Get quick answers to your questions about the article from our AI researcher chatbot
{'id': 'https://openalex.org/W2145037531', 'doi': 'https://doi.org/10.1101/gr.221202', 'title': 'Structural Characterization of the Human Proteome', 'display_name': 'Structural Characterization of the Human Proteome', 'publication_year': 2002, 'publication_date': '2002-11-01', 'ids': {'openalex': 'https://openalex.org/W2145037531', 'doi': 'https://doi.org/10.1101/gr.221202', 'mag': '2145037531', 'pmid': 'https://pubmed.ncbi.nlm.nih.gov/12421749', 'pmcid': 'https://www.ncbi.nlm.nih.gov/pmc/articles/187559'}, 'language': 'en', 'primary_location': {'is_oa': True, 'landing_page_url': 'https://doi.org/10.1101/gr.221202', 'pdf_url': 'https://genome.cshlp.org/content/12/11/1625.full.pdf', 'source': {'id': 'https://openalex.org/S43092948', 'display_name': 'Genome Research', 'issn_l': '1088-9051', 'issn': ['1088-9051', '1549-5469'], 'is_oa': False, 'is_in_doaj': False, 'is_core': True, 'host_organization': 'https://openalex.org/P4310315909', 'host_organization_name': 'Cold Spring Harbor Laboratory Press', 'host_organization_lineage': ['https://openalex.org/P4310315909'], 'host_organization_lineage_names': ['Cold Spring Harbor Laboratory Press'], 'type': 'journal'}, 'license': 'cc-by-nc', 'license_id': 'https://openalex.org/licenses/cc-by-nc', 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, 'type': 'article', 'type_crossref': 'journal-article', 'indexed_in': ['crossref', 'pubmed'], 'open_access': {'is_oa': True, 'oa_status': 'hybrid', 'oa_url': 'https://genome.cshlp.org/content/12/11/1625.full.pdf', 'any_repository_has_fulltext': True}, 'authorships': [{'author_position': 'first', 'author': {'id': 'https://openalex.org/A5000384693', 'display_name': 'Arne Müller', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I47508984', 'display_name': 'Imperial College London', 'ror': 'https://ror.org/041kmwe10', 'country_code': 'GB', 'type': 'education', 'lineage': ['https://openalex.org/I47508984']}, {'id': 'https://openalex.org/I2801316944', 'display_name': 'Cancer Research UK', 'ror': 'https://ror.org/054225q67', 'country_code': 'GB', 'type': 'nonprofit', 'lineage': ['https://openalex.org/I2801316944']}], 'countries': ['GB'], 'is_corresponding': False, 'raw_author_name': 'Arne Müller', 'raw_affiliation_strings': ['2Department of Biological Sciences, Structural Bioinformatics Group, Imperial College of Science, Technology and Medicine,\n South Kensington, London, United Kingdom', 'Biomolecular Modelling Laboratory, Cancer Research UK, London, United Kingdom'], 'affiliations': [{'raw_affiliation_string': '2Department of Biological Sciences, Structural Bioinformatics Group, Imperial College of Science, Technology and Medicine,\n South Kensington, London, United Kingdom', 'institution_ids': ['https://openalex.org/I47508984']}, {'raw_affiliation_string': 'Biomolecular Modelling Laboratory, Cancer Research UK, London, United Kingdom', 'institution_ids': ['https://openalex.org/I2801316944']}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5090122303', 'display_name': 'Robert M. MacCallum', 'orcid': 'https://orcid.org/0000-0001-5070-4493'}, 'institutions': [{'id': 'https://openalex.org/I2801316944', 'display_name': 'Cancer Research UK', 'ror': 'https://ror.org/054225q67', 'country_code': 'GB', 'type': 'nonprofit', 'lineage': ['https://openalex.org/I2801316944']}, {'id': 'https://openalex.org/I47508984', 