Interpretable, similarity-driven multi-view embeddings from high-dimensional biomedical data
This work addresses the challenge of joint signal estimation from disparate biomedical modalities for researchers, offering a practical tool with default parameters, though it appears incremental as it builds on multi-view embedding techniques.
The authors tackled the problem of transforming high-dimensional biomedical data into interpretable low-dimensional spaces by developing SiMLR, a similarity-driven multi-view linear reconstruction algorithm, which outperformed related methods on supervised learning tasks in simulations, multi-omics cancer survival prediction, and neuroimaging datasets.
Similarity-driven multi-view linear reconstruction (SiMLR) is an algorithm that exploits inter-modality relationships to transform large scientific datasets into smaller, more well-powered and interpretable low-dimensional spaces. SiMLR contributes a novel objective function for identifying joint signal, regularization based on sparse matrices representing prior within-modality relationships and an implementation that permits application to joint reduction of large data matrices, each of which may have millions of entries. We demonstrate that SiMLR outperforms closely related methods on supervised learning problems in simulation data, a multi-omics cancer survival prediction dataset and multiple modality neuroimaging datasets. Taken together, this collection of results shows that SiMLR may be applied with default parameters to joint signal estimation from disparate modalities and may yield practically useful results in a variety of application domains.