Prognostically Relevant Subtypes and Survival Prediction for Breast Cancer Based on Multimodal Genomics Data

Karim, Rezaul; Wicaksono, Galih Wasis; Costa, Ivan G.; Decker, Stefan; Beyan, Oya

doi:10.1109/access.2019.2941796

Cited by 21 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, we intend to extend this work by (i) alleviating more samples by combining genomics data from different sources and training a multimodal architecture, (ii) comparing studies on clustering based on feature extracted by DNN vs. PCA and (iii) improving the explanations about the predictions using both ante-hoc and post-hoc approaches. In particular, we plan to employ multimodality [ 55 ], since multiple factors are involved in disease diagnosis (e.g. estrogen, progesterone and epidermal growth receptors in breast cancer), AI-based diagnoses might not be trustworthy solely based on a single modality, which demands the requirements of multimodal features (e.g.…”

Section: Discussionmentioning

confidence: 99%

Deep learning-based clustering approaches for bioinformatics

Karim

Beyan

Zappa

et al. 2020

Briefings in Bioinformatics

Self Cite

204

162

View full text Add to dashboard Cite

Clustering is central to many data-driven bioinformatics research and serves a powerful computational method. In particular, clustering helps at analyzing unstructured and high-dimensional data in the form of sequences, expressions, texts and images. Further, clustering is used to gain insights into biological processes in the genomics level, e.g. clustering of gene expressions provides insights on the natural structure inherent in the data, understanding gene functions, cellular processes, subtypes of cells and understanding gene regulations. Subsequently, clustering approaches, including hierarchical, centroid-based, distribution-based, density-based and self-organizing maps, have long been studied and used in classical machine learning settings. In contrast, deep learning (DL)-based representation and feature learning for clustering have not been reviewed and employed extensively. Since the quality of clustering is not only dependent on the distribution of data points but also on the learned representation, deep neural networks can be effective means to transform mappings from a high-dimensional data space into a lower-dimensional feature space, leading to improved clustering results. In this paper, we review state-of-the-art DL-based approaches for cluster analysis that are based on representation learning, which we hope to be useful, particularly for bioinformatics research. Further, we explore in detail the training procedures of DL-based clustering algorithms, point out different clustering quality metrics and evaluate several DL-based approaches on three bioinformatics use cases, including bioimaging, cancer genomics and biomedical text mining. We believe this review and the evaluation results will provide valuable insights and serve a starting point for researchers wanting to apply DL-based unsupervised methods to solve emerging bioinformatics research problems.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning-based clustering approaches for bioinformatics

Karim

Beyan

Zappa

et al. 2020

Briefings in Bioinformatics

Self Cite

204

162

View full text Add to dashboard Cite

show abstract

“…In the review of studies using incidence prediction for related risk factors, Artificial Intelligence (AI), or algorithms related to machine learning were used. The method of cancer gene mapping analysis was described in [16], where multimodal autoencoder (MAE) classifiers constructed using various risk factor data in breast cancer diagnosis were used to predict the survival rates of breast cancer prognosis. Abdikenov et al [17] proposed a Pareto optimality-based prognostic model to understanding changes in hyper-parameters in various performance metrics, and [18] presented a wrapper method that embeds Bayesian classifiers for hybrid feature selection of breast cancer datasets.…”

Section: Introductionmentioning

confidence: 99%

Breast Cancer–Detection System Using PCA, Multilayer Perceptron, Transfer Learning, and Support Vector Machine

Chiu

Kuo

2020

IEEE Access

View full text Add to dashboard Cite

“…Since GVs data are high-dimensional, learning the association between each feature was fairly considered. Inspired by literature [20], [21], [52] and to qualitatively study whether the learned representation can express the biological characteristics of the individuals, t-SNE of the CAE encoder's output, i.e., latent FM and raw GVs are plotted in Fig. 6.…”

Section: Qualitative Study Of the Learned Representationsmentioning

confidence: 99%

“…In contrast, approaches based on neural networks (DNNs) can be more effective at RL and feature extraction [18]. In particular, DNN architectures (e.g., autoencoder (AE)) with multiple hidden layers and non-linear activation functions, can capture more complex and higher-level features and contextual information from the input [19], [20], [21], [22]. Further, non-linear mappings allows transforming input data into more clusteringfriendly representations in which the data is mapped into a lower-dimensional feature space that helps fine-tune clustering [23].…”

Section: Introductionmentioning

confidence: 99%

Convolutional Embedded Networks for Population Scale Clustering and Bio-Ancestry Inferencing

Karim

Cochez

Zappa

et al. 2022

IEEE/ACM Trans. Comput. Biol. and Bioinf.

Self Cite

View full text Add to dashboard Cite

The study of genetic variants (GVs) can help find correlating population groups and to identify cohorts that are predisposed to common diseases and explain differences in disease susceptibility and how patients react to drugs. Machine learning techniques are increasingly being applied to identify interacting GVs to understand their complex phenotypic traits. Since the performance of a learning algorithm not only depends on the size and nature of the data but also on the quality of underlying representation, deep neural networks (DNNs) can learn non-linear mappings that allow transforming GVs data into more clustering and classification friendly representations than manual feature selection. In this paper, we propose convolutional embedded networks (CEN) in which we combine two DNN architectures called convolutional embedded clustering (CEC) and convolutional autoencoder (CAE) classifier for clustering individuals and predicting geographic ethnicity based on GVs, respectively. We employed CAE-based representation learning to 95 million GVs from the '1000 genomes' (covering 2,504 individuals from 26 ethnic origins) and 'Simons genome diversity' (covering 279 individuals from 130 ethnic origins) projects. Quantitative and qualitative analyses with a focus on accuracy and scalability show that our approach outperforms state-of-the-art approaches such as VariantSpark and ADMIXTURE. In particular, CEC can cluster targeted population groups in 22 hours with an adjusted rand index (ARI) of 0.915, the normalized mutual information (NMI) of 0.92, and the clustering accuracy (ACC) of 89 percent. Contrarily, the CAE classifier can predict the geographic ethnicity of unknown samples with an F1 and Mathews correlation coefficient (MCC) score of 0.9004 and 0.8245, respectively. Further, to provide interpretations of the predictions, we identify significant biomarkers using gradient boosted trees (GBT) and SHapley Additive exPlanations (SHAP). Overall, our approach is transparent and faster than the baseline methods, and scalable for 5 to 100 percent of the full human genome.

show abstract

Prognostically Relevant Subtypes and Survival Prediction for Breast Cancer Based on Multimodal Genomics Data

Cited by 21 publications

References 25 publications

Deep learning-based clustering approaches for bioinformatics

Deep learning-based clustering approaches for bioinformatics

Breast Cancer–Detection System Using PCA, Multilayer Perceptron, Transfer Learning, and Support Vector Machine

Convolutional Embedded Networks for Population Scale Clustering and Bio-Ancestry Inferencing

Contact Info

Product

Resources

About