{"id":{"repo_id":"vilnius","oai_identifier":"oai:vu.lt:elaba:210578101"},"canonical_url":"https://search.dev.ndltd.org/etd/vilnius/oai:vu.lt:elaba:210578101","repository":{"repo_id":"vilnius","name":"Vilnius University","base_url":"https://epublications.vu.lt/oai"},"display":{"title":"Dirbtinio intelekto panaudojimo tyrimas baltymų analizei /","abstract":"This paper reviews the literature on carotenoids, quantum chemistry, molecular dynamics and artificial intelligence. Carotenoids in plants contribute to photosynthesis and protect plants from various reactive oxygen species. For humans, carotenoids are of great nutritional and medical importance, as these pigments are associated with a lower risk of cardiovascular disease, obesity, diabetes and cancer. Quantum chemistry is based on the principles of quantum mechanics to describe the properties, structures and behaviour of atoms and molecules. Molecular dynamics (MD) methods are used to analyse the microscopic behaviour of various biophysical phenomena. Analyses of molecular systems, and in particular MD results, require methods for categorising data, and artificial intelligence (AI) is one such algorithm. AI is a description of machines that have cognitive human skills such as learning and problem solving. The main objective of this work is to investigate the potential of deep neural networks for structural element recognition in large structures, choosing the LH1-RC complex for analysis. The main objectives of this work are: to investigate the applicability of deep, fully connected neural networks for two and three category prediction of the LH1-RC complex from the PDB database; to investigate the applicability of deep, fully connected neural networks for part and all of the selected LH1-RC complex from the PDB database. The blastochloris viridis LH1-RC complex from the RCSB PDB database, with identification code \"6et5\", was used for this work. Four models were fitted for two and three category detection. For the 11 categories, 6 models were used. For 31 categories, 13 models were used. A deep, fully connected neural network application of neurosporene (all-trans-1, 2-dihydroneurosporene) carotenoid detection in the 6et5 complex showed that all models predicted the training data with 97.81% accuracy and the testing data with 98.03% accuracy. The application of a deep fully connected neural network for the detection of the two neurosporene carotenoid groups all-trans-1, 2-dihydroneurosporene and 15-cis-1, 2-dihydroneurosporene in the 6et5 complex resulted in all models predicting the training data with an accuracy of 97,67% and the testing data with an accuracy of 97,93%. The deep fully connected neural network fitting of the \"6et5\" part of the complex, i.e. for the detection of the 11 categories, shows that the best model hits the training data with 59.63% accuracy and the testing data with 52.85% accuracy. The fitting of a deep, fully connected neural network to all 31 groups of the selected 6et5 complex resulted in a 74.04% hit rate for training data and 49.73% accuracy for testing data.","abstract_html":"This paper reviews the literature on carotenoids, quantum chemistry, molecular dynamics and artificial intelligence. Carotenoids in plants contribute to photosynthesis and protect plants from various reactive oxygen species. For humans, carotenoids are of great nutritional and medical importance, as these pigments are associated with a lower risk of cardiovascular disease, obesity, diabetes and cancer. Quantum chemistry is based on the principles of quantum mechanics to describe the properties, structures and behaviour of atoms and molecules. Molecular dynamics (MD) methods are used to analyse the microscopic behaviour of various biophysical phenomena. Analyses of molecular systems, and in particular MD results, require methods for categorising data, and artificial intelligence (AI) is one such algorithm. AI is a description of machines that have cognitive human skills such as learning and problem solving. The main objective of this work is to investigate the potential of deep neural networks for structural element recognition in large structures, choosing the LH1-RC complex for analysis. The main objectives of this work are: to investigate the applicability of deep, fully connected neural networks for two and three category prediction of the LH1-RC complex from the PDB database; to investigate the applicability of deep, fully connected neural networks for part and all of the selected LH1-RC complex from the PDB database. The blastochloris viridis LH1-RC complex from the RCSB PDB database, with identification code "6et5", was used for this work. Four models were fitted for two and three category detection. For the 11 categories, 6 models were used. For 31 categories, 13 models were used. A deep, fully connected neural network application of neurosporene (all-trans-1, 2-dihydroneurosporene) carotenoid detection in the 6et5 complex showed that all models predicted the training data with 97.81% accuracy and the testing data with 98.03% accuracy. The application of a deep fully connected neural network for the detection of the two neurosporene carotenoid groups all-trans-1, 2-dihydroneurosporene and 15-cis-1, 2-dihydroneurosporene in the 6et5 complex resulted in all models predicting the training data with an accuracy of 97,67% and the testing data with an accuracy of 97,93%. The deep fully connected neural network fitting of the "6et5" part of the complex, i.e. for the detection of the 11 categories, shows that the best model hits the training data with 59.63% accuracy and the testing data with 52.85% accuracy. The fitting of a deep, fully connected neural network to all 31 groups of the selected 6et5 complex resulted in a 74.04% hit rate for training data and 49.73% accuracy for testing data.","abstract_has_math":false,"creators":["Kuklys, Domantas,"],"institution":"Institutional Repository of Vilnius University","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-24T05:55:48Z","subjects":[],"languages":["lit"],"rights":["info:eu-repo/semantics/openAccess"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://repository.vu.lt/VU:ELABAETD210578101&prefLang=en_US","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Kuklys, Domantas,"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024"]},{"key":"dc:publisher","label":"Institution","values":["Institutional Repository of Vilnius University"]},{"key":"dc:relation","label":"Dc