'display_name': 'Imperial College London', 'ror': 'https://ror.org/041kmwe10', 'country_code': 'GB', 'type': 'education', 'lineage': ['https://openalex.org/I47508984']}], 'countries': ['GB'], 'is_corresponding': False, 'raw_author_name': 'Robert M. MacCallum', 'raw_affiliation_strings': ['2Department of Biological Sciences, Structural Bioinformatics Group, Imperial College of Science, Technology and Medicine,\n South Kensington, London, United Kingdom', 'Biomolecular Modelling Laboratory, Cancer Research UK, London, United Kingdom'], 'affiliations': [{'raw_affiliation_string': 'Biomolecular Modelling Laboratory, Cancer Research UK, London, United Kingdom', 'institution_ids': ['https://openalex.org/I2801316944']}, {'raw_affiliation_string': '2Department of Biological Sciences, Structural Bioinformatics Group, Imperial College of Science, Technology and Medicine,\n South Kensington, London, United Kingdom', 'institution_ids': ['https://openalex.org/I47508984']}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5023619547', 'display_name': 'Michael J.E. Sternberg', 'orcid': 'https://orcid.org/0000-0002-1884-5445'}, 'institutions': [{'id': 'https://openalex.org/I2801316944', 'display_name': 'Cancer Research UK', 'ror': 'https://ror.org/054225q67', 'country_code': 'GB', 'type': 'nonprofit', 'lineage': ['https://openalex.org/I2801316944']}, {'id': 'https://openalex.org/I47508984', 'display_name': 'Imperial College London', 'ror': 'https://ror.org/041kmwe10', 'country_code': 'GB', 'type': 'education', 'lineage': ['https://openalex.org/I47508984']}], 'countries': ['GB'], 'is_corresponding': False, 'raw_author_name': 'Michael J.E. Sternberg', 'raw_affiliation_strings': ['2Department of Biological Sciences, Structural Bioinformatics Group, Imperial College of Science, Technology and Medicine,\n South Kensington, London, United Kingdom', 'Biomolecular Modelling Laboratory, Cancer Research UK, London, United Kingdom'], 'affiliations': [{'raw_affiliation_string': 'Biomolecular Modelling Laboratory, Cancer Research UK, London, United Kingdom', 'institution_ids': ['https://openalex.org/I2801316944']}, {'raw_affiliation_string': '2Department of Biological Sciences, Structural Bioinformatics Group, Imperial College of Science, Technology and Medicine,\n South Kensington, London, United Kingdom', 'institution_ids': ['https://openalex.org/I47508984']}]}], 'institution_assertions': [], 'countries_distinct_count': 1, 'institutions_distinct_count': 2, 'corresponding_author_ids': [], 'corresponding_institution_ids': [], 'apc_list': None, 'apc_paid': None, 'fwci': 2.824, 'has_fulltext': True, 'fulltext_origin': 'pdf', 'cited_by_count': 79, 'citation_normalized_percentile': {'value': 0.897598, 'is_in_top_1_percent': False, 'is_in_top_10_percent': False}, 'cited_by_percentile_year': {'min': 95, 'max': 96}, 'biblio': {'volume': '12', 'issue': '11', 'first_page': '1625', 'last_page': '1641'}, 'is_retracted': False, 'is_paratext': False, 'primary_topic': {'id': 'https://openalex.org/T10015', 'display_name': 'Genomics and Phylogenetic Studies', 'score': 0.9996, 'subfield': {'id': 'https://openalex.org/subfields/1312', 'display_name': 'Molecular Biology'}, 'field': {'id': 'https://openalex.org/fields/13', 'display_name': 'Biochemistry, Genetics and Molecular Biology'}, 'domain': {'id': 'https://openalex.org/domains/1', 'display_name': 'Life Sciences'}}, 'topics': [{'id': 'https://openalex.org/T10015', 