Abstract:For the past three decades, the use of genomics to inform drug discovery and development pipelines has generated both excitement and scepticism. Although earlier efforts successfully identified some new drug targets, the overall clinical efficacy of developed drugs has remained unimpressive, owing in large part to the heterogeneous causes of disease. Recent technological and analytical advances in genomics, however, have now made it possible to rapidly identify and interpret the genetic variation underlying a … Show more
“…GENet-Lap and GENet-NLap were the two versions developed from ENet through incorporating the (normalized) Laplacian matrix of a protein-protein interaction network into the last regularization term in Eqn. (1). Interestingly, the two methods outperformed ENet for seven out of the nine metrics ( Figure 1-2, see also Figure S1-S2).…”
Section: Protein-protein Interaction Network Are Informativementioning
confidence: 85%
“…In this method, B n×n = I n×n in Eqn. (1). We assessed two versions of this model: GENet-Lap and GENet-NLap in which M is set to the Laplacian matrix and the normalized Laplacian matrix of a gene interaction network [14], respectively.…”
Section: Generalized Enet (Genet)mentioning
confidence: 99%
“…This approach uses an iterative procedure to set (b j ) and compute the coefficient vector w in Eqn. (1). Here, the drug response data R n×1 = (r i ) n i=1 is assumed to follow a normal distribution N (µ, σ 2 ) with the parameters being estimated as [12]:…”
“…This problem can be solved as easily as solving Eqn. (1). The reason is that one only needs to know how to compute the inner product f (u) · f (v) of image vectors to solve the optimization problem.…”
Section: Kernel Ridge Regression (Krr)mentioning
confidence: 99%
“…Recent cancer genome studies have suggested that each cancer patient owns a unique profile of gene mutations and that there is no silver bullet for defeating all the cancers. Therefore, how to use the genomic profiles of cancer patients to design a personalized treatment is vital for effective control of disease progression [1,2]. This requires accurate prediction of the patients' response to target-specific drugs and therapies.…”
Drug response prediction arises from both basic and clinical research of personalized therapy, as well as drug discovery for cancer and other diseases. With gene expression profiles and other omics data being available for over 1000 cancer cell lines and tissues, different machine learning approaches have been applied to solve drug response prediction problems. These methods appear in a body of literature and have been evaluated on different datasets with only one or two accuracy metrics. We systematically assessed 17 representative methods for drug response prediction, which have been developed in the past five years, on four large public datasets in nine metrics. This study provides insights and lessons for future research into drug response prediction.
“…GENet-Lap and GENet-NLap were the two versions developed from ENet through incorporating the (normalized) Laplacian matrix of a protein-protein interaction network into the last regularization term in Eqn. (1). Interestingly, the two methods outperformed ENet for seven out of the nine metrics ( Figure 1-2, see also Figure S1-S2).…”
Section: Protein-protein Interaction Network Are Informativementioning
confidence: 85%
“…In this method, B n×n = I n×n in Eqn. (1). We assessed two versions of this model: GENet-Lap and GENet-NLap in which M is set to the Laplacian matrix and the normalized Laplacian matrix of a gene interaction network [14], respectively.…”
Section: Generalized Enet (Genet)mentioning
confidence: 99%
“…This approach uses an iterative procedure to set (b j ) and compute the coefficient vector w in Eqn. (1). Here, the drug response data R n×1 = (r i ) n i=1 is assumed to follow a normal distribution N (µ, σ 2 ) with the parameters being estimated as [12]:…”
“…This problem can be solved as easily as solving Eqn. (1). The reason is that one only needs to know how to compute the inner product f (u) · f (v) of image vectors to solve the optimization problem.…”
Section: Kernel Ridge Regression (Krr)mentioning
confidence: 99%
“…Recent cancer genome studies have suggested that each cancer patient owns a unique profile of gene mutations and that there is no silver bullet for defeating all the cancers. Therefore, how to use the genomic profiles of cancer patients to design a personalized treatment is vital for effective control of disease progression [1,2]. This requires accurate prediction of the patients' response to target-specific drugs and therapies.…”
Drug response prediction arises from both basic and clinical research of personalized therapy, as well as drug discovery for cancer and other diseases. With gene expression profiles and other omics data being available for over 1000 cancer cell lines and tissues, different machine learning approaches have been applied to solve drug response prediction problems. These methods appear in a body of literature and have been evaluated on different datasets with only one or two accuracy metrics. We systematically assessed 17 representative methods for drug response prediction, which have been developed in the past five years, on four large public datasets in nine metrics. This study provides insights and lessons for future research into drug response prediction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.