{"id":"https://openalex.org/W7225385362","doi":"https://doi.org/10.26434/chemrxiv.15011781/v1","title":"Toward Chemical Accuracy in Biomolecular Simulations through Data-Driven Many-Body Potentials: III. A Library of Amino Acid Building Blocks","display_name":"Toward Chemical Accuracy in Biomolecular Simulations through Data-Driven Many-Body Potentials: III. A Library of Amino Acid Building Blocks","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225385362","doi":"https://doi.org/10.26434/chemrxiv.15011781/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15011781/v1","doi":"https://doi.org/10.26434/chemrxiv.15011781/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011781/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011781/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011781/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161129612","display_name":"Xinmao Lyu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinmao Lyu","raw_affiliation_strings":["\u2020Department of Chemistry , University of California San Diego , La Jolla , California 92093 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2020Department of Chemistry , University of California San Diego , La Jolla , California 92093 , United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025151187","display_name":"Ethan F. Bull-Vulpe","orcid":"https://orcid.org/0000-0002-3826-4306","observed_orcids":["https://orcid.org/0000-0002-3826-4306"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ethan F. Bull-Vulpe","raw_affiliation_strings":["\u2020Department of Chemistry , University of California San Diego , La Jolla , California 92093 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2020Department of Chemistry , University of California San Diego , La Jolla , California 92093 , United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161063042","display_name":"Jiwon Huh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiwon Huh","raw_affiliation_strings":["\u2020Department of Chemistry , University of California San Diego , La Jolla , California 92093 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u2020Department of Chemistry , University of California San Diego , La Jolla , California 92093 , United States","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063875420","display_name":"Francesco Paesani","orcid":"https://orcid.org/0000-0002-4451-1203","observed_orcids":["https://orcid.org/0000-0002-4451-1203"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Francesco Paesani","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4451-1203","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10002","display_name":"Advanced Chemical Physics Studies","score":0.8740000128746033,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10002","display_name":"Advanced Chemical Physics Studies","score":0.8740000128746033,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.055799998342990875,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.036400001496076584,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/many-body-expansion","display_name":"many-body expansion","score":0.8410000205039978},{"id":"https://openalex.org/keywords/amino-acid-building-blocks","display_name":"amino acid building blocks","score":0.8679999709129333},{"id":"https://openalex.org/keywords/permutationally-invariant-polynomials","display_name":"permutationally invariant polynomials","score":0.9089999794960022},{"id":"https://openalex.org/keywords/protein-force-fields","display_name":"protein force fields","score":0.6830000281333923},{"id":"https://openalex.org/keywords/asparagine","display_name":"asparagine","score":0.5979999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5766000151634216},{"id":"https://openalex.org/C14301744","wikidata":"https://www.wikidata.org/wiki/Q579211","display_name":"Ramachandran plot","level":3,"score":0.5706999897956848},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.48969998955726624},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.45750001072883606},{"id":"https://openalex.org/C75079739","wikidata":"https://www.wikidata.org/wiki/Q1571801","display_name":"Intramolecular force","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C515207424","wikidata":"https://www.wikidata.org/wiki/Q8066","display_name":"Amino acid","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C38111792","wikidata":"https://www.wikidata.org/wiki/Q15712714","display_name":"Biomolecular structure","level":3,"score":0.3617999851703644},{"id":"https://openalex.org/C155911762","wikidata":"https://www.wikidata.org/wiki/Q422321","display_name":"Blueprint","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C2994376932","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Amino acid