Optimal transport-based machine learning to match specific expression patterns in omics data - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Optimal transport-based machine learning to match specific expression patterns in omics data

(1) , (1) , (1, 2) , (3) , (1)
1
2
3

Abstract

We present two 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 (miRNA) regulation in the striatum of Huntington's disease (HD) model mice. The two data sets contain miRNA and messenger-RNA (mRNA) data, respectively, each data point consisting in a multi-dimensional profile. The biological hypothesis is that if a miRNA induces the degradation of a target mRNA or blocks its translation into proteins, or both, then the profile of the former should be similar to minus the profile of the latter (a particular form of affine relationship). The algorithms unfold in two stages. During the first stage, an optimal transport plan P and an optimal affine transformation are learned, using the Sinkhorn-Knopp algorithm and a mini-batch gradient descent. During the second stage, P is exploited to derive either several co-clusters or several sets of matched elements. We share codes that implement our algorithms. A simulation study illustrates how they work and perform. A brief summary of the real data application in the motivating case-study further illustrates the applicability and interest of the algorithms.
Fichier principal
Vignette du fichier
otml_matching_expression_data_v1.pdf (760.38 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03293786 , version 1 (21-07-2021)
hal-03293786 , version 2 (10-01-2022)

Identifiers

Cite

Thi Thanh Yen Nguyen, Olivier Bouaziz, Warith Harchaoui, Christian Neri, Antoine Chambaz. Optimal transport-based machine learning to match specific expression patterns in omics data. 2022. ⟨hal-03293786v2⟩
210 View
100 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More