{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T22:11:48Z","timestamp":1781043108309,"version":"3.54.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,11,20]],"date-time":"2018-11-20T00:00:00Z","timestamp":1542672000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/N014189\/1"],"award-info":[{"award-number":["EP\/N014189\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/L015722\/1"],"award-info":[{"award-number":["EP\/L015722\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1186\/s13321-018-0308-5","type":"journal-article","created":{"date-parts":[[2018,11,19]],"date-time":"2018-11-19T23:37:13Z","timestamp":1542670633000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Improved understanding of aqueous solubility modeling through topological data analysis"],"prefix":"10.1186","volume":"10","author":[{"given":"Mariam","family":"Pirashvili","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lee","family":"Steinberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francisco","family":"Belchi Guillamon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mahesan","family":"Niranjan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeremy G.","family":"Frey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacek","family":"Brodzki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,11,20]]},"reference":[{"issue":"10","key":"308_CR1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1016\/S1359-6446(97)01099-4","volume":"2","author":"T Kennedy","year":"1997","unstructured":"Kennedy T (1997) Managing the drug discovery\/development interface. Drug Discov Today 2(10):436\u2013444. \n                    https:\/\/doi.org\/10.1016\/S1359-6446(97)01099-4","journal-title":"Drug Discov Today"},{"issue":"3","key":"308_CR2","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/S0169-409X(02)00008-X","volume":"54","author":"WL Jorgensen","year":"2002","unstructured":"Jorgensen WL, Duffy EM (2002) Prediction of drug solubility from structure. Adv Drug Deliv Rev 54(3):355\u2013366. \n                    https:\/\/doi.org\/10.1016\/S0169-409X(02)00008-X","journal-title":"Adv Drug Deliv Rev"},{"issue":"3","key":"308_CR3","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1021\/CI9901338","volume":"40","author":"J Huuskonen","year":"2000","unstructured":"Huuskonen J (2000) Estimation of aqueous solubility for a diverse set of organic compounds based on molecular topology. J Chem Inf Model 40(3):773\u2013777. \n                    https:\/\/doi.org\/10.1021\/CI9901338","journal-title":"J Chem Inf Model"},{"issue":"3","key":"308_CR4","doi-asserted-by":"publisher","first-page":"450","DOI":"10.1021\/ci970100x","volume":"38","author":"Jarmo Huuskonen","year":"1998","unstructured":"Huuskonen J, Marja S, Taskinen J (1998) Aqueous solubility prediction of drugs based on molecular topology and neural network modeling. J Chem Inf Comput Sci. \n                    https:\/\/doi.org\/10.1021\/CI970100X","journal-title":"Journal of Chemical Information and Computer Sciences"},{"issue":"3","key":"308_CR5","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1021\/ci034243x","volume":"44","author":"JS Delaney","year":"2004","unstructured":"Delaney JS (2004) ESOL: estimating aqueous solubility directly from molecular structure. J Chem Inf Comput Sci 44(3):1000\u20131005. \n                    https:\/\/doi.org\/10.1021\/ci034243x","journal-title":"J Chem Inf Comput Sci"},{"issue":"7","key":"308_CR6","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1021\/ci400187y","volume":"53","author":"A Lusci","year":"2013","unstructured":"Lusci A, Pollastri G, Baldi P (2013) Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules. J Chem Inf Model 53(7):1563\u201375. \n                    https:\/\/doi.org\/10.1021\/ci400187y","journal-title":"J Chem Inf Model"},{"issue":"7","key":"308_CR7","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1021\/ci800058v","volume":"48","author":"A Llin\u00e0s","year":"2008","unstructured":"Llin\u00e0s A, Glen RC, Goodman JM (2008) Solubility challenge: can you predict solubilities of 32 molecules using a database of 100 reliable measurements? J Chem Inf Model 48(7):1289\u20131303. \n                    https:\/\/doi.org\/10.1021\/ci800058v","journal-title":"J Chem Inf Model"},{"issue":"11","key":"308_CR8","doi-asserted-by":"publisher","first-page":"2572","DOI":"10.1021\/ci900286s","volume":"49","author":"M