# OTMODE: an optimal transport theory-based framework for identifying differential features in single-cell multi-omics data

## TL;DR

OTMODE is a new method that improves the identification of important features in complex single-cell multi-omics data using optimal transport theory.

## Contribution

OTMODE introduces a non-parametric framework using unbalanced Sinkhorn algorithm and Wald test for differential feature identification.

## Key findings

- OTMODE achieved an average 90% F1 score and 92% AUC score in simulations.
- It outperforms existing methods in detecting meaningful biological processes.
- OTMODE can identify potentially misannotated clusters from auto-annotation tools.

## Abstract

Single-cell technologies enable high-resolution cellular studies but face challenges in identifying differential features due to data complexity.

We present OTMODE, a non-parametric method using unbalanced Sinkhorn algorithm and Wald test to improve differential feature identification in single-cell multi-omics data. Under simulation, OTMODE achieved superior performance (average 90% F1 score; average 92% AUC score) with high efficiency (2.2 s for 5000 cells). In practice, it shows greater sensitivity than other state-of-the-art methods in detecting meaningful processes and can evaluate annotation accuracy by identifying potentially misannotated clusters from auto-annotation tools. Furthermore, OTMODE integrates seamlessly with Scanpy, offering a user-friendly solution for researchers.

OTMODE is freely available at https://github.com/Eggong/OTMODE and also available at https://pypi.org/project/OTMODE/.