Abstract
Conceptually, protein crystallization can be divided into two phases search and optimization. Robotic protein crystallization screening can speed up the search phase, and has a potential to increase process quality. Automated image classification helps to increase throughput and consistently generate objective results. Although the classification accuracy can always be improved, our image analysis system can classify images from 1536-well plates with high classification accuracy (85%) and ROC score (0.87), as evaluated on 127 human-classified protein screens containing 5600 crystal images and 189472 non-crystal images. Data mining can integrate results from high-throughput screens with information about crystallizing conditions, intrinsic protein properties, and results from crystallization optimization. We apply association mining, a data mining approach that identifies frequently occurring patterns among variables and their values. This approach segregates proteins into groups based on how they react in a broad range of conditions, and clusters cocktails to reflect their potential to achieve crystallization. These results may lead to crystallization screen optimization, and reveal associations between protein properties and crystallization conditions. We also postulate that past experience may lead us to the identification of initial conditions favorable to crystallization for novel proteins.
Similar content being viewed by others
References
T.B. Acton K. Gunsalus R. Xiao L. Ma J. Aramini M.C. Baron Y. Chiang T. Clement B. Cooper N. Denissova S. Douglas J.K. Everett D. Palacios R.H. Paranji R. Shastry M. Wu C.-H. Ho L. Shih G.V.T. Swapna M. Wilson M. Gerstein M. Inouye J.F. Hunt G.T. Montelione (2005) Meth. Enzymol 394 210–243 Occurrence Handle10.1016/S0076-6879(05)94008-1 Occurrence Handle15808222
Agrawal, R., Imielinski, T. and Swami, A.N. (1993). In Mining Association Rules between Sets of Items in Large Databases. (Eds., Buneman, P., Jajodia, S.), Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data, ACM Press, 207–216
R. Apweiler A. Bairoch C.H. Wu W.C. Barker B. Boeckmann S. Ferro E. Gasteiger H. Huang R. Lopez M. Magrane M.J. Martin D.A. Natale C. O’Donovan N. Redaschi L.S. Yeh (2004) Nucleic Acids Res. 32 D115–D119 Occurrence Handle10.1093/nar/gkh131 Occurrence Handle14681372
M. Bern D. Goldberg R.C. Stevens P. Kuhn (2004) J. Appl. Cryst. 37 279–287 Occurrence Handle10.1107/S0021889804001761
C. Cumbaa A.M. Lauricella N.A. Fehrman C.K. Veatch R.J. Collins J.R. Luft G.T. Titta ParticleDe I. Jurisica (2003) Acta Cryst., D 59 1619–1627
R. Fisher (1936) Ann. Eugenics 7 179–188
G.L. Gilliland M. Tung J. Ladner (1996) J. Res. Natl. Inst. Stand. Technol. 101 IssueID3 309–320 Occurrence Handle11542472
Goethals, B. (2003). Survey on Frequent Pattern Mining. http://www.cs.helsinki.fi/u/goethals/publications/survey.pdf Manuscript
C.S. Goh N. Lan N. Echols S.M. Douglas D. Milburn P. Bertone R. Xiao L.C. Ma D. Zheng Z. Wunderlich T. Acton G.T. Montelione M. Gerstein (2003) Nucleic Acids Res. 31 IssueID11 2833–2838 Occurrence Handle10.1093/nar/gkg397 Occurrence Handle12771210
V. Gopalakrishnan G. Livingston D. Hennessy B. Buchanan J.M. Rosenberg (2004) Acta Crystallogr. D. Biol. Crystallogr. 60 1705–1716 Occurrence Handle10.1107/S090744490401683X Occurrence Handle15388916
J.R. Luft R.J. Collins N.A. Fehrman A.M. Lauricella C.K. Veatch G.T. Titta ParticleDe (2003) J. Struct. Biol. 142 IssueID1 170–1799 Occurrence Handle10.1016/S1047-8477(03)00048-0 Occurrence Handle12718929
Putnam C. (1999). The Protein Calculator. http://www.scripps.edu/ cdputnam/protcalc.html. Scripps Research Institute
G. Spraggon S.A. Lesley A. Kreusch J.P. Priestle (2002) Acta Crystallogr. D Biol. Crystallogr. 58 IssueID11 1915–1923 Occurrence Handle10.1107/S0907444902016840 Occurrence Handle12393922
Srikant, R. and Agrawal, R. (1996). In Mining Quantitative Association Rules in Large Relational Tables. (Eds., Jagadish, H.V., Mumick, I.S.). Proceedings of the 1996 ACM SIGMOD International Conference on Management of Data, ACM Press, 1–12
J. Wilson (2002) Acta Cryst. D. 58 1907–1914 Occurrence Handle10.1107/S0907444902016633
Zhu, X., Sun, S., Cheng, S.E. and Bern, M. (2004). Classification of Protein Crystallization Imagery. 26th Annual International Conference of IEEE Engineering in Medicine and Biology Society, IEEE Press
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Cumbaa, C., Jurisica, I. Automatic Classification and Pattern Discovery in High-throughput Protein Crystallization Trials. J Struct Funct Genomics 6, 195–202 (2005). https://doi.org/10.1007/s10969-005-5243-9
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s10969-005-5243-9