Benchmarking joint multi-omics dimensionality reduction approaches for cancer study

Abstract

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 singlecell 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.

Integrative Network Fusion: A Multi-Omics Approach in Molecular Profiling

“…Indeed, the underlying hypothesis of multi-omics integration is that different omics data can provide complementary information ( 56 ) [although sometimes redundant ( 9 )], and thus a broader insight with respect to single-layer analysis, for a better understanding of disease mechanisms ( 59 ). This assumption has been confirmed by multiple studies on diverse diseases, such as cardiovascular disease ( 60 ), diabetes ( 61 ), liver disease ( 62 ), or mitochondrial diseases ( 63 ), and also longitudinally ( 64 ), suggesting that the more complex the disease the more advantageous the integration.…”

“…In the early-integration approach, also known as juxtaposition-based, the multi-omics datasets are first concatenated into one matrix. To deal with the high-dimensionality of the joint dataset, these methods generally adopt matrix factorization ( 55 , 56 , 58 , 71 ), statistical ( 47 , 49 , 58 , 60 , 62 , 72 – 76 ), and machine learning tools ( 58 , 76 , 77 ). Alternatively, data models relying on polyglot approaches can be used especially in (bio)informatics applications ( 78 , 79 ).…”

“…The lack of common methodologies and terminologies can transform this synergy into a further level of complexity in the process of data integration (54). As observed in (55,56), specific technological limits, noise levels and variability ranges affect the different omics, and thus confounding the underlying biological signals, yielding that really integrative analysis is still very rare, while different methods often discover different kinds of patterns, as evidenced by the lack of consistency in the published results, although efforts in this direction have started appearing (57,58).…”

Integrative Network Fusion: a multi-omics approach in molecular profiling

“…The lack of common methodologies and terminologies can transform this synergy into a further level of complexity in the process of data integration (51). As observed in (52,53), specific technological limits, noise levels and variability ranges affect the different omics, and thus confounding the underlying biological signals, yielding that really integrative analysis is still very rare, while different methods often discover different kinds of patterns, as evidenced by the lack of consistency in the published results, although efforts in this direction have started appearing (54,55).…”

“…In the early-integration approach, also known as juxtaposition-based, the multi-omics datasets are first concatenated into one matrix. To deal with the high-dimensionality of the joint dataset, these methods generally adopt matrix factorization (68,53,55,52), statistical (46,69,70,59,57,44,71,72,73,55), and machine learning tools (74,73,55). Although the dimensionality reduction procedure is necessary and may improve the predictive performance, it can also cause the loss of key information (66).…”