@article{Clark01102003,
author = {Clark, Hilary F. and Gurney, Austin L. and Abaya, Evangeline and Baker, Kevin and Baldwin, Daryl and Brush, Jennifer and Chen, Jian and Chow, Bernard and Chui, Clarissa and Crowley, Craig and Currell, Bridget and Deuel, Bethanne and Dowd, Patrick and Eaton, Dan and Foster, Jessica and Grimaldi, Christopher and Gu, Qimin and Hass, Philip E. and Heldens, Sherry and Huang, Arthur and Kim, Hok Seon and Klimowski, Laura and Jin, Yisheng and Johnson, Stephanie and Lee, James and Lewis, Lhney and Liao, Dongzhou and Mark, Melanie and Robbie, Edward and Sanchez, Celina and Schoenfeld, Jill and Seshagiri, Somasekar and Simmons, Laura and Singh, Jennifer and Smith, Victoria and Stinson, Jeremy and Vagts, Alicia and Vandlen, Richard and Watanabe, Colin and Wieand, David and Woods, Kathryn and Xie, Ming-Hong and Yansura, Daniel and Yi, Sothy and Yu, Guoying and Yuan, Jean and Zhang, Min and Zhang, Zemin and Goddard, Audrey and Wood, William I. and Godowski, Paul}, 
title = {The Secreted Protein Discovery Initiative (SPDI), a Large-Scale Effort to Identify Novel Human Secreted and Transmembrane Proteins: A Bioinformatics Assessment},
volume = {13}, 
number = {10}, 
pages = {2265-2270}, 
year = {2003}, 
doi = {10.1101/gr.1293003}, 
abstract ={A large-scale effort, termed the Secreted Protein Discovery Initiative (SPDI), was undertaken to identify novel secreted and transmembrane proteins. In the first of several approaches, a biological signal sequence trap in yeast cells was utilized to identify cDNA clones encoding putative secreted proteins. A second strategy utilized various algorithms that recognize features such as the hydrophobic properties of signal sequences to identify putative proteins encoded by expressed sequence tags (ESTs) from human cDNA libraries. A third approach surveyed ESTs for protein sequence similarity to a set of known receptors and their ligands with the BLAST algorithm. Finally, both signal-sequence prediction algorithms and BLAST were used to identify single exons of potential genes from within human genomic sequence. The isolation of full-length cDNA clones for each of these candidate genes resulted in the identification of >1000 novel proteins. A total of 256 of these cDNAs are still novel, including variants and novel genes, per the most recent GenBank release version. The success of this large-scale effort was assessed by a bioinformatics analysis of the proteins through predictions of protein domains, subcellular localizations, and possible functional roles. The SPDI collection should facilitate efforts to better understand intercellular communication, may lead to new understandings of human diseases, and provides potential opportunities for the development of therapeutics.}, 
URL = {http://genome.cshlp.org/content/13/10/2265.abstract}, 
eprint = {http://genome.cshlp.org/content/13/10/2265.full.pdf+html}, 
journal = {Genome Research} 
}