@article{Zheng01062007,
author = {Zheng, Deyou and Frankish, Adam and Baertsch, Robert and Kapranov, Philipp and Reymond, Alexandre and Choo, Siew Woh and Lu, Yontao and Denoeud, France and Antonarakis, Stylianos E. and Snyder, Michael and Ruan, Yijun and Wei, Chia-Lin and Gingeras, Thomas R. and Guigó, Roderic and Harrow, Jennifer and Gerstein, Mark B.}, 
title = {Pseudogenes in the ENCODE regions: Consensus annotation, analysis of transcription, and evolution},
volume = {17}, 
number = {6}, 
pages = {839-851}, 
year = {2007}, 
doi = {10.1101/gr.5586307}, 
abstract ={Arising from either retrotransposition or genomic duplication of functional genes, pseudogenes are “genomic fossils” valuable for exploring the dynamics and evolution of genes and genomes. Pseudogene identification is an important problem in computational genomics, and is also critical for obtaining an accurate picture of a genome’s structure and function. However, no consensus computational scheme for defining and detecting pseudogenes has been developed thus far. As part of the ENCyclopedia Of DNA Elements (ENCODE) project, we have compared several distinct pseudogene annotation strategies and found that different approaches and parameters often resulted in rather distinct sets of pseudogenes. We subsequently developed a consensus approach for annotating pseudogenes (derived from protein coding genes) in the ENCODE regions, resulting in 201 pseudogenes, two-thirds of which originated from retrotransposition. A survey of orthologs for these pseudogenes in 28 vertebrate genomes showed that a significant fraction (∼80%) of the processed pseudogenes are primate-specific sequences, highlighting the increasing retrotransposition activity in primates. Analysis of sequence conservation and variation also demonstrated that most pseudogenes evolve neutrally, and processed pseudogenes appear to have lost their coding potential immediately or soon after their emergence. In order to explore the functional implication of pseudogene prevalence, we have extensively examined the transcriptional activity of the ENCODE pseudogenes. We performed systematic series of pseudogene-specific RACE analyses. These, together with complementary evidence derived from tiling microarrays and high throughput sequencing, demonstrated that at least a fifth of the 201 pseudogenes are transcribed in one or more cell lines or tissues.}, 
URL = {http://genome.cshlp.org/content/17/6/839.abstract}, 
eprint = {http://genome.cshlp.org/content/17/6/839.full.pdf+html}, 
journal = {Genome Research} 
}