aiqbench analysis
This research introduces ARO, a machine learning model designed to reconstruct missing data modalities in multi-omics cancer datasets, addressing the high costs and incompleteness typical of functional molecular assays. By prioritizing practical applicability over the scale of foundation models, the approach demonstrates that integrated analysis of diverse molecular layers can reliably support downstream tasks like cancer classification even with limited experimental data.
ARO: Aligned Representation learning for multi-Omics data
arXiv:2610.06443v1 Announce Type: cross Abstract: The high cost of functional molecular assays, and prevalence of missing modalities and unmatched samples in computational biology, create significant barriers to comprehensive multi-omic profiling, essential for capturing and reasoning over molecules, cells, tissues, and organisms. This work proposes a model that learns meaningful representations from multi-omics cancer data supporting the reconstruction of missing and unpaired modalities. Contrary to increasingly complex, larger models, e.g. Foundation Models (FMs), ARO prioritizes practical applicability in limited or incomplete data settings. ARO optimally reconstructs missing modalities (MSE of $0.15$ on the validation and test data in the Unmasked settings), with its learned latent embeddings enabling a downstream cancer classification task. Our findings indicate that analyzing diverse molecular layers as a single integrated system offers a reliable and cost-efficient approach, reducing dependence on large-scale experimental testing, while still supporting multi-omic exploration in limited data settings.
Abstract:The high cost of functional molecular assays, and prevalence of missing modalities and unmatched samples in computational biology, create significant barriers to comprehensive multi-omic profiling, essential for capturing and reasoning over molecules, cells, tissues, and organisms. This work proposes a model that learns meaningful representations from multi-omics cancer data supporting the reconstruction of missing and unpaired modalities. Contrary to increasingly complex, larger models, e.g. Foundation Models (FMs), ARO prioritizes practical applicability in limited or incomplete data settings. ARO optimally reconstructs missing modalities (MSE of $0.15$ on the validation and test data in the Unmasked settings), with its learned latent embeddings enabling a downstream cancer classification task. Our findings indicate that analyzing diverse molecular layers as a single integrated system offers a reliable and cost-efficient approach, reducing dependence on large-scale experimental testing, while still supporting multi-omic exploration in limited data settings.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2610.06443 [cs.LG]
(or arXiv:2610.06443v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.06443 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 237 words
Related coverage
The Trade-off Between Covariate Dependence and Latent Structure in Representation Learning
arXiv · Aug 19, 2026
Representation-Aware Distributionally Robust Optimization: A Knowledge Transfer Framework
arXiv · Jul 21, 2026
DoGMA: A Central-Dogma-Guided Foundation Model for Multi-Omics Alignment and Multi-Task Learning in Oncology
arXiv · Sep 9, 2026
When to Align, When to Predict: A Phase Diagram for Multimodal Learning
arXiv · Sep 9, 2026