Hewitt","year":"2009","unstructured":"Hewitt M, Cronin MTD, Enoch SJ, Madden JC, Roberts DW, Dearden JC In (2009) Silico prediction of aqueous solubility: the solubility challenge. J Chem Inf Model 49(11):2572\u20132587. \n                    https:\/\/doi.org\/10.1021\/ci900286s","journal-title":"J Chem Inf Model"},{"key":"308_CR9","doi-asserted-by":"publisher","first-page":"2962","DOI":"10.1021\/mp500103r","volume":"11","author":"DS Palmer","year":"2014","unstructured":"Palmer DS, Mitchell JBO (2014) Is experimental data quality the limiting factor in predicting the aqueous solubility of druglike molecules? Mol Pharm 11:2962\u20132972. \n                    https:\/\/doi.org\/10.1021\/mp500103r","journal-title":"Mol Pharm"},{"issue":"2","key":"308_CR10","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1021\/ci000338c","volume":"41","author":"Y Ran","year":"2001","unstructured":"Ran Y, Yalkowsky SH (2001) Prediction of drug solubility by the general solubility equation (GSE). J Chem Inf Comput Sci 41(2):354\u2013357. \n                    https:\/\/doi.org\/10.1021\/ci000338c","journal-title":"J Chem Inf Comput Sci"},{"issue":"2","key":"308_CR11","first-page":"237","volume":"56","author":"a Mauri","year":"2006","unstructured":"Mauri a, Consonni V, Pavan M, Todeschini R (2006) Dragon software: an easy approach to molecular descriptor calculations. Match Commun Math Comput Chem 56(2):237\u2013248","journal-title":"Match Commun Math Comput Chem"},{"issue":"3","key":"308_CR12","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1021\/ci800406y","volume":"49","author":"J Wang","year":"2009","unstructured":"Wang J, Hou T, Xu X (2009) Aqueous solubility prediction based on weighted atom type counts and solvent accessible surface areas. J Chem Inf Model 49(3):571\u2013581. \n                    https:\/\/doi.org\/10.1021\/ci800406y","journal-title":"J Chem Inf Model"},{"key":"308_CR13","doi-asserted-by":"publisher","first-page":"15396","DOI":"10.1038\/ncomms15396","volume":"8","author":"Yongjin Lee","year":"2017","unstructured":"Lee Y, Barthel SD, D\u0142otko P, Moosavi SM, Hess K, Smit B (2017) Quantifying similarity of pore-geometry in nanoporous materials. Nat Commun. \n                    https:\/\/doi.org\/10.1038\/ncomms15396","journal-title":"Nature Communications"},{"issue":"26","key":"308_CR14","doi-asserted-by":"publisher","first-page":"7035","DOI":"10.1073\/pnas.1520877113","volume":"113","author":"Yasuaki Hiraoka","year":"2016","unstructured":"Hiraoka Y, Nakamura T, Hirata A, Escolar EG, Matsue K, Nishiura Y, Parisi G (2016) Hierarchical structures of amorphous solids characterized by persistent homology. Proc Natl Acad Sci U S A. \n                    https:\/\/doi.org\/10.1073\/pnas.1520877113","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"1","key":"308_CR15","doi-asserted-by":"publisher","first-page":"012504","DOI":"10.1103\/PhysRevE.95.012504","volume":"95","author":"T Ichinomiya","year":"2017","unstructured":"Ichinomiya T, Obayashi I, Hiraoka Y (2017) Persistent homology analysis of craze formation. Phys Rev E 95(1):012504. \n                    https:\/\/doi.org\/10.1103\/PhysRevE.95.012504","journal-title":"Phys Rev E"},{"issue":"30","key":"308_CR16","doi-asserted-by":"publisher","first-page":"304001","DOI":"10.1088\/0957-4484\/26\/30\/304001","volume":"26","author":"T Nakamura","year":"2015","unstructured":"Nakamura T, Hiraoka Y, Hirata A, Escolar EG, Nishiura Y (2015) Persistent homology and many-body atomic structure for medium-range order in the glass. Nanotechnology 26(30):304001. \n                    https:\/\/doi.org\/10.1088\/0957-4484\/26\/30\/304001","journal-title":"Nanotechnology"},{"key":"308_CR17","first-page":"3549","volume":"33","author":"Z Cang","year":"2017","unstructured":"Cang Z, Wei G-W (2017) Analysis and prediction of protein folding energy changes upon mutation by element specific persistent homology. Bioinformatics 33:3549","journal-title":"Bioinformatics"},{"key":"308_CR18","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1515\/mlbmb-2015-0009","volume":"3","author":"Z Cang","year":"2015","unstructured":"Cang Z, Mu L, Wu K, Opron K, Xia K, Wei G-W (2015) A topological approach for protein classification. Mol Based Math Biol 3:140\u2013162. \n                    https:\/\/doi.org\/10.1515\/mlbmb-2015-0009","journal-title":"Mol Based Math Biol"},{"issue":"8","key":"308_CR19","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1002\/cnm.2655","volume":"30","author":"K