Dynamic regulatory module networks for inference of cell type specific transcriptional networks
Fotuhi Siahpirani, A.; Chasman, D.; Seirup, M.; Knaack, S.; Sridharan, R.; Stewart, R.; Thomson, J.; Roy, S.
Show abstract
Multi-omic datasets with parallel transcriptomic and epigenomic measurements across time or cell types are becoming increasingly common. However, integrating these data to infer regulatory network dynamics is a major challenge. We present Dynamic Regulatory Module Networks (DRMNs), a novel approach that uses multi-task learning to infer cell type-specific cis-regulatory networks dynamics. Compared to existing approaches, DRMN integrates expression, chromatin state and accessibility, accurately predicts cis-regulators of context-specific expression and models network dynamics across linearly and hierarchically related contexts. We apply DRMN to three dynamic processes of different experimental designs and predict known and novel regulators driving cell type-specific expression patterns.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Scalable identification of lineage-specific gene regulatory networks from metacells with NetID 97%
- Simultaneous smoothing and detection of topological units of genome organization from sparse chromatin contact count matrices with matrix factorization 96%
- Integrating temporal single-cell gene expression modalities for trajectory inference and disease prediction 96%
Similar papers in this journal
Similar papers in this journal
- An efficient not-only-linear correlation coefficient based on machine learning 95%
- Belayer: Modeling discrete and continuous spatial variation in gene expression from spatially resolved transcriptomics 94%
- Automated assignment of cell identity from single-cell multiplexed imaging and proteomic data 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.