{"id":{"repo_id":"sdstate","oai_identifier":"oai:openprairie.sdstate.edu:etd2-3122"},"canonical_url":"https://search.ndltd.org/etd/sdstate/oai:openprairie.sdstate.edu:etd2-3122","repository":{"repo_id":"sdstate","name":"South Dakota State University","base_url":"https://openprairie.sdstate.edu/do/oai/"},"display":{"title":"Semantic Discovery of Genomic Datasets with AI","abstract":"Traditional keyword-based search in genomic databases often fails to capture the latent semantic context of biological studies, leading to a ``Lexical Gap\" in research discovery. This thesis presents a high-performance dual-engine discovery system built upon 10,000 studies. By utilizing 1,536-dimensional vector embeddings, with large language models (LLMs) we implement a search engine coupled with a novel Hybrid Boosting layer that integrates semantic intent with factual metadata. Furthermore, we apply a high-dimensional K-Means clustering algorithm for unsupervised topic discovery. Empirical benchmarking demonstrates that the Hybrid Boosting engine achieves a 38.1% gain in precision and a 41.2% increase in Mean Reciprocal Rank (MRR) over pure semantic baselines. Validation via clinical WordClouds and Medical Subject Headings (MeSH) heatmaps confirms that unsupervised clusters align with expert-labeled clinical classifications, providing a scalable framework for cross-dataset exploration in functional genomics.","abstract_html":"Traditional keyword-based search in genomic databases often fails to capture the latent semantic context of biological studies, leading to a ``Lexical Gap&quot; in research discovery. This thesis presents a high-performance dual-engine discovery system built upon 10,000 studies. By utilizing 1,536-dimensional vector embeddings, with large language models (LLMs) we implement a search engine coupled with a novel Hybrid Boosting layer that integrates semantic intent with factual metadata. Furthermore, we apply a high-dimensional K-Means clustering algorithm for unsupervised topic discovery. Empirical benchmarking demonstrates that the Hybrid Boosting engine achieves a 38.1% gain in precision and a 41.2% increase in Mean Reciprocal Rank (MRR) over pure semantic baselines. Validation via clinical WordClouds and Medical Subject Headings (MeSH) heatmaps confirms that unsupervised clusters align with expert-labeled clinical classifications, providing a scalable framework for cross-dataset exploration in functional genomics.","abstract_has_math":false,"creators":["Allibah, Lawrence"],"institution":null,"degree_name":"Master of Science (MS)","degree_level":"Thesis - Open Access","degree_discipline":"Mathematics and Statistics","degree_department":null,"school":null,"contributors":["Xijin Ge"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T09:06:13Z","subjects":[],"languages":[],"rights":["Copyright © 2026 the author"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://openprairie.sdstate.edu/etd2/2177","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://openprairie.sdstate.edu/etd2/2177","record_label":"Repository record","record_kind":"record","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://openprairie.sdstate.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aopenprairie.sdstate.edu%3Aetd2-3122","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Xijin Ge"]},{"key":"dc:creator","label":"Author","values":["Allibah, Lawrence"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-07-29T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-01-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Mathematics and Statistics"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis - Open Access"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Copyright © 2026 the author","http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://openprairie.sdstate.edu/etd2/2177"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Traditional keyword-based search in genomic databases often fails to capture the latent semantic context of biological studies, leading to a ``Lexical Gap\" in research discovery. This thesis presents a high-performance dual-engine discovery system built upon 10,000 studies. By utilizing 1,536-dimensional vector embeddings, with large language models (LLMs) we implement a search engine coupled with a novel Hybrid Boosting layer that integrates semantic intent with factual metadata. Furthermore, we apply a high-dimensional K-Means clustering algorithm for unsupervised topic discovery. Empirical benchmarking demonstrates that the Hybrid Boosting engine achieves a 38.1% gain in precision and a 41.2% increase in Mean Reciprocal Rank (MRR) over pure semantic baselines. Validation via clinical WordClouds and Medical Subject Headings (MeSH) heatmaps confirms that unsupervised clusters align with expert-labeled clinical classifications, providing a scalable framework for cross-dataset exploration in functional genomics."]},{"key":"dc:title","label":"Title","values":["Semantic Discovery of Genomic Datasets with AI"]}]}],"canonical_facts":{"dc:contributor":["Xijin Ge"],"dc:creator":["Allibah, Lawrence"],"dc:date.available":["2026-07-29T07:00:00Z"],"dc:date.created":["2026-01-01T08:00:00Z"],"dc:description.abstract":["Traditional keyword-based search in genomic databases often fails to capture the latent semantic context of biological studies, leading to a ``Lexical Gap\" in research discovery. This thesis presents a high-performance dual-engine discovery system built upon 10,000 studies. By utilizing 1,536-dimensional vector embeddings, with large language models (LLMs) we implement a search engine coupled with a novel Hybrid Boosting layer that integrates semantic intent with factual metadata. Furthermore, we apply a high-dimensional K-Means clustering algorithm for unsupervised topic discovery. Empirical benchmarking demonstrates that the Hybrid Boosting engine achieves a 38.1% gain in precision and a 41.2% increase in Mean Reciprocal Rank (MRR) over pure semantic baselines. Validation via clinical WordClouds and Medical Subject Headings (MeSH) heatmaps confirms that unsupervised clusters align with expert-labeled clinical classifications, providing a scalable framework for cross-dataset exploration in functional genomics."],"dc:identifier":["https://openprairie.sdstate.edu/etd2/2177"],"dc:rights":["Copyright © 2026 the author","http://rightsstatements.org/vocab/InC/1.0/"],"dc:title":["Semantic Discovery of Genomic Datasets with AI"],"thesis:degree_discipline":["Mathematics and Statistics"],"thesis:degree_level":["Thesis - Open Access"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T09:06:13Z"}