'display_name': 'Genomics and Phylogenetic Studies', 'score': 0.9996, 'subfield': {'id': 'https://openalex.org/subfields/1312', 'display_name': 'Molecular Biology'}, 'field': {'id': 'https://openalex.org/fields/13', 'display_name': 'Biochemistry, Genetics and Molecular Biology'}, 'domain': {'id': 'https://openalex.org/domains/1', 'display_name': 'Life Sciences'}}, {'id': 'https://openalex.org/T12254', 'display_name': 'Machine Learning in Bioinformatics', 'score': 0.9984, 'subfield': {'id': 'https://openalex.org/subfields/1312', 'display_name': 'Molecular Biology'}, 'field': {'id': 'https://openalex.org/fields/13', 'display_name': 'Biochemistry, Genetics and Molecular Biology'}, 'domain': {'id': 'https://openalex.org/domains/1', 'display_name': 'Life Sciences'}}, {'id': 'https://openalex.org/T10521', 'display_name': 'RNA and protein synthesis mechanisms', 'score': 0.9976, 'subfield': {'id': 'https://openalex.org/subfields/1312', 'display_name': 'Molecular Biology'}, 'field': {'id': 'https://openalex.org/fields/13', 'display_name': 'Biochemistry, Genetics and Molecular Biology'}, 'domain': {'id': 'https://openalex.org/domains/1', 'display_name': 'Life Sciences'}}], 'keywords': [{'id': 'https://openalex.org/keywords/proteome', 'display_name': 'Proteome', 'score': 0.9310126}, {'id': 'https://openalex.org/keywords/human-proteome-project', 'display_name': 'Human proteome project', 'score': 0.8292763}, {'id': 'https://openalex.org/keywords/human-proteins', 'display_name': 'Human proteins', 'score': 0.41789633}], 'concepts': [{'id': 'https://openalex.org/C104397665', 'wikidata': 'https://www.wikidata.org/wiki/Q860947', 'display_name': 'Proteome', 'level': 2, 'score': 0.9310126}, {'id': 'https://openalex.org/C86803240', 'wikidata': 'https://www.wikidata.org/wiki/Q420', 'display_name': 'Biology', 'level': 0, 'score': 0.8757218}, {'id': 'https://openalex.org/C94795543', 'wikidata': 'https://www.wikidata.org/wiki/Q3813754', 'display_name': 'Human proteome project', 'level': 4, 'score': 0.8292763}, {'id': 'https://openalex.org/C70721500', 'wikidata': 'https://www.wikidata.org/wiki/Q177005', 'display_name': 'Computational biology', 'level': 1, 'score': 0.67471266}, {'id': 'https://openalex.org/C141231307', 'wikidata': 'https://www.wikidata.org/wiki/Q7020', 'display_name': 'Genome', 'level': 3, 'score': 0.54695296}, {'id': 'https://openalex.org/C197077220', 'wikidata': 'https://www.wikidata.org/wiki/Q720988', 'display_name': 'Human genome', 'level': 4, 'score': 0.4885972}, {'id': 'https://openalex.org/C54355233', 'wikidata': 'https://www.wikidata.org/wiki/Q7162', 'display_name': 'Genetics', 'level': 1, 'score': 0.47674477}, {'id': 'https://openalex.org/C46111723', 'wikidata': 'https://www.wikidata.org/wiki/Q471857', 'display_name': 'Proteomics', 'level': 3, 'score': 0.43814793}, {'id': 'https://openalex.org/C24530287', 'wikidata': 'https://www.wikidata.org/wiki/Q424204', 'display_name': 'Transmembrane protein', 'level': 3, 'score': 0.43514636}, {'id': 'https://openalex.org/C144292202', 'wikidata': 'https://www.wikidata.org/wiki/Q898273', 'display_name': 'Protein domain', 'level': 3, 'score': 0.4196735}, {'id': 'https://openalex.org/C2911029443', 'wikidata': 'https://www.wikidata.org/wiki/Q21296145', 'display_name': 'Human proteins', 'level': 3, 'score': 0.41789633}, {'id': 'https://openalex.org/C550995028', 'wikidata': 'https://www.wikidata.org/wiki/Q10872', 'display_name': 'Archaea', 'level': 3, 