AI-Driven Drug Response Prediction for Personalized Cancer Medicine
Kazi, Julhash U. LU
(2023)
1.
p.45-70
- Abstract
- Artificial intelligence (AI) has been used to develop drug sensitivity prediction models, raising the opportunity of using it for personalized cancer medicine. This chapter describes recent advancements in drug response prediction methods using machine learning algorithms. Pharmacogenomic datasets come with different types of biological data including genetic mutations, gene expression, copy number variations, protein expression, epigenetic modifications, and metabolomic data. The computational challenges in the implementation of AI in precision medicine have been highlighted, including medical data processing, environmental data collection, clinical text, and data processing. Several initial studies developed sparse linear regression... (More)
- Artificial intelligence (AI) has been used to develop drug sensitivity prediction models, raising the opportunity of using it for personalized cancer medicine. This chapter describes recent advancements in drug response prediction methods using machine learning algorithms. Pharmacogenomic datasets come with different types of biological data including genetic mutations, gene expression, copy number variations, protein expression, epigenetic modifications, and metabolomic data. The computational challenges in the implementation of AI in precision medicine have been highlighted, including medical data processing, environmental data collection, clinical text, and data processing. Several initial studies developed sparse linear regression models to predict drug sensitivity. These studies usually applied ridge regression and elastic net algorithms. The kernel functions can handle not only classification and regression problems for supervised learning but also can be applied to unsupervised learning. Matrix factorization is one of the widely used unsupervised learning algorithms for dimensionality reduction but can also be used for supervised learning problems. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3e4e6f5e-95f0-4a83-9fc3-92ab7bb83f91
- author
- Kazi, Julhash U.
LU
- organization
- publishing date
- 2023-03-03
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- machine learning, drug response, Prediction models
- host publication
- Artificial Intelligence for Disease Diagnosis and Prognosis in Smart Healthcare
- editor
- Kouadri Mostefaoui, Ghita ; Riazul Islam, S. M. and Tariq, Faisal
- volume
- 1
- edition
- 1st
- pages
- 26 pages
- publisher
- CRC Press
- ISBN
- 9781032168302
- 9781032171265
- 9781003251903
- DOI
- 10.1201/9781003251903-4
- language
- English
- LU publication?
- yes
- id
- 3e4e6f5e-95f0-4a83-9fc3-92ab7bb83f91
- date added to LUP
- 2023-03-09 15:43:22
- date last changed
- 2024-05-17 10:17:09
@inbook{3e4e6f5e-95f0-4a83-9fc3-92ab7bb83f91,
abstract = {{Artificial intelligence (AI) has been used to develop drug sensitivity prediction models, raising the opportunity of using it for personalized cancer medicine. This chapter describes recent advancements in drug response prediction methods using machine learning algorithms. Pharmacogenomic datasets come with different types of biological data including genetic mutations, gene expression, copy number variations, protein expression, epigenetic modifications, and metabolomic data. The computational challenges in the implementation of AI in precision medicine have been highlighted, including medical data processing, environmental data collection, clinical text, and data processing. Several initial studies developed sparse linear regression models to predict drug sensitivity. These studies usually applied ridge regression and elastic net algorithms. The kernel functions can handle not only classification and regression problems for supervised learning but also can be applied to unsupervised learning. Matrix factorization is one of the widely used unsupervised learning algorithms for dimensionality reduction but can also be used for supervised learning problems.}},
author = {{Kazi, Julhash U.}},
booktitle = {{Artificial Intelligence for Disease Diagnosis and Prognosis in Smart Healthcare}},
editor = {{Kouadri Mostefaoui, Ghita and Riazul Islam, S. M. and Tariq, Faisal}},
isbn = {{9781032168302}},
keywords = {{machine learning; drug response; Prediction models}},
language = {{eng}},
month = {{03}},
pages = {{45--70}},
publisher = {{CRC Press}},
title = {{AI-Driven Drug Response Prediction for Personalized Cancer Medicine}},
url = {{http://dx.doi.org/10.1201/9781003251903-4}},
doi = {{10.1201/9781003251903-4}},
volume = {{1}},
year = {{2023}},
}