Convolutional neural network approach to lung cancer classification integrating protein interaction network and gene expression profiles

Matsubara, Teppei; Ochiai, Tomoshiro; Hayashida, Morihiro; Akutsu, Tatsuya; Nacher, Jose C.

doi:10.1142/s0219720019400079

Cited by 26 publications

(15 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…While works of Matsubara et al ., Aliper et al ., and Antonio et al . rely on deep learning, the authors focus on data other than RNA sequencing and the architecture of their network differs considerably [ 41 , 42 , 43 ]. In the current study, we show high performance of imPlatelet method applied to cancer sample classification.…”

Section: Discussionmentioning

confidence: 99%

imPlatelet classifier: image‐converted RNA biomarker profiles enable blood‐based cancer diagnostics

et al. 2021

View full text Add to dashboard Cite

Liquid biopsies offer a minimally invasive sample collection, outperforming traditional biopsies employed for cancer evaluation. The widely used material is blood, which is the source of tumoreducated platelets. Here, we developed the imPlatelet classifier, which converts RNA-sequenced platelet data into images in which each pixel corresponds to the expression level of a certain gene.Biological knowledge from the Kyoto Encyclopedia of Genes and Genomes was also implemented to improve accuracy. Images obtained from samples can then be compared against standard images for specific cancers to determine a diagnosis. We tested imPlatelet on a cohort of 401 non-small cell lung cancer patients, 62 sarcoma patients and 28 ovarian cancer patients. imPlatelet provided excellent discrimination between lung cancer cases and healthy controls, with accuracy equal to 1 in the independent dataset. When discriminating between non-cancer cases and sarcoma or ovarian cancer patients, accuracy equaled 0.91 or 0.95, respectively, in the independent datasets. According to our knowledge, this is the first study implementing an imagebased deep-learning approach combined with biological knowledge to classify human samples.The performance of imPlatelet considerably exceeds previously published methods and our own alternative attempts of sample discrimination. We show that the deep-learning image-based classifier accurately identifies cancer, even when a limited number of samples is available.

show abstract

Section: Discussionmentioning

confidence: 99%

imPlatelet classifier: image‐converted RNA biomarker profiles enable blood‐based cancer diagnostics

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Additionally, the ensemble model is difficult to interpret. Matsubara et al [35], used CNN (combining spectral clustering information processing) to classify lung cancer using both protein interaction network data and gene expression data from 639 samples (152 benign and 487 malignant).…”

Section: ) Classical Machine Learning and Feature Selection Methodsmentioning

confidence: 99%

A Survey of Machine Learning Approaches Applied to Gene Expression Analysis for Cancer Prediction

et al. 2022

View full text Add to dashboard Cite

Machine learning approaches are powerful techniques commonly employed for developing cancer prediction models using associated gene expression and mutation data. Our survey provides a comprehensive review of recent cancer studies that have employed gene expression data from several cancer types (breast, lung, kidney, ovarian, liver, central nervous system and gallbladder) for survival prediction,tumor identification and stratification. We also provide an overview of biomarker studies that are associated with these cancer types. The survey captures multiple aspects of machine learning associated cancer studies,including cancer classification, cancer prediction, identification of biomarker genes, microarray, and RNA-Seq data. We discuss the technical issues with current cancer prediction models and the corresponding measurement tools for determining the activity levels of gene expression between cancerous tissues and noncancerous tissues. Additionally, we investigate how identifying putative biomarker gene expression patterns can aid in predicting future risk of cancer and inform the provision of personalized treatment.

show abstract

“…classified. It is interesting to note that the previous algorithms have already selected the gene (feature), however, they have skipped analysing the minimum number of effective genes [20][21][22][23][24][25][26][27][28][29][30][31][32][33][34]. In the proposed method, using the cross-validation method, and K-fold with variable K values adopted as 5, 10, 15 and 20, criteria were estimated.…”

Section: Conflict Of Interestmentioning

confidence: 99%

Deep learning‐based microarray cancer classification and ensemble gene selection approach

Rezaee

Jeon

Khosravi

et al. 2022

IET Systems Biology

View full text Add to dashboard Cite

Malignancies and diseases of various genetic origins can be diagnosed and classified with microarray data. There are many obstacles to overcome due to the large size of the gene and the small number of samples in the microarray. A combination strategy for gene expression in a variety of diseases is described in this paper, consisting of two steps: identifying the most effective genes via soft ensembling and classifying them with a novel deep neural network. The feature selection approach combines three strategies to select wrapper genes and rank them according to the k-nearest neighbour algorithm, resulting in a very generalisable model with low error levels. Using soft ensembling, the most effective subsets of genes were identified from three microarray datasets of diffuse large cell lymphoma, leukaemia, and prostate cancer. A stacked deep neural network was used to classify all three datasets, achieving an average accuracy of 97.51%, 99.6%, and 96.34%, respectively. In addition, two previously unreported datasets from small, round blue cell tumors (SRBCTs)and multiple sclerosis-related brain tissue lesions were examined to show the generalisability of the model method.

show abstract

Convolutional neural network approach to lung cancer classification integrating protein interaction network and gene expression profiles

Cited by 26 publications

References 17 publications

imPlatelet classifier: image‐converted RNA biomarker profiles enable blood‐based cancer diagnostics

imPlatelet classifier: image‐converted RNA biomarker profiles enable blood‐based cancer diagnostics

A Survey of Machine Learning Approaches Applied to Gene Expression Analysis for Cancer Prediction

Deep learning‐based microarray cancer classification and ensemble gene selection approach

Contact Info

Product

Resources

About