'score': 0.4121163}, {'id': 'https://openalex.org/C104317684', 'wikidata': 'https://www.wikidata.org/wiki/Q7187', 'display_name': 'Gene', 'level': 2, 'score': 0.31747627}, {'id': 'https://openalex.org/C170493617', 'wikidata': 'https://www.wikidata.org/wiki/Q208467', 'display_name': 'Receptor', 'level': 2, 'score': 0.0}], 'mesh': [{'descriptor_ui': 'D020543', 'descriptor_name': 'Proteome', 'qualifier_ui': 'Q000737', 'qualifier_name': 'chemistry', 'is_major_topic': True}, {'descriptor_ui': 'D000465', 'descriptor_name': 'Algorithms', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D000818', 'descriptor_name': 'Animals', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D019843', 'descriptor_name': 'Archaeal Proteins', 'qualifier_ui': 'Q000235', 'qualifier_name': 'genetics', 'is_major_topic': False}, {'descriptor_ui': 'D019843', 'descriptor_name': 'Archaeal Proteins', 'qualifier_ui': 'Q000737', 'qualifier_name': 'chemistry', 'is_major_topic': False}, {'descriptor_ui': 'D019843', 'descriptor_name': 'Archaeal Proteins', 'qualifier_ui': 'Q000145', 'qualifier_name': 'classification', 'is_major_topic': False}, {'descriptor_ui': 'D019843', 'descriptor_name': 'Archaeal Proteins', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D019843', 'descriptor_name': 'Archaeal Proteins', 'qualifier_ui': 'Q000502', 'qualifier_name': 'physiology', 'is_major_topic': False}, {'descriptor_ui': 'D001426', 'descriptor_name': 'Bacterial Proteins', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D001426', 'descriptor_name': 'Bacterial Proteins', 'qualifier_ui': 'Q000737', 'qualifier_name': 'chemistry', 'is_major_topic': False}, {'descriptor_ui': 'D001426', 'descriptor_name': 'Bacterial Proteins', 'qualifier_ui': 'Q000145', 'qualifier_name': 'classification', 'is_major_topic': False}, {'descriptor_ui': 'D001426', 'descriptor_name': 'Bacterial Proteins', 'qualifier_ui': 'Q000235', 'qualifier_name': 'genetics', 'is_major_topic': False}, {'descriptor_ui': 'D001426', 'descriptor_name': 'Bacterial Proteins', 'qualifier_ui': 'Q000502', 'qualifier_name': 'physiology', 'is_major_topic': False}, {'descriptor_ui': 'D029742', 'descriptor_name': 'Caenorhabditis elegans Proteins', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D029742', 'descriptor_name': 'Caenorhabditis elegans Proteins', 'qualifier_ui': 'Q000737', 'qualifier_name': 'chemistry', 'is_major_topic': False}, {'descriptor_ui': 'D029742', 'descriptor_name': 'Caenorhabditis elegans Proteins', 'qualifier_ui': 'Q000145', 'qualifier_name': 'classification', 'is_major_topic': False}, {'descriptor_ui': 'D029742', 'descriptor_name': 'Caenorhabditis elegans Proteins', 'qualifier_ui': 'Q000235', 'qualifier_name': 'genetics', 'is_major_topic': False}, {'descriptor_ui': 'D029742', 'descriptor_name': 'Caenorhabditis elegans Proteins', 'qualifier_ui': 'Q000502', 'qualifier_name': 'physiology', 'is_major_topic': False}, {'descriptor_ui': 'D030541', 'descriptor_name': 'Databases, Genetic', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D030541', 'descriptor_name': 'Databases, Genetic', 'qualifier_ui': 'Q000706', 'qualifier_name': 'statistics & numerical data', 'is_major_topic': False}, {'descriptor_ui': 'D029721', 'descriptor_name': 'Drosophila Proteins', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D029721', 'descriptor_name': 'Drosophila Proteins', 'qualifier_ui': 'Q000145', 'qualifier_name': 'classification', 'is_major_topic': False}, {'descriptor_ui': 