Abstract
Stratification of breast cancer (BC) into molecular subtypes by multigene expression assays is of demonstrated clinical utility. In principle, global RNA-sequencing (RNA-seq) should enable reconstructing existing transcriptional classifications of BC samples. Yet, it is not clear whether adaptation to RNA-seq of classifiers originally developed using PCR or microarrays, or reconstruction through machine learning (ML) is preferable. Hence, we focused on robustness and portability of PAM50, a nearest-centroid classifier developed on microarray data to identify five BC “intrinsic subtypes”. We found that standard PAM50 is profoundly affected by the composition of the sample cohort used for reference construction, and we propose a strategy, named AWCA, to mitigate this issue, improving classification robustness, with over 90% of concordance, and prognostic ability; we also show that AWCA-based PAM50 can even be applied as single-sample method. Furthermore, we explored five supervised learners to build robust, single-sample intrinsic subtype callers via RNA-seq. From our ML-based survey, regularized multiclass logistic regression (mLR) displayed the best performance, further increased by ad-hoc gene selection on the global transcriptome. On external test sets, mLR classifications reached 90% concordance with PAM50-based calls, without need of reference sample; mLR proven robustness and prognostic ability make it an equally valuable single-sample method to strengthen BC subtyping.
Highlights
Breast cancer (BC) is the most common cancer in women worldwide, and in about 80% of cases is invasive, i.e. it breaks through the walls of the glands or ducts where it originated and grows into surrounding breast tissue
Even if these groups firstly emerged by unsupervised hierarchical clustering on global microarray gene expression profiles[1], breast cancer (BC) classification into intrinsic subtypes is primarily achieved by measuring the expression of a set of only 50 genes, the so-called “PAM50 panel”[15]
At https://github.com/DEIB-GECO/BC_Intrinsic_subtyping we make publicly available the R codes to perform single-sample PAM50 classifications using precomputed average of within-class averages” (AWCA) references, and to build AWCA references on any expression data, even from other platforms, as we successfully experienced with microarray data from Affymetrix
Summary
Breast cancer (BC) is the most common cancer in women worldwide, and in about 80% of cases is invasive, i.e. it breaks through the walls of the glands or ducts where it originated and grows into surrounding breast tissue. To explore in detail the potential of RNA-seq in reconstructing a BC classification system originally developed with a different technology, we considered the so-called “intrinsic molecular subtypes” (Luminal A, Luminal B, Normal-like, Her2-Enriched and Basal), which have become part of the common knowledge on the disease and are recognized as prognostically and therapeutically r elevant[7]. Even if these groups firstly emerged by unsupervised hierarchical clustering on global microarray gene expression profiles[1], BC classification into intrinsic subtypes is primarily achieved by measuring the expression of a set of only 50 genes, the so-called “PAM50 panel”[15]. Intrinsic subtypes summarize BC biological and molecular features, which are known to involve many more genes than the PAM50 set[20]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.