Deep-learning approach to identifying cancer subtypes using high-dimensional genomic data

Chen, Runpu; Yang, Le; Goodison, Steve; Sun, Yijun

doi:10.1093/bioinformatics/btz769

Cited by 101 publications

(70 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The formulation and the architecture of the clustering network are built upon DeepType [25], which also uses representation, classification, and clustering modules. Different from DeepType, DeepCrossCancer’s clustering network contains an additional survival module.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Identifying Cross-Cancer Similar Patients via a Semi-Supervised Deep Clustering Approach

Taştan

2020

Preprint

View full text Add to dashboard Cite

The treatment decisions for a cancer patient are typically based on the patient’s diagnosed cancer type. With the characterization of cancer tumors at the molecular level, there have been reports of patients that bear molecular similarities to other patients that are diagnosed with other cancer types. Motivated from these observations, we aim at discovering cross-cancer patients, which we define as patients whose tumors are more similar to patient tumors diagnosed with another cancer type. Our framework, DeepCrossCancer, identifies a core set of cross-cancer patients that always co-cluster with the other patient from another cancer type. The input to DeepCrossCancer is the transcriptomic profiles of the patient tumors, the age, and gender of the patient. To solve the clustering problem, we propose a deep learning-based clustering method in which the clustering task is supervised by cancer type labels and the survival times of the patients. Applying the method to patient data from nine different cancers, we discover 20 cross-cancer patients. By analyzing the predictive genes of the cross-cancer patients and other genomic information available for the patient such as somatic mutations and copy number variations, we identify striking similarities across these patients validating their similarities. The detection of cross-cancer patients opens up possibilities for transferring clinical decisions across patients at a single patient level. DeepCrossCancer is available at https://github.com/Tastanlab/DeepCrossCancer.

show abstract

Section: Methodsmentioning

confidence: 99%

“…We use the cross-entropy loss to quantify the discrepancy between the correct cancer type of the patient and the predicted cancer types of the patient. As in [25], we impose an £ 1 regularization [27] on the weight matrix of the first layer to control the model complexity. The cross-entropy and sparsity losses are defined as: …”

Section: Methodsmentioning

confidence: 99%

Identifying Cross-Cancer Similar Patients via a Semi-Supervised Deep Clustering Approach

Taştan

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…AEs have been also successfully applied on gene-expression or multi-omics data to tackle more complex and biologically-relevant cancer prediction tasks, such as classifying cancer sub-types or characterizing functional gene profiles [22][23][24]. Feed-forward MLNNs have been recently utilized to predict clinical outcomes from high-dimensional genomic data [25] or to identify cancer sub-types by combining supervised and unsupervised learning [26].…”

Section: Plos Onementioning

confidence: 99%

Transfer learning with convolutional neural networks for cancer survival prediction using gene-expression data

et al. 2020

View full text Add to dashboard Cite

Precision medicine in oncology aims at obtaining data from heterogeneous sources to have a precise estimation of a given patient's state and prognosis. With the purpose of advancing to personalized medicine framework, accurate diagnoses allow prescription of more effective treatments adapted to the specificities of each individual case. In the last years, nextgeneration sequencing has impelled cancer research by providing physicians with an overwhelming amount of gene-expression data from RNA-seq high-throughput platforms. In this scenario, data mining and machine learning techniques have widely contribute to geneexpression data analysis by supplying computational models to supporting decision-making on real-world data. Nevertheless, existing public gene-expression databases are characterized by the unfavorable imbalance between the huge number of genes (in the order of tenths of thousands) and the small number of samples (in the order of a few hundreds) available. Despite diverse feature selection and extraction strategies have been traditionally applied to surpass derived over-fitting issues, the efficacy of standard machine learning pipelines is far from being satisfactory for the prediction of relevant clinical outcomes like follow-up endpoints or patient's survival. Using the public Pan-Cancer dataset, in this study we pre-train convolutional neural network architectures for survival prediction on a subset composed of thousands of gene-expression samples from thirty-one tumor types. The resulting architectures are subsequently fine-tuned to predict lung cancer progression-free interval. The application of convolutional networks to gene-expression data has many limitations, derived from the unstructured nature of these data. In this work we propose a methodology to rearrange RNA-seq data by transforming RNA-seq samples into gene-expression images, from which convolutional networks can extract high-level features. As an additional objective, we investigate whether leveraging the information extracted from other tumor-type samples contributes to the extraction of high-level features that improve lung cancer progression prediction, compared to other machine learning approaches.

show abstract

“…On these data sets, we compared ClusterATAC with four state-ofart clustering algorithms: K-means, spectral clustering (Spectral), autoencoder (AE), variational autoencoder (VAE). K-means and Spectral are the two most stable and effective clustering algorithms, while AE and VAE are two deep learning algorithms applied to omics data clustering [29][30][31]. Especially, VAE has been proven by previous work to handle high-dimensional ATAC-seq data [20].…”

Section: Evaluate the Performance Of Clusteratac On Benchmark Data Setsmentioning

confidence: 99%

Cancer classification based on chromatin accessibility profiles with deep adversarial learning model

Yang

Wei

et al. 2020

PLoS Comput Biol

View full text Add to dashboard Cite

Given the complexity and diversity of the cancer genomics profiles, it is challenging to identify distinct clusters from different cancer types. Numerous analyses have been conducted for this propose. Still, the methods they used always do not directly support the high-dimensional omics data across the whole genome (Such as ATAC-seq profiles). In this study, based on the deep adversarial learning, we present an end-to-end approach ClusterATAC to leverage high-dimensional features and explore the classification results. On the ATAC-seq dataset and RNA-seq dataset, ClusterATAC has achieved excellent performance. Since ATAC-seq data plays a crucial role in the study of the effects of non-coding regions on the molecular classification of cancers, we explore the clustering solution obtained by ClusterATAC on the pan-cancer ATAC dataset. In this solution, more than 70% of the clustering are single-tumor-type-dominant, and the vast majority of the remaining clusters are associated with similar tumor types. We explore the representative non-coding loci and their linked genes of each cluster and verify some results by the literature search. These results suggest that a large number of non-coding loci affect the development and progression of cancer through its linked genes, which can potentially advance cancer diagnosis and therapy.

show abstract

Deep-learning approach to identifying cancer subtypes using high-dimensional genomic data

Cited by 101 publications

References 38 publications

Identifying Cross-Cancer Similar Patients via a Semi-Supervised Deep Clustering Approach

Identifying Cross-Cancer Similar Patients via a Semi-Supervised Deep Clustering Approach

Transfer learning with convolutional neural networks for cancer survival prediction using gene-expression data

Cancer classification based on chromatin accessibility profiles with deep adversarial learning model

Contact Info

Product

Resources

About