Classifying Breast Cancer Subtypes Using Multiple Kernel Learning Based on Omics Data

Tao, Mengchu; Song, Tianci; Du, Wei; Han, Siyu; Zuo, Chunman; Li, Ying; Wang, Yan; Yang, Zekun

doi:10.3390/genes10030200

Cited by 40 publications

(39 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the study of breast cancer subtypes is of great significance for precision medicine and prognosis prediction of breast cancer [5]. By understanding the molecular subtypes of breast cancer, doctors can better decide which treatment is suitable for each patient, thus saving money for the whole medical system and avoiding the side effects of unnecessary treatment [6].…”

Section: Introductionmentioning

confidence: 99%

“…The current research on breast cancer subtypes focuses mainly on the molecular typing. In 1999, molecular typing of cancer was first proposed by the National Cancer Institute (NCI) [6]. In 2000, Perou et al first proposed the molecular typing of breast cancer and concluded that breast cancer is divided into four subtypes, namely luminal subtype, basal-like subtype, human epidermal growth subtype and normal breast-like subtype [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classifying Breast Cancer Subtypes Using Deep Neural Networks Based on Multi-Omics Data

Lin

Zhang

Cao

et al. 2020

Genes

Self Cite

View full text Add to dashboard Cite

With the high prevalence of breast cancer, it is urgent to find out the intrinsic difference between various subtypes, so as to infer the underlying mechanisms. Given the available multi-omics data, their proper integration can improve the accuracy of breast cancer subtype recognition. In this study, DeepMO, a model using deep neural networks based on multi-omics data, was employed for classifying breast cancer subtypes. Three types of omics data including mRNA data, DNA methylation data, and copy number variation (CNV) data were collected from The Cancer Genome Atlas (TCGA). After data preprocessing and feature selection, each type of omics data was input into the deep neural network, which consists of an encoding subnetwork and a classification subnetwork. The results of DeepMO based on multi-omics on binary classification are better than other methods in terms of accuracy and area under the curve (AUC). Moreover, compared with other methods using single omics data and multi-omics data, DeepMO also had a higher prediction accuracy on multi-classification. We also validated the effect of feature selection on DeepMO. Finally, we analyzed the enrichment gene ontology (GO) terms and biological pathways of these significant genes, which were discovered during the feature selection process. We believe that the proposed model is useful for multi-omics data analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Classifying Breast Cancer Subtypes Using Deep Neural Networks Based on Multi-Omics Data

Lin

Zhang

Cao

et al. 2020

Genes

Self Cite

View full text Add to dashboard Cite

show abstract

“…Then AutoOmics linked all the three models and again generated an optimal model for data integration as an ENAS-based three-FC-layer network with 512, 64 and 16 neurons (Figure 5A), with an improved top-1 accuracy as 0.907 (Luminal A: 0.939, Luminal B: 0.778, HER2-enriched: 0.889, Basal-like: 1), significantly better than each of the single-omics model (Figure 5B and 5C). It outperformed a published approach using SMO-MKL, which achieved a 0.798 average accuracy of any two immunohistochemistry-marker-based subtypes 28 . When direct concatenating three omics data together, the top-1 accuracy is 0.773, better than that of gene mutation and worse than gene expression and protein expression (Figure 5B).…”

Section: Resultsmentioning

confidence: 93%

AutoGenome V2: New Multimodal Approach Developed for Multi-Omics Research

Liu

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

Deep learning is very promising in solving problems in omics research, such as genomics, epigenomics, proteomics, and metabolics. The design of neural network architecture is very important in modeling omics data against different scientific problems. Residual fully-connected neural network (RFCN) was proposed to provide better neural network architectures for modeling omics data. The next challenge for omics research is how to integrate informations from different omics data using deep learning, so that information from different molecular system levels could be combined to predict the target. In this paper, we present a novel multimodal approach that could efficiently integrate information from different omics data and achieve better accuracy than previous approaches. We evaluate our method in four different tasks: drug repositioning, target gene prediction, breast cancer subtyping and cancer type prediction, and all the four tasks achieved state of art performances.The multimodal approach is implemented in a software package called AutoOmics to facilitate researchers to use.

show abstract

“…However, SVM is not suitable for analyzing multiple data sources using a single kernel function. We can use Multiple Kernel Learning (MKL) method to combine kernels calculated on different input data modality to obtain better predictive performance [29,30].…”

Section: Subtype Prediction Of New Asd Patientsmentioning

confidence: 99%

Design Of ASD Subtyping Approach based on Multi-Omics Data to Promote Personalized Healthcare

Chen¹,

Lu²,

Lu³

2020

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Autism spectrum disorder (ASD) is a heterogeneous neurodevelopmental disorder that has been confirmed to be related to some genetics risk factors which can lead to different clinical phenotypes. At present, ASD is mainly diagnosed based on some behavior and cognitive scales, which can not reveal the mechanism of disease occurrence, development and prognosis. In recent years, some studies have applied omics techniques into ASD research, but these studies are only based on single omics data source such as genomics, proteomics or transcriptomic without investigating ASD subtypes from integration of multiomics data. In this study, we proposed an ASD subtyping framework that integrates clinical and multiomics data to identify and analyze ASD subtypes at the molecular level. Due to the heterogeneity of different data modalities, a fusion clustering strategy was used to produce more accurate and interpretable clusters. Based on ASD subtyping results, we also proposed a classification framework to predict the subtype of new ASD patients. Deep learning method was used to extract features from each data modality, then all extracted features were integrated by the multiple kernel learning method to improve the classification accuracy.

show abstract

Classifying Breast Cancer Subtypes Using Multiple Kernel Learning Based on Omics Data

Cited by 40 publications

References 43 publications

Classifying Breast Cancer Subtypes Using Deep Neural Networks Based on Multi-Omics Data

Classifying Breast Cancer Subtypes Using Deep Neural Networks Based on Multi-Omics Data

AutoGenome V2: New Multimodal Approach Developed for Multi-Omics Research

Design Of ASD Subtyping Approach based on Multi-Omics Data to Promote Personalized Healthcare

Contact Info

Product

Resources

About