Dataset Information

Machine Learning Approaches to Classify Primary and Metastatic Cancers Using Tissue of Origin-Based DNA Methylation Profiles.

ABSTRACT: Metastatic cancers account for up to 90% of cancer-related deaths. The clear differentiation of metastatic cancers from primary cancers is crucial for cancer type identification and developing targeted treatment for each cancer type. DNA methylation patterns are suggested to be an intriguing target for cancer prediction and are also considered to be an important mediator for the transition to metastatic cancer. In the present study, we used 24 cancer types and 9303 methylome samples downloaded from publicly available data repositories, including The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO). We constructed machine learning classifiers to discriminate metastatic, primary, and non-cancerous methylome samples. We applied support vector machines (SVM), Naive Bayes (NB), extreme gradient boosting (XGBoost), and random forest (RF) machine learning models to classify the cancer types based on their tissue of origin. RF outperformed the other classifiers, with an average accuracy of 99%. Moreover, we applied local interpretable model-agnostic explanations (LIME) to explain important methylation biomarkers to classify cancer types.

SUBMITTER: Modhukur V

PROVIDER: S-EPMC8345047 | biostudies-literature | 2021 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning Approaches to Classify Primary and Metastatic Cancers Using Tissue of Origin-Based DNA Methylation Profiles.

Modhukur Vijayachitra V Sharma Shakshi S Mondal Mainak M Lawarde Ankita A Kask Keiu K Sharma Rajesh R Salumets Andres A

Cancers 20210727 15

Metastatic cancers account for up to 90% of cancer-related deaths. The clear differentiation of metastatic cancers from primary cancers is crucial for cancer type identification and developing targeted treatment for each cancer type. DNA methylation patterns are suggested to be an intriguing target for cancer prediction and are also considered to be an important mediator for the transition to metastatic cancer. In the present study, we used 24 cancer types and 9303 methylome samples downloaded f ...[more]

PMID: 34359669

Similar Datasets

Project description:BackgroundAlthough triple-negative breast cancer (TNBC) is associated with an increased risk of recurrence and metastasis, the molecular mechanisms underlying metastasis in TNBC remain unknown. To identify transcriptional changes and genes regulating metastatic progression in TNBC, we compared the transcriptomic profiles of primary and matched metastatic tumors using massively parallel RNA sequencing.MethodsWe performed gene expression profiling using formalin-fixed paraffin-embedded (FFPE) TNBC tissues of patients from two cohorts: the Zurich cohort (n = 31) and the Stavanger cohort (n = 5). Among the 31 patients in the Zurich cohort, 18 had primary TNBC tumors that did not metastasize, and 13 had primary tumors that metastasized (11 paired primary and locoregional recurrences). The Stavanger cohort included five matched primary and metastatic TNBC tumors. Significantly differentially expressed genes (DEGs; absolute fold change ≥2, p < 0.05) were identified and subjected to functional analyses. We investigated if there was any overlap between DEGs from both the cohorts with epithelial-to-mesenchymal-to-amoeboid transition (EMAT) gene signature. xCell was used to estimate relative fractions of 64 immune and stromal cell types in each RNA-seq sample.ResultsIn the Zurich cohort, we identified 1624 DEGs between primary TNBC tumors and matched metastatic lesions. xCell analysis revealed a significantly higher immune scores for metastatic lesions compared to paired primary tumors in the Zurich cohort. We also found significant upregulation of three MammaPrint signature genes (HRASLS, TGFB3 and RASSF7) in primary tumors that metastasized compared to primary tumors that remained metastasis-free. In the Stavanger cohort, we identified 818 DEGs between primary tumors and matched metastatic lesions. No significant differences in xCell immune scores were observed. We found that 21 and 14 DEGs from Zurich and Stavanger cohort, respectively, overlapped with the EMAT gene signature. In both cohorts, genes belonging to the MMP, FGF, and PDGFR families were upregulated in primary tumors compared to matched metastatic lesions.ConclusionsOur results suggest that distinct gene expression patterns exist between primary TNBCs and matched metastatic tumors. Further studies are warranted to explore whether these discrete expression profiles underlie or result from disease status.

Project description:BackgroundMalaria is still a major global health burden, with more than 3.2 billion people in 91 countries remaining at risk of the disease. Accurately distinguishing malaria from other diseases, especially uncomplicated malaria (UM) from non-malarial infections (nMI), remains a challenge. Furthermore, the success of rapid diagnostic tests (RDTs) is threatened by Pfhrp2/3 deletions and decreased sensitivity at low parasitaemia. Analysis of haematological indices can be used to support the identification of possible malaria cases for further diagnosis, especially in travellers returning from endemic areas. As a new application for precision medicine, we aimed to evaluate machine learning (ML) approaches that can accurately classify nMI, UM, and severe malaria (SM) using haematological parameters.MethodsWe obtained haematological data from 2,207 participants collected in Ghana: nMI (n = 978), SM (n = 526), and UM (n = 703). Six different ML approaches were tested, to select the best approach. An artificial neural network (ANN) with three hidden layers was used for multi-classification of UM, SM, and uMI. Binary classifiers were developed to further identify the parameters that can distinguish UM or SM from nMI. Local interpretable model-agnostic explanations (LIME) were used to explain the binary classifiers.ResultsThe multi-classification model had greater than 85% training and testing accuracy to distinguish clinical malaria from nMI. To distinguish UM from nMI, our approach identified platelet counts, red blood cell (RBC) counts, lymphocyte counts, and percentages as the top classifiers of UM with 0.801 test accuracy (AUC = 0.866 and F1 score = 0.747). To distinguish SM from nMI, the classifier had a test accuracy of 0.96 (AUC = 0.983 and F1 score = 0.944) with mean platelet volume and mean cell volume being the unique classifiers of SM. Random forest was used to confirm the classifications, and it showed that platelet and RBC counts were the major classifiers of UM, regardless of possible confounders such as patient age and sampling location.ConclusionThe study provides proof of concept methods that classify UM and SM from nMI, showing that the ML approach is a feasible tool for clinical decision support. In the future, ML approaches could be incorporated into clinical decision-support algorithms for the diagnosis of acute febrile illness and monitoring response to acute SM treatment particularly in endemic settings.

Dataset Information

Machine Learning Approaches to Classify Primary and Metastatic Cancers Using Tissue of Origin-Based DNA Methylation Profiles.

Publications

Machine Learning Approaches to Classify Primary and Metastatic Cancers Using Tissue of Origin-Based DNA Methylation Profiles.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets