@article{Zhang01122003,
author = {Zhang, Zhaolei and Harrison, Paul M. and Liu, Yin and Gerstein, Mark}, 
title = {Millions of Years of Evolution Preserved: A Comprehensive Catalog of the Processed Pseudogenes in the Human Genome},
volume = {13}, 
number = {12}, 
pages = {2541-2558}, 
year = {2003}, 
doi = {10.1101/gr.1429003}, 
abstract ={Processed pseudogenes were created by reverse-transcription of mRNAs; they provide snapshots of ancient genes existing millions of years ago in the genome. To find them in the present-day human, we developed a pipeline using features such as intron-absence, frame-disruption, polyadenylation, and truncation. This has enabled us to identify in recent genome drafts ∼8000 processed pseudogenes (distributed from http://pseudogene.org). Overall, processed pseudogenes are very similar to their closest corresponding human gene, being 94% complete in coding regions, with sequence similarity of 75% for amino acids and 86% for nucleotides. Their chromosomal distribution appears random and dispersed, with the numbers on chromosomes proportional to length, suggesting sustained “bombardment” over evolution. However, it does vary with GC-content: Processed pseudogenes occur mostly in intermediate GC-content regions. This is similar to Alus but contrasts with functional genes and L1-repeats. Pseudogenes, moreover, have age profiles similar to Alus. The number of pseudogenes associated with a given gene follows a power-law relationship, with a few genes giving rise to many pseudogenes and most giving rise to few. The prevalence of processed pseudogenes agrees well with germ-line gene expression. Highly expressed ribosomal proteins account for ∼20% of the total. Other notables include cyclophilin-A, keratin, GAPDH, and cytochrome c.}, 
URL = {http://genome.cshlp.org/content/13/12/2541.abstract}, 
eprint = {http://genome.cshlp.org/content/13/12/2541.full.pdf+html}, 
journal = {Genome Research} 
}