{"database":"GPMDB","file_versions":[],"scores":{"citationCount":0,"reanalysisCount":0,"viewCount":20,"searchCount":5},"additional":{"omics_type":["Other"],"submitter":["Lange PF, et al."],"instrument_platform":["Instrument"],"disease":["Not Available"],"brenda_tissue":["Not available"],"species":["Homo_sapiens_viruses, Human"],"submitter_mail":["lange.philipp@ubc.ca"],"publication":["24555563"],"model":["http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000253","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000252","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000251","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000250","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000259","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000258","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000255","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000254","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000242","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000249","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000248","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000247","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000246","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000245","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000244","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000243","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000275","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000274","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000273","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000272","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000271","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000270","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000316","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000315","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000314","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000313","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000279","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000312","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000278","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000311","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000310","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000277","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000276","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000319","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000318","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000317","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000264","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000263","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000262","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000261","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000305","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000304","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000303","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000269","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000302","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000268","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000301","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000300","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000267","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000266","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000265","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000309","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000308","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000307","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000306","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000297","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000330","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000296","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000295","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000294","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000293","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000292","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000291","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000290","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000299","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000298","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000331","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000286","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000285","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000284","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000283","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000282","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000281","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000280","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000327","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000326","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000325","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000324","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000323","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000289","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000322","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000321","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000288","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000287","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000320","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000329","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000328","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000231","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000230","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000238","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000237","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000236","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000235","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000234","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000233","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000232","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000228","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000227","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000226","http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000229"],"submitter_affiliation":["Centre for Blood Research, University of British Columbia"],"cell_type":["CL:0000232 erythrocyte"],"repository":["GPMDB"],"pubmed_abstract":["A goal of the Chromosome-centric Human Proteome Project is to identify all human protein species. With 3844 proteins annotated as \"missing\", this is challenging. Moreover, proteolytic processing generates new protein species with characteristic neo-N termini that are frequently accompanied by altered half-lives, function, interactions, and location. Enucleated and largely void of internal membranes and organelles, erythrocytes are simple yet proteomically challenging cells due to the high hemoglobin content and wide dynamic range of protein concentrations that impedes protein identification. Using the N-terminomics procedure TAILS, we identified 1369 human erythrocyte natural and neo-N-termini and 1234 proteins. Multiple semitryptic N-terminal peptides exhibited improved mass spectrometric identification properties versus the intact tryptic peptide enabling identification of 281 novel erythrocyte proteins and six missing proteins identified for the first time in the human proteome. With an improved bioinformatics workflow, we developed a new classification system and the Terminus Cluster Score. Thereby we described a new stabilizing N-end rule for processed protein termini, which discriminates novel protein species from degradation remnants, and identified protein domain hot spots susceptible to cleavage. Strikingly, 68% of the N-termini were within genome-encoded protein sequences, revealing alternative translation initiation sites, pervasive endoproteolytic processing, and stabilization of protein fragments in vivo. The mass spectrometry proteomics data have been deposited to ProteomeXchange with the data set identifier <PXD000434>."],"pubmed_title":["Annotating N termini for the human proteome project: N termini and Nα-acetylation status differentiate stable cleaved protein species from degradation remnants in the human erythrocyte proteome."],"pubmed_authors":["Lange Philipp F PF,Huesgen Pitter F PF,Nguyen Karen K,Overall Christopher M CM,","Lange Philipp F PF, Huesgen Pitter F PF, Nguyen Karen K, Overall Christopher M CM"],"name_synonyms":["multicellular organismal catabolic process, single-organism catabolic process, Homo sapients, human being, breakdown, degradation, catabolism, red blood corpuscle, red blood cell, acetylation, RBC, Humo sapiens, Acetylations, proteins, Homo sapiense, man, Homo sapines, human, polypeptide, Homo spaiens, Homo spiens, \"human\" EXACT genbank_common_name [], Homo sapien, Homo sapience, Homo sapian, Homo sampiens, Homo sapians, Proteomes., species, Homo sapeins, Home sapiens, Proteomes"],"description_synonyms":["Gene., Membrane Tissue, Intervention Strategies, APR, data, human being, wide/broad, LRP, Proteins, RBC, APOER, Red Blood Cell, Organelle, Hemoglobin, broad, compositionality, Procedure, Homo sapiense, composed of, Cell, Intervention or Procedure, polypeptide, Membrane Tissues, Homo spaiens, Experiment, CD91, Homo sapien, Homo sapian, PIG7, Homo sapians, Protein, Gene Products, Corpuscles, TGFBR5, Red Blood Corpuscle, Homo sapeins, Blood Corpuscle, Intervention, Blood Cells, Blood Cell, Homo sapients, Ferrous, Red Blood, Identification, interventionDescription, Tissues, red blood corpuscle, NOXA, content, Tails, red blood cell, Tissue, Humo sapiens, Identifications (Psychology), Interventional, composition, proteins, Membrane, man, Homo sapines, SURGICAL AND MEDICAL PROCEDURES, human, Protein Gene Products, Gene Proteins, Red Blood Corpuscles, Corpuscle, wide, Homo spiens, \"human\" EXACT genbank_common_name [], A2MR, Ferrous Hemoglobin, Homo sapience, Red Blood Cells, Concentration, Homo sampiens, Concentrations, structure, LRP1A, Erythrocyte, Red, Blood Corpuscles, SIMPLE, Eryhem, Home sapiens, Proteomes, Attentions, IGFBP3R, TP53I7"],"pubmed_title_synonyms":["multicellular organismal catabolic process, single-organism catabolic process, Homo sapients, human being, breakdown, degradation, catabolism, red blood corpuscle, red blood cell, acetylation, RBC, Humo sapiens, Acetylations, proteins, Homo sapiense, man, Homo sapines, human, polypeptide, Homo spaiens, Homo spiens, \"human\" EXACT genbank_common_name [], Homo sapien, Homo sapience, Homo sapian, Homo sampiens, Homo sapians, Proteomes., species, Homo sapeins, Home sapiens, Proteomes"],"pubmed_abstract_synonyms":["multicellular organismal catabolic process, single-organism catabolic process, human being, Effects, taxonomy, Goal, RBC, cleavage, FBN, Gene, Organelle, broad, Spectrum Analyses, Homo sapiense, composed of, body system, Long Term, Intervention or Procedure, peptide, period, Classifications, Protein Gm1141, Membrane Tissues, Polypeptides, Homo spaiens, hierarchies, Homo sapien, hierarchy, ECTOL1, systematics, HOT, Homo sapians, susceptible, Gene Products, Mass, system, Analysis, Work Flow, Blood Corpuscle, Effect, CD105, placement, WMS, Mass Spectroscopy, Mass Spectrum Analysis, Taxonomy, Homo sapients, anatomical systems, ADHFe1, Ferrous, Red Blood, Identification, Genomes, Analyses, interventionDescription, Longterm, 1.1.99.24, Tissues, red blood corpuscle, catabolism, hot, ADH8, Tissue, Interventional, composition, chromatid, proteins, Long-Term, protein synthesis initiation, cell surface MJ7/18 antigen, man, SURGICAL AND MEDICAL PROCEDURES, OCTD, biopolymerisation, Homo sapience, Concentration, Homo sampiens, Concentrations, Red, Long-Term Effect, species, SIMPLE, Eryhem, GPHYSD2, Home sapiens, Long-Term Effects, HHT1, SGS, TP53I7, Data Set., Membrane Tissue, Intervention Strategies, data, wide/broad, biopolymerization, Edg, degradation, Proteins, Novel protein, Longterm Effect, Systematics, Red Blood Cell, function, Hemoglobin, compositionality, Procedure, Spectrum Analysis, Cell, ACMICD, Fe-containing alcohol dehydrogenase, Spectroscopy, polypeptide, Taxonomies, prophase chromosome, Workflows, Homo sapian, PIG7, Protein, Long Term Effects, Corpuscles, Red Blood Corpuscle, MFS1, relational spatial quality, Homo sapeins, connected anatomical system, END, Mass Spectrum Analyses, WMS2, ENG, Intervention, Blood Cells, centric, Mass Spectrum, Blood Cell, breakdown, translation initiation, interphase chromosome, content, Tails, red blood cell, Spectrometry, Humo sapiens, Identifications (Psychology), MASS, whole genome, Membrane, Homo sapines, human, Alcohol dehydrogenase iron-containing protein 1, Longterm Effects, Protein Gene Products, organ system, Gene Proteins, Red Blood Corpuscles, Corpuscle, wide, Homo spiens, \"human\" EXACT genbank_common_name [], Ferrous Hemoglobin, Chromosome, Red Blood Cells, structure, SSKS, high temperature, Erythrocyte, Blood Corpuscles, ORW1, location, Proteomes, Attentions, time, Work Flows"],"view_count":["20"],"citation_count":["0"],"search_count":["5"],"full_dataset_link":["http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=GPM32310000272"],"search_domains":["dbgap_ncbi~0","patentfamilies~0","rfam~0","merops~0","complex-portal~0","uniprot~0","wormbaseparasite~0","embl-covid19~0","reactome~0","emdb~0","wgs_masters~0","ebiweb_resources~0","opentargets_genetics~0","biomodels_all~0","ipd-mhc~0","ebiweb_teams~0","taxonomy~0","genome_assembly~0","sc-experiments~0","ebiweb_people~0","enzymeportal_enzymes~0","ipd-nhkir~0","cellosaurus~0","pdbe~0","chebi~0","patentproteins~0","interpro7~0","uniref~0","chembl~0","pdbekb~0","gpcrdb~0","hgnc~0","sc-genes~0","intact~0","rhea~0","ebiweb_training~0","alphafold~0","imgt-hla~0","patentnucleotides~0","ensemblroot~0","eva_studies~0","non-coding~0","europepmc~0","pubmed~1","identifiers_registry~0","pdbechem~0","hpa-covid19~0","eva-variants-covid19~0","biosamples~0","gwas_catalog~0","biotools~0","tls_masters~0","mesh~0","coding~0","sra~0","opentargets~0","efo~0","embl-pathogen~0","project~0","pride~1","human_diseases~0","geo_datasets~0","embl~0","treefam~0","uniparc~0","ols~0","dgva~0","intenz~0","go~0","tsa_masters~0","biosamples-covid19~0","ebiweb_corporate~0","omim~0","lrg~0","earlycause-molecular-sequences~0","ipd-kir~0","empiar~0","rnacentral~0","orcid_data_claims~0","gpmdb~2","lineage-covid19~0","metagenomics~0","pfam~0","pride archive~1","varsite~0"],"reanalysis_count":["0"],"submitter_keywords":["Resource Reanalysis"],"citation_count_scaled":["0.0"],"reanalysis_count_scaled":["0.0"],"view_count_scaled":["0.006169031462060457"],"download_count_scaled":["0.0"],"normalized_connections":["1.0"],"additional_accession":[]},"is_claimable":false,"name":"Annotating N termini for the human proteome project: N termini and N&#945;-acetylation status differentiate stable cleaved protein species from degradation remnants in the human erythrocyte proteome.","description":"Data from ProteomeXchange, PXD ID: PXD000434. Experiment: 111213_RBC5_MG, file: 111213_RBC5_MG_Fr15_17.mzml. Published as part of J Proteome Res. 2014 Apr 4;13(4):2028-44  . From the Abstract: {{i}} Enucleated and largely void of internal membranes and organelles, erythrocytes are simple yet proteomically challenging cells due to the high hemoglobin content and wide dynamic range of protein concentrations that impedes protein identification. Using the N-terminomics procedure TAILS, we identified 1369 human erythrocyte natural and neo-N-termini and 1234 proteins. {{/i}}","dates":{"submission":"2014-05-21"},"accession":"GPM32310000272","cross_references":{"pubmed":["24555563"],"Pride":["PXD000434"],"pride":[],"Pride Archive":["PXD000434"]}}