Dataset Information

An Improved, Assay Platform Agnostic, Absolute Single Sample Breast Cancer Subtype Classifier.

ABSTRACT: While intrinsic molecular subtypes provide important biological classification of breast cancer, the subtype assignment of individuals is influenced by assay technology and study cohort composition. We sought to develop a platform-independent absolute single-sample subtype classifier based on a minimal number of genes. Pairwise ratios for subtype-specific differentially expressed genes from un-normalized expression data from 432 breast cancer (BC) samples of The Cancer Genome Atlas (TCGA) were used as inputs for machine learning. The subtype classifier with the fewest number of genes and maximal classification power was selected during cross-validation. The final model was evaluated on 5816 samples from 10 independent studies profiled with four different assay platforms. Upon cross-validation within the TCGA cohort, a random forest classifier (MiniABS) with 11 genes achieved the best accuracy of 88.2%. Applying MiniABS to five validation sets of RNA-seq and microarray data showed an average accuracy of 85.15% (vs. 77.72% for Absolute Intrinsic Molecular Subtype (AIMS)). Only MiniABS could be applied to five low-throughput datasets, showing an average accuracy of 87.93%. The MiniABS can absolutely subtype BC using the raw expression levels of only 11 genes, regardless of assay platform, with higher accuracy than existing methods.

SUBMITTER: Seo MK

PROVIDER: S-EPMC7761033 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An Improved, Assay Platform Agnostic, Absolute Single Sample Breast Cancer Subtype Classifier.

Seo Mi-Kyoung MK Paik Soonmyung S Kim Sangwoo S

Cancers 20201125 12

While intrinsic molecular subtypes provide important biological classification of breast cancer, the subtype assignment of individuals is influenced by assay technology and study cohort composition. We sought to develop a platform-independent absolute single-sample subtype classifier based on a minimal number of genes. Pairwise ratios for subtype-specific differentially expressed genes from un-normalized expression data from 432 breast cancer (BC) samples of The Cancer Genome Atlas (TCGA) were u ...[more]

PMID: 33255759

Similar Datasets

Project description:Purpose To develop a radiosensitivity gene expression assay to predict the response to adjuvant radiotherapy (RT) after breast conserving surgery (BCS) in breast cancer. Patients and methods Fresh frozen primary tumors from 336 patients operated with BCS with or without RT were collected. Patients were split in a discovery cohort (N=172) and a validation cohort (N=164). Genes predicting ipsilateral breast tumor recurrence (IBTR) in an Illumina HT12 v4 whole transcriptome analysis were combined with genes from the literature (248 genes in total) to develop a targeted radiosensitivity assay on the Nanostring nCounter platform. Single sample predictors (SSPs) for IBTR based on a k-top scoring pairs algorithm were trained stratified for estrogen receptor (ER) status and RT. Two previously published profiles (radiosensitivity index, RSI, and radiosensitivity score, RSS) were also tested in our data Results The SSPs were prognostic for IBTR in ER+RT- patients (AUC 0.67, p=0.005), ER+RT- patients (AUC=0.89, p=0.015) and ER-RT+ patients (AUC=0.78, p<0.001). Among ER+ patients, radiosensitive tumors had an excellent effect of RT (p<0.001), while radioresistant tumors had no effect of RT (p=0.4) and a high risk of IBTR (55% at 10 years). Our SSPs developed in ER+ tumors and the RSS correlated with proliferation, while SSPs developed in ER- tumors correlated with immune response. RSI negatively correlated with both proliferation and immune response. Conclusions Our targeted SSPs were prognostic for IBTR and has the potential to stratify patients for RT. The biology behind models may explain the different performance in subgroups of breast cancer. Purpose To develop a radiosensitivity gene expression assay to predict the response to adjuvant radiotherapy (RT) after breast conserving surgery (BCS) in breast cancer. Patients and methods Fresh frozen primary tumors from 336 patients operated with BCS with or without RT were collected. Patients were split in a discovery cohort (N=172) and a validation cohort (N=164). Genes predicting ipsilateral breast tumor recurrence (IBTR) in an Illumina HT12 v4 whole transcriptome analysis were combined with genes from the literature (248 genes in total) to develop a targeted radiosensitivity assay on the Nanostring nCounter platform. Single sample predictors (SSPs) for IBTR based on a k-top scoring pairs algorithm were trained stratified for estrogen receptor (ER) status and RT. Two previously published profiles (radiosensitivity index, RSI, and radiosensitivity score, RSS) were also tested in our data Results The SSPs were prognostic for IBTR in ER+RT- patients (AUC 0.67, p=0.005), ER+RT- patients (AUC=0.89, p=0.015) and ER-RT+ patients (AUC=0.78, p<0.001). Among ER+ patients, radiosensitive tumors had an excellent effect of RT (p<0.001), while radioresistant tumors had no effect of RT (p=0.4) and a high risk of IBTR (55% at 10 years). Our SSPs developed in ER+ tumors and the RSS correlated with proliferation, while SSPs developed in ER- tumors correlated with immune response. RSI negatively correlated with both proliferation and immune response. Conclusions Our targeted SSPs were prognostic for IBTR and has the potential to stratify patients for RT. The biology behind models may explain the different performance in subgroups of breast cancer.

Dataset Information

An Improved, Assay Platform Agnostic, Absolute Single Sample Breast Cancer Subtype Classifier.

Publications

An Improved, Assay Platform Agnostic, Absolute Single Sample Breast Cancer Subtype Classifier.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets