fullrecord |
[{"key": "dc.contributor.advisor", "value": "Pihlajam\u00e4ki, Antti", "language": null, "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.advisor", "value": "H\u00e4kkinen, Hannu", "language": null, "element": "contributor", "qualifier": "advisor", "schema": "dc"}, {"key": "dc.contributor.author", "value": "Sikoniemi, Anssi", "language": "", "element": "contributor", "qualifier": "author", "schema": "dc"}, {"key": "dc.date.accessioned", "value": "2024-06-11T08:43:13Z", "language": null, "element": "date", "qualifier": "accessioned", "schema": "dc"}, {"key": "dc.date.available", "value": "2024-06-11T08:43:13Z", "language": null, "element": "date", "qualifier": "available", "schema": "dc"}, {"key": "dc.date.issued", "value": "2024", "language": null, "element": "date", "qualifier": "issued", "schema": "dc"}, {"key": "dc.identifier.uri", "value": "https://jyx.jyu.fi/handle/123456789/95736", "language": null, "element": "identifier", "qualifier": "uri", "schema": "dc"}, {"key": "dc.description.abstract", "value": "In this work a custom graph convolutional network was succesfully constructed and\ntrained to predict interaction energies in molecular dynamics simulations between\nAu25(SR)18 nanoclusters and BSA proteins based on their physical and chemical\nfeatures. Data from molecular dynamics simulations was used as target data in supervised learning. The performance of this model was compared to a feed forward neural\nnetwork with Weisfeiler-Lehman updates on graph form data. The energy terms\npredicted were the non-bonded Lennard-Jones and Coulombic terms for the force field\nused in the simulations. The models were created using the Keras Tensorflow package.\nBoth neural network architectures showed valid performance and the graph convolutional network based on localised spectral filters on graphs was at least as effective\nas the feed forward neural network with Weisfeiler-Lehman updates. The results\nshow that these machine learning methods could be used in the future to improve\nmolecular dynamics simulations by creating a better initialization for the simulations.\nTo get more reliable results and generalise the models a larger data set would be\nrequired.", "language": "en", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.abstract", "value": "T\u00e4ss\u00e4 tutkielmassa tutkittiin vuorovaikutusenergioiden ennustamista Au25(SR)18\nnanoklusterien ja BSA-proteiinien v\u00e4lill\u00e4 kahdella eri neuroverkkoarkkitehtuurilla.\nMallien kouluttaminen toteutettiin nanoklusterien ja proteiinien graafimuotoista\nesityst\u00e4 hy\u00f6dynt\u00e4en. Ennustetut vuorovaikutusenergiatermit olivat Lennard-Jones ja\nCoulombinen vuorovaikutusenergia simulaatioissa k\u00e4ytetylle voimakent\u00e4lle. Ensimm\u00e4inen k\u00e4ytetty neuroverkkoarkkitehtuuri oli yksinkertainen eteenp\u00e4insy\u00f6tt\u00e4v\u00e4 malli,\njossa datan esik\u00e4sittelyss\u00e4 k\u00e4ytettiin Weisfeiler-Lehman -p\u00e4ivityksi\u00e4 graafiesityksen\nparantamiseksi. Toinen k\u00e4ytetty koneoppimismalli oli graafikonvoluutioverkko, joka\nperustui graafien lokalisoituihin spektraalifilttereihin. Verkot rakennettiin hy\u00f6dynt\u00e4m\u00e4ll\u00e4 Keras Tensorflow -pakettia.\nMolempien mallien ennustuksien ja validaatiodatan v\u00e4linen suhde oli hyvin lineaarinen. Molemmat mallit toimivat siis hyvin vuorovaikutusenergioiden ennustamiseen.\nN\u00e4iden tulosten pohjalta ty\u00f6ss\u00e4 k\u00e4ytetty\u00e4 graafineuroverkkoa ja eteenp\u00e4insy\u00f6tt\u00e4v\u00e4\u00e4\nneuroverkkoa voisi hy\u00f6dynt\u00e4\u00e4 molekyylidynamiikkasimulaatioiden alustamisen parantamiseen tulevaisuudessa. Suurin rajoittava tekij\u00e4 tutkimuksessa oli k\u00e4ytetyn datan\nm\u00e4\u00e4r\u00e4. Luotettavampien tulosten saamiseksi ja mallien yleist\u00e4miseksi vaadittaisiin\nsuurempi m\u00e4\u00e4r\u00e4 dataa. Datam\u00e4\u00e4r\u00e4n lis\u00e4\u00e4minen auttaisi luotettavampien johtop\u00e4\u00e4t\u00f6sten muodostamiseen my\u00f6s siit\u00e4, kumpi neuroverkkoarkkitehtuuri on luotettavampi\nja tehokkaampi vuorovaikutusenergioiden ennustamisessa.", "language": "fi", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted by Miia Hakanen (mihakane@jyu.fi) on 2024-06-11T08:43:13Z\nNo. of bitstreams: 0", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Made available in DSpace on 2024-06-11T08:43:13Z (GMT). No. of bitstreams: 0\n Previous issue date: 2024", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.format.extent", "value": "52", "language": "", "element": "format", "qualifier": "extent", "schema": "dc"}, {"key": "dc.language.iso", "value": "eng", "language": null, "element": "language", "qualifier": "iso", "schema": "dc"}, {"key": "dc.rights", "value": "In Copyright", "language": "en", "element": "rights", "qualifier": null, "schema": "dc"}, {"key": "dc.subject.other", "value": "molekyylidynamiikkasimulaatiot", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "nanoklusterit", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "graafikonvoluutioverkko", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.title", "value": "Analyzing protein-nanocluster interactions with graph-based machine learning for molecular dynamics", "language": "", "element": "title", "qualifier": null, "schema": "dc"}, {"key": "dc.type", "value": "master thesis", "language": null, "element": "type", "qualifier": null, "schema": "dc"}, {"key": "dc.identifier.urn", "value": "URN:NBN:fi:jyu-202406114504", "language": null, "element": "identifier", "qualifier": "urn", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Master\u2019s thesis", "language": "en", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Pro gradu -tutkielma", "language": "fi", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Faculty of Sciences", "language": "en", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Matemaattis-luonnontieteellinen tiedekunta", "language": "fi", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Department of Physics", "language": "en", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Fysiikan laitos", "language": "fi", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "University of Jyv\u00e4skyl\u00e4", "language": "en", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "Jyv\u00e4skyl\u00e4n yliopisto", "language": "fi", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Physics", "language": "en", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Fysiikka", "language": "fi", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "yvv.contractresearch.funding", "value": "0", "language": "", "element": "contractresearch", "qualifier": "funding", "schema": "yvv"}, {"key": "dc.type.coar", "value": "http://purl.org/coar/resource_type/c_bdcc", "language": null, "element": "type", "qualifier": "coar", "schema": "dc"}, {"key": "dc.rights.accesslevel", "value": "openAccess", "language": null, "element": "rights", "qualifier": "accesslevel", "schema": "dc"}, {"key": "dc.type.publication", "value": "masterThesis", "language": null, "element": "type", "qualifier": "publication", "schema": "dc"}, {"key": "dc.subject.oppiainekoodi", "value": "4021", "language": null, "element": "subject", "qualifier": "oppiainekoodi", "schema": "dc"}, {"key": "dc.subject.yso", "value": "biofysiikka", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "voimakent\u00e4t (fysiikka)", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "proteiinit", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "neuroverkot", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "koneoppiminen", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "molekyylidynamiikka", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "nanotieteet", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "biophysics", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "force fields", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "proteins", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "neural networks (information technology)", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "machine learning", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "molecular dynamics", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "nanosciences", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.rights.url", "value": "https://rightsstatements.org/page/InC/1.0/", "language": null, "element": "rights", "qualifier": "url", "schema": "dc"}]
|