Robust identification of molecular phenotypes using semi-supervised learning
Abstract Background Modern molecular profiling techniques are yielding vast amounts of data from patient samples that could be utilized with machine learning methods to provide important biological insights and improvements in patient outcomes. Unsupervised methods have been successfully used to ide...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-05-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12859-019-2885-3 |
| _version_ | 1818459812123377664 |
|---|---|
| author | Heinrich Roder Carlos Oliveira Lelia Net Benjamin Linstid Maxim Tsypin Joanna Roder |
| author_facet | Heinrich Roder Carlos Oliveira Lelia Net Benjamin Linstid Maxim Tsypin Joanna Roder |
| author_sort | Heinrich Roder |
| collection | DOAJ |
| description | Abstract Background Modern molecular profiling techniques are yielding vast amounts of data from patient samples that could be utilized with machine learning methods to provide important biological insights and improvements in patient outcomes. Unsupervised methods have been successfully used to identify molecularly-defined disease subtypes. However, these approaches do not take advantage of potential additional clinical outcome information. Supervised methods can be implemented when training classes are apparent (e.g., responders or non-responders to treatment). However, training classes can be difficult to define when assessing relative benefit of one therapy over another using gold standard clinical endpoints, since it is often not clear how much benefit each individual patient receives. Results We introduce an iterative approach to binary classification tasks based on the simultaneous refinement of training class labels and classifiers towards self-consistency. As training labels are refined during the process, the method is well suited to cases where training class definitions are not obvious or noisy. Clinical data, including time-to-event endpoints, can be incorporated into the approach to enable the iterative refinement to identify molecular phenotypes associated with a particular clinical variable. Using synthetic data, we show how this approach can be used to increase the accuracy of identification of outcome-related phenotypes and their associated molecular attributes. Further, we demonstrate that the advantages of the method persist in real world genomic datasets, allowing the reliable identification of molecular phenotypes and estimation of their association with outcome that generalizes to validation datasets. We show that at convergence of the iterative refinement, there is a consistent incorporation of the molecular data into the classifier yielding the molecular phenotype and that this allows a robust identification of associated attributes and the underlying biological processes. Conclusions The consistent incorporation of the structure of the molecular data into the classifier helps to minimize overfitting and facilitates not only good generalization of classification and molecular phenotypes, but also reliable identification of biologically relevant features and elucidation of underlying biological processes. |
| first_indexed | 2024-12-14T23:20:18Z |
| format | Article |
| id | doaj.art-212178dfa247411b8864f81c70ed1d7c |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-14T23:20:18Z |
| publishDate | 2019-05-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-212178dfa247411b8864f81c70ed1d7c2022-12-21T22:43:59ZengBMCBMC Bioinformatics1471-21052019-05-0120112510.1186/s12859-019-2885-3Robust identification of molecular phenotypes using semi-supervised learningHeinrich Roder0Carlos Oliveira1Lelia Net2Benjamin Linstid3Maxim Tsypin4Joanna Roder5Biodesix IncBiodesix IncBiodesix IncBiodesix IncBiodesix IncBiodesix IncAbstract Background Modern molecular profiling techniques are yielding vast amounts of data from patient samples that could be utilized with machine learning methods to provide important biological insights and improvements in patient outcomes. Unsupervised methods have been successfully used to identify molecularly-defined disease subtypes. However, these approaches do not take advantage of potential additional clinical outcome information. Supervised methods can be implemented when training classes are apparent (e.g., responders or non-responders to treatment). However, training classes can be difficult to define when assessing relative benefit of one therapy over another using gold standard clinical endpoints, since it is often not clear how much benefit each individual patient receives. Results We introduce an iterative approach to binary classification tasks based on the simultaneous refinement of training class labels and classifiers towards self-consistency. As training labels are refined during the process, the method is well suited to cases where training class definitions are not obvious or noisy. Clinical data, including time-to-event endpoints, can be incorporated into the approach to enable the iterative refinement to identify molecular phenotypes associated with a particular clinical variable. Using synthetic data, we show how this approach can be used to increase the accuracy of identification of outcome-related phenotypes and their associated molecular attributes. Further, we demonstrate that the advantages of the method persist in real world genomic datasets, allowing the reliable identification of molecular phenotypes and estimation of their association with outcome that generalizes to validation datasets. We show that at convergence of the iterative refinement, there is a consistent incorporation of the molecular data into the classifier yielding the molecular phenotype and that this allows a robust identification of associated attributes and the underlying biological processes. Conclusions The consistent incorporation of the structure of the molecular data into the classifier helps to minimize overfitting and facilitates not only good generalization of classification and molecular phenotypes, but also reliable identification of biologically relevant features and elucidation of underlying biological processes.http://link.springer.com/article/10.1186/s12859-019-2885-3Machine learningClusteringMolecular phenotypeSemi-supervised learning |
| spellingShingle | Heinrich Roder Carlos Oliveira Lelia Net Benjamin Linstid Maxim Tsypin Joanna Roder Robust identification of molecular phenotypes using semi-supervised learning BMC Bioinformatics Machine learning Clustering Molecular phenotype Semi-supervised learning |
| title | Robust identification of molecular phenotypes using semi-supervised learning |
| title_full | Robust identification of molecular phenotypes using semi-supervised learning |
| title_fullStr | Robust identification of molecular phenotypes using semi-supervised learning |
| title_full_unstemmed | Robust identification of molecular phenotypes using semi-supervised learning |
| title_short | Robust identification of molecular phenotypes using semi-supervised learning |
| title_sort | robust identification of molecular phenotypes using semi supervised learning |
| topic | Machine learning Clustering Molecular phenotype Semi-supervised learning |
| url | http://link.springer.com/article/10.1186/s12859-019-2885-3 |
| work_keys_str_mv | AT heinrichroder robustidentificationofmolecularphenotypesusingsemisupervisedlearning AT carlosoliveira robustidentificationofmolecularphenotypesusingsemisupervisedlearning AT lelianet robustidentificationofmolecularphenotypesusingsemisupervisedlearning AT benjaminlinstid robustidentificationofmolecularphenotypesusingsemisupervisedlearning AT maximtsypin robustidentificationofmolecularphenotypesusingsemisupervisedlearning AT joannaroder robustidentificationofmolecularphenotypesusingsemisupervisedlearning |