{"doi":"10.1073/pnas.022408799","title":"Improved recognition of native-like protein structures using a family of designed sequences","abstract":"<jats:p>\n            The goal of the inverse protein folding problem is to identify amino acid sequences that stabilize a given target protein conformation. Methods that attempt to solve this problem have proven useful for protein sequence design. Here we show that the same methods can provide valuable information for protein fold recognition and for\n            <jats:italic>ab initio</jats:italic>\n            protein structure prediction. We present a measure of the compatibility of a test sequence with a target model structure, based on computational protein design. The model structure is used as input to design a family of low free energy sequences, and these sequences are compared with the test sequence by using a metric in sequence space based on nearest-neighbor connectivity. We find that this measure is able to recognize the native fold of a myoglobin sequence among different globin folds. It is also powerful enough to recognize near-native protein structures among nonnative models.\n          </jats:p>","journal":"Proceedings of the National Academy of Sciences","year":2002,"id":14693,"datarank":1.0215217510899117,"base_score":2.772588722239781,"endowment":2.772588722239781,"self_citation_contribution":0.41588830833596724,"citation_network_contribution":0.6056334427539445,"self_endowment_contribution":0.41588830833596724,"citer_contribution":0.6056334427539445,"corpus_percentile":null,"corpus_rank":null,"citation_count":15,"citer_count":14,"citers_with_citation_signal":12,"citers_with_endowment":12,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":946,"name":"Michael Levitt","orcid":"0000-0002-8414-7397","position":1,"is_corresponding":false},{"id":114980,"name":"Patrice Koehl","orcid":null,"position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"base_score":2.772588722239781,"endowment":2.772588722239781,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"11782533","pmcid":"PMC117367","openalex_id":"https://openalex.org/W2047083294","authors":[],"funders":[{"funder_name":"NIGMS NIH HHS","grant_id":"R01 GM041455","title":null},{"funder_name":"NIGMS NIH HHS","grant_id":"R37 GM041455","title":null},{"funder_name":"NIGMS NIH HHS","grant_id":"GM 41455","title":null}],"total_grants":3,"fwci":0.5751,"citation_percentile":0.65028764,"influential_citations":1,"citation_trend":[{"year":2012,"count":1},{"year":2018,"count":1}],"oa_status":"green","license":null,"oa_locations":[{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/117367","host_type":"repository"},{"url":"https://europepmc.org/articles/pmc117367?pdf=render","host_type":"GREEN"},{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/117367","host_type":"repository"},{"url":"https://pnas.org/doi/pdf/10.1073/pnas.022408799","host_type":"publisher"},{"url":"https://doi.org/10.1073/pnas.022408799","host_type":"journal"}],"fields_of_study":["Protein Structure and Dynamics","RNA and protein synthesis mechanisms","Machine Learning in Bioinformatics","Biology","Medicine","Computer Science","Amino Acid Sequence","Biophysical Phenomena","Biophysics","Drug Design","Protein Conformation","Protein Folding","Proteins","Thermodynamics"],"mesh_terms":["Proteins","Biophysics","Amino Acid Sequence","Protein Conformation","Protein Folding","Drug Design","Thermodynamics","Biophysical Phenomena"],"keywords":["Protein structure prediction","Protein design","Protein sequencing","Computational biology","Protein structure","Protein folding","Sequence (biology)","Computer science","Loop modeling","Protein family","Protein structure database","k-nearest neighbors algorithm","Myoglobin","Peptide sequence","Sequence alignment","Pattern recognition (psychology)","Artificial intelligence","Biology","Genetics","Gene","Biochemistry","Sequence database"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Affordable and clean energy"}],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[{"name":"pdb"}],"source":"live","citation_network_status":"fetched"},"created_at":"2026-06-01T13:48:23.625922Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}