample reuse method with applications. J. Am. Stat. Assoc. 70, 320–328.
24.
GeraciF., SahaI., and BianchiniM.2020. Rna-seq analysis: Methods, applications and challenges. Front. Genet. 11, 220.
25.
HarringtonP.2012. Machine Learning in Action, Volume 5. Manning Greenwich, CT, Shelter Island, NY, 11964.
26.
HrdlickovaR., ToloueM., and TianB.2017. Rna-seq methods for transcriptome analysis. Wiley Interdiscipl. Rev. RNA. 8, e1364.
27.
HuangY. and LiL. 2011. Naive Bayes classification algorithm based on small sample set, 34–39. CCIS2011-Proceedings: 2011 IEEE International Conference on Cloud Computing and Intelligence Systems, Beijing, China.
28.
IshimineH., ZhouR., SumitomoK., et al.2016. Lipase member h frequently overexpressed in human esophageal adenocarcinomas. Tumor Biol. 37, 2075–2081.
29.
JiangZ., HaoY., DingX., et al.2016. The effects and mechanisms of slc34a2 on tumorigenicity in human non-small cell lung cancer stem cells. Tumor Biol. 37, 10383–10392.
30.
Jirapech-UmpaiT. and AitkenS.2005. Feature selection and classification for microarray data analysis: Evolutionary methods for identifying predictive genes. BMC Bioinform. 6, 148.
31.
KotsiantisS.B., ZaharakisI.D., and PintelasP.E.2006. Machine learning: A review of classification and combining techniques. Artif. Intell. Rev. 26, 159–190.
32.
KovalenkoT. and PatrushevL.2018. Pseudogenes as functionally significant elements of the genome. Biochemistry (Moscow). 83, 1332–1349.
33.
KubatM.2017. An Introduction to Machine Learning. Springer International: Switzerland, 1st edition.
34.
LachenbruchP.A. and MickeyM.R.1968. Estimation of error rates in discriminant analysis. Technometrics. 10, 1–11.
35.
LazarC., TaminauJ., MeganckS., et al.2012. A survey on filter techniques for feature selection in gene expression microarray analysis. IEEE ACM Trans. Comput. Biol. Bioinform. 9, 1106–1119.
36.
LiB. and DeweyC.N.2011. RSEM: Accurate transcript quantification from RNA-seq data with or without a reference genome. BMC Bioinfo. 12, 323.
37.
LiJ. and LiuH.2017. Challenges of feature selection for big data analytics. IEEE Intell. Syst. 32, 9–15.
38.
LiW.V. and LiJ.J.2018. Modeling and analysis of RNA-seq data: A review from a statistical perspective. Quant. Biol. 6, 195–209.
39.
LiZ., MouH., WangT., et al.2013. A non-secretory form of fam3b promotes invasion and metastasis of human colon cancer cells by upregulating slug expression. Cancer Lett. 328, 278–284.
40.
LingadahalliS., JadhaoS., SungY.Y., et al.2018. Novel lncRNA LINC00844 regulates prostate cancer cell migration and invasion through AR signaling. Mol. Cancer Res. 16, 1865–1878.
41.
LiuB., LiuJ., LiuK., et al.2019a. A prognostic signature of five pseudogenes for predicting lower-grade gliomas. Biomed. Pharmacother. 117, 109116.
42.
LiuF., XingL., ZhangX., et al.2019b. A four-pseudogene classifier identified by machine learning serves as a novel prognostic marker for survival of osteosarcoma. Genes. 10, 414.
43.
LoveM.I., HuberW., and AndersS.2014. Moderated estimation of fold change and dispersion for RNA-seq data with deseq2. Genome Biol. 15, 550.
44.
MaatenL.v.d. and HintonG. 2008. Visualizing data using t-SNE. J. Mach. Learn Res. 9, 2579–2605.
45.
MirzapoiazovaT., MambetsarievN., LennonF.E., et al.2015. Habp2 is a novel regulator of hyaluronan-mediated human lung cancer progression. Front. Oncol. 5, 164.
46.
NiknafsY.S., HanS., MaT., et al.2016. The lncRNA landscape of breast cancer reveals a role for DSCAM-AS1 in breast cancer progression. Nat. Commun. 7, 1–13.
47.
PedregosaF., VaroquauxG., GramfortA., et al.2011. SCIKIT-learn: Machine learning in python. J. Mach. Learn. Res. 12, 2825–2830.
48.
RodriguezM. and PotterD.A.2013. Cyp1a1 regulates breast cancer proliferation and survival. Mol. Cancer Res. 11, 780–792.
49.
Rodríguez-RoderoS., FernándezA.F., Fernández-MoreraJ.L., et al.2013. DNA methylation signatures identify biologically distinct thyroid cancer subtypes. J. Clin. Endocrinol. Metabol. 98, 2811–2821.
50.
SafavianS.R. and LandgrebeD.1991. A survey of decision tree classifier methodology. IEEE Trans. Syst. Man Cybernet. 21, 660–674.
51.
ŠimundićA.-M.2009. Measures of diagnostic accuracy: Basic definitions. Ejifcc. 19, 203.
52.
SokolovaM., JapkowiczN., and SzpakowiczS.2006. Beyond accuracy, f-score and ROC: A family of discriminant measures for performance evaluation,1015–1021. In Sattar, A., and Kang, B., eds. AI 2006: Advances in Artificial Intelligence. Springer, Berlin, Heidelberg.
53.
SonesonC., LoveM.I., and RobinsonM.D.2015. Differential analyses for RNA-seq: Transcript-level estimates improve gene-level inferences. F1000Res. 4, 1521.
54.
SongP., JiangB., LiuZ., et al.2017. A three-lncRNA expression signature associated with the prognosis of gastric cancer patients. Cancer Med. 6, 1154–1164.
55.
STONEM.1977. Asymptotics for and against cross-validation. Biometrika. 64, 29–35.
56.
SunK., JiaZ., DuanR., et al.2019. Long non-coding RNA XIST regulates mir-106b-5p/p21 axis to suppress tumor progression in renal cell carcinoma. Biochem. Biophys. Res. Commun. 510, 416–420.
57.
TangJ., AlelyaniS., and LiuM.2014. Feature selection for classification: A review. In Aggarwal, C.C. ed. Data Classification: Algorithms and Applications. (first edition). Chapman and Hall/CRC. Pgs 37–58.
58.
TangX.-D., ZhangD.-D., JiaL., et al.2018. lncRNA AFAP1-AS1 promotes migration and invasion of non-small cell lung cancer via up-regulating IRF7 and the rig-i-like receptor signaling pathway. Cell. Physiol. Biochem. 50179–195.
TutarL., ÖzgürA., and TutarY.2018. Involvement of miRNAs and pseudogenes in cancer,45–66. In Wu, W. ed. MicroRNA and Cancer. Methods in Molecular Biology, vol 1699. Humana Press: New York, New York, USA.
61.
TutarY., ÖzgürA., TutarE., et al.2016. Regulation of oncogenic genes by micrornas and pseudogenes in human lung cancer. Biomed. Pharmacother. 83, 1182–1190.
62.
Van Den BergeK., HembachK.M., SonesonC., et al.2019. RNA sequencing data: Hitchhiker's guide to expression analysis. Ann. Rev. Biomed. Data Sci. 2, 139–173.
63.
VerleysenM. and FrançoisD.2005. The curse of dimensionality in data mining and time series prediction. IWANN. 5, 758–770.
64.
WangO., ZhengZ., WangQ., et al.2017. Zcchc12, a novel oncogene in papillary thyroid cancer. J. Cancer Res. Clin. Oncol. 143, 1679–1686.
65.
XiaoL., LanzR.B., FrolovA., et al.2016. The germ cell gene TDRD1 as an erg target gene and a novel prostate cancer biomarker. Prostate. 76, 1271–1284.
66.
XuL., LuC., HuangY., et al.2018. SPINK1 promotes cell growth and metastasis of lung adenocarcinoma and acts as a novel prognostic biomarker. BMB Reports. 51, 648.
67.
YangG., LiangY., ZhengT., et al.2016. FCN2 inhibits epithelial–mesenchymal transition-induced metastasis of hepatocellular carcinoma via TGF-β/SMAD signaling. Cancer Lett. 378, 80–86.
68.
YinD., LuX., SuJ., et al.2018. Long noncoding RNA AFAP1-AS1 predicts a poor prognosis and regulates non–small cell lung cancer cell proliferation by epigenetically repressing p21 expression. Mol. Cancer. 17, 1–12.
69.
ZararsızG.2015. Development and application of novel machine learning approaches for RNA-seq data classification. Int. J. Comput. Trends Tech. (IJCT). 2017, 62–64.
70.
ZhangX., XiaoZ., LiuX., et al.2012. The potential role of ORM2 in the development of colorectal cancer. PLoS One. 7, e31868.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
