2018
DOI: 10.1159/000495826
|View full text |Cite
|
Sign up to set email alerts
|

Clinical Drug Response Prediction by Using a Lq Penalized Network-Constrained Logistic Regression Method

Abstract: Background/Aims: One of the most important impacts of personalized medicine is the connection between patients’ genotypes and their drug responses. Despite a series of studies exploring this relationship, the predictive ability of such analyses still needs to be strengthened. Methods: Here we present the Lq penalized network-constrained logistic regression (Lq-NLR) method to meet this need, in which the predictors are integrated into the gene expression data and biological network knowledge and are combined wi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
8
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
3
2
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 12 publications
(8 citation statements)
references
References 46 publications
0
8
0
Order By: Relevance
“…However, due to the technical and ethical challenges of screening individuals against many drugs [5], such models are either trained for only a handful of drugs [6] or are trained using preclinical samples such as 2D cancer cell line cultures (CCLs) [7][8][9][10]. In spite of the success of these methods in predicting the drug response of left-out preclinical samples using models trained on preclinical samples, they have had limited success in predicting the CDR of real patients [9,11], with some exceptions [12][13][14].…”
Section: Introductionmentioning
confidence: 99%
“…However, due to the technical and ethical challenges of screening individuals against many drugs [5], such models are either trained for only a handful of drugs [6] or are trained using preclinical samples such as 2D cancer cell line cultures (CCLs) [7][8][9][10]. In spite of the success of these methods in predicting the drug response of left-out preclinical samples using models trained on preclinical samples, they have had limited success in predicting the CDR of real patients [9,11], with some exceptions [12][13][14].…”
Section: Introductionmentioning
confidence: 99%
“…However, due to the technical and ethical challenges of screening individuals against many drugs [5], such models are either trained for only a handful of drugs [6] or are trained using preclinical samples such as 2D cancer cell line cultures (CCLs) [7–10]. In spite of the success of these methods in predicting the drug response of left-out preclinical samples using models trained on preclinical samples, they have had limited success in predicting the CDR of real patients [9, 11], with some exceptions [1214].…”
Section: Introductionmentioning
confidence: 99%
“…At this stage, statements about the current performance of ML-based DRP methods overall are difficult to make. In the clinic, molecular patient data are already an established input for treatment decisions [ 152 ], and the potential of ML-based DRP models to predict tumoral responses to anticancer drugs has been established [ 30 , 44 , 46 , 58 , 67 , 71 , 101 ]. However, ML-based DRP seems to be rarely used in clinical practice.…”
Section: Discussion and Outlookmentioning
confidence: 99%
“…Huang et al. [ 58 ] proposed a logistic regression model that is additionally constrained based on biomolecular networks.…”
Section: Drp Modelsmentioning
confidence: 99%