Synthetic augmentation of cancer cell line multi-omic datasets using unsupervised deep learning
Zhaoxiang Cai, Sofia Apolinário, Ana R Baião, Clare Pacini, Miguel D Sousa, Susana Vinga, Roger R Reddel, Phillip J Robinson, Mathew J Garnett, Qing Zhong, Emanuel Gonçalves · 2024
Read Synthetic augmentation of cancer cell line multi-omic datasets using unsupervised deep learning by Zhaoxiang Cai, Sofia Apolinário, Ana R Baião, Clare Pacini, Miguel D Sousa, Susana Vinga, Roger R Reddel, Phillip J Robinson, Mathew J Garnett, Qing Zhong, Emanuel Gonçalves (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11607321.txt.
Description
Zhaoxiang Cai and co-authors present MOSA in 2024, a deep learning model that fills gaps in cancer cell line data by making synthetic profiles. Cancer research joins many data types for each cell line, yet those sets are patchy and uneven, which weakens statistics. Their model learns without labels from the data types that do overlap.
Trained on the Cancer Dependency Map, MOSA generates full molecular and trait profiles, lifting the count of complete cell line records by about a third and covering more than fifteen hundred lines. The richer set sharpened drug resistance findings and gene association calls. An explanation method then pulled out which multi type features drive cell line grouping and mark drug or gene dependence. The authors offer synthetic filling as a way to get more from costly lab data without new experiments.
Catalog record
| CREATOR | Zhaoxiang Cai, Sofia Apolinário, Ana R Baião, Clare Pacini, Miguel D Sousa, Susana Vinga, Roger R Reddel, Phillip J Robinson, Mathew J Garnett, Qing Zhong, Emanuel Gonçalves |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 55 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |