{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T06:22:16Z","timestamp":1693808536491},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2016,10,2]],"date-time":"2016-10-02T00:00:00Z","timestamp":1475366400000},"content-version":"vor","delay-in-days":1576,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/3.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,6,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Motivation: The recent development of high-throughput drug profiling (high content screening or HCS) provides a large amount of quantitative multidimensional data. Despite its potentials, it poses several challenges for academia and industry analysts alike. This is especially true for ranking the effectiveness of several drugs from many thousands of images directly. This paper introduces, for the first time, a new framework for automatically ordering the performance of drugs, called fractional adjusted bi-partitional score (FABS). This general strategy takes advantage of graph-based formulations and solutions and avoids many shortfalls of traditionally used methods in practice. We experimented with FABS framework by implementing it with a specific algorithm, a variant of normalized cut\u2014normalized cut prime (FABS-NC\u2032), producing a ranking of drugs. This algorithm is known to run in polynomial time and therefore can scale well in high-throughput applications.<\/jats:p>\n               <jats:p>Results: We compare the performance of FABS-NC\u2032 to other methods that could be used for drugs ranking. We devise two variants of the FABS algorithm: FABS-SVM that utilizes support vector machine (SVM) as black box, and FABS-Spectral that utilizes the eigenvector technique (spectral) as black box. We compare the performance of FABS-NC\u2032 also to three other methods that have been previously considered: center ranking (Center), PCA ranking (PCA), and graph transition energy method (GTEM). The conclusion is encouraging: FABS-NC\u2032 consistently outperforms all these five alternatives. FABS-SVM has the second best performance among these six methods, but is far behind FABS-NC\u2032: In some cases FABS-NC\u2032 produces over half correctly predicted ranking experiment trials than FABS-SVM.<\/jats:p>\n               <jats:p>Availability: The system and data for the evaluation reported here will be made available upon request to the authors after this manuscript is accepted for publication.<\/jats:p>\n               <jats:p>Contact: \u00a0yxy128@berkeley.edu<\/jats:p>","DOI":"10.1093\/bioinformatics\/bts232","type":"journal-article","created":{"date-parts":[[2012,6,11]],"date-time":"2012-06-11T14:09:18Z","timestamp":1339423758000},"page":"i106-i114","source":"Crossref","is-referenced-by-count":9,"title":["Ranking of multidimensional drug profiling data by fractional-adjusted bi-partitional scores"],"prefix":"10.1093","volume":"28","author":[{"given":"Dorit S.","family":"Hochbaum","sequence":"first","affiliation":[{"name":"1 Department of Industrial Engineering and Operations Research, University of California, Berkeley, CA 94720, 2Information Sciences Institute, University of Southern California, Marina del Ray, CA 90292 and 3Institute of Information Science, Academia Sinica, Taipei 115, Taiwan"}]},{"given":"Chun-Nan","family":"Hsu","sequence":"additional","affiliation":[{"name":"1 Department of Industrial Engineering and Operations Research, University of California, Berkeley, CA 94720, 2Information Sciences Institute, University of Southern California, Marina del Ray, CA 90292 and 3Institute of Information Science, Academia Sinica, Taipei 115, Taiwan"},{"name":"1 Department of Industrial Engineering and Operations Research, University of California, Berkeley, CA 94720, 2Information Sciences Institute, University of Southern California, Marina del Ray, CA 90292 and 3Institute of Information Science, Academia Sinica, Taipei 115, Taiwan"}]},{"given":"Yan T.","family":"Yang","sequence":"additional","affiliation":[{"name":"1 Department of Industrial Engineering and Operations Research, University of California, Berkeley, CA 94720, 2Information Sciences Institute, University of Southern California, Marina del Ray, CA 90292 and 3Institute of Information Science, Academia Sinica, Taipei 115, Taiwan"}]}],"member":"286","published-online":{"date-parts":[[2012,6,9]]},"reference":[{"key":"2023012512371493900_B1","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1016\/j.cell.2010.04.033","article-title":"Cellular heterogeneity: Do differences make a difference?","volume":"141","author":"Altschuler","year":"2010","journal-title":"Cell"},{"key":"2023012512371493900_B2","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1023\/A:1009715923555","article-title":"A tutorial on support vector machines for pattern recognition","volume":"2","author":"Burges","year":"1998","journal-title":"Data Min. Knowl. Disc."