'D029721', 'descriptor_name': 'Drosophila Proteins', 'qualifier_ui': 'Q000235', 'qualifier_name': 'genetics', 'is_major_topic': False}, {'descriptor_ui': 'D029721', 'descriptor_name': 'Drosophila Proteins', 'qualifier_ui': 'Q000502', 'qualifier_name': 'physiology', 'is_major_topic': False}, {'descriptor_ui': 'D029721', 'descriptor_name': 'Drosophila Proteins', 'qualifier_ui': 'Q000737', 'qualifier_name': 'chemistry', 'is_major_topic': False}, {'descriptor_ui': 'D029968', 'descriptor_name': 'Escherichia coli Proteins', 'qualifier_ui': 'Q000145', 'qualifier_name': 'classification', 'is_major_topic': False}, {'descriptor_ui': 'D029968', 'descriptor_name': 'Escherichia coli Proteins', 'qualifier_ui': 'Q000235', 'qualifier_name': 'genetics', 'is_major_topic': False}, {'descriptor_ui': 'D029968', 'descriptor_name': 'Escherichia coli Proteins', 'qualifier_ui': 'Q000502', 'qualifier_name': 'physiology', 'is_major_topic': False}, {'descriptor_ui': 'D029968', 'descriptor_name': 'Escherichia coli Proteins', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D029968', 'descriptor_name': 'Escherichia coli Proteins', 'qualifier_ui': 'Q000737', 'qualifier_name': 'chemistry', 'is_major_topic': False}, {'descriptor_ui': 'D020440', 'descriptor_name': 'Gene Duplication', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D030342', 'descriptor_name': 'Genetic Diseases, Inborn', 'qualifier_ui': 'Q000235', 'qualifier_name': 'genetics', 'is_major_topic': False}, {'descriptor_ui': 'D030342', 'descriptor_name': 'Genetic Diseases, Inborn', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D006801', 'descriptor_name': 'Humans', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D008390', 'descriptor_name': 'Markov Chains', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D008565', 'descriptor_name': 'Membrane Proteins', 'qualifier_ui': 'Q000502', 'qualifier_name': 'physiology', 'is_major_topic': False}, {'descriptor_ui': 'D008565', 'descriptor_name': 'Membrane Proteins', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D008565', 'descriptor_name': 'Membrane Proteins', 'qualifier_ui': 'Q000737', 'qualifier_name': 'chemistry', 'is_major_topic': False}, {'descriptor_ui': 'D008565', 'descriptor_name': 'Membrane Proteins', 'qualifier_ui': 'Q000145', 'qualifier_name': 'classification', 'is_major_topic': False}, {'descriptor_ui': 'D008565', 'descriptor_name': 'Membrane Proteins', 'qualifier_ui': 'Q000235', 'qualifier_name': 'genetics', 'is_major_topic': False}, {'descriptor_ui': 'D009862', 'descriptor_name': 'Online Systems', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D009862', 'descriptor_name': 'Online Systems', 'qualifier_ui': 'Q000706', 'qualifier_name': 'statistics & numerical data', 'is_major_topic': False}, {'descriptor_ui': 'D010802', 'descriptor_name': 'Phylogeny', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D020836', 'descriptor_name': 'Protein Structure, Quaternary', 'qualifier_ui': 'Q000502', 'qualifier_name': 'physiology', 'is_major_topic': False}, {'descriptor_ui': 'D020836', 'descriptor_name': 'Protein Structure, Quaternary', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D020836', 'descriptor_name': 'Protein Structure, Quaternary', 'qualifier_ui': 'Q000235', 'qualifier_name': 'genetics', 'is_major_topic': False}, {'descriptor_ui': 'D020543', 'descriptor_name': 'Proteome', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D020543', 'descriptor_name': 