Xia","year":"2014","unstructured":"Xia K, Wei G-W (2014) Persistent homology analysis of protein structure, flexibility, and folding. Int J Numer Methods Biomed Eng 30(8):814\u2013844. \n                    https:\/\/doi.org\/10.1002\/cnm.2655","journal-title":"Int J Numer Methods Biomed Eng"},{"key":"308_CR20","doi-asserted-by":"publisher","unstructured":"Emmett K, Schweinhart B, Rabadan R (2016) Multiscale topology of chromatin folding. In: Proceedings of the 9th EAI international conference on bio-inspired information and communications technologies (formerly BIONETICS), pp 177\u2013180. ACM. \n                    https:\/\/doi.org\/10.4108\/eai.3-12-2015.2262453","DOI":"10.4108\/eai.3-12-2015.2262453"},{"issue":"2","key":"308_CR21","doi-asserted-by":"publisher","first-page":"e2914","DOI":"10.1002\/cnm.2914","volume":"34","author":"Zixuan Cang","year":"2017","unstructured":"Cang Z, Wei G-W (2017) Integration of element specific persistent homology and machine learning for protein-ligand binding affinity prediction. Int J Numer Methods Biomed Eng 2914. \n                    https:\/\/doi.org\/10.1002\/cnm.2914","journal-title":"International Journal for Numerical Methods in Biomedical Engineering"},{"issue":"7","key":"308_CR22","doi-asserted-by":"publisher","first-page":"1005690","DOI":"10.1371\/journal.pcbi.1005690","volume":"13","author":"Z Cang","year":"2017","unstructured":"Cang Z, Wei G-W (2017) TopologyNet: topology based deep convolutional and multi-task neural networks for biomolecular property predictions. PLOS Comput Biol 13(7):1005690. \n                    https:\/\/doi.org\/10.1371\/journal.pcbi.1005690","journal-title":"PLOS Comput Biol"},{"issue":"6","key":"308_CR23","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1002\/jcc.23816","volume":"36","author":"K Xia","year":"2014","unstructured":"Xia K, Feng X, Tong Y, Wei G-W (2014) Persistent homology for the quantitative prediction of fullerene stability. J Comput Chem 36(6):408\u2013422","journal-title":"J Comput Chem"},{"key":"308_CR24","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.aca.2017.11.029","volume":"1000","author":"L Duponchel","year":"2018","unstructured":"Duponchel L (2018) Exploring hyperspectral imaging data sets with topological data analysis. Anal Chem Acta 1000:123\u2013131","journal-title":"Anal Chem Acta"},{"key":"308_CR25","doi-asserted-by":"publisher","first-page":"144115","DOI":"10.1063\/1.3103496","volume":"130","author":"Y Yao","year":"2009","unstructured":"Yao Y, Sun J, Huang X, Bowman GR, Singh G, Lesnick M, Guibas LJ, Pande VS, Carlsson G (2009) Topological methods for exploring low-density states in biomolecular folding pathways. J Chem Phys 130:144115. \n                    https:\/\/doi.org\/10.1063\/1.3103496","journal-title":"J Chem Phys"},{"key":"308_CR26","first-page":"247","volume":"45","author":"H Adams","year":"2011","unstructured":"Adams H, Atanasov A, Carlsson G (2011) Nudged elastic band in topological data analysis. Topol Methods Nonlinear Anal 45:247","journal-title":"Topol Methods Nonlinear Anal"},{"issue":"1","key":"308_CR27","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1002\/zamm.19660460126","volume":"46","author":"M. Landsberg","year":"1966","unstructured":"Books (1987) Introductory to functional analysis with applications (Kreyszig). Books. \n                    https:\/\/doi.org\/10.1002\/zamm.19660460126","journal-title":"ZAMM - Zeitschrift f\u00fcr Angewandte Mathematik und Mechanik"},{"issue":"1","key":"308_CR28","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1021\/ci960109j","volume":"37","author":"Sheila Ash","year":"1997","unstructured":"Ash S, Cline MA, Homer RW, Hurst T, Smith GB (1997) SYBYL line notation (SLN): a versatile language for chemical structure representation. J Chem Inf Comput Sci. \n                    https:\/\/doi.org\/10.1021\/ci960109j","journal-title":"Journal of Chemical Information and Computer Sciences"},{"key":"308_CR29","unstructured":"Landrum G RDKIT: open source cheminformatics"},{"issue":"1","key":"308_CR30","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/1758-2946-3-33","volume":"3","author":"NM O\u2019Boyle","year":"2011","unstructured":"O\u2019Boyle NM, Banck M, James CA, Morley C, Vandermeersch T, Hutchison GR (2011) Open babel: an open chemical toolbox. J Cheminf 3(1):33. \n                    https:\/\/doi.org\/10.1186\/1758-2946-3-33","journal-title":"J