SRIQ clustering: A fusion of Random Forest, QT clustering, and KNN concepts
Gene expression profiling together with unsupervised analysis methods, typically clustering methods, has been used extensively in cancer research to unravel, e.g., new molecular subtypes that hold promise of disease refinement that may ultimately benefit patients. However, many of the commonly used...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-01-01
|
| Series: | Computational and Structural Biotechnology Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2001037022001118 |
| _version_ | 1828088010972856320 |
|---|---|
| author | Jacob Karlström Mattias Aine Johan Staaf Srinivas Veerla |
| author_facet | Jacob Karlström Mattias Aine Johan Staaf Srinivas Veerla |
| author_sort | Jacob Karlström |
| collection | DOAJ |
| description | Gene expression profiling together with unsupervised analysis methods, typically clustering methods, has been used extensively in cancer research to unravel, e.g., new molecular subtypes that hold promise of disease refinement that may ultimately benefit patients. However, many of the commonly used methods require a prespecified number of clusters to extract and frequently require some type of feature pre-selection, e.g. variance filtering. This introduces subjectivity to the process of cluster discovery and the definition of putative novel tumor subtypes. Here, we introduce SRIQ, a novel unsupervised clustering method that could circumvent some of the issues in commonly used unsupervised analysis methods. SRIQ incorporates concepts from random forest machine learning as well as quality threshold- and k-nearest neighbor clustering. It is implemented as a Java and Python pipeline including data pre-processing, differential expression analysis, and pathway analysis. Using 434 lung adenocarcinomas profiled by RNA sequencing, we demonstrate the technical reproducibility of SRIQ and benchmark its performance compared to the commonly used consensus clustering method. Based on differential gene expression analysis and auxiliary molecular data we show that SRIQ can define new tumor subsets that appear biologically relevant and consistent compared and that these new subgroups seem to refine existing transcriptional subtypes that were defined using consensus clustering. Together, this provides support that SRIQ may be a useful new tool for unsupervised analysis of gene expression data from human malignancies. |
| first_indexed | 2024-04-11T05:20:07Z |
| format | Article |
| id | doaj.art-f72b08a56ae947ceb3458ab37b76c041 |
| institution | Directory Open Access Journal |
| issn | 2001-0370 |
| language | English |
| last_indexed | 2024-04-11T05:20:07Z |
| publishDate | 2022-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computational and Structural Biotechnology Journal |
| spelling | doaj.art-f72b08a56ae947ceb3458ab37b76c0412022-12-24T04:51:55ZengElsevierComputational and Structural Biotechnology Journal2001-03702022-01-012015671579SRIQ clustering: A fusion of Random Forest, QT clustering, and KNN conceptsJacob Karlström0Mattias Aine1Johan Staaf2Srinivas Veerla3Division of Oncology, Department of Clinical Sciences Lund, Lund University, Medicon Village, SE-22381 Lund, SwedenDivision of Oncology, Department of Clinical Sciences Lund, Lund University, Medicon Village, SE-22381 Lund, SwedenCorresponding authors.; Division of Oncology, Department of Clinical Sciences Lund, Lund University, Medicon Village, SE-22381 Lund, SwedenCorresponding authors.; Division of Oncology, Department of Clinical Sciences Lund, Lund University, Medicon Village, SE-22381 Lund, SwedenGene expression profiling together with unsupervised analysis methods, typically clustering methods, has been used extensively in cancer research to unravel, e.g., new molecular subtypes that hold promise of disease refinement that may ultimately benefit patients. However, many of the commonly used methods require a prespecified number of clusters to extract and frequently require some type of feature pre-selection, e.g. variance filtering. This introduces subjectivity to the process of cluster discovery and the definition of putative novel tumor subtypes. Here, we introduce SRIQ, a novel unsupervised clustering method that could circumvent some of the issues in commonly used unsupervised analysis methods. SRIQ incorporates concepts from random forest machine learning as well as quality threshold- and k-nearest neighbor clustering. It is implemented as a Java and Python pipeline including data pre-processing, differential expression analysis, and pathway analysis. Using 434 lung adenocarcinomas profiled by RNA sequencing, we demonstrate the technical reproducibility of SRIQ and benchmark its performance compared to the commonly used consensus clustering method. Based on differential gene expression analysis and auxiliary molecular data we show that SRIQ can define new tumor subsets that appear biologically relevant and consistent compared and that these new subgroups seem to refine existing transcriptional subtypes that were defined using consensus clustering. Together, this provides support that SRIQ may be a useful new tool for unsupervised analysis of gene expression data from human malignancies.http://www.sciencedirect.com/science/article/pii/S2001037022001118Lung adenocarcinomaClusteringMolecular subtypesGene expressionRandom ForestQT clustering |
| spellingShingle | Jacob Karlström Mattias Aine Johan Staaf Srinivas Veerla SRIQ clustering: A fusion of Random Forest, QT clustering, and KNN concepts Computational and Structural Biotechnology Journal Lung adenocarcinoma Clustering Molecular subtypes Gene expression Random Forest QT clustering |
| title | SRIQ clustering: A fusion of Random Forest, QT clustering, and KNN concepts |
| title_full | SRIQ clustering: A fusion of Random Forest, QT clustering, and KNN concepts |
| title_fullStr | SRIQ clustering: A fusion of Random Forest, QT clustering, and KNN concepts |
| title_full_unstemmed | SRIQ clustering: A fusion of Random Forest, QT clustering, and KNN concepts |
| title_short | SRIQ clustering: A fusion of Random Forest, QT clustering, and KNN concepts |
| title_sort | sriq clustering a fusion of random forest qt clustering and knn concepts |
| topic | Lung adenocarcinoma Clustering Molecular subtypes Gene expression Random Forest QT clustering |
| url | http://www.sciencedirect.com/science/article/pii/S2001037022001118 |
| work_keys_str_mv | AT jacobkarlstrom sriqclusteringafusionofrandomforestqtclusteringandknnconcepts AT mattiasaine sriqclusteringafusionofrandomforestqtclusteringandknnconcepts AT johanstaaf sriqclusteringafusionofrandomforestqtclusteringandknnconcepts AT srinivasveerla sriqclusteringafusionofrandomforestqtclusteringandknnconcepts |