A Context-Aware Graph Transformer Framework for microRNA–Gene Regulatory Inference Across Bulk Tumor and Single-Cell Cancer Data
Jane Ohia, Juan Cui · 2026
Read A Context-Aware Graph Transformer Framework for microRNA–Gene Regulatory Inference Across Bulk Tumor and Single-Cell Cancer Data by Jane Ohia, Juan Cui (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13512291.txt.
Description
Jane Ohia and Juan Cui present a graph-based learning system, named miR-CellMap, that infers how tiny RNA regulators control genes across tumor bulk data and single-cell cancer data, in 2026 work. Most older tools predict targets from sequence alone or from bulk averages, missing how regulation rewires in different cell states. The system builds a mixed graph of microRNAs, genes, and contexts, where a context is one cell or one tumor profile.
Transformer learning on the graph produced regulatory fingerprints, a Bayesian step pruned candidate links, and a scoring layer picked out master regulators plus cooperating target groups. Run on matched single-cell data from a leukemia line and on bulk sets spanning several cancers, the system found repeated and dataset-specific programs, naming regulators from the let-7 family and others. The authors say context-aware maps can expose control switches that bulk tools blur.
Catalog record
| CREATOR | Jane Ohia, Juan Cui |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60628 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |