{"id":{"repo_id":"gmu","oai_identifier":"oai:MARS:1920/10794"},"canonical_url":"https://search.dev.ndltd.org/etd/gmu/oai:MARS:1920/10794","repository":{"repo_id":"gmu","name":"George Mason University","base_url":"https://mars.gmu.edu/server/oai/request"},"display":{"title":"Classification of Thermophilic and Mesophilic Proteins Using N-Grams","abstract":"The project is focused on machine learning classification of thermophilic and mesophilic proteins using N-gram based representation of protein sequences. Two datasets containing proteins from both classes were used for the analysis. Alphabet reduction was performed on all datasets, and n-gram frequencies were calculated for each sequence using the reduced alphabet. Data normalization was done by calculating n-gram likelihoods. Four different machine learning algorithms (Naïve Bayes, Support Vector Machines, Decision Trees and Random Forests) were used for the protein classification. Accuracies of 100.0% were achieved using SVM, 99.3% using Random Forests, 90.3% using Naïve Bayes and 99.6 using Decision Trees.","abstract_html":"The project is focused on machine learning classification of thermophilic and mesophilic proteins using N-gram based representation of protein sequences. Two datasets containing proteins from both classes were used for the analysis. Alphabet reduction was performed on all datasets, and n-gram frequencies were calculated for each sequence using the reduced alphabet. Data normalization was done by calculating n-gram likelihoods. Four different machine learning algorithms (Naïve Bayes, Support Vector Machines, Decision Trees and Random Forests) were used for the protein classification. Accuracies of 100.0% were achieved using SVM, 99.3% using Random Forests, 90.3% using Naïve Bayes and 99.6 using Decision Trees.","abstract_has_math":false,"creators":["Elattar, Marwy"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-07-27T19:52:04Z","subjects":["Thermophilic","Mesophilic","N-grams","Machine learning"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["hdl:1920/10794"],"render_values":[{"text":"hdl:1920/10794","href":null,"code":true}]}]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Thermophilic","Mesophilic","N-grams","Machine learning"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["hdl:1920/10794"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.other","label":"Dc Description Other","values":["The project is focused on machine learning classification of thermophilic and mesophilic proteins using N-gram based representation of protein sequences. Two datasets containing proteins from both classes were used for the analysis. Alphabet reduction was performed on all datasets, and n-gram frequencies were calculated for each sequence using the reduced alphabet. Data normalization was done by calculating n-gram likelihoods. Four different machine learning algorithms (Naïve Bayes, Support Vector Machines, Decision Trees and Random Forests) were used for the protein classification. Accuracies of 100.0% were achieved using SVM, 99.3% using Random Forests, 90.3% using Naïve Bayes and 99.6 using Decision Trees."]},{"key":"dc:title","label":"Title","values":["Classification of Thermophilic and Mesophilic Proteins Using N-Grams"]}]}],"canonical_facts":{"dc:description.other":["The project is focused on machine learning classification of thermophilic and mesophilic proteins using N-gram based representation of protein sequences. Two datasets containing proteins from both classes were used for the analysis. Alphabet reduction was performed on all datasets, and n-gram frequencies were calculated for each sequence using the reduced alphabet. Data normalization was done by calculating n-gram likelihoods. Four different machine learning algorithms (Naïve Bayes, Support Vector Machines, Decision Trees and Random Forests) were used for the protein classification. Accuracies of 100.0% were achieved using SVM, 99.3% using Random Forests, 90.3% using Naïve Bayes and 99.6 using Decision Trees."],"dc:identifier":["hdl:1920/10794"],"dc:subject":["Thermophilic","Mesophilic","N-grams","Machine learning"],"dc:title":["Classification of Thermophilic and Mesophilic Proteins Using N-Grams"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T19:52:04Z"}