SUBIC: A Supervised Bi-Clustering Approach for Precision Medicine

Nezhad, Milad Zafar; Zhu, Dongxiao; Sadati, Najibesadat; Yang, Kai; Levi, Phillip

doi:10.1109/icmla.2017.00-68

Cited by 12 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, appropriate biomarkers with appreciable specificity and sensitivity are hard to come by. Using the combinatorial capacity of a variety of distinct biomarkers is one possibility to improve the overall specificity [132,133]. Present-day metabolomics have substantially benefited from upgraded study design that contributed to the decrease in the demographic differences and sources of bias.…”

Section: Limitations Of Statistics In Biomarker Discoverymentioning

confidence: 99%

Statistical methods and resources for biomarker discovery using metabolomics

et al. 2023

View full text Add to dashboard Cite

Metabolomics is a dynamic tool for elucidating biochemical changes in human health and disease. Metabolic profiles provide a close insight into physiological states and are highly volatile to genetic and environmental perturbations. Variation in metabolic profiles can inform mechanisms of pathology, providing potential biomarkers for diagnosis and assessment of the risk of contracting a disease. With the advancement of high-throughput technologies, large-scale metabolomics data sources have become abundant. As such, careful statistical analysis of intricate metabolomics data is essential for deriving relevant and robust results that can be deployed in real-life clinical settings. Multiple tools have been developed for both data analysis and interpretations. In this review, we survey statistical approaches and corresponding statistical tools that are available for discovery of biomarkers using metabolomics.

show abstract

Section: Limitations Of Statistics In Biomarker Discoverymentioning

confidence: 99%

Statistical methods and resources for biomarker discovery using metabolomics

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In medicine, certain treatments are often applied to all individuals with the same disease. In this case, the application of clustering allows one to distinguish groups of patients and to summarize these groups to provide much more precise recommendations [14]. Studies show that clustering algorithms can be applied to identify different diseases [15,16,17,18,19].…”

Section: Data Clustering Application In Medicinementioning

confidence: 99%

Data clustering and its applications in medicine

Lukauskas¹,

Ruzgas²

2022

ntmsci

View full text Add to dashboard Cite

Artificial intelligence was first mentioned back in 1956, but the biggest leap in its use has been seen in the last two decades. It goes without saying that with the increasing availability of artificial intelligence, one of the most important areas in which it must be applied is medicine. The purpose of this short article is to provide an overview of one of the groups of machine learning, by reviewing clustering algorithms and also by reviewing the use in medicine. For an excellent interpretation, this can usually be done by finding certain groups in your data that are much easier to interpret than individual observations. This task can be solved using a clustering. In medicine, the application of clustering allows one to distinguish various groups of patients and to summarize these groups to provide much more precise recommendations. Different clustering techniques are used to identify breast cancer, Parkinson's disease, migraine, various psychological and psychiatric disorders, heart and diabetes diseases, Huntington's disease, and Alzheimer's disease, among others. Looking at all the examples, it can be seen that even when evaluating only one area, clustering is applied particularly widely. Every year, more and more different research is carried out, which allows us to apply these algorithms in medicine and helps doctors assess the situation and start treatment faster or even more accurately. It can be assumed that only a greater use of AI and clustering in medicine will be observed in the coming years.

show abstract

“…Various decomposition techniques have achieved effective results on bi-clustering [10], [20]- [25]. For example, Liu et al designed a network-assisted algorithm for bi-clustering to find cancer sub-types [21].…”

Section: A Decomposition Techniques For Bi-clusteringmentioning

confidence: 99%

“…For example, Liu et al designed a network-assisted algorithm for bi-clustering to find cancer sub-types [21]. Nezhad et al introduced labels into the model, providing the possibility of accurate medical diagnosis [20]. Based on Bayesian theory, Pessia et al estimated the population structure hidden by bi-clustering for multiple sequence alignments [10].…”

Section: A Decomposition Techniques For Bi-clusteringmentioning

confidence: 99%

Dual Graph-Laplacian PCA: A Closed-Form Solution for Bi-Clustering to Find “Checkerboard” Structures on Gene Expression Data

et al. 2019

View full text Add to dashboard Cite

In the context of cancer, internal ''checkerboard'' structures are normally found in the matrices of gene expression data, which correspond to genes that are significantly up-or down-regulated in patients with specific types of tumors. In this paper, we propose a novel method, called dual graph-regularization principal component analysis (DGPCA). The main innovation of this method is that it simultaneously considers the internal geometric structures of the condition manifold and the gene manifold. Specifically, we obtain principal components (PCs) to represent the data and approximate the cluster membership indicators through Laplacian embedding. This new method is endowed with internal geometric structures, such as the condition manifold and gene manifold, which are both suitable for bi-clustering. A closed-form solution is provided for DGPCA. We apply this new method to simultaneously cluster genes and conditions (e.g., different samples) with the aim of finding internal ''checkerboard'' structures on gene expression data, if they exist. Then, we use this new method to identify regulatory genes under the particular conditions and to compare the results with those of other state-of-the-art PCA-based methods. Promising results on gene expression data have been verified by extensive experiments. INDEX TERMS Bi-clustering, gene expression data, Laplacian embedding, principal component analysis. I. INTRODUCTION A. BIOLOGICAL ANALYSIS OF PCA

show abstract

SUBIC: A Supervised Bi-Clustering Approach for Precision Medicine

Cited by 12 publications

References 20 publications

Statistical methods and resources for biomarker discovery using metabolomics

Statistical methods and resources for biomarker discovery using metabolomics

Data clustering and its applications in medicine

Dual Graph-Laplacian PCA: A Closed-Form Solution for Bi-Clustering to Find “Checkerboard” Structures on Gene Expression Data

Contact Info

Product

Resources

About