'Proteome', 'qualifier_ui': 'Q000145', 'qualifier_name': 'classification', 'is_major_topic': False}, {'descriptor_ui': 'D020543', 'descriptor_name': 'Proteome', 'qualifier_ui': 'Q000502', 'qualifier_name': 'physiology', 'is_major_topic': False}, {'descriptor_ui': 'D029701', 'descriptor_name': 'Saccharomyces cerevisiae Proteins', 'qualifier_ui': '', 'qualifier_name': None, 'is_major_topic': False}, {'descriptor_ui': 'D029701', 'descriptor_name': 'Saccharomyces cerevisiae Proteins', 'qualifier_ui': 'Q000502', 'qualifier_name': 'physiology', 'is_major_topic': False}, {'descriptor_ui': 'D029701', 'descriptor_name': 'Saccharomyces cerevisiae Proteins', 'qualifier_ui': 'Q000737', 'qualifier_name': 'chemistry', 'is_major_topic': False}, {'descriptor_ui': 'D029701', 'descriptor_name': 'Saccharomyces cerevisiae Proteins', 'qualifier_ui': 'Q000145', 'qualifier_name': 'classification', 'is_major_topic': False}, {'descriptor_ui': 'D029701', 'descriptor_name': 'Saccharomyces cerevisiae Proteins', 'qualifier_ui': 'Q000235', 'qualifier_name': 'genetics', 'is_major_topic': False}], 'locations_count': 4, 'locations': [{'is_oa': True, 'landing_page_url': 'https://doi.org/10.1101/gr.221202', 'pdf_url': 'https://genome.cshlp.org/content/12/11/1625.full.pdf', 'source': {'id': 'https://openalex.org/S43092948', 'display_name': 'Genome Research', 'issn_l': '1088-9051', 'issn': ['1088-9051', '1549-5469'], 'is_oa': False, 'is_in_doaj': False, 'is_core': True, 'host_organization': 'https://openalex.org/P4310315909', 'host_organization_name': 'Cold Spring Harbor Laboratory Press', 'host_organization_lineage': ['https://openalex.org/P4310315909'], 'host_organization_lineage_names': ['Cold Spring Harbor Laboratory Press'], 'type': 'journal'}, 'license': 'cc-by-nc', 'license_id': 'https://openalex.org/licenses/cc-by-nc', 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, {'is_oa': True, 'landing_page_url': 'https://europepmc.org/articles/pmc187559', 'pdf_url': 'https://europepmc.org/articles/pmc187559?pdf=render', 'source': {'id': 'https://openalex.org/S4306400806', 'display_name': 'Europe PMC (PubMed Central)', 'issn_l': None, 'issn': None, 'is_oa': True, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I1303153112', 'host_organization_name': 'European Bioinformatics Institute', 'host_organization_lineage': ['https://openalex.org/I1303153112'], 'host_organization_lineage_names': ['European Bioinformatics Institute'], 'type': 'repository'}, 'license': None, 'license_id': None, 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, {'is_oa': True, 'landing_page_url': 'https://www.ncbi.nlm.nih.gov/pmc/articles/PMC187559', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S2764455111', 'display_name': 'PubMed Central', 'issn_l': None, 'issn': None, 'is_oa': True, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I1299303238', 'host_organization_name': 'National Institutes of Health', 'host_organization_lineage': ['https://openalex.org/I1299303238'], 'host_organization_lineage_names': ['National Institutes of Health'], 'type': 'repository'}, 'license': None, 'license_id': None, 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, {'is_oa': False, 'landing_page_url': 'https://pubmed.ncbi.nlm.nih.gov/12421749', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S4306525036', 'display_name': 'PubMed', 'issn_l': None, 'issn': None, 'is_oa': False, 'is_in_doaj': False, 'is_core': False, 'host_organization': 