{"id":"https://openalex.org/W2051551739","doi":"https://doi.org/10.1371/journal.pcbi.1003946","title":"The Amino Acid Alphabet and the Architecture of the Protein Sequence-Structure Map. I. Binary Alphabets","display_name":"The Amino Acid Alphabet and the Architecture of the Protein Sequence-Structure Map. I. Binary Alphabets","publication_year":2014,"publication_date":"2014-12-04","ids":{"openalex":"https://openalex.org/W2051551739","doi":"https://doi.org/10.1371/journal.pcbi.1003946","mag":"2051551739","pmid":"https://pubmed.ncbi.nlm.nih.gov/25473967"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1003946","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1003946","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1003946&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1003946&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075863884","display_name":"Evandro Ferrada","orcid":"https://orcid.org/0000-0003-3242-1726"},"institutions":[{"id":"https://openalex.org/I1308548392","display_name":"Santa Fe Institute","ror":"https://ror.org/01arysc35","country_code":"US","type":"funder","lineage":["https://openalex.org/I1308548392"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Evandro Ferrada","raw_affiliation_strings":["Santa Fe Institute, Santa Fe, New Mexico, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Santa Fe Institute, Santa Fe, New Mexico, United States of America","institution_ids":["https://openalex.org/I1308548392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5075863884"],"corresponding_institution_ids":["https://openalex.org/I1308548392"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":0.4278,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.63726889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"10","issue":"12","first_page":"e1003946","last_page":"e1003946"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9995999932289124,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994999766349792,"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/sequence","display_name":"Sequence (biology)","score":0.5753932595252991},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5256615281105042},{"id":"https://openalex.org/keywords/sequence-space","display_name":"Sequence space","score":0.46810030937194824},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41140758991241455},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3429378271102905},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.3250962793827057},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3190992474555969},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.23312073945999146},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2027125060558319},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.13757216930389404}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5753932595252991},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5256615281105042},{"id":"https://openalex.org/C30711495","wikidata":"https://www.wikidata.org/wiki/Q289411","display_name":"Sequence space","level":3,"score":0.46810030937194824},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41140758991241455},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3429378271102905},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3250962793827057},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3190992474555969},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.23312073945999146},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2027125060558319},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.13757216930389404},{"id":"https://openalex.org/C132954091","wikidata":"https://www.wikidata.org/wiki/Q194397","display_name":"Banach space","level":2,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D000596","descriptor_name":"Amino Acids","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005838","descriptor_name":"Genotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010641","descriptor_name":"Phenotype","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":7,"locations":[{"id":"doi:10.1371/journal.pcbi.1003946","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1003946","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1003946&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},{"id":"pmid:25473967","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25473967","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"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":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.990.349","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.990.349","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://europepmc.org/backend/ptpmcrender.fcgi?accid%3DPMC4256021%26blobtype%3Dpdf","raw_type":"text"},{"id":"pmh:oai:RePEc:plo:pcbi00:1003946","is_oa":false,"landing_page_url":"https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1003946","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:f4da58da22ac455fad83f67879b9c9e6","is_oa":true,"landing_page_url":"https://doaj.org/article/f4da58da22ac455fad83f67879b9c9e6","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 10, Iss 12, p e1003946 (2014)","raw_type":"article"},{"id":"pmh:oai:figshare.com:article/1260845","is_oa":true,"landing_page_url":"https://figshare.com/articles/dataset/_The_Amino_Acid_Alphabet_and_the_Architecture_of_the_Protein_Sequence_Structure_Map_I_Binary_Alphabets_/1260845","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Dataset"},{"id":"pmh:oai:pubmedcentral.nih.gov:4256021","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4256021","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"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":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1003946","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1003946","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1003946&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G6778350887","display_name":null,"funder_award_id":"1053575","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312777","display_name":"Santa Fe Institute","ror":"https://ror.org/01arysc35"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2051551739.pdf","grobid_xml":"https://content.openalex.org/works/W2051551739.grobid-xml"},"referenced_works_count":92,"referenced_works":["https://openalex.org/W1505216348","https://openalex.org/W1535631466","https://openalex.org/W1566565124","https://openalex.org/W1569560802","https://openalex.org/W1589812083","https://openalex.org/W1713928683","https://openalex.org/W1899071745","https://openalex.org/W1965857389","https://openalex.org/W1971013467","https://openalex.org/W1972573335","https://openalex.org/W1973220360","https://openalex.org/W1973722782","https://openalex.org/W1975017420","https://openalex.org/W1977940795","https://openalex.org/W1980073965","https://openalex.org/W1981608708","https://openalex.org/W1984248485","https://openalex.org/W1984527736","https://openalex.org/W1986347357","https://openalex.org/W1991053771","https://openalex.org/W1992613346","https://openalex.org/W1995024825","https://openalex.org/W1995143868","https://openalex.org/W1997325518","https://openalex.org/W1997550234","https://openalex.org/W2000664454","https://openalex.org/W2009570821","https://openalex.org/W2013077139","https://openalex.org/W2014059004","https://openalex.org/W2018970839","https://openalex.org/W2023092767","https://openalex.org/W2028841335","https://openalex.org/W2036847257","https://openalex.org/W2039299698","https://openalex.org/W2040594319","https://openalex.org/W2042997873","https://openalex.org/W2044130469","https://openalex.org/W2046585679","https://openalex.org/W2047849624","https://openalex.org/W2047919241","https://openalex.org/W2050618468","https://openalex.org/W2052376307","https://openalex.org/W2057272352","https://openalex.org/W2058078532","https://openalex.org/W2060778016","https://openalex.org/W2067733982","https://openalex.org/W2069504710","https://openalex.org/W2070004581","https://openalex.org/W2072843928","https://openalex.org/W2075121899","https://openalex.org/W2077235131","https://openalex.org/W2079052324","https://openalex.org/W2079119965","https://openalex.org/W2079955671","https://openalex.org/W2085277871","https://openalex.org/W2085764610","https://openalex.org/W2086270870","https://openalex.org/W2091778154","https://openalex.org/W2094715989","https://openalex.org/W2103047198","https://openalex.org/W2104222426","https://openalex.org/W2108884725","https://openalex.org/W2109441358","https://openalex.org/W2114520383","https://openalex.org/W2114899912","https://openalex.org/W2115503115","https://openalex.org/W2119313530","https://openalex.org/W2119885004","https://openalex.org/W2131851875","https://openalex.org/W2132577746","https://openalex.org/W2133082603","https://openalex.org/W2135232979","https://openalex.org/W2136724628","https://openalex.org/W2140012758","https://openalex.org/W2144729032","https://openalex.org/W2146423415","https://openalex.org/W2149389103","https://openalex.org/W2157680389","https://openalex.org/W2162151744","https://openalex.org/W2163987934","https://openalex.org/W2169546600","https://openalex.org/W2171755502","https://openalex.org/W2342204193","https://openalex.org/W2399031292","https://openalex.org/W3030183899","https://openalex.org/W3105820968","https://openalex.org/W3124837637","https://openalex.org/W4234228545","https://openalex.org/W4241088457","https://openalex.org/W4245668478","https://openalex.org/W4299702438","https://openalex.org/W6648961563"],"related_works":["https://openalex.org/W2100050212","https://openalex.org/W4300594067","https://openalex.org/W1548813692","https://openalex.org/W2285386646","https://openalex.org/W4387059535","https://openalex.org/W113975114","https://openalex.org/W2092600334","https://openalex.org/W778889052","https://openalex.org/W2944011748","https://openalex.org/W2188227093"],"abstract_inverted_index":{"The":[0,20,55],"correspondence":[1],"between":[2,48,60],"protein":[3],"sequences":[4,31,123,132,188],"and":[5,17,32,99,117,124,146,168,184,193,216,265],"structures,":[6,33],"or":[7,34],"sequence-structure":[8,88,155,253],"map,":[9],"relates":[10],"to":[11,38,171,190,234],"fundamental":[12],"aspects":[13],"of":[14,22,29,46,57,76,80,86,97,102,105,109,121,131,143,151,157,174,187,196,201,208,228,239,245,251,255,260,263,269],"structural,":[15],"evolutionary":[16],"synthetic":[18],"biology.":[19],"specifics":[21],"the":[23,27,35,44,49,53,65,74,77,81,84,87,103,119,125,140,163,172,175,181,194,206,236,249,252,258,266,270],"mapping,":[24],"such":[25],"as":[26,129,198],"fraction":[28],"accessible":[30],"sequences'":[36],"ability":[37],"fold":[39],"fast,":[40],"are":[41,180],"dictated":[42],"by":[43,64,134],"type":[45],"interactions":[47,59],"monomers":[50,61],"that":[51,139,153,218,232],"compose":[52],"sequences.":[54],"set":[56],"possible":[58],"is":[62,220],"encapsulated":[63],"potential":[66,82,106],"energy":[67,107],"function.":[68],"In":[69],"this":[70],"study,":[71],"I":[72,112,137,161,204,242],"explore":[73],"impact":[75],"relative":[78,141,185],"forces":[79,148],"on":[83,93],"architecture":[85,250],"map.":[89],"My":[90],"observations":[91,247],"rely":[92],"simple":[94],"exact":[95],"models":[96],"proteins":[98],"random":[100,261],"samples":[101],"space":[104],"functions":[108],"binary":[110,209],"alphabets.":[111],"adopt":[113],"a":[114,199,221,230],"graph":[115],"perspective":[116],"study":[118,205],"distribution":[120,186],"viable":[122],"structures":[126,192,197],"they":[127],"produce,":[128],"networks":[130],"connected":[133],"point":[135],"mutations.":[136],"observe":[138],"proportion":[142],"attractive,":[144],"neutral":[145],"repulsive":[147],"defines":[149],"types":[150,207,227],"potentials,":[152,229],"induce":[154],"maps":[156],"vastly":[158],"different":[159],"architectures.":[160],"characterize":[162,235],"properties":[164,179],"underlying":[165],"these":[166,178,246],"differences":[167],"relate":[169],"them":[170],"structure":[173],"potential.":[176],"Among":[177],"expected":[182],"number":[183],"associated":[189],"specific":[191],"diversity":[195],"function":[200],"sequence":[202],"divergence.":[203],"potentials":[210],"observed":[211],"in":[212],"natural":[213,240,256,271],"amino":[214,272],"acids":[215],"show":[217],"there":[219],"strong":[222],"bias":[223,231],"towards":[224],"only":[225],"some":[226],"seems":[233],"folding":[237],"code":[238],"proteins.":[241],"discuss":[243],"implications":[244],"for":[248],"map":[254],"proteins,":[257],"construction":[259],"libraries":[262],"peptides,":[264],"early":[267],"evolution":[268],"acid":[273],"alphabet.":[274]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}