{"id":{"repo_id":"toronto-retro","oai_identifier":"oai:utoronto.scholaris.ca:1807/140023"},"canonical_url":"https://search.dev.ndltd.org/etd/toronto-retro/oai:utoronto.scholaris.ca:1807/140023","repository":{"repo_id":"toronto-retro","name":"University of Toronto","base_url":"https://utoronto.scholaris.ca/server/oai/request"},"display":{"title":"RNA secondary structure prediction using hybrid methods","abstract":"This work presents a novel two-stage framework for RNA secondary structure prediction, introducing deep learning models that address local substructure prediction and global structure assembly. Drawing insights from RNA folding kinetics, the stage-1 (S1) model proposes local substructures as pixel-level square bounding boxes. The subsequent stage-2 (S2) models, including the scoring network (S2SC) and the encoder-decoder transformer (S2ED), leverage recurrent neural networks (RNNs) with Dynamic Programming (DP) and an encoder-decoder network with a subset prediction formulation, respectively, to achieve efficient global structure assembly. The proposed framework exhibits high accuracy on the human-transcriptome (HT) dataset. However, challenges in performance on the bpRNA dataset are observed, potentially stemming from dataset bias and limitations of the S1 model. Nevertheless, the models exhibit strong generalization capabilities compared to other deep learning models, attributed to the robust inductive bias introduced by the two-stage formulation. Anticipating advancements in computational resources and model architecture, ongoing improvements in performance are expected. The adaptability of the framework is a key highlight, as demonstrated by its capacity to be tailored to new datasets. For example, adjusting the reinforcement learning reward facilitates training the S2ED model on datasets with different structure distributions, showcasing the versatility of the proposed approach. In conclusion, this work offers a unique and effective perspective in RNA secondary structure prediction. Despite current limitations, the framework's adaptability and generalization underscore its potential for continuous evolution, particularly with the anticipated advancements in computational capabilities and the availability of diverse datasets.","abstract_html":"This work presents a novel two-stage framework for RNA secondary structure prediction, introducing deep learning models that address local substructure prediction and global structure assembly. Drawing insights from RNA folding kinetics, the stage-1 (S1) model proposes local substructures as pixel-level square bounding boxes. The subsequent stage-2 (S2) models, including the scoring network (S2SC) and the encoder-decoder transformer (S2ED), leverage recurrent neural networks (RNNs) with Dynamic Programming (DP) and an encoder-decoder network with a subset prediction formulation, respectively, to achieve efficient global structure assembly. The proposed framework exhibits high accuracy on the human-transcriptome (HT) dataset. However, challenges in performance on the bpRNA dataset are observed, potentially stemming from dataset bias and limitations of the S1 model. Nevertheless, the models exhibit strong generalization capabilities compared to other deep learning models, attributed to the robust inductive bias introduced by the two-stage formulation. Anticipating advancements in computational resources and model architecture, ongoing improvements in performance are expected. The adaptability of the framework is a key highlight, as demonstrated by its capacity to be tailored to new datasets. For example, adjusting the reinforcement learning reward facilitates training the S2ED model on datasets with different structure distributions, showcasing the versatility of the proposed approach. In conclusion, this work offers a unique and effective perspective in RNA secondary structure prediction. Despite current limitations, the framework's adaptability and generalization underscore its potential for continuous evolution, particularly with the anticipated advancements in computational capabilities and the availability of diverse datasets.","abstract_has_math":false,"creators":["GAO, JIEXIN"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Electrical and Computer Engineering","school":null,"contributors":[],"advisors":["Frey, Brendan BF"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-06","date_published":"2024-06","updated_at":"2026-07-27T21:27:58Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/1807/140023","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Frey, Brendan BF"]},{"key":"dc:contributor.department","label":"Department","values":["Electrical and Computer Engineering"]},{"key":"dc:creator","label":"Author","values":["GAO, JIEXIN"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-06"]},{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-11-08T16:32:28Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-11-08T16:32:28Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-06"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/1807/140023"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This work presents a novel two-stage framework for RNA secondary structure prediction, introducing deep learning models that address local substructure prediction and global structure assembly. Drawing insights from RNA folding kinetics, the stage-1 (S1) model proposes local substructures as pixel-level square bounding boxes. The subsequent stage-2 (S2) models, including the scoring network (S2SC) and the encoder-decoder transformer (S2ED), leverage recurrent neural networks (RNNs) with Dynamic Programming (DP) and an encoder-decoder network with a subset prediction formulation, respectively, to achieve efficient global structure assembly. The proposed framework exhibits high accuracy on the human-transcriptome (HT) dataset. However, challenges in performance on the bpRNA dataset are observed, potentially stemming from dataset bias and limitations of the S1 model. Nevertheless, the models exhibit strong generalization capabilities compared to other deep learning models, attributed to the robust inductive bias introduced by the two-stage formulation. Anticipating advancements in computational resources and model architecture, ongoing improvements in performance are expected. The adaptability of the framework is a key highlight, as demonstrated by its capacity to be tailored to new datasets. For example, adjusting the reinforcement learning reward facilitates training the S2ED model on datasets with different structure distributions, showcasing the versatility of the proposed approach. In conclusion, this work offers a unique and effective perspective in RNA secondary structure prediction. Despite current limitations, the framework's adaptability and generalization underscore its potential for continuous evolution, particularly with the anticipated advancements in computational capabilities and the availability of diverse datasets."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:title","label":"Title","values":["RNA secondary structure prediction using hybrid methods"]}]}],"canonical_facts":{"dc:contributor.advisor":["Frey, Brendan BF"],"dc:contributor.department":["Electrical and Computer Engineering"],"dc:creator":["GAO, JIEXIN"],"dc:date":["2024-06"],"dc:date.accessioned":["2024-11-08T16:32:28Z"],"dc:date.available":["2024-11-08T16:32:28Z"],"dc:date.issued":["2024-06"],"dc:description.abstract":["This work presents a novel two-stage framework for RNA secondary structure prediction, introducing deep learning models that address local substructure prediction and global structure assembly. Drawing insights from RNA folding kinetics, the stage-1 (S1) model proposes local substructures as pixel-level square bounding boxes. The subsequent stage-2 (S2) models, including the scoring network (S2SC) and the encoder-decoder transformer (S2ED), leverage recurrent neural networks (RNNs) with Dynamic Programming (DP) and an encoder-decoder network with a subset prediction formulation, respectively, to achieve efficient global structure assembly. The proposed framework exhibits high accuracy on the human-transcriptome (HT) dataset. However, challenges in performance on the bpRNA dataset are observed, potentially stemming from dataset bias and limitations of the S1 model. Nevertheless, the models exhibit strong generalization capabilities compared to other deep learning models, attributed to the robust inductive bias introduced by the two-stage formulation. Anticipating advancements in computational resources and model architecture, ongoing improvements in performance are expected. The adaptability of the framework is a key highlight, as demonstrated by its capacity to be tailored to new datasets. For example, adjusting the reinforcement learning reward facilitates training the S2ED model on datasets with different structure distributions, showcasing the versatility of the proposed approach. In conclusion, this work offers a unique and effective perspective in RNA secondary structure prediction. Despite current limitations, the framework's adaptability and generalization underscore its potential for continuous evolution, particularly with the anticipated advancements in computational capabilities and the availability of diverse datasets."],"dc:description.degree":["Ph.D."],"dc:identifier.uri":["http://hdl.handle.net/1807/140023"],"dc:title":["RNA secondary structure prediction using hybrid methods"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T21:27:58Z"}