Gaussian mixture clustering and imputation of microarray data
Open accessAbstract
MOTIVATION: In microarray experiments, missing entries arise from blemishes on the chips. In large-scale studies, virtually every chip contains some missing entries and more than 90% of the genes are affected. Many analysis methods require a full set of data. Either those genes with missing entries are excluded, or the missing entries are filled with estimates prior to the analyses. This study compares methods of missing value estimation. RESULTS: Two evaluation metrics of imputation accuracy are employed. First, the root mean squared error measures the difference between the true values and the imputed values. Second, the number of mis-clustered genes measures the difference between clustering with true values and that with imputed values; it examines the bias introduced by imputation to clustering. The Gaussian mixture clustering with model averaging imputation is superior to all other imputation methods, according to both evaluation metrics, on both time-series (correlated) and non-time series (uncorrelated) data sets.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Missing values in large-scale 'omics data can hinder downstream analyses.
“It has been shown that missing values in large-scale ‘omics data can hinder downstream analyses (Ouyang et al., 2004; Jörnsten et al., 2005).”
From Missing data in multi-omics integration: Recent advances through artificial intelligence (2023) · cites this paper as Ouyang et al., 2004
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Maximum Likelihood from Incomplete Data Via the <i>EM</i> Algorithm
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1977.tb01600.x · Cited by 50,444 · cited 1× · see citing works
“In GMCimpute, data are modeled by Gaussian mixtures, and missing entries are estimated by the Expectation– Maximization algorithm (EM; Dempster et al., 1977).”
Estimating the Dimension of a Model
Schwarz, G. (1978) · The Annals of Statistics · doi:10.1214/aos/1176344136 · Cited by 47,033 · cited 1× · see citing works
“With Gaussian mixture clustering, the Bayesian information criterion (BIC; Schwarz, 1978) and the Bayes factor (Kass and Raftery, 1995) can be applied to select the number of components.”
Cluster 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 12,617 · cited 3× · see citing works
“Clustering methods usually fall into two categories: hierarchical methods (Eisen et al., 1998) and relocational methods.”
Finding groups in data: an introduction to cluster analysis
(1991) · Choice Reviews Online · doi:10.5860/choice.28-4558 · Cited by 10,537 · see citing works
Estimating the Number of Clusters in a Data Set Via the Gap Statistic
Tibshirani, R., Walther, G., & Hastie, T. (2001) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/1467-9868.00293 · Cited by 6,205 · cited 1× · see citing works
“There are several statistics that estimate the number of clusters, such as the statistic B (Fowlkes and Mallows, 1983), the silhouette statistic (Kaufman and Rousseeuw, 1990), the gap statistic (Tibshirani et al., 2001).”
(1975) · CERN Document Server (European Organization for Nuclear Research) · Cited by 5,958 · see citing works
Genomic Expression Programs in the Response of Yeast Cells to Environmental Changes
Gasch, A. P., Spellman, P. T., Kao, C. M., Carmel-Harel, O., Eisen, M. B., Storz, G., Botstein, D., & Brown, P. O. (2000) · Molecular Biology of the Cell · doi:10.1091/mbc.11.12.4241 · Cited by 4,815 · cited 2× · see citing works
“The yeast environmental stress data (Gasch et al., 2000) in Stanford Microarray Database (Sherlock et al., 2001) contains 6361 rows and 156 columns.”
Missing Value Estimation Methods for DNA Microarrays
Troyanskaya, O., Cantor, M., Sherlock, G., Brown, P., Hastie, T., Tibshirani, R., Botstein, D., & Altman, R. B. (2001) · Bioinformatics · doi:10.1093/bioinformatics/17.6.520 · Cited by 4,230 · cited 4× · see citing works
“Troyanskaya et al. (2001) compared ROWimpute, k nearest neighbor imputation (KNNimpute), and singular value decomposition based imputation (SVDimpute).”
InfluentialModel-Based Gaussian and Non-Gaussian Clustering
Banfield, J. D., & Raftery, A. E. (1993) · Biometrics · doi:10.2307/2532201 · Cited by 2,427 · see citing works
A Method for Comparing Two Hierarchical Clusterings
Fowlkes, E. B., & Mallows, C. L. (1983) · Journal of the American Statistical Association · doi:10.1080/01621459.1983.10478008 · Cited by 1,515 · cited 2× · see citing works
“The value of K in k-means is determined by the sub-sampling algorithm in Ben-Hur et al. (2002) and the statistic B of Fowlkes and Mallows (1983), although Ben-Hur et al. used hierarchical clustering and we use k-means.”
Refining Initial Points for K-Means Clustering
Bradley, P. S., & Fayyad, U. M. (1998) · Cited by 1,036 · see citing works
Gaussian parsimonious clustering models
Celeux, G., & Govaert, G. (1995) · Pattern Recognition · doi:10.1016/0031-3203(94)00125-6 · Cited by 874 · see citing works
Model-based clustering and data transformations for gene expression data
Yeung, K. Y., Fraley, C., Murua, A., Raftery, A. E., & Ruzzo, W. L. (2001) · Bioinformatics · doi:10.1093/bioinformatics/17.10.977 · Cited by 869 · cited 3× · see citing works
“Yeung et al. (2001a) and Ghosh and Chinnaiyan (2002) have considered Gaussian mixture clustering of microarray data, but they did not apply the method to missing value estimations.”
Fundamentals of Matrix Computations.
S., G. W., & Watkins, D. S. (1992) · Mathematics of Computation · doi:10.2307/2153000 · Cited by 860 · cited 1× · see citing works
“In Singular Value Decomposition (SVD; Watkins, 1991), the m×n matrix A, m > n, is expressed as the product of three matrices: A = UUV T , where the m × m matrix U and the n × n matrix V are orthogonal matrices, and (not related to the covariance matrices of multivariate normal distributions) is an…”
A classification EM algorithm for clustering and two stochastic versions
Celeux, G., & Govaert, G. (1992) · Computational Statistics & Data Analysis · doi:10.1016/0167-9473(92)90042-e · Cited by 773 · cited 1× · see citing works
“K-means clustering (Hartigan, 1975) corresponds to a special case of Gaussian mixture clustering (Celeux and Govaert, 1992).”
Validating clustering for gene expression data
Yeung, K. Y., Haynor, D. R., & Ruzzo, W. L. (2001) · Bioinformatics · doi:10.1093/bioinformatics/17.4.309 · Cited by 713 · see citing works
A stability based method for discovering structure in clustered data
Ben‐Hur, A., Elisseeff, A., & Guyon, I. (2001) · Pacific Symposium on Biocomputing (PSB) · doi:10.1142/9789812799623_0002 · Cited by 559 · cited 2× · see citing works
“The value of K in k-means is determined by the sub-sampling algorithm in Ben-Hur et al. (2002) and the statistic B of Fowlkes and Mallows (1983), although Ben-Hur et al. used hierarchical clustering and we use k-means.”
The Stanford Microarray Database
Sherlock, G. J. (2001) · Nucleic Acids Research · doi:10.1093/nar/29.1.152 · Cited by 534 · cited 1× · see citing works
“The yeast environmental stress data (Gasch et al., 2000) in Stanford Microarray Database (Sherlock et al., 2001) contains 6361 rows and 156 columns.”
Fundamental patterns underlying gene expression profiles: Simplicity from complexity
Holter, N. S., Mitra, M., Maritan, A., Cieplak, M., Banavar, J. R., & Fedoroff, N. V. (2000) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.150242097 · Cited by 475 · cited 1× · see citing works
“Holter et al. (2000) showed that the product of the first two or three columns of UU and the corresponding rows of V T can capture the fundamental patterns in cell cycle data.”
Resampling Method for Unsupervised Estimation of Cluster Validity
Levine, E., & Domany, E. (2001) · Neural Computation · doi:10.1162/089976601753196030 · Cited by 275 · cited 1× · see citing works
“There are resampling procedures that determine the number of clusters (Levine and Domany, 2001; Yeung et al., 2001b; Ben-Hur et al., 2002).”
Mixture modelling of gene expression data from microarray experiments
Ghosh, D., & Chinnaiyan, A. M. (2002) · Bioinformatics · doi:10.1093/bioinformatics/18.2.275 · Cited by 208 · cited 1× · see citing works
“Yeung et al. (2001a) and Ghosh and Chinnaiyan (2002) have considered Gaussian mixture clustering of microarray data, but they did not apply the method to missing value estimations .”
A new approach to analyzing gene expression time series data
Bar‐Joseph, Z., Gerber, G. K., Gifford, D. K., Jaakkola, T., & Simon, I. (2002) · doi:10.1145/565196.565202 · Cited by 199 · cited 1× · see citing works
“Bar-Joseph et al. (2002) described a model-based spline fitting method for time-series data; it can estimate missing entries at observed time points, and it can also predict entire columns of data at unobserved time points.”
Flagged first, then by citations
Cited by
Sorted by citations
A Survey of Evolutionary Algorithms for Clustering
Hruschka, E. R., Campello, R. J. G. B., Freitas, A. A., & de Carvalho, A. C. P. L. F. (2009) · IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews) · doi:10.1109/tsmcc.2008.2007252 · Cited by 761 · see citing works
DrImpute: imputing dropout events in single cell RNA sequencing data
Gong, W., Kwak, I., Pota, P., Koyano‐Nakagawa, N., & Garry, D. J. (2018) · BMC Bioinformatics · doi:10.1186/s12859-018-2226-y · Cited by 311 · see citing works
“Various statistical methods have been proposed to 96 estimate the missing values in the data ([29], [30], [31], [32], [33]).”
MethodPham, T.-H., Qiu, Y., Zeng, J., Xie, L., & Zhang, P. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-020-00285-9 · Cited by 219 · see citing works
Handling data irregularities in classification: Foundations, trends, and future challenges
Das, S., Datta, S., & Chaudhuri, B. B. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.03.008 · Cited by 216 · see citing works
Liew, A. W., Law, N.-F., & Yan, H. (2010) · Briefings in Bioinformatics · doi:10.1093/bib/bbq080 · Cited by 218 · see citing works
“Nevertheless, unlike KNNimpute where K is usually taken to be around 10 to 20, the mixture components in GMCimpute can consists of hundreds of genes.”
MethodInfluentialMissing data in multi-omics integration: Recent advances through artificial intelligence
Flores, J. E., Claborne, D. M., Weller, Z. D., Webb-Robertson, B.-J. M., Waters, K. M., & Bramer, L. M. (2023) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2023.1098308 · Cited by 181 · see citing works
“It has been shown that missing values in large-scale ‘omics data can hinder downstream analyses (Ouyang et al., 2004; Jörnsten et al., 2005).”
BackgroundDealing with missing values in large-scale studies: microarray data imputation and beyond
Aittokallio, T. A. (2009) · Briefings in Bioinformatics · doi:10.1093/bib/bbp059 · Cited by 171 · see citing works
“the stability of clustering algorithms, such as hierarchical and k-means clustering, but their stability can be improved using imputation methods, such as KNN and GMC impute [6, 7].”
BackgroundMethodInfluentialRogers, S., Girolami, M., Kölch, W., Waters, K. M., Liu, T., Thrall, B. D., & Wiley, H. S. (2008) · Bioinformatics · doi:10.1093/bioinformatics/btn553 · Cited by 153 · see citing works
Improved methods for the imputation of missing data by nearest neighbor methods
Tutz, G., & Ramzan, S. (2015) · Computational Statistics & Data Analysis · doi:10.1016/j.csda.2015.04.009 · Cited by 151 · see citing works
“Several alternative procedures have been proposed that rely on the basic concept to impute values by building averages over qualifying neighbors, see, for example Ouyang et al. (2004), Kim et al. (2004), Sehgal et al. (2005), Scheel et al. (2005).”
BackgroundGene Expression Profile Classification: A Review
Asyalı, M. H., Çolak, D., Demirkaya, O., & Inan, M. S. (2006) · Current Bioinformatics · doi:10.2174/157489306775330615 · Cited by 145 · see citing works
“by assigning some reasonable values to missing data [40-42].”
BackgroundJournal De La Société Française De Statistique
Caussinus, H., & de Falguerolles, A. (2005) · Wiley eBooks · doi:10.1002/0471667196.ess7017 · Cited by 141 · see citing works
A Review of Integrative Imputation for Multi-Omics Datasets
Song, M., Greenbaum, J., Luttrell, J., Zhou, W., Wu, C., Shen, H., Gong, P., Zhang, C., & Deng, H.-W. (2020) · Frontiers in Genetics · doi:10.3389/fgene.2020.570255 · Cited by 127 · see citing works
DNA microarray data imputation and significance analysis of differential expression
Jörnsten, R., Wang, H.-Y., Welsh, W. J., & Ouyang, M. (2005) · Bioinformatics · doi:10.1093/bioinformatics/bti638 · Cited by 121 · see citing works
Improving missing value estimation in microarray data with gene ontology
Tuikkala, J., Elo, L. L., Nevalainen, O., & Aittokallio, T. A. (2005) · Bioinformatics · doi:10.1093/bioinformatics/btk019 · Cited by 114 · see citing works
CMF-Impute: an accurate imputation tool for single-cell RNA-seq data
Xu, J., Cai, L., Liao, B., Zhu, W. Q., & Yang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa109 · Cited by 107 · see citing works
Zhang, Y., Chen, Y., Gu, X., Sze, N. N., & Huang, J. (2023) · Accident Analysis & Prevention · doi:10.1016/j.aap.2023.107072 · Cited by 106 · see citing works
Sehgal, M. S. B., Gondal, I., & Dooley, L. S. (2005) · Computer applications in the biosciences · doi:10.1093/bioinformatics/bti345 · Cited by 105 · see citing works
“Despite the wide usage of microarray data, they frequently contain missing values with up to 90% of genes affected (Ouyang et al., 2004).”
BackgroundMethodInfluentialCelton, M., Malpertuy, A., Lelandais, G., & de Brevern, A. G. (2010) · BMC Genomics · doi:10.1186/1471-2164-11-15 · Cited by 97 · see citing works
“In addition we can list the following relevant methodologies applied in MVs replacement for microarray analysis: Support Vector Regression [39], Factor Analysis Regression [40], Ordinary Least Square Impute [41], Gaussian Mixture Clustering [42], LinCmb [43], Collateral Missing Value Estimation [44], Linear based mode…”
MethodMicroarray missing data imputation based on a set theoretic framework and biological knowledge
Gan, X. (2006) · Nucleic Acids Research · doi:10.1093/nar/gkl047 · Cited by 94 · see citing works
“Several methods including K-nearest neighbors (KNN) method (KNNimpute), the SVD method (SVDimpute) (12), least square imputation (LSimpute) (13), Bayesian principle component analysis (BPCA) (9), local least square imputation (LLSimpute) (14) and Gaussian mixture imputation (GMCimpute) (5) have all been used.”
BackgroundMethodITERATED LOCAL LEAST SQUARES MICROARRAY MISSING VALUE IMPUTATION
Cai, Z., Heydari, M., & Lin, G. (2006) · Journal of Bioinformatics and Computational Biology · doi:10.1142/s0219720006002302 · Cited by 83 · see citing works
“With some clustering information known ahead of time, Ouyang et al.(6) proposed to use the number of mis-clustered genes to measure the difference, in addition to NRMSE.”
MethodImproving cluster-based missing value estimation of DNA microarray data
Brás, L. P., & de Menezes, J. C. (2007) · Biomolecular Engineering · doi:10.1016/j.bioeng.2007.04.003 · Cited by 82 · see citing works
“In the literature, such evaluations are lacking, and only a few cases can be found (for example, see de Brevern et al., 2004; Ouyang et al., 2004; Scheel et al., 2005; Jörnsten et al., 2005).”
BackgroundSayani, A., Bueno-de-Mesquita, J. M., & van de Vijver, M. J. (2006) · Nature Clinical Practice Oncology · doi:10.1038/ncponc0587 · Cited by 77 · see citing works
Georgopoulos, P. G., & Lioy, P. J. (2006) · Journal of Toxicology and Environmental Health Part B · doi:10.1080/10937400600755929 · Cited by 69 · see citing works
“A computational implementation of this method was incorporated as a stand-alone module of MENTOR (Ouyang et al. 2004).”
MethodBiological impact of missing-value imputation on downstream analyses of gene expression profiles
Oh, S., Kang, D., Brock, G. N., & Tseng, G. C. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btq613 · Cited by 65 · see citing works
Scheel, I., Aldrin, M., Glad, I. K., Falk, R. S., Lyng, H., & Frigessi, A. (2005) · Bioinformatics · doi:10.1093/bioinformatics/bti708 · Cited by 64 · see citing works
Combining Fourier and lagged k -nearest neighbor imputation for biomedical time series data
Rahman, S. A., Huang, Y., Claassen, J., Heintzman, N. D., & Kleinberg, S. (2015) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2015.10.004 · Cited by 64 · see citing works
“In clustering based single imputation (SI) methods [19,20], data are first clustered using the non-missing values and then missing values are imputed using the instances of the cluster that contain the missing value instance.”
García, S., Luengo, J., & Herrera, F. (2014) · Intelligent systems reference library · doi:10.1007/978-3-319-10247-4_4 · Cited by 63 · see citing works
Metabolomics in the developmental origins of obesity and its cardiometabolic consequences
Hivert, M., Perng, W., Watkins, S. M., Newgard, C. B., Kenny, L. C., Kristal, B. S., Patti, M., ISGANAITIS, E. M., DeMeo, D. L., Oken, E., et al. (2015) · Journal of Developmental Origins of Health and Disease · doi:10.1017/s204017441500001x · Cited by 60 · see citing works
Probing infectious disease by single-cell RNA sequencing: Progresses and perspectives
Luo, G., Gao, Q., Zhang, S., & Yan, B. (2020) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2020.10.016 · Cited by 59 · see citing works
“Imputation is an appropriate method to address the problem [118,119].”
Locally linear reconstruction based missing value imputation for supervised learning
Kang, P. (2013) · Neurocomputing · doi:10.1016/j.neucom.2013.02.016 · Cited by 58 · see citing works
A Review on Missing Value Imputation Algorithms for Microarray Gene Expression Data
Moorthy, K., Mohamad, M. S., & Deris, S. (2014) · Current Bioinformatics · doi:10.2174/1574893608999140109120957 · Cited by 57 · see citing works
“Gaussian mixture clustering imputation or known as GMCimpute [15] is able to use more global correlation information even though it is categorized as local approach algorithm.”
BackgroundMissing value imputation for microarray data: a comprehensive comparison study and a web tool
Chiu, C.-C., Chan, S.-Y., Wang, C.-C., & Wu, W.-S. (2013) · BMC Systems Biology · doi:10.1186/1752-0509-7-s6-s12 · Cited by 52 · see citing works
“…values in microarray data disad-vantageously influences downstream analyses, such as discovery of differentially expressed genes [11,12], construction of gene regulatory networks [13,14], supervised classification of clinical samples [15], gene cluster analysis [10,16], and biomarker detection.”
BackgroundAdaptive filtering of microarray gene expression data based on Gaussian mixture decomposition
Marczyk, M., Jaksik, R., Polański, A., & Polańska, J. (2013) · BMC Bioinformatics · doi:10.1186/1471-2105-14-101 · Cited by 49 · see citing works
“In [20-23] mixture decompositions are used for unsupervised clustering of microarray data.”
MethodA Review On Missing Value Estimation Using Imputation Algorithm
Armina, R., Zain, A. M., Ali, N. A., & Sallehuddin, R. S. (2017) · Journal of Physics Conference Series · doi:10.1088/1742-6596/892/1/012004 · Cited by 47 · see citing works
“Even though GMCimpute is a local approach algorithm ,it is able to using more global correlation information.”
MethodInfluentialA Review of Imputation Strategies for Isobaric Labeling-Based Shotgun Proteomics
Bramer, L. M., Irvahn, J., Piehowski, P. D., Rodland, K. D., & Webb-Robertson, B.-J. M. (2021) · Journal of Proteome Research · doi:10.1021/acs.jproteome.0c00123 · Cited by 47 · see citing works
Missing value imputation for microarray gene expression data using histone acetylation information
Xiang, Q., Dai, X., Deng, Y., He, C., Wang, J., Feng, J., & Dai, Z. (2008) · BMC Bioinformatics · doi:10.1186/1471-2105-9-252 · Cited by 46 · see citing works
“Generally, microarray datasets are estimated to have more than 5% missing values and up to 90% of genes are affected [13,14].”
BackgroundMethodHephzibah Cathryn, R., Kumar, S. U., Younes, S. N., Zayed, H., & Doss, C. G. P. (2022) · Advances in protein chemistry and structural biology · doi:10.1016/bs.apcsb.2022.05.002 · Cited by 45 · see citing works
Alkhaleel, B. A. (2023) · International Journal of Critical Infrastructure Protection · doi:10.1016/j.ijcip.2023.100646 · Cited by 43 · see citing works
Robust imputation method for missing values in microarray data
Yoon, D., Lee, E. K., & Park, T. (2007) · BMC Bioinformatics · doi:10.1186/1471-2105-8-s2-s6 · Cited by 40 · see citing works
“Gaussian mixture imputation (GMCimpute) estimates missing values using Gaussian mixture and model averaging [1].”
