Fast and sensitive validation of fusion transcripts in whole-genome sequencing data.

BACKGROUND: In cancer, genomic rearrangements can create fusion genes that either combine protein-coding sequences from two different partner genes or place one gene under the control of the promoter of another gene. These fusion genes can act as oncogenic drivers in tumor development and several fusions involving kinases have been successfully exploited as drug targets. Expressed fusions can be identified in RNA sequencing (RNA-Seq) data, but fusion prediction software often has a high fraction of false positive fusion transcript predictions. This is problematic for both research and clinical applications. RESULTS: We describe a method for validation of fusion transcripts detected by RNA-Seq in matched whole-genome sequencing (WGS) data. Our pipeline uses discordant read pairs to identify supported fusion events and analyzes soft-clipped read alignments to determine genomic breakpoints. We have tested it on matched RNA-Seq and WGS data for both tumors and cancer cell lines and show that it can be used to validate both new predicted gene fusions and experimentally validated fusion events. It was considerably faster and more sensitive than using BreakDancer and Manta, software that is instead designed to detect many different types of structural variants on a genome-wide scale. CONCLUSIONS: We have developed a fast and very sensitive pipeline for validation of gene fusions detected by RNA-Seq in matched WGS data. It can be used to identify high-quality gene fusions for further bioinformatic and experimental studies, including validation of genomic breakpoints and studies of the mechanisms that generate fusions. In a clinical setting, it could help find expressed gene fusions for personalized therapy.

Improved detection of clinically relevant fusion transcripts in cancer by machine learning classification.

BACKGROUND: Genomic rearrangements in cancer cells can create fusion genes that encode chimeric proteins or alter the expression of coding and non-coding RNAs. In some cancer types, fusions involving specific kinases are used as targets for therapy. Fusion genes can be detected by whole genome sequencing (WGS) and targeted fusion panels, but RNA sequencing (RNA-Seq) has the advantageous capability of broadly detecting expressed fusion transcripts. RESULTS: We developed a pipeline for validation of fusion transcripts identified in RNA-Seq data using matched WGS data from The Cancer Genome Atlas (TCGA) and applied it to 910 tumors from 11 different cancer types. This resulted in 4237 validated gene fusions, 3049 of them with at least one identified genomic breakpoint. Utilizing validated fusions as true positive events, we trained a machine learning classifier to predict true and false positive fusion transcripts from RNA-Seq data. The final precision and recall metrics of the classifier were 0.74 and 0.71, respectively, in an independent dataset of 249 breast tumors. Application of this classifier to all samples with RNA-Seq data from these cancer types vastly extended the number of likely true positive fusion transcripts and identified many potentially targetable kinase fusions. Further analysis of the validated gene fusions suggested that many are created by intrachromosomal amplification events with microhomology-mediated non-homologous end-joining. CONCLUSIONS: A classifier trained on validated fusion events increased the accuracy of fusion transcript identification in samples without WGS data. This allowed the analysis to be extended to all samples with RNA-Seq data, facilitating studies of tumor biology and increasing the number of detected kinase fusions. Machine learning could thus be used in identification of clinically relevant fusion events for targeted therapy. The large dataset of validated gene fusions generated here presents a useful resource for development and evaluation of fusion transcript detection algorithms.

Regulatory networks and 5' partner usage of miRNA host gene fusions in breast cancer.

Genomic rearrangements in cancer cells can create gene fusions where the juxtaposition of two different genes leads to the production of chimeric proteins or altered gene expression through promoter-swapping. We have previously shown that fusion transcripts involving microRNA (miRNA) host genes contribute to deregulation of miRNA expression regardless of the protein-coding potential of these transcripts. Many different genes can also be used as 5' partners by a miRNA host gene in what we named recurrent miRNA-convergent fusions. Here, we have explored the properties of 5' partners in fusion transcripts that involve miRNA hosts in breast tumours from The Cancer Genome Atlas (TCGA). We hypothesised that firstly, 5' partner genes should belong to pathways and transcriptional programmes that reflect the tumour phenotype and secondly, there should be a selection for fusion events that shape miRNA expression to benefit the tumour cell through the known hallmarks of cancer. We found that the set of 5' partners in miRNA host fusions is non-random, with overrepresentation of highly expressed genes in pathways active in cancer including epithelial-to-mesenchymal transition, translational regulation and oestrogen signalling. Furthermore, many miRNAs were upregulated in samples with host gene fusions, including established oncogenic miRNAs such as mir-21 and the mir-106b~mir-93~mir-25 cluster. To the list of mechanisms for deregulation of miRNA expression, we have added fusion transcripts that change the promoter region. We propose that this adds material for genetic selection and tumour evolution in cancer cells and that miRNA host fusions can act as tumour 'drivers'.

Molecular analyses of triple-negative breast cancer in the young and elderly.

BACKGROUND: Breast cancer in young adults has been implicated with a worse outcome. Analyses of genomic traits associated with age have been heterogenous, likely because of an incomplete accounting for underlying molecular subtypes. We aimed to resolve whether triple-negative breast cancer (TNBC) in younger versus older patients represent similar or different molecular diseases in the context of genetic and transcriptional subtypes and immune cell infiltration. PATIENTS AND METHODS: In total, 237 patients from a reported population-based south Swedish TNBC cohort profiled by RNA sequencing and whole-genome sequencing (WGS) were included. Patients were binned in 10-year intervals. Complimentary PD-L1 and CD20 immunohistochemistry and estimation of tumor-infiltrating lymphocytes (TILs) were performed. Cases were analyzed for differences in patient outcome, genomic, transcriptional, and immune landscape features versus age at diagnosis. Additionally, 560 public WGS breast cancer profiles were used for validation. RESULTS: Median age at diagnosis was 62 years (range 26-91). Age was not associated with invasive disease-free survival or overall survival after adjuvant chemotherapy. Among the BRCA1-deficient cases (82/237), 90% were diagnosed before the age of 70 and were predominantly of the basal-like subtype. In the full TNBC cohort, reported associations of patient age with changes in Ki67 expression, PIK3CA mutations, and a luminal androgen receptor subtype were confirmed. Within DNA repair deficiency or gene expression defined molecular subgroups, age-related alterations in, e.g., overall gene expression, immune cell marker gene expression, genetic mutational and rearrangement signatures, amount of copy number alterations, and tumor mutational burden did, however, not appear distinct. Similar non-significant associations for genetic alterations with age were obtained for other breast cancer subgroups in public WGS data. Consistent with age-related immunosenescence, TIL counts decreased linearly with patient age across different genetic TNBC subtypes. CONCLUSIONS: Age-related alterations in TNBC, as well as breast cancer in general, need to be viewed in the context of underlying genomic phenotypes. Based on this notion, age at diagnosis alone does not appear to provide an additional layer of biological complexity above that of proposed genetic and transcriptional phenotypes of TNBC. Consequently, treatment decisions should be less influenced by age and more driven by tumor biology.

Analysis of fusion transcripts indicates widespread deregulation of snoRNAs and their host genes in breast cancer.

Genomic rearrangements in cancer can join the sequences of two separate genes. Studies of such gene fusion events have mainly focused on identification of fusion proteins from the chimeric transcripts. We have previously investigated how fusions instead can affect the expression of intronic microRNA (miRNA) genes that are encoded within fusion gene partners. Here, we extend our analysis to small nucleolar RNAs (snoRNAs) that also are embedded within protein-coding or noncoding host genes. We found that snoRNA hosts are selectively enriched in fusion transcripts, like miRNA host genes, and that this enrichment is associated with all snoRNA classes. These structural changes may have functional consequences for the cell; proteins involved in the protein translation machinery are overrepresented among snoRNA host genes, a gene architecture assumed to be needed for closely coordinated expression of snoRNAs and host proteins. Our data indicate that this structure is frequently disrupted in cancer. We furthermore observed that snoRNA genes involved in fusions tend to associate with stronger promoters than the natural host, suggesting a mechanism that selects for snoRNA overexpression. In summary, we highlight a previously unexplored frequent structural change in cancer that affects important components of cellular physiology.

Agreement between molecular subtyping and surrogate subtype classification: a contemporary population-based study of ER-positive/HER2-negative primary breast cancer.

PURPOSE: Oestrogen receptor-positive (ER+) and human epidermal receptor 2-negative (HER2-) breast cancers are classified as Luminal A or B based on gene expression, but immunohistochemical markers are used for surrogate subtyping. The aims of this study were to examine the agreement between molecular subtyping (MS) and surrogate subtyping and to identify subgroups consisting mainly of Luminal A or B tumours. METHODS: The cohort consisted of 2063 patients diagnosed between 2013-2017, with primary ER+/HER2- breast cancer, analysed by RNA sequencing. Surrogate subtyping was performed according to three algorithms (St. Gallen 2013, Maisonneuve and our proposed Grade-based classification). Agreement (%) and kappa statistics (κ) were used as concordance measures and ROC analysis for luminal distinction. Ki67, progesterone receptor (PR) and histological grade (HG) were further investigated as surrogate markers. RESULTS: The agreement rates between the MS and St. Gallen 2013, Maisonneuve and Grade-based classifications were 62% (κ = 0.30), 66% (κ = 0.35) and 70% (κ = 0.41), respectively. PR did not contribute to distinguishing Luminal A from B tumours (auROC = 0.56). By classifying HG1-2 tumours as Luminal A-like and HG3 as Luminal B-like, agreement with MS was 80% (κ = 0.46). Moreover, by combining HG and Ki67 status, a large subgroup of patients (51% of the cohort) having > 90% Luminal A tumours could be identified. CONCLUSIONS: Agreement between MS and surrogate classifications was generally poor. However, a post hoc analysis showed that a combination of HG and Ki67 could identify patients very likely to have Luminal A tumours according to MS.

Molecular and genetic diversity in the metastatic process of melanoma.

Diversity between metastatic melanoma tumours in individual patients is known; however, the molecular and genetic differences remain unclear. To examine the molecular and genetic differences between metastatic tumours, we performed gene-expression profiling of 63 melanoma tumours obtained from 28 patients (two or three tumours/patient), followed by analysis of their mutational landscape, using targeted deep sequencing of 1697 cancer genes and DNA copy number analysis. Gene-expression signatures revealed discordant phenotypes between tumour lesions within a patient in 50% of the cases. In 18 of 22 patients (where matched normal tissue was available), we found that the multiple lesions within a patient were genetically divergent, with one or more melanoma tumours harbouring 'private' somatic mutations. In one case, the distant subcutaneous metastasis of one patient occurring 3 months after an earlier regional lymph node metastasis had acquired 37 new coding sequence mutations, including mutations in PTEN and CDH1. However, BRAF and NRAS mutations, when present in the first metastasis, were always preserved in subsequent metastases. The patterns of nucleotide substitutions found in this study indicate an influence of UV radiation but possibly also DNA alkylating agents. Our results clearly demonstrate that metastatic melanoma is a molecularly highly heterogeneous disease that continues to progress throughout its clinical course. The private aberrations observed on a background of shared aberrations within a patient provide evidence of continued evolution of individual tumours following divergence from a common parental clone, and might have implications for personalized medicine strategies in melanoma treatment.

Subtype and cell type specific expression of lncRNAs provide insight into breast cancer.

Long non-coding RNAs (lncRNAs) are involved in breast cancer pathogenesis through chromatin remodeling, transcriptional and post-transcriptional gene regulation. We report robust associations between lncRNA expression and breast cancer clinicopathological features in two population-based cohorts: SCAN-B and TCGA. Using co-expression analysis of lncRNAs with protein coding genes, we discovered three distinct clusters of lncRNAs. In silico cell type deconvolution coupled with single-cell RNA-seq analyses revealed that these three clusters were driven by cell type specific expression of lncRNAs. In one cluster lncRNAs were expressed by cancer cells and were mostly associated with the estrogen signaling pathways. In the two other clusters, lncRNAs were expressed either by immune cells or fibroblasts of the tumor microenvironment. To further investigate the cis-regulatory regions driving lncRNA expression in breast cancer, we identified subtype-specific transcription factor (TF) occupancy at lncRNA promoters. We also integrated lncRNA expression with DNA methylation data to identify long-range regulatory regions for lncRNA which were validated using ChiA-Pet-Pol2 loops. lncRNAs play an important role in shaping the gene regulatory landscape in breast cancer. We provide a detailed subtype and cell type-specific expression of lncRNA, which improves the understanding of underlying transcriptional regulation in breast cancer.

RNA sequencing-based single sample predictors of molecular subtype and risk of recurrence for clinical assessment of early-stage breast cancer.

Multigene assays for molecular subtypes and biomarkers can aid management of early invasive breast cancer. Using RNA-sequencing we aimed to develop single-sample predictor (SSP) models for clinical markers, subtypes, and risk of recurrence (ROR). A cohort of 7743 patients was divided into training and test set. We trained SSPs for subtypes and ROR assigned by nearest-centroid (NC) methods and SSPs for biomarkers from histopathology. Classifications were compared with Prosigna in two external cohorts (ABiM, n = 100 and OSLO2-EMIT0, n = 103). Prognostic value was assessed using distant recurrence-free interval. Agreement between SSP and NC for PAM50 (five subtypes) was high (85%, Kappa = 0.78) for Subtype (four subtypes) very high (90%, Kappa = 0.84) and for ROR risk category high (84%, Kappa = 0.75, weighted Kappa = 0.90). Prognostic value was assessed as equivalent and clinically relevant. Agreement with histopathology was very high or high for receptor status, while moderate for Ki67 status and poor for Nottingham histological grade. SSP and Prosigna concordance was high for subtype (OSLO-EMIT0 83%, Kappa = 0.73 and ABiM 80%, Kappa = 0.72) and moderate and high for ROR risk category (68 and 84%, Kappa = 0.50 and 0.70, weighted Kappa = 0.70 and 0.78). Pooled concordance for emulated treatment recommendation dichotomized for chemotherapy was high (85%, Kappa = 0.66). Retrospective evaluation suggested that SSP application could change chemotherapy recommendations for up to 17% of postmenopausal ER+/HER2-/N0 patients with balanced escalation and de-escalation. Results suggest that NC and SSP models are interchangeable on a group-level and nearly so on a patient level and that SSP models can be derived to closely match clinical tests.

Preexisting Somatic Mutations of Estrogen Receptor Alpha (ESR1) in Early-Stage Primary Breast Cancer.

Background: More than three-quarters of primary breast cancers are positive for estrogen receptor alpha (ER; encoded by the gene ESR1), the most important factor for directing anti-estrogenic endocrine therapy (ET). Recently, mutations in ESR1 were identified as acquired mechanisms of resistance to ET, found in 12% to 55% of metastatic breast cancers treated previously with ET. Methods: We analyzed 3217 population-based invasive primary (nonmetastatic) breast cancers (within the SCAN-B study, ClinicalTrials.gov NCT02306096), sampled from initial diagnosis prior to any treatment, for the presence of ESR1 mutations using RNA sequencing. Mutations were verified by droplet digital polymerase chain reaction on tumor and normal DNA. Patient outcomes were analyzed using Kaplan-Meier estimation and a series of 2-factor Cox regression multivariable analyses. Results: We identified ESR1 resistance mutations in 30 tumors (0.9%), of which 29 were ER positive (1.1%). In ET-treated disease, presence of ESR1 mutation was associated with poor relapse-free survival and overall survival (2-sided log-rank test P < .001 and P = .008, respectively), with hazard ratios of 3.00 (95% confidence interval = 1.56 to 5.88) and 2.51 (95% confidence interval = 1.24 to 5.07), respectively, which remained statistically significant when adjusted for other prognostic factors. Conclusions: These population-based results indicate that ESR1 mutations at diagnosis of primary breast cancer occur in about 1% of women and identify for the first time in the adjuvant setting that such preexisting mutations are associated to eventual resistance to standard hormone therapy. If replicated, tumor ESR1 screening should be considered in ER-positive primary breast cancer, and for patients with mutated disease, ER degraders such as fulvestrant or other therapeutic options may be considered as more appropriate.

The mutational landscape of the SCAN-B real-world primary breast cancer transcriptome.

Breast cancer is a disease of genomic alterations, of which the panorama of somatic mutations and how these relate to subtypes and therapy response is incompletely understood. Within SCAN-B (ClinicalTrials.gov: NCT02306096), a prospective study elucidating the transcriptomic profiles for thousands of breast cancers, we developed a RNA-seq pipeline for detection of SNVs/indels and profiled a real-world cohort of 3,217 breast tumors. We describe the mutational landscape of primary breast cancer viewed through the transcriptome of a large population-based cohort and relate it to patient survival. We demonstrate that RNA-seq can be used to call mutations in genes such as PIK3CA, TP53, and ERBB2, as well as the status of molecular pathways and mutational burden, and identify potentially druggable mutations in 86.8% of tumors. To make this rich dataset available for the research community, we developed an open source web application, the SCAN-B MutationExplorer (http://oncogenomics.bmc.lu.se/MutationExplorer). These results add another dimension to the use of RNA-seq as a clinical tool, where both gene expression- and mutation-based biomarkers can be interrogated in real-time within 1 week of tumor sampling.

Tumor genetic heterogeneity analysis of chronic sun-damaged melanoma.

Chronic sun-damaged (CSD) melanoma represents 10%-20% of cutaneous melanomas and is characterized by infrequent BRAF V600E mutations and high mutational load. However, the order of genetic events or the extent of intra-tumor heterogeneity (ITH) in CSDhigh melanoma is still unknown. Ultra-deep targeted sequencing of 40 cancer-associated genes was performed in 72 in situ or invasive CMM, including 23 CSDhigh cases. In addition, we performed whole exome and RNA sequencing on multiple regions of primary tumor and multiple in-transit metastases from one CSDhigh melanoma patient. We found no significant difference in mutation frequency in melanoma-related genes or in mutational load between in situ and invasive CSDhigh lesions, while this difference was observed in CSDlow lesions. In addition, increased frequency of BRAF V600K, NF1, and TP53 mutations (p < .01, Fisher's exact test) was found in CSDhigh melanomas. Sequencing of multiple specimens from one CSDhigh patient revealed strikingly limited ITH with >95% shared mutations. Our results provide evidence that CSDhigh and CSDlow melanomas are distinct molecular entities that progress via different genetic routes.

Prognostic implications of the expression levels of different immunoglobulin heavy chain-encoding RNAs in early breast cancer.

The extent and composition of the immune response in a breast cancer is one important prognostic factor for the disease. The aim of the current work was to refine the analysis of the humoral component of an immune response in breast tumors by quantifying mRNA expression of different immunoglobulin classes and study their association with prognosis. We used RNA-Seq data from two local population-based breast cancer cohorts to determine the expression of IGJ and immunoglobulin heavy (IGH) chain-encoding RNAs. The association with prognosis was investigated and public data sets were used to corroborate the findings. Except for IGHE and IGHD, mRNAs encoding heavy chains were generally detected at substantial levels and correlated with other immune-related genes. High IGHG1 mRNA was associated with factors related to poor prognosis such as estrogen receptor negativity, HER2 amplification, and high grade, whereas high IGHA2 mRNA levels were primarily associated with lower age at diagnosis. High IGHA2 and IGJ mRNA levels were associated with a more favorable prognosis both in univariable and multivariable Cox models. When adjusting for other prognostic factors, high IGHG1 mRNA levels were positively associated with improved prognosis. To our knowledge, these results are the first to demonstrate that expression of individual Ig class types has prognostic implications in breast cancer.

Comprehensive molecular comparison of BRCA1 hypermethylated and BRCA1 mutated triple negative breast cancers.

