Exploring high dimensional data with Butterfly: a novel classification algorithm based on discrete dynamical systems

Geraci, Joseph; Dharsee, Moyez; Nuin, Paulo; Haslehurst, Alexandria; Koti, Madhuri; Feilotter, Harriet; Evans, Kenneth R.

doi:10.1093/bioinformatics/btt602

Cited by 7 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Maldonado et al have applied SVM for simultaneous feature selection and classification [ 18 ]. New approach for classification of microarray high-dimensional data has been evolved [ 19 ]. Chen et al applied classification trees for larger datasets in Bioinformatics [ 20 ].…”

Section: Introductionmentioning

confidence: 99%

Ensemble Merit Merge Feature Selection for Enhanced Multinomial Classification in Alzheimer’s Dementia

Sivapriya

Kamal²,

Thangaiah

2015

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

The objective of this study is to develop an ensemble classifier with Merit Merge feature selection that will enhance efficiency of classification in a multivariate multiclass medical data for effective disease diagnostics. The large volumes of features extracted from brain Magnetic Resonance Images and neuropsychological tests for diagnosis lead to more complexity in classification procedures. A higher level of objectivity than what readers have is needed to produce reliable dementia diagnostic techniques. Ensemble approach which is trained with features selected from multiple biomarkers facilitated accurate classification when compared with conventional classification techniques. Ensemble approach for feature selection is experimented with classifiers like Naïve Bayes, Random forest, Support Vector Machine, and C4.5. Feature search is done with Particle Swarm Optimisation to retrieve the subset of features for further selection with the ensemble classifier. Features selected by the proposed C4.5 ensemble classifier with Particle Swarm Optimisation search, coupled with Merit Merge technique (CPEMM), outperformed bagging feature selection of SVM, NB, and Random forest classifiers. The proposed CPEMM feature selection found the best subset of features that efficiently discriminated normal individuals and patients affected with Mild Cognitive Impairment and Alzheimer's Dementia with 98.7% accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Ensemble Merit Merge Feature Selection for Enhanced Multinomial Classification in Alzheimer’s Dementia

Sivapriya

Kamal²,

Thangaiah

2015

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…The composite model considers unlabeled data; the objectives are not only to classify samples into subgroups and predict new samples but also to characterize the relationships among subgroups. Recently, Geraci et al [53] proposed “Butterfly”, a discrete dynamic system, for visualization, clustering, and classification of unlabeled data. Butterfly provided a 2D representation of the relationship between samples according to a set of variables.…”

Section: Discussionmentioning

confidence: 99%

A Composite Model for Subgroup Identification and Prediction via Bicluster Analysis

Chen

Zou

et al. 2014

PLoS ONE

View full text Add to dashboard Cite

BackgroundA major challenges in the analysis of large and complex biomedical data is to develop an approach for 1) identifying distinct subgroups in the sampled populations, 2) characterizing their relationships among subgroups, and 3) developing a prediction model to classify subgroup memberships of new samples by finding a set of predictors. Each subgroup can represent different pathogen serotypes of microorganisms, different tumor subtypes in cancer patients, or different genetic makeups of patients related to treatment response.MethodsThis paper proposes a composite model for subgroup identification and prediction using biclusters. A biclustering technique is first used to identify a set of biclusters from the sampled data. For each bicluster, a subgroup-specific binary classifier is built to determine if a particular sample is either inside or outside the bicluster. A composite model, which consists of all binary classifiers, is constructed to classify samples into several disjoint subgroups. The proposed composite model neither depends on any specific biclustering algorithm or patterns of biclusters, nor on any classification algorithms.ResultsThe composite model was shown to have an overall accuracy of 97.4% for a synthetic dataset consisting of four subgroups. The model was applied to two datasets where the sample’s subgroup memberships were known. The procedure showed 83.7% accuracy in discriminating lung cancer adenocarcinoma and squamous carcinoma subtypes, and was able to identify 5 serotypes and several subtypes with about 94% accuracy in a pathogen dataset.ConclusionThe composite model presents a novel approach to developing a biclustering-based classification model from unlabeled sampled data. The proposed approach combines unsupervised biclustering and supervised classification techniques to classify samples into disjoint subgroups based on their associated attributes, such as genotypic factors, phenotypic outcomes, efficacy/safety measures, or responses to treatments. The procedure is useful for identification of unknown species or new biomarkers for targeted therapy.

show abstract

“…To validate these findings, we performed an unbiased assessment of unstimulated CD4+ and CD8+ T cells from LNs based on the above markers (Fig 4a and g, Supplementary Tables 7 and 8, respectively) 48 followed by Monocle3-based trajectory analysis 49,50 (Fig 4b and h, respectively).…”

Section: Combo Therapy Is Associated With the Establishment Of A T Ce...mentioning

confidence: 93%

Dual blockade of IL-10 and PD-1 leads to control of SIV viral rebound following analytical treatment interruption.

Sékaly

Ribeiro

Strongin

et al. 2023

Preprint

View full text Add to dashboard Cite

HIV persistence during antiretroviral therapy (ART) is associated with heightened plasma IL-10 levels and the expression of the co-inhibitory receptor PD-1. We hypothesized that IL-10 and PD-1 blockade would synergize to boost immune function leading to control of viral rebound post-analytical treatment interruption (ATI). Twenty-eight ART-treated, SIVmac239-infected rhesus macaques (RMs) were treated with anti-IL-10 alone, anti-IL-10 in combination with anti-PD-1 (« combo »), or vehicle. ART was interrupted 12 weeks after the first dose of immunotherapy, which was continued for 14 weeks post-ATI. Durable control of viral rebound (<103 SIV RNA copies per mL plasma) was observed in 8 of 9 (88.9%) combo-treated RMs for more than the 24 weeks of follow up post-ATI. The induction of an inflammatory cytokine environment, proliferation of effector CD8+ T cells in lymph nodes, and reduced expression of BCL-2 in CD4+ T cells in blood and lymph nodes pre-ATI were strong predictors of control of viral rebound. Twenty-four weeks post-ATI, control of viral replication was associated with a rapid expansion of SIV-specific CD4+ and CD8+ T cells in blood and lymph nodes upon in vitro stimulation, followed by the contraction of this memory T cell pool and their differentiation to cells expressing TCF-1, the hallmark transcription factor that regulates stemness. These results provide a mechanistic framework to understand the immunological events that lead to the control of viral rebound post-ATI and map a path to guide the development of a functional cure of chronic HIV/SIV infection.

show abstract

Exploring high dimensional data with Butterfly: a novel classification algorithm based on discrete dynamical systems

Cited by 7 publications

References 19 publications

Ensemble Merit Merge Feature Selection for Enhanced Multinomial Classification in Alzheimer’s Dementia

Ensemble Merit Merge Feature Selection for Enhanced Multinomial Classification in Alzheimer’s Dementia

A Composite Model for Subgroup Identification and Prediction via Bicluster Analysis

Dual blockade of IL-10 and PD-1 leads to control of SIV viral rebound following analytical treatment interruption.

Contact Info

Product

Resources

About