%Aigaion2 BibTeX export from Idiap Publications
%Sunday 14 April 2024 06:53:45 AM

         author = {Wysocka, Magdalena and Wysocki, Oskar and Zufferey, Marie and Landers, Donal and Freitas, Andre},
       keywords = {Cancer Genomics, deep learning, Domain Knowledge Integration, Explainable AI, Graph Neural Networks, Multi-omics Data, Sparse Neural Networks},
       projects = {Idiap},
          month = may,
          title = {A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data},
        journal = {BMC Bioinformatics},
         volume = {24},
         number = {198},
           year = {2023},
            doi = {https://doi.org/10.1186/s12859-023-05262-8},
       abstract = {Background
There is an increasing interest in the use of Deep Learning (DL) based methods as a supporting analytical framework in oncology. However, most direct applications of DL will deliver models with limited transparency and explainability, which constrain their deployment in biomedical settings.

This systematic review discusses DL models used to support inference in cancer biology with a particular emphasis on multi-omics analysis. It focuses on how existing models address the need for better dialogue with prior knowledge, biological plausibility and interpretability, fundamental properties in the biomedical domain. For this, we retrieved and analyzed 42 studies focusing on emerging architectural and methodological advances, the encoding of biological domain knowledge and the integration of explainability methods.

We discuss the recent evolutionary arch of DL models in the direction of integrating prior biological relational and network knowledge to support better generalisation (e.g. pathways or Protein-Protein-Interaction networks) and interpretability. This represents a fundamental functional shift towards models which can integrate mechanistic and statistical inference aspects. We introduce a concept of bio-centric interpretability and according to its taxonomy, we discuss representational methodologies for the integration of domain prior knowledge in such models.

The paper provides a critical outlook into contemporary methods for explainability and interpretability used in DL for cancer. The analysis points in the direction of a convergence between encoding prior knowledge and improved interpretability. We introduce bio-centric interpretability which is an important step towards formalisation of biological interpretability of DL models and developing methods that are less problem- or application-specific.}