@article{Shah_Alkhnbashi_Behler-Compr_searc_for-2019,
author = {Shah, Shiraz A. and Alkhnbashi, Omer S. and Behler, Juliane 
          and Han, Wenyuan and She, Qunxin and Hess, Wolfgang R. and 
          Garrett, Roger A. and Backofen, Rolf},
title = {Comprehensive search for accessory proteins encoded with 
         archaeal and bacterial type {III} {CRISPR}-cas gene 
         cassettes reveals 39 new cas gene families},
journal = {RNA Biol},
year = {2019},
doi = {10.1080/15476286.2018.1483685},
volume = {16},
user = {backofen},
pmid = {29911924},
pages = {530-542},
number = {4},
issn = {1555-8584},
abstract = {A study was undertaken to identify conserved proteins that 
            are encoded adjacent to cas gene cassettes of Type III 
            CRISPR-Cas (Clustered Regularly Interspaced Short 
            Palindromic Repeats - CRISPR associated) interference 
            modules. Type III modules have been shown to target and 
            degrade dsDNA, ssDNA and ssRNA and are frequently 
            intertwined with cofunctional accessory genes, including 
            genes encoding CRISPR-associated Rossman Fold (CARF) 
            domains. Using a comparative genomics approach, and defining 
            a Type III association score accounting for coevolution and 
            specificity of flanking genes, we identified and classified 
            39 new Type III associated gene families. Most archaeal and 
            bacterial Type III modules were seen to be flanked by 
            several accessory genes, around half of which did not encode 
            CARF domains and remain of unknown function. Northern 
            blotting and interference assays in Synechocystis confirmed 
            that one particular non-CARF accessory protein family was 
            involved in crRNA maturation. Non-CARF accessory genes were 
            generally diverse, encoding nuclease, helicase, protease, 
            ATPase, transporter and transmembrane domains with some 
            encoding no known domains. We infer that additional families 
            of non-CARF accessory proteins remain to be found. The 
            method employed is scalable for potential application to 
            metagenomic data once automated pipelines for annotation of 
            CRISPR-Cas systems have been developed. All accessory genes 
            found in this study are presented online in a readily 
            accessible and searchable format for researchers to audit 
            their model organism of choice: http://accessory.crispr.dk .}
}