An explainable graph neural network approach for integrating multi-omics data with prior knowledge to identify biomarkers from interacting biological domains DOI Creative Commons
Rohit Tripathy,

Zachary Frohock,

Hong Wang

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Авг. 26, 2024

Abstract The rapid growth of multi-omics datasets, in addition to the wealth existing biological prior knowledge, necessitates development effective methods for their integration. Such are essential building predictive models and identifying disease-related molecular markers. We propose a framework supervised integration data with priors represented as knowledge graphs. Our leverages graph neural networks (GNNs) model relationships among features from high-dimensional ‘omics set transformers integrate low-dimensional representations features. Furthermore, our incorporates explainability elucidate important biomarkers extract interaction between quantities interest. demonstrate effectiveness approach by applying it Alzheimer’s disease (AD) ROSMAP cohort, showing that transcriptomics proteomics AD domain network improves prediction accuracy status highlights functional biomarkers.

Язык: Английский

Characterization of covalent inhibitors that disrupt the interaction between the tandem SH2 domains of SYK and FCER1G phospho-ITAM DOI Creative Commons
Frances M. Bashore, V.L. Katis,

Yuhong Du

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2023, Номер unknown

Опубликована: Июль 29, 2023

RNA sequencing and genetic data support spleen tyrosine kinase (SYK) high affinity immunoglobulin epsilon receptor subunit gamma (FCER1G) as putative targets to be modulated for Alzheimer's disease (AD) therapy. FCER1G is a component of Fc complexes that contain an immunoreceptor tyrosine-based activation motif (ITAM). SYK interacts with the by binding doubly phosphorylated ITAM (p-ITAM) via its two tandem SH2 domains (SYK-tSH2). Interaction p-ITAM SYK-tSH2 enables phosphorylation. Since reported exacerbate AD pathology, we hypothesized disruption this interaction would beneficial patients. Herein, developed biochemical biophysical assays enable discovery small molecules perturb between SYK-tSH2. We identified distinct chemotypes using high-throughput screen (HTS) orthogonally assessed their binding. Both covalently modify inhibit p-ITAM.

Язык: Английский

Процитировано

3
An explainable graph neural network approach for integrating multi-omics data with prior knowledge to identify biomarkers from interacting biological domains DOI Creative Commons
Rohit Tripathy,

Zachary Frohock,

Hong Wang

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Авг. 26, 2024

Abstract The rapid growth of multi-omics datasets, in addition to the wealth existing biological prior knowledge, necessitates development effective methods for their integration. Such are essential building predictive models and identifying disease-related molecular markers. We propose a framework supervised integration data with priors represented as knowledge graphs. Our leverages graph neural networks (GNNs) model relationships among features from high-dimensional ‘omics set transformers integrate low-dimensional representations features. Furthermore, our incorporates explainability elucidate important biomarkers extract interaction between quantities interest. demonstrate effectiveness approach by applying it Alzheimer’s disease (AD) ROSMAP cohort, showing that transcriptomics proteomics AD domain network improves prediction accuracy status highlights functional biomarkers.

Язык: Английский

Процитировано

0