Classification of gene expression patterns using a novel type-2 fuzzy multigranulation-based SVM model for the recognition of cancer mediating biomarkers

2020 ◽  
Author(s):  
Swarup Kr Ghosh ◽  
Anupam Ghosh
Keyword(s):  
Gene Expression ◽  
Expression Patterns ◽  
Gene Expression Patterns ◽  
Svm Model

Classification of the images of gene expression patterns using neural networks based on multivalued neurons with the minimal number of inputs

2002 ◽  
Author(s):  
Igor N. Aizenberg ◽  
Constantine Butakoff ◽  
Ekaterina Myasnikova ◽  
Maria Samsonova ◽  
John Reinitz
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Expression Patterns ◽  
Gene Expression Patterns

scholarly journals Unraveling the molecular heterogeneity in type 2 diabetes: A potential subtype discovery study followed by metabolic modeling

2020 ◽  
Author(s):  
Maryam Khoshnejat ◽  
Kaveh Kavousi ◽  
Ali Mohammad Banaei-Moghaddam ◽  
Ali Akbar Moosavi-Movahedi
Keyword(s):  
Gene Expression ◽  
Type 2 Diabetes ◽  
Molecular Mechanisms ◽  
Expression Patterns ◽  
Critical Role ◽  
Gene Expression Pattern ◽  
Gene Expression Patterns ◽  
Diabetic Patients ◽  
Molecular Heterogeneity

Abstract BackgroundType 2 diabetes mellitus (T2DM) is a complex multifactorial disease with a high prevalence in the world. Insulin resistance and impaired insulin secretion are the two major abnormalities in the pathogenesis of T2DM. Skeletal muscle is responsible for over 75% of the glucose uptake, thus plays a critical role in T2DM. Here, we attempted to provide a better understanding of abnormalities in this tissue. MethodsThe muscle gene expression patterns in healthy and newly diagnosed T2DM individuals were explored using supervised and unsupervised classification approach. Moreover, the potential of sub-typing T2DM patients based on the gene expression patterns was evaluated.ResultsA machine-learning technique was applied to identify a gene expression pattern that could discriminate between normoglycemic and diabetic groups. A gene set comprises of 26 genes was found that was able to discriminate healthy from diabetic individuals with 94% accuracy. In addition, three distinct clusters of diabetic patients with different dysregulated genes and metabolic pathways were identified. Conclusions This study implies that it seems the disease has triggered through different cellular/molecular mechanisms, and it has the potential to be categorized in different sub-types. Possibly, subtyping of T2DM patients in combination with their real clinical profiles will provide a better understanding of abnormalities in each group. Thus, this approach will help to recommend the appropriate treatment for each subtype in the future.

scholarly journals Automatic Classification of Embryonic Fruit Fly Gene Expression Patterns

2009 ◽  
pp. 415-419 ◽  
Author(s):  
Andreas Heffel ◽  
Sonja J. Prohaska ◽  
Peter F. Stadler ◽  
Gerhard Kauer ◽  
Jens-Peer Kuska
Keyword(s):  
Gene Expression ◽  
Expression Patterns ◽  
Fruit Fly ◽  
Automatic Classification ◽  
Gene Expression Patterns

scholarly journals Unraveling the molecular heterogeneity in type 2 diabetes: A potential subtype discovery followed by metabolic modeling

2020 ◽  
Author(s):  
Maryam Khoshnejat ◽  
Kaveh Kavousi ◽  
Ali Mohammad Banaei-Moghaddam ◽  
Ali Akbar Moosavi-Movahedi
Keyword(s):  
Gene Expression ◽  
Type 2 Diabetes ◽  
Molecular Mechanisms ◽  
Expression Patterns ◽  
Critical Role ◽  
Unsupervised Classification ◽  
Gene Expression Patterns ◽  
Diabetic Patients ◽  
Molecular Heterogeneity

Abstract BackgroundType 2 diabetes mellitus (T2DM) is a complex multifactorial disease with a high prevalence worldwide. Insulin resistance and impaired insulin secretion are the two major abnormalities in the pathogenesis of T2DM. Skeletal muscle is responsible for over 75% of the glucose uptake and plays a critical role in T2DM. Here, we sought to provide a better understanding of the abnormalities in this tissue. MethodsThe muscle gene expression patterns were explored in healthy and newly diagnosed T2DM individuals using supervised and unsupervised classification approaches. Moreover, the potential of subtyping T2DM patients was evaluated based on the gene expression patterns.ResultsA machine-learning technique was applied to identify a set of genes whose expression patterns could discriminate diabetic subjects from healthy ones. A gene set comprising of 26 genes was found that was able to distinguish healthy from diabetic individuals with 94% accuracy. In addition, three distinct clusters of diabetic patients with different dysregulated genes and metabolic pathways were identified. Conclusions This study indicates that T2DM is triggered by different cellular/molecular mechanisms, and it can be categorized into different subtypes. Subtyping of T2DM patients in combination with their real clinical profiles will provide a better understanding of the abnormalities in each group and more effective therapeutic approaches in the future.

scholarly journals Towards a novel classification of human malignancies based on gene expression patterns

2001 ◽  
Vol 195 (1) ◽  
pp. 41-52 ◽  
Author(s):  
Ash A. Alizadeh ◽  
Douglas T. Ross ◽  
Charles M. Perou ◽  
Matt van de Rijn
Keyword(s):  
Gene Expression ◽  
Expression Patterns ◽  
Gene Expression Patterns
Sign in / Sign up

Export Citation Format

Share Document