},{"key":"2023012512371493900_B3","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1287\/opre.1080.0572","article-title":"A computational study of the pseudoflow and push-relabel algorithms for the maximum flow problem","volume":"57","author":"Chandran","year":"2009","journal-title":"Operations Res."},{"key":"2023012512371493900_B4","first-page":"27:1","article-title":"Libsvm: a library for support vector machines","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans. Intell. Sys. Technol."},{"key":"2023012512371493900_B5","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1083\/jcb.200910105","article-title":"Automated microscopy for high-content rnai screening","volume":"188","author":"Conrad","year":"2010","journal-title":"J. Cell Biol."},{"key":"2023012512371493900_B6","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511801389","volume-title":"An Introduction to Support Vector Machines and Other Kernel-based Learning Methods.","author":"Cristianini","year":"2000"},{"key":"2023012512371493900_B7","doi-asserted-by":"crossref","first-page":"216","DOI":"10.2174\/138620708783877780","article-title":"High-content analysis in preclinical drug discovery","volume":"11","author":"Denner","year":"2008","journal-title":"Comb. Chem. High Throughput Screen"},{"key":"2023012512371493900_B8","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1038\/nrd2876","article-title":"Multi-parameter phenotypic profiling: using cellular effects to characterize small-molecule compounds","volume":"8","author":"Feng","year":"2009","journal-title":"Nat. Rev. Drug Discov."},{"key":"2023012512371493900_B9","doi-asserted-by":"crossref","first-page":"686","DOI":"10.1145\/502090.502093","article-title":"An efficient algorithm for image segmentation, markov random fields and related problems","volume":"48","author":"Hochbaum","year":"2001","journal-title":"J. ACM"},{"key":"2023012512371493900_B10","doi-asserted-by":"crossref","first-page":"992","DOI":"10.1287\/opre.1080.0524","article-title":"The pseudoflow algorithm: A new algorithm for the maximum flow problem","volume":"58","author":"Hochbaum","year":"2008","journal-title":"Operations Res."},{"key":"2023012512371493900_B11","author":"Hochbaum","year":"2010","journal-title":"HPF: Hochbaum's Pseudo-Flow Algorithm Implementation"},{"key":"2023012512371493900_B12","doi-asserted-by":"crossref","first-page":"889","DOI":"10.1109\/TPAMI.2009.80","article-title":"Polynomial time algorithms for ratio regions and a variant of normalized cut","volume":"32","author":"Hochbaum","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2023012512371493900_B13","author":"Hochbaum","year":"2010","journal-title":"Replacing spectral techniques for expander ratio and normalized cut by combinatorial flow algorithms."},{"key":"2023012512371493900_B14","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1186\/1471-2105-5-78","article-title":"Boosting accuracy of automated classification of fluorescence microscope images for location proteomics","volume":"5","author":"Huang","year":"2004","journal-title":"BMC Bioinformatics"},{"key":"2023012512371493900_B15","doi-asserted-by":"crossref","first-page":"163","DOI":"10.2307\/1403192","article-title":"A test for normality of observations and regression residuals","volume":"55","author":"Jarque","year":"1987","journal-title":"Int. Stat. Rev."},{"key":"2023012512371493900_B16","volume-title":"Learning in Graphical Models.","author":"Jordan","year":"1996"},{"key":"2023012512371493900_B17","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1038\/nrd2008","article-title":"Cellular imaging in drug discovery","volume":"5","author":"Lang","year":"2006","journal-title":"Nat. Rev. Drug Discov."