ATTENTION: The works hosted here are being migrated to a new repository that will consolidate resources, improve discoverability, and better show UTA's research impact on the global community. We will update authors as the migration progresses. Please see MavMatrix for more information.
Show simple item record
dc.contributor.advisor | Huang, Junzhou | |
dc.creator | Zhang, Xiaoyu | |
dc.date.accessioned | 2019-02-27T00:57:02Z | |
dc.date.available | 2019-02-27T00:57:02Z | |
dc.date.created | 2018-12 | |
dc.date.issued | 2018-11-26 | |
dc.date.submitted | December 2018 | |
dc.identifier.uri | http://hdl.handle.net/10106/27815 | |
dc.description.abstract | Observing the recent progress in Deep Learning, the employment of AI is surging to accelerate drug discovery and cut R&D costs in the last few years. However, the success of deep learning is attributed to large-scale clean high-quality labeled data, which is generally unavailable in drug discovery practices.
In this thesis, we address this issue by proposing an end-to-end deep learning framework in a semi supervised learning fashion. That is said, the proposed deep learning approach can utilize both labeled and unlabeled data. While labeled data is of very limited availability, the amount of available unlabeled data is generally huge. The proposed framework, named as seq3seq fingerprint, automatically learns a strong representation of each molecule in an unsupervised way from a huge training data pool containing a mixture of both unlabeled and labeled molecules. In the meantime, the representation is also adjusted to further help predictive tasks, e.g., acidity, alkalinity or solubility classification. The entire framework is trained end-to-end and simultaneously learn the representation and inference results. Extensive
experiments support the superiority of the proposed framework. | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en_US | |
dc.subject | Semi-supervised learning | |
dc.subject | Unsupervised learning | |
dc.subject | Structured prediction | |
dc.subject | Learning representation | |
dc.subject | Sequence to sequence learning | |
dc.subject | Deep learning | |
dc.subject | Drug discovery | |
dc.subject | Virtual screening | |
dc.subject | Molecular representation | |
dc.subject | Imaging | |
dc.subject | Computational biology | |
dc.title | TOWARDS END-TO-END SEMI-SUPERVISED DEEP LEARNING FOR DRUG DISCOVERY | |
dc.type | Thesis | |
dc.contributor.committeeMember | Zhu, Dajiang | |
dc.degree.department | Computer Science and Engineering | |
dc.degree.name | Master of Science in Computer Science | |
dc.date.updated | 2019-02-27T00:57:03Z | |
thesis.degree.department | Computer Science and Engineering | |
thesis.degree.grantor | The University of Texas at Arlington | |
thesis.degree.level | Masters | |
thesis.degree.name | Master of Science in Computer Science | |
dc.type.material | text | |
dc.creator.orcid | 0000-0003-4154-9676 | |
Files in this item
- Name:
- ZHANG-THESIS-2018.pdf
- Size:
- 480.7Kb
- Format:
- PDF
This item appears in the following Collection(s)
Show simple item record