# SiCmiR Atlas: Single‐Cell miRNA Landscape Reveals Hub‐miRNA and Network Signatures in Human Cancers

## TL;DR

SiCmiR uses a neural network to predict miRNA activity at single-cell resolution, enabling new insights into cancer biology and biomarker discovery.

## Contribution

Introduces SiCmiR, a novel two-layer neural network for predicting miRNA expression from 977 landmark genes, and the SiCmiR Atlas database for single-cell miRNA analysis.

## Key findings

- SiCmiR accurately predicts miRNA expression from 977 landmark genes, overcoming dropout issues in single-cell RNA-seq data.
- The SiCmiR Atlas is the first database of single-cell mature miRNA expression, containing 9.36 million cells and 726 cell types.
- The method identifies hub-miRNAs and miRNA–target networks in various cancers, aiding biomarker discovery and regulatory analysis.

## Abstract

MicroRNAs (miRNAs) are pivotal post‑transcriptional regulators whose single‑cell behavior has remained largely inaccessible due to technical barriers in single‐cell small‑RNA profiling. We present SiCmiR, a two‑layer neural network that predicts miRNA expression profiles from only 977 LINCS L1000 landmark genes, thereby reducing sensitivity to dropout in single‐cell RNA‐seq (scRNA‐seq) data. Proof‑of‑concept analyses illustrate how SiCmiR can uncover candidate hub‑miRNAs in bulk‐seq cell lines and hepatocellular carcinoma, scRNA‐seq pancreatic ductal carcinoma, and ACTH‑secreting pituitary adenoma and extracellular vesicle (EV)‑mediated crosstalk in glioblastoma. Trained on 6,462 TCGA paired miRNA–mRNA samples, SiCmiR attains state‑of‑the‑art accuracy on cancers and generalizes to unseen cancer types and drug perturbations. We next construct SiCmiR‑Atlas, containing 362 public datasets, 9.36 million cells, and 726 cell types, which is the first dedicated database of single‑cell mature miRNA expression, providing interactive visualization, biomarker identification, and cell‑type‑resolved miRNA–target networks. SiCmiR transforms bulk‑derived statistical power into a single‑cell view of miRNA biology and provides a community resource for biomarker discovery. SiCmiR Atlas is available at https://awi.cuhk.edu.cn/∼SiCmiR/.

SiCmiR predicts mature miRNA activity at single‐cell resolution using only 977 landmark genes, enabling scalable reconstruction of miRNA landscapes across diverse tissues and disease contexts. The SiCmiR Atlas integrates 9.36 million cells with analytical tools for hub‐miRNA discovery, biomarker prioritization, and regulatory network interrogation, supporting both mechanistic insights and translational applications.