residue","level":4,"score":0.34950000047683716},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.32030001282691956},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.30809998512268066},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C2779281246","wikidata":"https://www.wikidata.org/wiki/Q172847","display_name":"Peptide","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C21951064","wikidata":"https://www.wikidata.org/wiki/Q899212","display_name":"Combinatorial chemistry","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C180577832","wikidata":"https://www.wikidata.org/wiki/Q127920","display_name":"Covalent bond","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2989164559","wikidata":"https://www.wikidata.org/wiki/Q15637420","display_name":"Low energy","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15011781/v1","doi":"https://doi.org/10.26434/chemrxiv.15011781/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011781/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011781/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15011781/v1","doi":"https://doi.org/10.26434/chemrxiv.15011781/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15011781/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15011781/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2810286258","display_name":null,"funder_award_id":"2311260","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4732022933","display_name":"Frameworks: Data-Driven Software Infrastructure for Next-Generation Molecular Simulations","funder_award_id":"2311260","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/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225385362.pdf","grobid_xml":"https://content.openalex.org/works/W7225385362.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W4414791947","https://openalex.org/W4417420689","https://openalex.org/W7131432983","https://openalex.org/W7133353006","https://openalex.org/W7197009140"],"related_works":["https://openalex.org/W4411182937","https://openalex.org/W4415280802","https://openalex.org/W4382501265","https://openalex.org/W2014748690","https://openalex.org/W2897732087","https://openalex.org/W4280547075","https://openalex.org/W4404166764","https://openalex.org/W4296082026","https://openalex.org/W7214671646","https://openalex.org/W3200535748"],"abstract_inverted_index":{"Extending":[0],"data-driven":[1],"many-body":[2,23],"potentials":[3,94,130,178],"to":[4,76,111],"peptides":[5],"and":[6,56,116,122,148,157,179,186],"proteins":[7],"requires":[8],"reusable":[9,172],"building":[10,174],"blocks":[11,175],"that":[12],"capture":[13],"the":[14,22,27,67,70,80,91,128,133,137,145,152],"chemical":[15],"diversity":[16],"of":[17,26,69,107,171],"amino":[18],"acids.":[19],"Building":[20],"on":[21,51,88],"expansion":[24,187],"(MBE)":[25],"energy,":[28],"we":[29],"construct":[30],"an":[31,168],"intramolecular":[32],"MB-nrg":[33,93,129],"library":[34,153,165],"for":[35,119,162,176,182],"all":[36],"20":[37],"natural":[38],"amino-acid":[39],"residues":[40],"by":[41,58,150],"combining":[42],"physics-based":[43],"interactions":[44],"with":[45,101,114,154],"machine-learned":[46],"(ML)":[47],"n-body":[48,173],"terms":[49],"trained":[50],"DLPNO-CCSD(T)":[52,138],"n-mer":[53],"reference":[54,139],"data":[55],"described":[57],"permutationally":[59],"invariant":[60],"polynomials.":[61],"Covalently":[62],"bonded":[63],"functional":[64],"groups":[65],"define":[66],"bodies":[68],"MBE,":[71],"allowing":[72],"each":[73],"ML":[74],"term":[75],"be":[77,141],"reused":[78],"wherever":[79],"same":[81],"chemically":[82],"defined":[83],"nmer":[84],"occurs.":[85],"Without":[86],"training":[87],"whole-dipeptide":[89],"energies,":[90],"assembled":[92],"predict":[95],"gas-phase":[96],"Ramachandran":[97],"potential":[98],"energy":[99],"surfaces":[100],"a":[102,180],"pooled":[103],"root-mean-square":[104],"deviation":[105],"(RMSD)":[106],"1.26":[108],"kcal/mol":[109,118],"relative":[110],"DLPNO-CCSD(T),":[112],"compared":[113],"6.65":[115],"5.43":[117],"Amber":[120],"ff14SB":[121],"ff19SB":[123],"force":[124],"fields,":[125],"respectively.":[126],"Because":[127],"are":[131],"modular,":[132],"remaining":[134],"deviations":[135],"from":[136],"can":[140],"systematically":[142],"analyzed":[143],"within":[144],"MBE":[146],"framework":[147],"addressed":[149],"expanding":[151],"additional":[155],"nonbonded":[156],"higher-body":[158],"terms,":[159],"as":[160],"demonstrated":[161],"asparagine.":[163],"The":[164],"thus":[166],"provides":[167],"initial":[169],"set":[170],"peptide":[177],"blueprint":[181],"their":[183],"systematic":[184],"refinement":[185],"toward":[188],"coupled-cluster":[189],"accuracy":[190],"in":[191],"biomolecular":[192],"simulations.":[193]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-07T00:00:00"}