'https://openalex.org/I1299303238', 'host_organization_name': 'National Institutes of Health', 'host_organization_lineage': ['https://openalex.org/I1299303238'], 'host_organization_lineage_names': ['National Institutes of Health'], 'type': 'repository'}, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}], 'best_oa_location': {'is_oa': True, 'landing_page_url': 'https://doi.org/10.1101/gr.221202', 'pdf_url': 'https://genome.cshlp.org/content/12/11/1625.full.pdf', 'source': {'id': 'https://openalex.org/S43092948', 'display_name': 'Genome Research', 'issn_l': '1088-9051', 'issn': ['1088-9051', '1549-5469'], 'is_oa': False, 'is_in_doaj': False, 'is_core': True, 'host_organization': 'https://openalex.org/P4310315909', 'host_organization_name': 'Cold Spring Harbor Laboratory Press', 'host_organization_lineage': ['https://openalex.org/P4310315909'], 'host_organization_lineage_names': ['Cold Spring Harbor Laboratory Press'], 'type': 'journal'}, 'license': 'cc-by-nc', 'license_id': 'https://openalex.org/licenses/cc-by-nc', 'version': 'publishedVersion', 'is_accepted': True, 'is_published': True}, 'sustainable_development_goals': [], 'grants': [], 'datasets': [], 'versions': [], 'referenced_works_count': 48, 'referenced_works': ['https://openalex.org/W140427365', 'https://openalex.org/W1513332069', 'https://openalex.org/W1582255757', 'https://openalex.org/W1839423960', 'https://openalex.org/W1971155547', 'https://openalex.org/W1972436355', 'https://openalex.org/W1989509003', 'https://openalex.org/W1994734987', 'https://openalex.org/W2003788979', 'https://openalex.org/W2024645073', 'https://openalex.org/W2056442535', 'https://openalex.org/W2058336694', 'https://openalex.org/W2059067075', 'https://openalex.org/W2070220641', 'https://openalex.org/W2071699363', 'https://openalex.org/W2079441999', 'https://openalex.org/W2096810446', 'https://openalex.org/W2099946731', 'https://openalex.org/W2100361137', 'https://openalex.org/W2101220662', 'https://openalex.org/W2103150692', 'https://openalex.org/W2112493377', 'https://openalex.org/W2112792893', 'https://openalex.org/W2114083522', 'https://openalex.org/W2116402707', 'https://openalex.org/W2117019496', 'https://openalex.org/W2117077088', 'https://openalex.org/W2123858481', 'https://openalex.org/W2127230663', 'https://openalex.org/W2130479394', 'https://openalex.org/W2139621307', 'https://openalex.org/W2140514445', 'https://openalex.org/W2141148930', 'https://openalex.org/W2141885858', 'https://openalex.org/W2151831732', 'https://openalex.org/W2154478075', 'https://openalex.org/W2158714788', 'https://openalex.org/W2160008147', 'https://openalex.org/W2160013892', 'https://openalex.org/W2164718466', 'https://openalex.org/W2165460636', 'https://openalex.org/W2168909179', 'https://openalex.org/W2171091522', 'https://openalex.org/W2916193864', 'https://openalex.org/W3216627664', 'https://openalex.org/W4235848672', 'https://openalex.org/W4252166161', 'https://openalex.org/W4252934881'], 'related_works': ['https://openalex.org/W4389024253', 'https://openalex.org/W4324132673', 'https://openalex.org/W2591608042', 'https://openalex.org/W2580329791', 'https://openalex.org/W2299447828', 'https://openalex.org/W2182694331', 'https://openalex.org/W2090672107', 'https://openalex.org/W2056499061', 'https://openalex.org/W2012034410', 'https://openalex.org/W2009541319'], 'abstract_inverted_index': {'This': [0], 'paper': [1], 'reports': [2], 'an': [3], 