Benchmarking joint multi-omics dimensionality reduction approaches for cancer study

Laura Cantini (1) , Pooya Zakeri , Céline Hernandez , Aurelien Naldi , Denis Thieffry , Elisabeth Remy , Anaïs Baudot

1 IBENS - Institut de biologie de l'ENS Paris

High-dimensional multi-omics data are now standard in biology. They can greatly enhance our understanding of biological systems when effectively integrated. To achieve this multi-omics data integration, Joint Dimensionality Reduction (jDR) methods are among the most efficient approaches. However, several jDR methods are available, urging the need for a comprehensive benchmark with practical guidelines.

We performed a systematic evaluation of nine representative jDR methods using three complementary benchmarks. First, we evaluated their performances in retrieving ground-truth sample clustering from simulated multi-omics datasets. Second, we used TCGA cancer data to assess their strengths in predicting survival, clinical annotations and known pathways/biological processes. Finally, we assessed their classification of multi-omics single-cell data.

From these in-depth comparisons, we observed that intNMF performs best in clustering, while MCIA offers a consistent and effective behavior across many contexts. The full code of this benchmark is implemented in a Jupyter notebook - multi-omics mix (momix) - to foster reproducibility, and support data producers, users and future developers.

High-dimensional multi-omics data are now standard in biology. They can greatly enhance our understanding of biological systems when effectively integrated. To achieve this multi-omics data integration, Joint Dimensionality Reduction (jDR) methods are among the most efficient approaches. However, several jDR methods are available, urging the need for a comprehensive benchmark with practical guidelines. We performed a systematic evaluation of nine representative jDR methods using three complementary benchmarks. First, we evaluated their performances in retrieving ground-truth sample clustering from simulated multi-omics datasets. Second, we used TCGA cancer data to assess their strengths in predicting survival, clinical annotations and known pathways/biological processes. Finally, we assessed their classification of multi-omics single-cell data. From these in-depth comparisons, we observed that intNMF performs best in clustering, while MCIA offers a consistent and effective behavior across many contexts. The full code of this benchmark is implemented in a Jupyter notebook-multi-omics mix (momix)-to foster reproducibility, and support data producers, users and future developers.

Mots clés: Matrix factorization; Dimensionality reduction; Data integration; Multi-omics; Cancer; Single-Cell

Domaines: Sciences du Vivant [q-bio]; Statistiques [stat]; Mathématiques [math]

Laura Cantini, Pooya Zakeri, Céline Hernandez, Aurelien Naldi, Denis Thieffry, et al.. Benchmarking joint multi-omics dimensionality reduction approaches for cancer study. 2020. ⟨hal-02998156⟩