Optimal transport-based machine learning to match specific patterns: application to the detection of molecular regulation patterns in omics data

2021/07/21 by Nguyen, Thi Thanh Yen, Harchaoui, Warith, Mégret, Lucile +4
#FOS: Biological sciences #FOS: Mathematics #Genomics (q-bio.GN) #Statistics Theory (math.ST)

paper · doi:10.48550/arxiv.2107.11192

Abstract

We present several algorithms designed to learn a pattern of correspondence between two data sets in situations where it is desirable to match elements that exhibit a relationship belonging to a known parametric model. In the motivating case study, the challenge is to better understand micro-RNA regulation in the striatum of Huntington's disease model mice. The algorithms unfold in two stages. First, an optimal transport plan P and an optimal affine transformation are learned, using the Sinkhorn-Knopp algorithm and a mini-batch gradient descent. Second, P is exploited to derive either several co-clusters or several sets of matched elements. A simulation study illustrates how the algorithms work and perform. The real data application further illustrates their applicability and interest.

Related

• A Trainable Optimal Transport Embedding for Feature Aggregation and its Relationship to Attention
• Integrating Optimal Transport and Structural Inference Models for GRN Inference from Single-cell Data
• Discovering Patterns in Biological Sequences by Optimal Segmentation
• Low-rank Optimal Transport: Approximation, Statistics and Debiasing
• Transcription Factor-DNA Binding Via Machine Learning Ensembles