BackgroundMethodIntegrative missing value estimation for microarray data
Hu, J., Li, H., Waterman, M. S., & Zhou, X. J. (2006) · BMC Bioinformatics · doi:10.1186/1471-2105-7-449 · Cited by 40 · see citing works
“We then apply all six algorithms and calculate the average and standard deviation of the normalized root mean square error (RMSE) relative to the zero-imputation method.”
BackgroundInfluentialPubChem BioAssays as a data source for predictive models
Chen, B., & Wild, D. J. (2009) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2009.10.001 · Cited by 39 · see citing works
“This procedure is termed imputation and has been extensively studied in various fields such as genetics [3], microarray analysis [4], and proteomics [5].”
MethodAn integrative imputation method based on multi-omics datasets
Lin, D., Zhang, J., Li, J., Xu, C., Deng, H., & Wang, Y. (2016) · BMC Bioinformatics · doi:10.1186/s12859-016-1122-6 · Cited by 39 · see citing works
“…have indicated that missing values in large-scale omics data can drastically hinder downstream analyses, such as unsupervised clustering of genes [12], detection of differentially expressed genes [13], supervised classification of clinical samples [14], construction of gene regulatory networks…”
BackgroundYan, X., Cao, Z., Murphy, A., Ye, Y., Wang, X., & Qiao, Y. (2023) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2023.165340 · Cited by 35 · see citing works
Iwata, M., Yuan, L., Zhao, Q., Tabei, Y., Berenger, F., Sawada, R., Akiyoshi, S., Hamano, M., & Yamanishi, Y. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz313 · Cited by 35 · see citing works
A comprehensive survey on computational learning methods for analysis of gene expression data
Bhandari, N., Walambe, R. A., Kotecha, K. V., & Khare, S. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.907150 · Cited by 35 · see citing works
Stokes, T. H., Moffitt, A. B., Phan, J. H., & Wang, M. D. (2007) · Annals of Biomedical Engineering · doi:10.1007/s10439-007-9313-y · Cited by 34 · see citing works
Chemical-induced gene expression ranking and its application to pancreatic cancer drug repurposing
Pham, T.-H., Qiu, Y., Liu, J., Zimmer, S., O’Neill, E. E., Xie, L., & Zhang, P. (2022) · Patterns · doi:10.1016/j.patter.2022.100441 · Cited by 33 · see citing works
A multi-stage approach to clustering and imputation of gene expression profiles
Wong, D. S. V., Wong, F., & Wood, G. R. (2007) · Bioinformatics · doi:10.1093/bioinformatics/btm053 · Cited by 33 · see citing works
Comments on selected fundamental aspects of microarray analysis
Riva, A., Carpentier, A.-S., Torrésani, B., & Hénaut, A. (2005) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2005.08.006 · Cited by 31 · see citing works
“The interested reader is referred to the works of Ouyang et al. (2004) , Kim et al. (2004) and Zhou et al. (2003) for the comparison of some currently used estimation methods.”
MethodLiang, F., Jia, B., Xue, J., Li, Q., & Luo, Y. (2018) · Journal of the Royal Statistical Society Series B (Statistical Methodology) · doi:10.1111/rssb.12279 · Cited by 30 · see citing works
“In some microarray experiments, missing values can occur for more than 90% of the genes (Ouyang et al. , 2004).”
BackgroundThe theoretic framework of local weighted approximation for microarray missing value estimation
Liu, C.-C., Dai, D., & Yan, H. (2010) · Pattern Recognition · doi:10.1016/j.patcog.2010.02.006 · Cited by 29 · see citing works
Suyundikov, A., Stevens, J. R., Corcoran, C. D., Herrick, J. S., Wolff, R. K., & Slattery, M. L. (2015) · PLoS ONE · doi:10.1371/journal.pone.0119876 · Cited by 28 · see citing works
Clustering with missing features: a penalized dissimilarity measure based approach
Datta, S., Bhattacharjee, S., & Das, S. (2018) · Machine Learning · doi:10.1007/s10994-018-5722-4 · Cited by 28 · see citing works
“urther combined LSI with Non-Negative LSI (NNLSI) in the Collateral Missing Value Estimation (CMVE) technique. These methods have also been shown to vastly improve the results ([Sehgal et al. 2004], [Ouyang et al. 2004]). However, model-based approaches are often computationally expensive. Moreover, most imputation me…”
MethodImproving missing value imputation of microarray data by using spot quality weights
Johansson, P. A., & Häkkinen, J. (2006) · BMC Bioinformatics · doi:10.1186/1471-2105-7-306 · Cited by 28 · see citing works
“Other imputation methods have been suggested [13-18] using the same basic idea that the imputation value is taken as an average over the neighbouring reporters.”
MethodMulti-Omics Integration in Nephrology: Advances, Challenges, and Future Directions
Saliba, A., Du, Y., Feng, T., & Garmire, L. X. (2024) · Seminars in Nephrology · doi:10.1016/j.semnephrol.2025.151584 · Cited by 30 · see citing works
“Missing values in large-scale ‘omics data can significantly hinder downstream analyses, 27 making the handling of missing data a regular challenge in multi-omics integration and analysis.”