},{"key":"2023012512371493900_B18","doi-asserted-by":"crossref","first-page":"3374","DOI":"10.1093\/bioinformatics\/btm497","article-title":"Boosting multiclass learning with repeating codes and weak detectors for protein subcellular localization","volume":"23","author":"Lin","year":"2007","journal-title":"Bioinformatics"},{"key":"2023012512371493900_B19","doi-asserted-by":"crossref","first-page":"i29","DOI":"10.1093\/bioinformatics\/btq194","article-title":"A spectral graph theoretic approach to quantification and calibration of collective morphological differences in cell images","volume":"26","author":"Lin","year":"2010","journal-title":"Bioinformatics"},{"key":"2023012512371493900_B20","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1002\/cbic.200400272","article-title":"Small-molecule screening and profiling by using automated microscopy","volume":"6","author":"Mitchison","year":"2005","journal-title":"Chembiochem"},{"key":"2023012512371493900_B21","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1089\/adt.2005.3.483","article-title":"Statistics of assay validation in high throughput cell imaging of nuclear factor \u03bab nuclear translocation","volume":"3","author":"Morelock","year":"2005","journal-title":"Assay Drug Dev. Technol."},{"key":"2023012512371493900_B22","first-page":"379","article-title":"High content screening as a screening tool in drug discovery","volume":"356","author":"Nichols","year":"2007","journal-title":"Methods Mol. Biol."},{"key":"2023012512371493900_B23","first-page":"3892","article-title":"Identification of novel antimitotic agents acting at the tubulin level by computer-assisted evaluation of differential cytotoxicity data","volume":"52","author":"Paull","year":"1992","journal-title":"Cancer Res."},{"key":"2023012512371493900_B24","doi-asserted-by":"crossref","first-page":"e1002212","DOI":"10.1371\/journal.pcbi.1002212","article-title":"Automatic morphological subtyping reveals new roles of caspases in mitochondrial dynamics","volume":"7","author":"Peng","year":"2011","journal-title":"PLoS Comput. Biol."},{"key":"2023012512371493900_B25","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1126\/science.1100709","article-title":"Multidimensional drug profiling by automated microscopy","volume":"306","author":"Perlman","year":"2004","journal-title":"Science"},{"key":"2023012512371493900_B26","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1109\/34.868688","article-title":"Normalized cut and image segmentation","volume":"22","author":"Shi","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2023012512371493900_B27","doi-asserted-by":"crossref","first-page":"11521","DOI":"10.1074\/jbc.M607279200","article-title":"Mitotic phosphorylation of dynamin-related gtpase drp1 participates in mitochondrial fission","volume":"282","author":"Taguchi","year":"2007","journal-title":"Biol. Chem."},{"key":"2023012512371493900_B28","volume-title":"High Contnet Screening: A Powerful Approach to Systems Cell Biology and Drug Discovery.","author":"Taylor","year":"2007"},{"key":"2023012512371493900_B29","author":"Timothee","year":"2004","journal-title":"Normalized Cuts Segmentation Code, for MATLAB"},{"key":"2023012512371493900_B30","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1145\/959242.959249","article-title":"State of the art of graph-based data mining","volume":"5","author":"Washio","year":"2003","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"2023012512371493900_B31","doi-asserted-by":"crossref","first-page":"279","DOI":"10.2174\/138620703106298527","article-title":"Phenotypic screening of small molecule libraries by high throughput cell imaging","volume":"6","author":"Yarrow","year":"2003","journal-title":"Comb. Chem. High Throughput Screen"},{"key":"2023012512371493900_B32","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1177\/108705719900400206","article-title":"A simple statistical parameter for use in evaluation and validation of high throughput screening assays","volume":"4","author":"Zhang","year":"1999","journal-title":"J. Biomol. Screen."},{"key":"2023012512371493900_B33","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1109\/MSP.2006.1628879","article-title":"Informatics challenges of high-throughput microscopy","volume":"23","author":"Zhou","year":"2006","journal-title":"IEEE Signal Proc. Mag."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/28\/12\/i106\/48884649\/bioinformatics_28_12_i106.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/28\/12\/i106\/48884649\/bioinformatics_28_12_i106.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T16:36:07Z","timestamp":1674664567000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/28\/12\/i106\/269708"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,9]]},"references-count":33,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2012,6,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bts232","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2012,6,15]]},"published":{"date-parts":[[2012,6,9]]}}}