A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data
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 biomedica...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-05-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12859-023-05262-8 |
| _version_ | 1797822602653204480 |
|---|---|
| author | Magdalena Wysocka Oskar Wysocki Marie Zufferey Dónal Landers André Freitas |
| author_facet | Magdalena Wysocka Oskar Wysocki Marie Zufferey Dónal Landers André Freitas |
| author_sort | Magdalena Wysocka |
| collection | DOAJ |
| description | 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. Methods 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. Results 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. Conclusions 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. |
| first_indexed | 2024-03-13T10:11:32Z |
| format | Article |
| id | doaj.art-6753814668ef4329977aeb5d3b503768 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-03-13T10:11:32Z |
| publishDate | 2023-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-6753814668ef4329977aeb5d3b5037682023-05-21T11:28:51ZengBMCBMC Bioinformatics1471-21052023-05-0124113110.1186/s12859-023-05262-8A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology dataMagdalena Wysocka0Oskar Wysocki1Marie Zufferey2Dónal Landers3André Freitas4Digital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of ManchesterDigital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of ManchesterIdiap Research Institute, National University of SciencesDeLondra Oncology LtdDigital Experimental Cancer Medicine Team, Cancer Biomarker Centre, CRUK Manchester Institute, University of ManchesterAbstract 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. Methods 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. Results 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. Conclusions 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.https://doi.org/10.1186/s12859-023-05262-8Multi-omics DataCancer GenomicsDeep LearningExplainable AIGraph Neural NetworksSparse Neural Networks |
| spellingShingle | Magdalena Wysocka Oskar Wysocki Marie Zufferey Dónal Landers André Freitas A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data BMC Bioinformatics Multi-omics Data Cancer Genomics Deep Learning Explainable AI Graph Neural Networks Sparse Neural Networks |
| title | A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data |
| title_full | A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data |
| title_fullStr | A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data |
| title_full_unstemmed | A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data |
| title_short | A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data |
| title_sort | systematic review of biologically informed deep learning models for cancer fundamental trends for encoding and interpreting oncology data |
| topic | Multi-omics Data Cancer Genomics Deep Learning Explainable AI Graph Neural Networks Sparse Neural Networks |
| url | https://doi.org/10.1186/s12859-023-05262-8 |
| work_keys_str_mv | AT magdalenawysocka asystematicreviewofbiologicallyinformeddeeplearningmodelsforcancerfundamentaltrendsforencodingandinterpretingoncologydata AT oskarwysocki asystematicreviewofbiologicallyinformeddeeplearningmodelsforcancerfundamentaltrendsforencodingandinterpretingoncologydata AT mariezufferey asystematicreviewofbiologicallyinformeddeeplearningmodelsforcancerfundamentaltrendsforencodingandinterpretingoncologydata AT donallanders asystematicreviewofbiologicallyinformeddeeplearningmodelsforcancerfundamentaltrendsforencodingandinterpretingoncologydata AT andrefreitas asystematicreviewofbiologicallyinformeddeeplearningmodelsforcancerfundamentaltrendsforencodingandinterpretingoncologydata AT magdalenawysocka systematicreviewofbiologicallyinformeddeeplearningmodelsforcancerfundamentaltrendsforencodingandinterpretingoncologydata AT oskarwysocki systematicreviewofbiologicallyinformeddeeplearningmodelsforcancerfundamentaltrendsforencodingandinterpretingoncologydata AT mariezufferey systematicreviewofbiologicallyinformeddeeplearningmodelsforcancerfundamentaltrendsforencodingandinterpretingoncologydata AT donallanders systematicreviewofbiologicallyinformeddeeplearningmodelsforcancerfundamentaltrendsforencodingandinterpretingoncologydata AT andrefreitas systematicreviewofbiologicallyinformeddeeplearningmodelsforcancerfundamentaltrendsforencodingandinterpretingoncologydata |