analiza aiqbench
This paper introduces DoGMA, a foundation model that integrates biological central dogma constraints into Transformer architectures for multi-omics cancer analysis. By enforcing directed attention mechanisms consistent with information flow from DNA to protein, the model achieves improved robustness and transferability across heterogeneous datasets compared to standard bidirectional approaches. The work highlights how embedding domain-specific inductive biases can enhance the performance of large models in complex biomedical tasks like survival prediction and metastasis detection.
DoGMA: A Central-Dogma-Guided Foundation Model for Multi-Omics Alignment and Multi-Task Learning in Oncology
arXiv:2608.08148v2 Announce Type: replace Abstract: Attention mechanisms have been widely utilized in modern deep learning, and many existing multi-omics models inherit their conventional use to allow unrestricted bidirectional interactions. However, the fundamental logic of life is directional. Existing designs often overlook the directionality suggested by the central dogma, potentially limiting transfer across heterogeneous cancers, downstream tasks, and incomplete modality settings. In this work, we present DoGMA, a central-dogma-guided foundation model for pan-cancer multi-omics analysis, arguing that robust transfer requires representations with domain-specific inductive bias. Concretely, we build it on a Transformer-MoE architecture where directed attention biases inter-omics communication toward central-dogma information flow. We further pretrain our model with masked hierarchical omics reconstruction to guide it toward learning central-dogma-consistent interactions. Across diverse downstream tasks, including cancer representation learning, survival prediction, and metastasis prediction, DoGMA consistently demonstrates strong predictive performance. Ablations and analyses further suggest that the performance gains arise from the synergy between central-dogma-guided directed attention and reconstruction-based pretraining, which together promote more biologically consistent cross-omics information exchange. Overall, DoGMA demonstrates that domain-specific inductive biases can improve the robustness and transferability of multi-omics foundation models, offering new insights into the design of attention mechanisms for multi-omics representation learning.
Abstract:Attention mechanisms have been widely utilized in modern deep learning, and many existing multi-omics models inherit their conventional use to allow unrestricted bidirectional interactions. However, the fundamental logic of life is directional. Existing designs often overlook the directionality suggested by the central dogma, potentially limiting transfer across heterogeneous cancers, downstream tasks, and incomplete modality settings. In this work, we present DoGMA, a central-dogma-guided foundation model for pan-cancer multi-omics analysis, arguing that robust transfer requires representations with domain-specific inductive bias. Concretely, we build it on a Transformer-MoE architecture where directed attention biases inter-omics communication toward central-dogma information flow. We further pretrain our model with masked hierarchical omics reconstruction to guide it toward learning central-dogma-consistent interactions. Across diverse downstream tasks, including cancer representation learning, survival prediction, and metastasis prediction, DoGMA consistently demonstrates strong predictive performance. Ablations and analyses further suggest that the performance gains arise from the synergy between central-dogma-guided directed attention and reconstruction-based pretraining, which together promote more biologically consistent cross-omics information exchange. Overall, DoGMA demonstrates that domain-specific inductive biases can improve the robustness and transferability of multi-omics foundation models, offering new insights into the design of attention mechanisms for multi-omics representation learning.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2608.08148 [cs.LG]
(or arXiv:2608.08148v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.08148 Focus to learn more arXiv-issued DOI via DataCite
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.
Text integral sub licența deschisă a publicației · 287 cuvinte
Subiecte conexe
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · 24 sept. 2026
34 Amazon Research Awards Build on Trainium recipients announced
Amazon Science · 5 aug. 2026
Cloud Forensics and the Digital Crime Scene: How Investigation, Prevention, and Resilience Have Evolved
AppDirect · 21 mai 2026
Amazon is investing in the Lean Focused Research Organization
Amazon Science · 26 iul. 2026