Meng, F., Cai, C., & Yan, H. (2013) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2013.2284795 · Cited by 25 · see citing works
“Due to the simplicity and effectiveness of LLS, various LLS-derived methods have been proposed, including iterated local least squares (iLLS) [11], sequential local least squares [12], weighted local least squares [13], and iterative bicluster-based least squares (bi-iLS) [14].”
MethodProduct failure prediction with missing data
Kang, S., Kim, E., Shim, J., Chang, W., & Cho, S. (2017) · International Journal of Production Research · doi:10.1080/00207543.2017.1407883 · Cited by 25 · see citing works
Ching, W., Li, M., Tsing, N. K., Tai, C. W., Ng, T. W., Wong, A. S. T., & Cheng, K. W. (2010) · International Journal of Data Mining and Bioinformatics · doi:10.1504/ijdmb.2010.033524 · Cited by 24 · see citing works
A meta-data based method for DNA microarray imputation
Jörnsten, R. J., Ouyang, M., & Wang, H.-Y. (2007) · BMC Bioinformatics · doi:10.1186/1471-2105-8-109 · Cited by 24 · see citing works
“We previously described GMCimpute [10].”
BackgroundAmeliorative missing value imputation for robust biological knowledge inference
Sehgal, M. S. B., Gondal, I., Dooley, L. S., & Coppel, R. L. (2008) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2007.10.005 · Cited by 22 · see citing works
“[23,29] for error estimation because H = 1 for zero imputation.”
BackgroundMethodTowards clustering of incomplete microarray data without the use of imputation
Kim, D., Lee, K., Lee, K. H., & Lee, D. (2006) · Bioinformatics · doi:10.1093/bioinformatics/btl555 · Cited by 22 · see citing works
“Tocluster these incomplete data sets with conventional methods, we first estimated the missing values using the widely used KNNimpute (Troyanskaya et al ., 2001) and EMimpute (Bo et al ., 2004; Ouyang et al ., 2004).”
Scaling out big data missing value imputations
Anagnostopoulos, C. B., & Triantafillou, P. (2014) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/2623330.2623615 · Cited by 21 · see citing works
Discovery of Gene Regulatory Networks in Aspergillus fumigatus
Guthke, R., Kniemeyer, O., Albrecht, D., Brakhage, A. A., & Möller, U. (2008) · Springer eBooks · doi:10.1007/978-3-540-71037-0_3 · Cited by 21 · see citing works
“Different methods for the imputation of missing data were applied, including the Gaussian mixture clustering method (gmc) [3], the k-nearest neighbor algorithm (knn) [4], and the tri-level alternating optimization method (tao) [5, 6].”
MethodMissing value imputation for gene expression data by tailored nearest neighbors
Faisal, S., & Tutz, G. (2017) · Statistical Applications in Genetics and Molecular Biology · doi:10.1515/sagmb-2015-0098 · Cited by 21 · see citing works
Georgopoulos, P. G. (2007) · Water Air and Soil Pollution Focus · doi:10.1007/s11267-007-9137-7 · Cited by 21 · see citing works
“DORIAN includes ebTrack, which expands the features of ArrayTrack (Tong et al. 2003), by incorporating a range of options for the analysis of proteomic and metabonomic datasets, in addition to providing additional analysis options for microarray gene expression data (e.g. Ouyang et al. 2004).”
BackgroundMethodA cluster-directed framework for neighbour based imputation of missing value in microarray data
Keerin, P., Kurutach, W., & Boongoen, T. (2016) · International Journal of Data Mining and Bioinformatics · doi:10.1504/ijdmb.2016.076535 · Cited by 20 · see citing works
Attention-Based Sequence-to-Sequence Model for Time Series Imputation
Li, Y., Du, M., & He, S. (2022) · Entropy · doi:10.3390/e24121798 · Cited by 19 · see citing works
“Methods based on machine learning: Clustering [13–17], KNN [18,19], and LSTM [20,21] are used to reconstruct missing values.”
MethodMu, T., Goulermas, J. Y., Korkontzelos, I., & Ananiadou, S. (2014) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.23374 · Cited by 19 · see citing works
“Other algorithms (Xu, 2005) can also be used, for example, mean shift clustering (Cheng, 1995), fuzzy clustering (Baraldi & Blonda, 1999a, 1999b), Gaussian mixture clustering (Ouyang, Welsh, & Georgopoulos, 2004), or spectral clustering (Luxburg, 2007).”
MethodImputation methods for high-dimensional mixed-type datasets by nearest neighbors
Faisal, S., & Tutz, G. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104577 · Cited by 19 · see citing works
Application of survival analysis methodology to the quantitative analysis of LC-MS proteomics data
Tekwe, C. D., Carroll, R. J., & Dabney, A. R. (2012) · Bioinformatics · doi:10.1093/bioinformatics/bts306 · Cited by 19 · see citing works
Missing Values Estimation in Microarray Data with Partial Least Squares Regression
Yang, K., Li, J., & Wang, C. (2006) · Lecture notes in computer science · doi:10.1007/11758525_90 · Cited by 19 · see citing works
“To evaluate the performance of different methods, artificial missing entries are created from a complete expression matrix (i.e. without missing values) according to the method of Ouyang et al [18].”
