This paper describes a group-level classification of 14 patients with prefrontal cortex (pFC) lesions from 20 healthy controls using multi-layer graph convolutional networks (GCN) with features inferred from the scalp EEG recorded from the encoding phase of working memory (WM) trials. We first construct undirected and directed graphs to represent the WM encoding for each trial for each subject using distance correlation- based functional connectivity measures and differential directed information-based effective connectivity measures, respectively. Centrality measures of betweenness centrality, eigenvector centrality, and closeness centrality are inferred for each of the 64 channels from the brain connectivity. Along with the three centrality measures, each graph uses the relative band powers in the five frequency bands - delta, theta, alpha, beta, and gamma- as node features. The summarized graph representation is learned using two layers of GCN followed by mean pooling, and fully connected layers are used for classification. The final class label for a subject is decided using majority voting based on the results from all the subject's trials. The GCN-based model can correctly classify 28 of the 34 subjects (82.35% accuracy) with undirected edges represented by functional connectivity measure of distance correlation and classify all 34 subjects (100% accuracy) with directed edges characterized by effective connectivity measure of differential directed information.
more »
« less
Seizure onset zone (SOZ) identification using effective brain connectivity of epileptogenic networks
- Award ID(s):
- 1954749
- PAR ID:
- 10517825
- Publisher / Repository:
- IOP Publishing
- Date Published:
- Journal Name:
- Journal of Neural Engineering
- Volume:
- 21
- Issue:
- 3
- ISSN:
- 1741-2560
- Format(s):
- Medium: X Size: Article No. 036053
- Size(s):
- Article No. 036053
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
2D layered metal-organic frameworks (MOFs) are a new class of multifunctional materials that can provide electrical conductivity on top of the conventional structural characteristics of MOFs, offering potential applications in electronics and optics. Here, for the first time, we employ Machine Learning (ML) techniques to predict the thermodynamic stability and electronic properties of layered electrically conductive (EC) MOFs, bypassing expensive ab initio calculations for the design and discovery of new materials. Proper feature engineering is a very important factor in utilizing ML models for such purposes. Here, we show that a combination of elemental features, using generic statistical reduction methods and crystal structure information curated from the recently introduced EC-MOF database, leads to a reasonable prediction of the thermodynamic and electronic properties of EC MOFs. We utilize these features in training a diverse range of ML classifiers and regressors. Evaluating the performance of these different models, we show that an ensemble learning approach in the form of stacking ML models can lead to higher accuracy and more reliability on the predictive power of ML to be employed in future MOF research.
-
more » « less
Summary Objective Copy number variations (
CNV s) represent a significant genetic risk for several neurodevelopmental disorders including epilepsy. As knowledge increases, reanalysis of existing data is essential. Reliable estimates of the contribution ofCNV s to epilepsies from sizeable populations are not available.Methods We assembled a cohort of 1255 patients with preexisting array comparative genomic hybridization or single nucleotide polymorphism array based
CNV data. All patients had “epilepsy plus,” defined as epilepsy with comorbid features, including intellectual disability, psychiatric symptoms, and other neurological and nonneurological features.CNV classification was conducted using a systematic filtering workflow adapted to epilepsy.Results Of 1097 patients remaining after genetic data quality control, 120 individuals (10.9%) carried at least one autosomal
CNV classified as pathogenic; 19 individuals (1.7%) carried at least one autosomalCNV classified as possibly pathogenic. Eleven patients (1%) carried more than one (possibly) pathogenicCNV . We identifiedCNV s covering recently reported (HNRNPU )RORB CNV carriers to those of noncarriers of pathogenicCNV s, we show that patients with nonneurological comorbidities, especially dysmorphism, were more likely to carry pathogenicCNV s (odds ratio = 4.09, confidence interval = 2.51‐6.68;P = 2.34 × 10−9). Meta‐analysis including data from published control groups showed that the presence or absence of epilepsy did not affect the detected frequency ofCNV s.Significance The use of a specifically adapted workflow enabled identification of pathogenic autosomal
CNV s in 10.9% of patients with epilepsy plus, which rose to 12.7% when we also considered possibly pathogenicCNV s. Our data indicate that epilepsy with comorbid features should be considered an indication for patients to be selected for a diagnostic algorithm includingCNV detection. Collaborative large‐scaleCNV reanalysis leads to novel declaration of pathogenicity in unexplained cases and can promote discovery of promising candidate epilepsy genes. -
null (Ed.)Abstract The use of graph theory models is widespread in biological pathway analyses as it is often desired to evaluate the position of genes and proteins in their interaction networks of the biological systems. In this article, we argue that the common standard graph centrality measures do not sufficiently capture the informative topological organizations of the pathways, and thus, limit the biological inference. While key pathway elements may appear both upstream and downstream in pathways, standard directed graph centralities attribute significant topological importance to the upstream elements and evaluate the downstream elements as having no importance.We present a directed graph framework, Source/Sink Centrality (SSC), to address the limitations of standard models. SSC separately measures the importance of a node in the upstream and the downstream of a pathway, as a sender and a receiver of biological signals, and combines the two terms for evaluating the centrality. To validate SSC, we evaluate the topological position of known human cancer genes and mouse lethal genes in their respective KEGG annotated pathways and show that SSC-derived centralities provide an effective framework for associating higher positional importance to the genes with higher importance from a priori knowledge. While the presented work challenges some of the modeling assumptions in the common pathway analyses, it provides a straight-forward methodology to extend the existing models. The SSC extensions can result in more informative topological description of pathways, and thus, more informative biological inference.more » « less
