A mechanism-aware and multiomic machine-learning pipeline characterizes yeast cell growth
- Submitting institution
-
Teesside University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 16651548
- Type
- D - Journal article
- DOI
-
10.1073/pnas.2002959117
- Title of journal
- Proceedings of the National Academy of Sciences
- Article number
- -
- First page
- 18869
- Volume
- 117
- Issue
- 31
- ISSN
- 0027-8424
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
3
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- In this interdisciplinary paper, we propose and validate a multimodal learning method that can leverage the advantages of both machine learning and metabolic modelling. We reveal unknown interactions between biological domains by incorporating mechanistic knowledge, and therefore overcoming black-box limitations of conventional data-driven approaches. The method, validated on yeast data, has been recently awarded two research grants - a Children's Liver Disease Foundation Research Grant and an Earlier.org Breast Cancer Award - to extend it towards two additional case studies on young hepatoblastoma and breast cancer. It also led to two invited talks at Swansea University and University of Hull.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -