ParCrys: a Parzen window density estimation approach to protein crystallization propensity prediction

@article{citeulike:2600028, abstract = {The ability to rank proteins by their likely success in crystallization is useful in current Structural Biology efforts and in particular in high-throughput Structural Genomics initiatives. We present ParCrys, a Parzen Window approach to estimate a protein's propensity to produce diffraction-quality crystals. The Protein Data Bank (PDB) provided training data whilst the databases TargetDB and PepcDB were used to define feature selection data as well as test data independent of feature selection and training. ParCrys outperforms the OB-Score, SECRET and CRYSTALP on the data examined, with accuracy and Matthews correlation coefficient values of 79.1\% and 0.582, respectively (74.0\% and 0.227, respectively, on data with a real-world' ratio of positive:negative examples). ParCrys predictions and associated data are available from www.compbio.dundee.ac.uk/parcrys. Contact: geoff@compbio.dundee.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online. 10.1093/bioinformatics/btn055}, author = {Overton, Ian M. and Padovani, Gianandrea and Girolami, Mark A. and Barton, Geoffrey J. }, citeulike-article-id = {2600028}, doi = {10.1093/bioinformatics/btn055}, journal = {Bioinformatics}, keywords = {bioinformatics, crystallography, prediction, propensity, protein, sg}, month = {April}, number = {7}, pages = {901--907}, posted-at = {2008-03-26 23:39:33}, priority = {2}, title = {ParCrys: a Parzen window density estimation approach to protein crystallization propensity prediction}, url = {http://dx.doi.org/10.1093/bioinformatics/btn055}, volume = {24}, year = {2008} }

TY - JOUR ID - citeulike:2600028 L3 - citeulike-article-id:2600028 TI - ParCrys: a Parzen window density estimation approach to protein crystallization propensity prediction JF - Bioinformatics VL - 24 IS - 7 SP - 901 EP - 907 N2 - The ability to rank proteins by their likely success in crystallization is useful in current Structural Biology efforts and in particular in high-throughput Structural Genomics initiatives. We present ParCrys, a Parzen Window approach to estimate a protein's propensity to produce diffraction-quality crystals. The Protein Data Bank (PDB) provided training data whilst the databases TargetDB and PepcDB were used to define feature selection data as well as test data independent of feature selection and training. ParCrys outperforms the OB-Score, SECRET and CRYSTALP on the data examined, with accuracy and Matthews correlation coefficient values of 79.1% and 0.582, respectively (74.0% and 0.227, respectively, on data with a real-world' ratio of positive:negative examples). ParCrys predictions and associated data are available from www.compbio.dundee.ac.uk/parcrys. Contact: geoff@compbio.dundee.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online. 10.1093/bioinformatics/btn055 KW - bioinformatics KW - crystallography KW - prediction KW - propensity KW - protein KW - sg AU - Overton, Ian AU - Padovani, Gianandrea AU - Girolami, Mark AU - Barton, Geoffrey PY - 2008/04/01/ UR - http://dx.doi.org/10.1093/bioinformatics/btn055 ER -