@article{PAR00000100,
  title = {{M}ultigenic families and proteomics : extended protein characterization as a tool for paralog gene identification},
  author = {{D}elalande, {F}. and {C}arapito, {C}. and {B}rizard, {J}ean-{P}aul and {B}rugidou, {C}hristophe and {V}an {D}orsselaer, {A}.},
  editor = {},
  language = {{ENG}},
  abstract = {{I}n classical proteomic studies, the searches in protein databases lead mostly to the identification of protein functions by homology due to the non-exhaustiveness of the protein databases. {T}he quality of the identification depends on the studied organism, its complexity and its representation in the protein databases. {N}evertheless, this basic function identification is insufficient for certain applications namely for the development of {RNA}-based gene-silencing strategies, commonly termed {RNA} interference ({RNA}i) in animals and post-transcriptional gene silencing ({PTGS}) in plants, that require an unambiguous identification of the targeted gene sequence. {A} {PTGS} strategy was considered in the study of the infection of {O}ryza sativa by the {R}ice {Y}ellow {M}ottle {V}irus ({RYMV}). {I}t is suspected that the {RYMV} recruits host proteins after its entry into plant cells to form a complex facilitating virus multiplication and spreading. {T}he protein partners of this complex were identified by a classical proteomic approach, nano liquid chromatography tandem mass spectrometry. {A}mong the identified proteins, several were retained for a {PTGS} strategy. {N}evertheless most of the protein candidates appear to be members of multigenic families for which all paralog genes are not present in protein databases. {T}hus the identification of the real expressed paralog gene with classical protein database searches is impossible. {C}onsequently, as the genome contains all genes and thus all paralog genes, a whole genome search strategy was developed to determine the specific expressed paralog gene. {W}ith this approach, the identification of peptides matching only a single gene, called discriminant peptides, allows definitive proof of the expression of this identified gene. {T}his strategy has several requirements: (i) a genome completely sequenced and accessible; (ii) high protein sequence coverage. {I}n the present work, through three examples, we report and validate for the first time a genome database search strategy to specifically identify paralog genes belonging to multigenic families expressed under specific conditions.},
  keywords = {multigenic family ; paralog gene ; post transcriptional gene silencing ; rice genome},
  booktitle = {},
  journal = {{P}roteomics},
  volume = {5},
  numero = {2},
  pages = {450--460},
  ISSN = {1615-9853},
  year = {2005},
  DOI = {10.1002/pmic.200400954},
  URL = {https://www.documentation.ird.fr/hor/{PAR}00000100},
}