{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_51858"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_51858","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"MACHINE LEARNING FOR TRANSITION METAL COMPLEXES","abstract":"Thesis (Ph.D.)--Michigan State University. Chemistry - Doctor of Philosophy, 2024","abstract_html":"Thesis (Ph.D.)--Michigan State University. Chemistry - Doctor of Philosophy, 2024","abstract_has_math":false,"creators":["Jin, Hongni"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Merz, Kenneth","Wilson, Angela","Blanchard, Gary","Wei, Guowei"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-11-18T18:58:43Z","subjects":["Chemistry"],"languages":["eng"],"rights":["Attribution 4.0 International"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:51858","local:Jin_grad.msu_0128D_20714"],"render_values":[{"text":"etd:51858","href":null,"code":true},{"text":"local:Jin_grad.msu_0128D_20714","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/7mby-3f31","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/7mby-3f31","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_51858","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Merz, Kenneth","Wilson, Angela","Blanchard, Gary","Wei, Guowei"]},{"key":"dc:creator","label":"Author","values":["Jin, Hongni"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["text","Electronic dissertations"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Chemistry"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Attribution 4.0 International"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:51858","local:Jin_grad.msu_0128D_20714","https://doi.org/doi:10.25335/7mby-3f31"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Thesis (Ph.D.)--Michigan State University. Chemistry - Doctor of Philosophy, 2024","Transition metal complexes, dubbed ‘Lego molecules’, are composed of small molecules, ions, or atoms arranged around a central metal. The diversified research field of organometallic compounds includes but is not limited to the study of metal- ligand interactions, structure-property relationships, and practical applications. This dissertation leverages machine learning techniques to expedite the research in this domain. The first part focuses on neural network potentials (NNPs). A Zn_NNPs model was built to depict the potential energy surface of zinc complexes. In this work, a simple but useful embedding of partial charges was proposed, which could model the long-range interactions accurately. Furthermore, an Fe_NNPs model was designed to identify the lowest energy spin state of Fe (II) complexes. The model integrates electronic characteristics such as total charge and spin state to account for long-range interactions effectively. For each model, a high-quality data set including tens of thousands of distinctive conformations was well curated using metadynamics. The third model is a scaffold-based diffusion model, called LigandDiff which can generate valid, novel, and unique ligands for organometallic compounds. Users only need to specify the desired size of the ligand, LigandDiff then generates a diverse and potentially infinite number of ligands of that size from scratch. Collectively, these models surpass traditional computational methods on both accuracy and efficiency, demonstrating substantial potential to acceleratetransition metal complexes research.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf","1 online resource (177 p.) : ill."]},{"key":"dc:title","label":"Title","values":["MACHINE LEARNING FOR TRANSITION METAL COMPLEXES"]}]}],"canonical_facts":{"dc:contributor":["Merz, Kenneth","Wilson, Angela","Blanchard, Gary","Wei, Guowei"],"dc:creator":["Jin, Hongni"],"dc:date":["2024"],"dc:description":["Thesis (Ph.D.)--Michigan State University. Chemistry - Doctor of Philosophy, 2024","Transition metal complexes, dubbed ‘Lego molecules’, are composed of small molecules, ions, or atoms arranged around a central metal. The diversified research field of organometallic compounds includes but is not limited to the study of metal- ligand interactions, structure-property relationships, and practical applications. This dissertation leverages machine learning techniques to expedite the research in this domain. The first part focuses on neural network potentials (NNPs). A Zn_NNPs model was built to depict the potential energy surface of zinc complexes. In this work, a simple but useful embedding of partial charges was proposed, which could model the long-range interactions accurately. Furthermore, an Fe_NNPs model was designed to identify the lowest energy spin state of Fe (II) complexes. The model integrates electronic characteristics such as total charge and spin state to account for long-range interactions effectively. For each model, a high-quality data set including tens of thousands of distinctive conformations was well curated using metadynamics. The third model is a scaffold-based diffusion model, called LigandDiff which can generate valid, novel, and unique ligands for organometallic compounds. Users only need to specify the desired size of the ligand, LigandDiff then generates a diverse and potentially infinite number of ligands of that size from scratch. Collectively, these models surpass traditional computational methods on both accuracy and efficiency, demonstrating substantial potential to acceleratetransition metal complexes research.","Description based on online resource. Title from PDF t.p. (Michigan State University Fedora Repository, viewed ).","Includes bibliographical references."],"dc:format":["application/pdf","1 online resource (177 p.) : ill."],"dc:identifier":["etd:51858","local:Jin_grad.msu_0128D_20714","https://doi.org/doi:10.25335/7mby-3f31"],"dc:language":["eng"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["Attribution 4.0 International"],"dc:subject":["Chemistry"],"dc:title":["MACHINE LEARNING FOR TRANSITION METAL COMPLEXES"],"dc:type":["text","Electronic dissertations"]},"updated_at":"2026-11-18T18:58:43Z"}