'analysis': [4], 'of': [5, 11, 14, 21, 27, 31, 45, 60, 71, 96, 112, 115, 135, 144, 154, 179], 'the': [6, 12, 28, 46, 61, 72, 85, 97, 100, 110, 119, 131, 145, 155], 'encoded': [7], 'proteins': [8, 117], '(the': [9], 'proteome)': [10], 'genomes': [13], 'human,': [15], 'fly,': [16], 'worm,': [17, 176], 'yeast,': [18], 'and': [19, 23, 175, 177, 196, 206, 211], 'representatives': [20], 'bacteria': [22], 'archaea': [24], 'in': [25, 99, 109, 170, 181, 186, 189, 198], 'terms': [26], 'three-dimensional': [29], 'structures': [30], 'their': [32], 'globular': [33, 113], 'domains': [34, 114, 180], 'together': [35], 'with': [36, 152], 'a': [37], 'general': [38], 'sequence-based': [39], 'study.': [40], 'We': [41, 55], 'show': [42], 'that': [43, 57, 81, 142], '39%': [44], 'human': [47, 86, 146, 171, 199], 'proteome': [48, 73, 101, 147], 'can': [49, 74, 208], 'be': [50, 75, 209], 'assigned': [51, 76], 'to': [52, 77, 140, 173], 'known': [53], 'structures.': [54], 'estimate': [56, 141], 'for': [58, 161], '77%': [59], 'proteome,': [62], 'there': [63], 'is': [64, 167, 183, 221], 'some': [65], 'functional': [66], 'annotation,': [67], 'but': [68, 93], 'only': [69, 94], '26%': [70], 'standard': [78], 'sequence': [79], 'motifs': [80], 'characterize': [82], 'function.': [83], 'Of': [84], 'protein': [87], 'sequences,': [88], '13%': [89], 'are': [90, 106, 128], 'transmembrane': [91, 116], 'proteins,': [92], '3%': [95], 'residues': [98], 'form': [102], 'membrane-spanning': [103], 'regions.': [104], 'There': [105], 'substantial': [107], 'differences': [108], 'composition': [111], 'between': [118], 'proteomes': [120], 'we': [121], 'have': [122, 202], 'analyzed.': [123], 'Commonly': [124], 'occurring': [125], 'structural': [126], 'superfamilies': [127, 137, 159, 194], 'identified': [129], 'within': [130], 'proteome.': [132], 'The': [133, 164], 'frequencies': [134], 'these': [136], 'enable': [138], 'us': [139], '98%': [143], 'evolved': [148], 'by': [149], 'domain': [150], 'duplication,': [151], 'four': [153], '10': [156], 'most': [157], 'duplicated': [158, 169], 'specific': [160], 'multicellular': [162], 'organisms.': [163, 192], 'zinc-finger': [165], 'superfamily': [166], 'massively': [168], 'compared': [172], 'fly': [174], 'occurrence': [178], 'repeats': [182], 'more': [184], 'common': [185], 'metazoa': [187], 'than': [188], 'single': [190], 'cellular': [191], 'Structural': [193], 'over-': [195], 'underrepresented': [197], 'disease': [200], 'genes': [201], 'been': [203], 'identified.': [204], 'Data': [205], 'results': [207], 'downloaded': [210], 'analyzed': [212], 'via': [213], 'web-based': [214], 'applications': [215], 'at': [216, 224], 'http://www.sbg.bio.ic.ac.uk': [217], '.': [218], '[Supplemental': [219], 'material': [220], 'available': [222], 'online': [223], 'http://www.genome.org': [225], '.]': [226]}, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W2145037531', 'counts_by_year': [{'year': 2024, 'cited_by_count': 1}, {'year': 2023, 'cited_by_count': 1}, {'year': 2022, 'cited_by_count': 1}, {'year': 2021, 'cited_by_count': 1}, {'year': 2020, 'cited_by_count': 1}, {'year': 2019, 'cited_by_count': 2}, {'year': 2017, 'cited_by_count': 5}, {'year': 2016, 'cited_by_count': 2}, {'year': 2015, 'cited_by_count': 5}, {'year': 2014, 'cited_by_count': 2}, {'year': 2013, 'cited_by_count': 6}, {'year': 2012, 'cited_by_count': 1}], 'updated_date': '2024-12-24T13:40:13.457968', 'created_date': '2016-06-24'}