Contexts and contradictions : reasoning with science for literature-based drug repurposing
Abstract/Contents
- Abstract
- Many diseases, especially rare or emergent diseases, lack therapeutic options leading to grim outcomes. When time or money is limited, drug repurposing, using existing drugs in the pharmacy to treat different diseases than those for which they were developed, may be the only feasible option. The trouble is identifying which drugs might be effective for which diseases when human experiments are impossible. One strategy for repurposing is by piecing together the biological puzzle pieces of knowledge about interactions between drugs, proteins, genes, and diseases. These pieces exist scattered across biomedical research, and can get lost as literature in the field proliferates exponentially. Advances in AI, natural language processing, and knowledge graph methods can help us distill knowledge into a form that scientists can use to connect the dots and predict pre-clinical opportunities for drug repurposing in silico. Reasoning directly with scientific knowledge yields multiple challenge, which I address in this thesis. I present work on (1) framing the task of generating repurposing hypotheses using knowledge extracted directly from literature, (2) elucidating contradictory research claims in a domain rife with contradictions—COVID-19 drug treatment efficacy, and (3) augmenting extracted relational knowledge with essential biological cell type and tissue contexts. I present novel data and methods for addressing complexities when reasoning over scientific knowledge for drug repurposing.
Description
| Type of resource | text |
|---|---|
| Form | electronic resource; remote; computer; online resource |
| Extent | 1 online resource. |
| Place | California |
| Place | [Stanford, California] |
| Publisher | [Stanford University] |
| Copyright date | 2023; ©2023 |
| Publication date | 2023; 2023 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Author | Sosa, Daniel Nicolas |
|---|---|
| Degree supervisor | Altman, Russ |
| Thesis advisor | Altman, Russ |
| Thesis advisor | Musen, Mark A |
| Thesis advisor | Potts, Christopher, 1977- |
| Degree committee member | Musen, Mark A |
| Degree committee member | Potts, Christopher, 1977- |
| Associated with | Stanford University, School of Medicine |
| Associated with | Stanford University, Department of Biomedical Informatics |
Subjects
| Genre | Theses |
|---|---|
| Genre | Text |
Bibliographic information
| Statement of responsibility | Daniel Nicolas Sosa. |
|---|---|
| Note | Submitted to the Department of Biomedical Informatics. |
| Thesis | Thesis Ph.D. Stanford University 2023. |
| Location | https://purl.stanford.edu/qr680tt7843 |
Access conditions
- Copyright
- © 2023 by Daniel Nicolas Sosa
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...