Cheminf"},{"issue":"1","key":"308_CR31","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1038\/srep01236","volume":"3","author":"PY Lum","year":"2013","unstructured":"Lum PY, Singh G, Lehman A, Ishkanov T, Vejdemo-Johansson M, Alagappan M, Carlsson J, Carlsson G (2013) Extracting insights from the shape of complex data using topology. Sci Rep 3(1):1236. \n                    https:\/\/doi.org\/10.1038\/srep01236","journal-title":"Sci Rep"},{"issue":"1","key":"308_CR32","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s10479-011-0841-3","volume":"219","author":"Carlos R. Garc\u00eda-Alonso","year":"2011","unstructured":"Maaten LVD, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res. \n                    https:\/\/doi.org\/10.1007\/s10479-011-0841-3","journal-title":"Annals of Operations Research"},{"key":"308_CR33","unstructured":"KeplerMapper. \n                    https:\/\/doi.org\/10.5281\/zenodo.1054444"},{"key":"308_CR34","doi-asserted-by":"publisher","unstructured":"Dey TK, Shi D, Wang Y (2015) Comparing graphs via persistence distortion. In: Arge L, Pach J (eds) 31st international symposium on computational geometry (SoCG 2015). Schloss Dagstuhl\u2013Leibniz-Zentrum fuer Informatik, pp 491\u2013506. \n                    https:\/\/doi.org\/10.4230\/LIPIcs.SOCG.2015.491","DOI":"10.4230\/LIPIcs.SOCG.2015.491"},{"key":"308_CR35","unstructured":"Bubenik P (2013) Statistical topology using persistence landscapes. \n                    arXiv:1207:6437"},{"key":"308_CR36","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.jsc.2016.03.009","volume":"78","author":"Peter Bubenik","year":"2017","unstructured":"Bubenik P, D\u0142otko P (2017) A persistence landscapes toolbox for topological statistics. J Symb Comput. \n                    https:\/\/doi.org\/10.1016\/j.jsc.2016.03.009","journal-title":"Journal of Symbolic Computation"},{"key":"308_CR37","unstructured":"Harer J, Bar-On R, Strawn N, Tralie C, Bendich P, Pieloch A, Slaczedek J (2014) TDATools. \n                    https:\/\/github.com\/ksian\/ML2015FP\/tree\/master\/3TDATools\n                    \n                  . Accessed 1 Mar 2018"},{"issue":"3","key":"308_CR38","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1038\/nmeth.2810","volume":"11","author":"Bo Wang","year":"2014","unstructured":"Wang B, Mezlini AM, Demir F, Fiume M, Tu Z, Brudno M, Haibe-Kains B, Goldenberg A (2014) Similarity network fusion for aggregating data types on a genomic scale. Nat Methods. \n                    https:\/\/doi.org\/10.1038\/nmeth.2810","journal-title":"Nature Methods"},{"issue":"3","key":"308_CR39","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1021\/ar500432k","volume":"48","author":"J-L Reymond","year":"2015","unstructured":"Reymond J-L (2015) The chemical space project. Acc Chem Res 48(3):722\u2013730. \n                    https:\/\/doi.org\/10.1021\/ar500432k","journal-title":"Acc Chem Res"},{"issue":"06","key":"308_CR40","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1055\/s-0034-1396322","volume":"81","author":"T Miyao","year":"2015","unstructured":"Miyao T, Reker D, Schneider P, Funatsu K, Schneider G (2015) Chemography of Natural Product Space. Planta Medica 81(06):429\u2013435. \n                    https:\/\/doi.org\/10.1055\/s-0034-1396322","journal-title":"Planta Medica"},{"issue":"W1","key":"308_CR41","doi-asserted-by":"publisher","first-page":"W442","DOI":"10.1093\/nar\/gkw287","volume":"44","author":"Jocelyn Sunseri","year":"2016","unstructured":"Sunseri J, Koes DR (2016) Pharmit: interactive exploration of chemical space. Nucleic Acids Res. \n                    https:\/\/doi.org\/10.1093\/nar\/gkw287","journal-title":"Nucleic Acids Research"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-018-0308-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13321-018-0308-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-018-0308-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,19]],"date-time":"2019-11-19T19:05:20Z","timestamp":1574190320000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-018-0308-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,20]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["308"],"URL":"https:\/\/doi.org\/10.1186\/s13321-018-0308-5","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,20]]},"assertion":[{"value":"23 May 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"54"}}