MethodFarswan, A., Gupta, A., Gupta, R., & Kaur, G. (2020) · Frontiers in Oncology · doi:10.3389/fonc.2019.01442 · Cited by 18 · see citing works
“Examples • K nearest-neighbor imputation (KNNimpute) (2) and its variations-SKNNimpute (Sequential KNN) (3), IKNNimpute (iterative KNNimpute) (4) • Gaussian mixture clustering imputation (GMCimpute) (5) • Least square imputation (LSimpute) (6) and its variationsLocal least square imputation (LLSimpute) (3), Sequential…”
MethodInfluentialPattern Recognition in Bioinformatics
Istrail, S., Waterman, M. S., Pevzner, P., Ngom, A., Chetty, M., & Ahmad, S. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88436-1 · Cited by 18 · see citing works
Aire drives steroid hormone biosynthesis by medullary thymic epithelial cells
Taves, M. D., Donahue, K. M., Bian, J., Cam, M. C., & Ashwell, J. D. (2023) · Science Immunology · doi:10.1126/sciimmunol.abo7975 · Cited by 17 · see citing works
“Web-based visualization of the datawas done using a ShinyCell (76) application published on the NIH RStudio Connect Server.”
MethodMixtures of common factor analyzers for high-dimensional data with missing information
Wang, W. (2013) · Journal of Multivariate Analysis · doi:10.1016/j.jmva.2013.02.003 · Cited by 17 · see citing works
“We undertook a small simulation study to compare the performance of the proposed procedure relative to the existing GMIX imputation approach [33,44] for learning incomplete multivariate data.”
MethodQian, X., Jaller, M., & Circella, G. (2023) · Cities · doi:10.1016/j.cities.2023.104290 · Cited by 16 · see citing works
K-Ranked Covariance Based Missing Values Estimation for Microarray Data Classification
Sehgal, M. S. B., Gondal, I., & Dooley, L. S. (2005) · International Conference on Hybrid Intelligent Systems (HIS) · doi:10.1109/ichis.2004.67 · Cited by 16 · see citing works
“The missing value estimation techniques were tested using the following two approaches.”
MethodPrediction of Missing Values in Microarray and Use of Mixed Models to Evaluate the Predictors
Feten, G., Almøy, T., & AASTVEIT, A. H. (2005) · Statistical Applications in Genetics and Molecular Biology · doi:10.2202/1544-6115.1120 · Cited by 15 · see citing works
“Ouyang et al. (2004) proposed an imputation method based on Gaussian mixture clustering and model averaging.”
Veri cation of Improving a Clustering Algorith for Microarray Data with Missing Values
Kim, S. (2011) · Korean Journal of Applied Statistics · doi:10.5351/kjas.2011.24.2.315 · Cited by 14 · see citing works
Chai, L. E., Mohamad, M. S., Deris, S., Chong, C. K., Choon, Y. W., Ibrahim, Z., & Omatu, S. (2012) · Advances in intelligent and soft computing · doi:10.1007/978-3-642-28765-7_45 · Cited by 14 · see citing works
“In addition, the missing values commonly found in expression data may influence up to 90% of the genes [10], thus affecting the inference results.”
BackgroundChai, L. E., Law, C. K., Mohamad, M. S., Chong, C. K., Choon, Y. W., Deris, S., & Illias, R. M. (2014) · Europe PMC (PubMed Central) · Cited by 13 · see citing works
An enhanced approach on handling missing values using bagging k-NN imputation
Kumutha, V., & Palaniammal, S. (2013) · International Conference on Computer Communication and Informatics (ICCCI) · doi:10.1109/iccci.2013.6466301 · Cited by 13 · see citing works
“Generally, microarray datasets are estimated to have more than 5% missing values and up to 90% of genes are affected [20] [21].”
BackgroundMissingness-Pattern-Adaptive Learning With Incomplete Data
Gong, Y., Li, Z., Liu, W., Lu, X., Liu, X., Tsang, I. W.-H., & Yin, Y. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3262784 · Cited by 12 · see citing works
“Probabilistic generative models such as Gaussian mixture model (GMM) [10] use expectation maximization (EM) algorithm to find the most probable completion.”
MethodResultImputation of Missing Values in Time Series with Lagged Correlations
Rahman, S. A., Huang, Y., Claassen, J., & Kleinberg, S. (2014) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2014.110 · Cited by 12 · see citing works
“In clustering based SI methods [14], [15], data are first clustered using the non-missing values and then missing values are imputed using the instances of the cluster that contain the missing value instance.”
MethodData Mining based Handling Missing Data
Dubey, A., & Rasool, A. (2019) · International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) · doi:10.1109/i-smac47947.2019.9032631 · Cited by 12 · see citing works
“Gaussian Mixture Clustering and model averaging (GMCimpute) [13] Local 2004 Accurate imputation for time series dataset having correlation and non-time series datasets having no correlations.”
MethodGenetic and molecular aspects of sport performance
Bouchard, C., & Hoffman, E. P. (2011) · Medical Entomology and Zoology · Cited by 12 · see citing works
Calabrese, B. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-809633-8.20458-5 · Cited by 12 · see citing works
Severson, K., Monian, B., Love, J. C., & Braatz, R. D. (2017) · Bioinformatics · doi:10.1093/bioinformatics/btx224 · Cited by 11 · see citing works
Blanchet, J., & Vignes, M. (2009) · Journal of Computational Biology · doi:10.1089/cmb.2008.0078 · Cited by 11 · see citing works
“Up to 90% of genes (rows) or experimental conditions (columns) can be affected (Ouyang et al., 2004).”
Tolstaya, E. V., Shakirov, А., Mezghani, M., & Safonov, S. (2023) · Journal of Imaging · doi:10.3390/jimaging9070126 · Cited by 10 · see citing works
Clustering with Missing Features: A Density-Based Approach
Gao, K., Khan, H. A., & Qu, W. (2022) · Symmetry · doi:10.3390/sym14010060 · Cited by 10 · see citing works
“Many clustering algorithms have been proposed: K-means [5], fuzzy C-means [6], affinity propagation [7], Gaussian mixtures [8], etc.”
MethodMicroarray missing values imputation methods: Critical analysis review
Hourani, M., & El, E. (2009) · Computer Science and Information Systems · doi:10.2298/csis0902165h · Cited by 10 · see citing works
“edu/listeria /gut/ The fourth data set is from an infection time series study [5] .”
BackgroundMethodInfluentialHou, J., Ji, X., Chu, X., Shi, Z., Wang, B., Sun, K., Wei, H., Song, Z., & Wen, F. (2024) · Journal of Animal Physiology and Animal Nutrition · doi:10.1111/jpn.13932 · Cited by 9 · see citing works
Missing Value Estimation for Compound‐Target Activity Data
Tanrikulu, Y., Kondru, R. K., Schneider, G., So, W. V., & Bitter, H.-M. (2010) · Molecular Informatics · doi:10.1002/minf.201000073 · Cited by 9 · see citing works
Implementation of machine learning in DNA barcoding for determining the plant family taxonomy
Riza, L. S., Zain, M. I., Izzuddin, A., Prasetyo, Y., Hidayat, T., & Samah, K. A. F. A. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e20161 · Cited by 9 · see citing works
“Finally, this research only uses a hierarchical clustering algorithm, any other algorithms like K-means [78], DBSCAN [79], Gaussian Mixture [80], etc.”
MethodShrinkage regression-based methods for microarray missing value imputation
Wang, H., Chiu, C.-C., Wu, Y.-C., & Wu, W. (2013) · BMC Systems Biology · doi:10.1186/1752-0509-7-s6-s11 · Cited by 9 · see citing works
“Since then, a lot of missing value imputation methods have been proposed such as Bayesian principal component analysis (BPCA) [14], Gaussian mixture clustering imputation (GMCimpute) [11], conditional ordered list imputation [15], random-forest-based imputation [16] and so on.”
BackgroundMethodInfluentialGao, Q., Luo, J., Pan, J., Zhang, L., Song, D., Zhang, M., Xu, D., & Guo, F. (2022) · Frontiers in Immunology · doi:10.3389/fimmu.2022.949509 · Cited by 8 · see citing works
“Two eligible microarray profiles were downloaded from the GEO database with the FPKM format, and the “impute” package (13) was used to impute few missing values based on the knearest neighboring (KNN) imputation algorithm.”
MethodTrimmed scores regression for k -means clustering data with high-missing ratio
Guo, G., Niu, R., Qian, G., Song, H., & Lu, T. (2022) · Communications in Statistics - Simulation and Computation · doi:10.1080/03610918.2022.2091779 · Cited by 8 · see citing works
“For example, Ouyang et al. (2004) pointed out that MR ( l ) of gene expression profile data was 90%.”
BackgroundRegularized Sparse Modelling for Microarray Missing Value Estimation
Wang, A., Yang, J., & An, N. (2021) · IEEE Access · doi:10.1109/access.2021.3053631 · Cited by 8 · see citing works
“For example, Ouyang et al. [26] gave the Gaussian mixture clustering imputation algorithm (GMCimpute), where the Gaussian mixture model is used to parameterize the gene expression profiles and estimate the missing values within a cluster.”
MethodKibinge, N., Ono, N., Horie, M., Sato, T., Sugiura, T., Altaf‐Ul‐Amin, M., Saito, A., & Kanaya, S. (2016) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2016.04.002 · Cited by 7 · see citing works
- Authors
- Ouyang, M., Welsh, W. J., & Georgopoulos, P.
- Affiliations
- Rutgers, The State University of New Jersey (US)
- University of Medicine and Dentistry of New Jersey (US)
- Corresponding author
- Ouyang, Ming
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2004-01-29
- Volume
- 20
- Issue
- 6
- Pages
- 917-923
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- OpenAlex
- W2119253710
- Cited by
- 202
- References
- 22
- Citations by year
- 2026: 2 · 2025: 2 · 2024: 5 · 2023: 16 · 2022: 11 · 2021: 9 · 2020: 6 · 2019: 5 · 2018: 9 · 2017: 4 · 2016: 5 · 2015: 6 · 2014: 9 · 2013: 10 · 2012: 31
- FWCI
- 4.26
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- public-domain
- Locations
- Bioinformatics (publishedVersion, public-domain)
- PubMed (publishedVersion)
- Funders
- U.S. Environmental Protection Agency
- Commission on Higher Education
- National Institutes of Health
- National Institute of Environmental Health Sciences (ES 0522)
- U.S. National Library of Medicine (G08LM006230, 2 G08 LM06230-01AI)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Gene expression and cancer classification
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Keywords
- microarray data, missing data imputation, Gaussian mixture model clustering, model averaging, gene expression data, imputation accuracy, clustering bias, temporal gene expression
- MeSH terms
- Algorithms, Cell Cycle, Models, Genetic, Sensitivity and Specificity, Yeasts, Reproducibility of Results, Models, Statistical, Cluster Analysis, Normal Distribution, Artifacts, Sequence Analysis, DNA, Benchmarking, 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
