The Phylogenetic Tree based Deep Forest for Metagenomic Data Classification

Zhu, Qiang; Zhu, Qing; Pan, Min; Jiang, Xingpeng; Hu, Xiaohua; He, Tingting

doi:10.1109/bibm.2018.8621463

Cited by 15 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to verify the proposed method, in this section, we tested the performances of various classifiers derived respectively from KPCCF and other state-of-the-art methods, including Decision Tree (DT) [45], standard ensemble method RF [21], the normal deep learning algorithm CNN [28], and the original deep forest model gcForest(DF) [33,27,34] on the four datasets shown in Table 1, and evaluated the results through classification accuracy.…”

Section: Resultsmentioning

confidence: 99%

“…DL is a high-level abstraction algorithm that uses multiple complex structures to represent multiple nonlinear changes [23]. Deep Neural Networks (DNNs) have been widely exploited recently for meta-genomic association studies [24,25], meta-genomic classification [26,27], and disease diagnose [28,29]. Large training data is necessary for DNNs to realize good performance, which may not be possible in small-scale datasets like biology and medical science.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Kernel principal components based cascade forest towards disease identiﬁcation with human microbiota

Zhou

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

Numerous pieces of clinical evidence have shown that many phenotypic traits of human disease are related to their gut microbiome. Through supervised classification, it is feasible to determine the human disease states by revealing the intestinal microbiota compositional information. However, the abundance matrix of microbiome data is so sparse, an interpretable deep model is crucial to further represent and mine the data for expansion, such as the deep forest. What's more, overfitting can still exist in the original deep forest model when dealing with such “large p, small n” biology data. Feature reduction is considered to improve the ensemble forest model especially towards the disease identification in the human microbiota. In this work, we propose the kernel principal components based cascade forest method, so-called KPCCF, to classify the disease states of patients by using taxonomic profiles of the microbiome at the family level. In detail, the kernel principal components analysis method is first used to reduce the original dimension of human microbiota datasets. Besides, the processed data is fed into the cascade forest to preliminarily discriminate the disease state of the samples. Thus, the proposed KPCCF algorithm can represent the small-scale and high-dimension human microbiota datasets with the sparse feature matrix. Systematic comparison experiments demonstrate that our method consistently outperforms the state-of-the-art methods with the comparative study on 4 datasets. Additionally, compared to other dimensionality reduction methods, kernel principal components analysis method is more suitable for microbiota datasets.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Kernel principal components based cascade forest towards disease identiﬁcation with human microbiota

Zhou

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In order to verify the proposed method, in this section, we tested the performances of various classifiers derived respectively from KPCCF and other state-of-the-art methods, including Decision Tree (DT) [46], standard ensemble method RF [21], the normal deep learning algorithm CNN [28], and the original deep forest model gcForest(DF) [33,27,34] on the four datasets shown in Table 1, and evaluated the results through classification accuracy.…”

Section: Resultsmentioning

confidence: 99%

“…The latter is the overall sequencing and analysis of all meta-genomic DNA, including Shotgun metagenomics, etc. Many people now use the above sequencing data to carry out prediction research [24] [40] [27].…”

Section: Microbiota Datasetsmentioning

confidence: 99%

“…Thus, the standard DF model still faces overfitting and ensemble diversity challenges when dealing with such "large p, small n" biology data. Many researchers have been exploring how to improve the DF algorithm of identification for special field [32,33,27]. Features are the key to determining similarity measure and classification prediction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Kernel principal components based cascade forest towards disease identification with human microbiota

Zhou

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

Numerous pieces of clinical evidence have shown that many phenotypic traits of human disease are related to their gut microbiome. Through supervised classification, it is feasible to determine the human disease states by revealing the intestinal microbiota compositional information. However, the abundance matrix of microbiome data is so sparse, an interpretable deep model is crucial to further represent and mine the data for expansion, such as the deep forest. What's more, overfitting can still exist in the original deep forest model when dealing with such “large p, small n” biology data. Feature reduction is considered to improve the ensemble forest model especially towards the disease identification in the human microbiota. In this work, we propose the kernel principal components based cascade forest method, so-called KPCCF, to classify the disease states of patients by using taxonomic profiles of the microbiome at the family level. In detail, the kernel principal components analysis method is first used to reduce the original dimension of human microbiota datasets. Besides, the processed data is fed into the cascade forest to preliminarily discriminate the disease state of the samples. Thus, the proposed KPCCF algorithm can represent the small-scale and high-dimension human microbiota datasets with the sparse feature matrix. Systematic comparison experiments demonstrate that our method consistently outperforms the state-of-the-art methods with the comparative study on 4 datasets. Additionally, compared to other dimensionality reduction methods, the kernel principal components analysis method is more suitable for microbiota datasets.

show abstract

DF classification algorithm for constructing a small sample size of data-oriented DF regression model

Xia

Qiao

Zhang

et al. 2022

Neural Comput & Applic

View full text Add to dashboard Cite

The Phylogenetic Tree based Deep Forest for Metagenomic Data Classification

Cited by 15 publications

References 14 publications

Kernel principal components based cascade forest towards disease identiﬁcation with human microbiota

Kernel principal components based cascade forest towards disease identiﬁcation with human microbiota

Kernel principal components based cascade forest towards disease identification with human microbiota

DF classification algorithm for constructing a small sample size of data-oriented DF regression model

Contact Info

Product

Resources

About