Relation","values":["https://epublications.vu.lt/object/elaba:210578101/210578101.pdf"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/bachelorThesis"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["lit"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://repository.vu.lt/VU:ELABAETD210578101&prefLang=en_US"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This paper reviews the literature on carotenoids, quantum chemistry, molecular dynamics and artificial intelligence. Carotenoids in plants contribute to photosynthesis and protect plants from various reactive oxygen species. For humans, carotenoids are of great nutritional and medical importance, as these pigments are associated with a lower risk of cardiovascular disease, obesity, diabetes and cancer. Quantum chemistry is based on the principles of quantum mechanics to describe the properties, structures and behaviour of atoms and molecules. Molecular dynamics (MD) methods are used to analyse the microscopic behaviour of various biophysical phenomena. Analyses of molecular systems, and in particular MD results, require methods for categorising data, and artificial intelligence (AI) is one such algorithm. AI is a description of machines that have cognitive human skills such as learning and problem solving. The main objective of this work is to investigate the potential of deep neural networks for structural element recognition in large structures, choosing the LH1-RC complex for analysis. The main objectives of this work are: to investigate the applicability of deep, fully connected neural networks for two and three category prediction of the LH1-RC complex from the PDB database; to investigate the applicability of deep, fully connected neural networks for part and all of the selected LH1-RC complex from the PDB database. The blastochloris viridis LH1-RC complex from the RCSB PDB database, with identification code \"6et5\", was used for this work. Four models were fitted for two and three category detection. For the 11 categories, 6 models were used. For 31 categories, 13 models were used. A deep, fully connected neural network application of neurosporene (all-trans-1, 2-dihydroneurosporene) carotenoid detection in the 6et5 complex showed that all models predicted the training data with 97.81% accuracy and the testing data with 98.03% accuracy. The application of a deep fully connected neural network for the detection of the two neurosporene carotenoid groups all-trans-1, 2-dihydroneurosporene and 15-cis-1, 2-dihydroneurosporene in the 6et5 complex resulted in all models predicting the training data with an accuracy of 97,67% and the testing data with an accuracy of 97,93%. The deep fully connected neural network fitting of the \"6et5\" part of the complex, i.e. for the detection of the 11 categories, shows that the best model hits the training data with 59.63% accuracy and the testing data with 52.85% accuracy. The fitting of a deep, fully connected neural network to all 31 groups of the selected 6et5 complex resulted in a 74.04% hit rate for training data and 49.73% accuracy for testing data."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Dirbtinio intelekto panaudojimo tyrimas baltymų analizei /","Research on the application of artificial intelligence in protein analysis."]}]}],"canonical_facts":{"dc:creator":["Kuklys, Domantas,"],"dc:date":["2024"],"dc:description":["This paper reviews the literature on carotenoids, quantum chemistry, molecular dynamics and artificial intelligence. Carotenoids in plants contribute to photosynthesis and protect plants from various reactive oxygen species. For humans, carotenoids are of great nutritional and medical importance, as these pigments are associated with a lower risk of cardiovascular disease, obesity, diabetes and cancer. Quantum chemistry is based on the principles of quantum mechanics to describe the properties, structures and behaviour of atoms and molecules. Molecular dynamics (MD) methods are used to analyse the microscopic behaviour of various biophysical phenomena. Analyses of molecular systems, and in particular MD results, require methods for categorising data, and artificial intelligence (AI) is one such algorithm. AI is a description of machines that have cognitive human skills such as learning and problem solving. The main objective of this work is to investigate the potential of deep neural networks for structural element recognition in large structures, choosing the LH1-RC complex for analysis. The main objectives of this work are: to investigate the applicability of deep, fully connected neural networks for two and three category prediction of the LH1-RC complex from the PDB database; to investigate the applicability of deep, fully connected neural networks for part and all of the selected LH1-RC complex from the PDB database. The blastochloris viridis LH1-RC complex from the RCSB PDB database, with identification code \"6et5\", was used for this work. Four models were fitted for two and three category detection. For the 11 categories, 6 models were used. For 31 categories, 13 models were used. A deep, fully connected neural network application of neurosporene (all-trans-1, 2-dihydroneurosporene) carotenoid detection in the 6et5 complex showed that all models predicted the training data with 97.81% accuracy and the testing data with 98.03% accuracy. The application of a deep fully connected neural network for the detection of the two neurosporene carotenoid groups all-trans-1, 2-dihydroneurosporene and 15-cis-1, 2-dihydroneurosporene in the 6et5 complex resulted in all models predicting the training data with an accuracy of 97,67% and the testing data with an accuracy of 97,93%. The deep fully connected neural network fitting of the \"6et5\" part of the complex, i.e. for the detection of the 11 categories, shows that the best model hits the training data with 59.63% accuracy and the testing data with 52.85% accuracy. The fitting of a deep, fully connected neural network to all 31 groups of the selected 6et5 complex resulted in a 74.04% hit rate for training data and 49.73% accuracy for testing data."],"dc:format":["application/pdf"],"dc:identifier":["https://repository.vu.lt/VU:ELABAETD210578101&prefLang=en_US"],"dc:language":["lit"],"dc:publisher":["Institutional Repository of Vilnius University"],"dc:relation":["https://epublications.vu.lt/object/elaba:210578101/210578101.pdf"],"dc:rights":["info:eu-repo/semantics/openAccess"],"dc:title":["Dirbtinio intelekto panaudojimo tyrimas baltymų analizei /","Research on the application of artificial intelligence in protein analysis."],"dc:type":["info:eu-repo/semantics/bachelorThesis"]},"updated_at":"2026-07-24T05:55:48Z"}