2017
DOI: 10.1186/s12885-017-3500-5
|View full text |Cite
|
Sign up to set email alerts
|

Improved anticancer drug response prediction in cell lines using matrix factorization with similarity regularization

Abstract: Background: Human cancer cell lines are used in research to study the biology of cancer and to test cancer treatments. Recently there are already some large panels of several hundred human cancer cell lines which are characterized with genomic and pharmacological data. The ability to predict drug responses using these pharmacogenomics data can facilitate the development of precision cancer medicines. Although several methods have been developed to address the drug response prediction, there are many challenges… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

3
148
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
4
2
2

Relationship

1
7

Authors

Journals

citations
Cited by 150 publications
(151 citation statements)
references
References 32 publications
3
148
0
Order By: Relevance
“…The sensitivity of the cell line to the anticancer drug between the observed and the predicted was approximately 96.0. Comparing with the previous SRMF model in [19], which at the best was 0.71 on its data by = 0, was about 0.25. For SRMF model on data was about 0.95 Figure 1.1 compares the mean PCC_S / R between a samples of drugs, and averaged RMSE_S /R (root mean square error) between observed and predicted cell lines response to drugs in DSRMF model was 0.30, and in SRMF model was about 0.31 for data in this Research.…”
Section: Measurements Of Prediction Performancementioning
confidence: 57%
“…The sensitivity of the cell line to the anticancer drug between the observed and the predicted was approximately 96.0. Comparing with the previous SRMF model in [19], which at the best was 0.71 on its data by = 0, was about 0.25. For SRMF model on data was about 0.95 Figure 1.1 compares the mean PCC_S / R between a samples of drugs, and averaged RMSE_S /R (root mean square error) between observed and predicted cell lines response to drugs in DSRMF model was 0.30, and in SRMF model was about 0.31 for data in this Research.…”
Section: Measurements Of Prediction Performancementioning
confidence: 57%
“…Recently, many methods have been developed to predict the response of multiple drugs in a single model [11,17,[19][20][21]26]. In this so-called multi-task learning framework [31], sharing information on different drugs (tasks) often enables us to obtain a prediction method with high accuracy.…”
Section: Single-task Vs Multi-task Learningmentioning
confidence: 99%
“…The similarity-regularized matrix factorization (SRMF) method This method simply assumes that the drug response matrix R n×m is approximately a product of two low-rank matrices U n×k (a compression of the cell line profile matrix) and V m×k (a compression of the drug profile matrix). Wang et al used a cell line similarity matrix S cell and a drug similarity matrix S drug to compute the two low-rank matrices [21] as follows:…”
Section: Dualnetsmentioning
confidence: 99%
See 1 more Smart Citation
“…Many computational models predict drug response using gene expression profiles and drug molecular data [9][10][11] . Wang et al designed a machine learning model based on the observation that cell lines with similar gene expression patterns, or drugs with similar chemical properties, will exhibit similar responses 12 .…”
mentioning
confidence: 99%