Obtaining leaner deep neural networks for decoding brain functional connectome in a single shot

Gupta, Sukrit; Chan, Yi Hao; Rajapakse, Jagath C.

doi:10.1016/j.neucom.2020.04.152

Cited by 13 publications

(27 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One possible area of future work is to perform decoding. Given a trained neural network model, it has been demonstrated that saliency scores can be computed to identify important features that contributed most to the model's decision (Gupta et al, 2021 ). While such an approach cannot be simply applied to JOIN-GCLA due to the attention layer, novel methods could be developed to weigh the saliency scores by the attention scores for each view.…”

Section: Discussionmentioning

confidence: 99%

Combining Neuroimaging and Omics Datasets for Disease Classification Using Graph Neural Networks

et al. 2022

Self Cite

View full text Add to dashboard Cite

Both neuroimaging and genomics datasets are often gathered for the detection of neurodegenerative diseases. Huge dimensionalities of neuroimaging data as well as omics data pose tremendous challenge for methods integrating multiple modalities. There are few existing solutions that can combine both multi-modal imaging and multi-omics datasets to derive neurological insights. We propose a deep neural network architecture that combines both structural and functional connectome data with multi-omics data for disease classification. A graph convolution layer is used to model functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI) data simultaneously to learn compact representations of the connectome. A separate set of graph convolution layers are then used to model multi-omics datasets, expressed in the form of population graphs, and combine them with latent representations of the connectome. An attention mechanism is used to fuse these outputs and provide insights on which omics data contributed most to the model's classification decision. We demonstrate our methods for Parkinson's disease (PD) classification by using datasets from the Parkinson's Progression Markers Initiative (PPMI). PD has been shown to be associated with changes in the human connectome and it is also known to be influenced by genetic factors. We combine DTI and fMRI data with multi-omics data from RNA Expression, Single Nucleotide Polymorphism (SNP), DNA Methylation and non-coding RNA experiments. A Matthew Correlation Coefficient of greater than 0.8 over many combinations of multi-modal imaging data and multi-omics data was achieved with our proposed architecture. To address the paucity of paired multi-modal imaging data and the problem of imbalanced data in the PPMI dataset, we compared the use of oversampling against using CycleGAN on structural and functional connectomes to generate missing imaging modalities. Furthermore, we performed ablation studies that offer insights into the importance of each imaging and omics modality for the prediction of PD. Analysis of the generated attention matrices revealed that DNA Methylation and SNP data were the most important omics modalities out of all the omics datasets considered. Our work motivates further research into imaging genetics and the creation of more multi-modal imaging and multi-omics datasets to study PD and other complex neurodegenerative diseases.

show abstract

Section: Discussionmentioning

confidence: 99%

Combining Neuroimaging and Omics Datasets for Disease Classification Using Graph Neural Networks

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, several studies have revealed that removing insignificant input features gives rise to performance enhancement 41 . Thus, after computing the attributions of each input features, we recursively removed the features one at a time depending on their attribution ranks, and tracked how the performance changes.…”

Section: Methodsmentioning

confidence: 99%

Network-based integration of multi-omics data for clinical outcome prediction in neuroblastoma

Wang

Lue

Kaalia

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Multi-omics data are increasingly being gathered for investigations of complex diseases such as cancer. However, high dimensionality, small sample size, and heterogeneity of different omics types pose huge challenges to integrated analysis. In this paper, we evaluate two network-based approaches for integration of multi-omics data in an application of clinical outcome prediction of neuroblastoma. We derive Patient Similarity Networks (PSN) as the first step for individual omics data by computing distances among patients from omics features. The fusion of different omics can be investigated in two ways: the network-level fusion is achieved using Similarity Network Fusion algorithm for fusing the PSNs derived for individual omics types; and the feature-level fusion is achieved by fusing the network features obtained from individual PSNs. We demonstrate our methods on two high-risk neuroblastoma datasets from SEQC project and TARGET project. We propose Deep Neural Network and Machine Learning methods with Recursive Feature Elimination as the predictor of survival status of neuroblastoma patients. Our results indicate that network-level fusion outperformed feature-level fusion for integration of different omics data whereas feature-level fusion is more suitable incorporating different feature types derived from same omics type. We conclude that the network-based methods are capable of handling heterogeneity and high dimensionality well in the integration of multi-omics.

show abstract

“…Wrapper methods have the highest computational cost and filter methods have the lowest one. From the analysis of the most recent literature, a new approach for feature selection has been proposed by Gupta et al [48].…”

Section: Feature Selectionmentioning

confidence: 99%

A Machine Learning Decision Support System (DSS) for Neuroendocrine Tumor Patients Treated with Somatostatin Analog (SSA) Therapy

et al. 2021

View full text Add to dashboard Cite

The application of machine learning (ML) techniques could facilitate the identification of predictive biomarkers of somatostatin analog (SSA) efficacy in patients with neuroendocrine tumors (NETs). We collected data from 74 patients with a pancreatic or gastrointestinal NET who received SSA as first-line therapy. We developed three classification models to predict whether the patient would experience a progressive disease (PD) after 12 or 18 months based on clinic-pathological factors at the baseline. The dataset included 70 samples and 15 features. We initially developed three classification models with accuracy ranging from 55% to 70%. We then compared ten different ML algorithms. In all but one case, the performance of the Multinomial Naïve Bayes algorithm (80%) was the highest. The support vector machine classifier (SVC) had a higher performance for the recall metric of the progression-free outcome (97% vs. 94%). Overall, for the first time, we documented that the factors that mainly influenced progression-free survival (PFS) included age, the number of metastatic sites and the primary site. In addition, the following factors were also isolated as important: adverse events G3–G4, sex, Ki67, metastatic site (liver), functioning NET, the primary site and the stage. In patients with advanced NETs, ML provides a predictive model that could potentially be used to differentiate prognostic groups and to identify patients for whom SSA therapy as a single agent may not be sufficient to achieve a long-lasting PFS.

show abstract

Obtaining leaner deep neural networks for decoding brain functional connectome in a single shot

Cited by 13 publications

References 51 publications

Combining Neuroimaging and Omics Datasets for Disease Classification Using Graph Neural Networks

Combining Neuroimaging and Omics Datasets for Disease Classification Using Graph Neural Networks

Network-based integration of multi-omics data for clinical outcome prediction in neuroblastoma

A Machine Learning Decision Support System (DSS) for Neuroendocrine Tumor Patients Treated with Somatostatin Analog (SSA) Therapy

Contact Info

Product

Resources

About