Homologous recombination deficiency (HRD) is a defining characteristic in BRCA-deficient breast tumors caused by genetic or epigenetic alterations in key pathway genes. We investigated the frequency of BRCA1 promoter hypermethylation in 237 triple-negative breast cancers (TNBCs) from a population-based study using reported whole genome and RNA sequencing data, complemented with analyses of genetic, epigenetic, transcriptomic and immune infiltration phenotypes. We demonstrate that BRCA1 promoter hypermethylation is twice as frequent as BRCA1 pathogenic variants in early-stage TNBC and that hypermethylated and mutated cases have similarly improved prognosis after adjuvant chemotherapy. BRCA1 hypermethylation confers an HRD, immune cell type, genome-wide DNA methylation, and transcriptional phenotype similar to TNBC tumors with BRCA1-inactivating variants, and it can be observed in matched peripheral blood of patients with tumor hypermethylation. Hypermethylation may be an early event in tumor development that progress along a common pathway with BRCA1-mutated disease, representing a promising DNA-based biomarker for early-stage TNBC.

Proteomics Data Collection - 5th ProDaC Workshop: 4 March 2009, Kolympari, Crete, Greece.

The Proteomics Data Collection (ProDaC) consortium, a "Coordination Action" funded by the 6th EU Framework Programme, started in October 2006. Its aim was to facilitate the collection and distribution of proteomics data and the public availability of data sets from proteomics experiments. Within the consortium standard formats are created and tools are developed to allow extensive data collection within the proteomics community. An important part of ProDaC is the organization of workshops twice a year to inform about the consortium's progress and to stimulate communication between the ProDaC partners and between partners and interested members of the proteomics community. ProDaC ends on March 31, 2009. The most recent (and final) workshop was the 5th ProDaC workshop held on March 4, 2009 in Kolympari, Crete, Greece. The progress since the last meeting and an overall summary was presented by the work package coordinators and partners. Four external speakers presented talks about their work in relation to ProDaC.

Proteomics data collection--4th ProDaC workshop 15 August 2008, Amsterdam, The Netherlands.

ProDaC (Proteomics Data Collection), a "Coordination Action" within the 6(th) EU framework programme, was created to support the collection, distribution and public availability of data from proteomics experiments. Within the consortium standards are created and maintained enabling an extensive data collection within the proteomics community. Important elements of ProDaC are workshops held twice a year to allow communication between the ProDaC partners and to report the ongoing progress. The most recent assembly was the 4(th) ProDaC workshop on August 15(th), 2008, in Amsterdam, The Netherlands. It took place directly before the 7(th) HUPO Annual World Congress (Human Proteome Organisation). Work package coordinators and partners presented the progress achieved since the last meeting. Additionally, an EU official presented funding opportunities for proteomics in the next EU framework programme and five external speakers presented talks about their work in relation to ProDaC.

Getting a grip on proteomics data - Proteomics Data Collection (ProDaC).

In proteomics, rapid developments in instrumentation led to the acquisition of increasingly large data sets. Correspondingly, ProDaC was founded in 2006 as a Coordination Action project within the 6th European Union Framework Programme to support data sharing and community-wide data collection. The objectives of ProDaC were the development of documentation and storage standards, setup of a standardized data submission pipeline and collection of data. Ending in March 2009, ProDaC has delivered a comprehensive toolbox of standards and computer programs to achieve these goals.

BASE--2nd generation software for microarray data management and analysis.

BACKGROUND: Microarray experiments are increasing in size and samples are collected asynchronously over long time. Available data are re-analysed as more samples are hybridized. Systematic use of collected data requires tracking of biomaterials, array information, raw data, and assembly of annotations. To meet the information tracking and data analysis challenges in microarray experiments we reimplemented and improved BASE version 1.2. RESULTS: The new BASE presented in this report is a comprehensive annotable local microarray data repository and analysis application providing researchers with an efficient information management and analysis tool. The information management system tracks all material from biosource, via sample and through extraction and labelling to raw data and analysis. All items in BASE can be annotated and the annotations can be used as experimental factors in downstream analysis. BASE stores all microarray experiment related data regardless if analysis tools for specific techniques or data formats are readily available. The BASE team is committed to continue improving and extending BASE to make it usable for even more experimental setups and techniques, and we encourage other groups to target their specific needs leveraging on the infrastructure provided by BASE. CONCLUSION: BASE is a comprehensive management application for information, data, and analysis of microarray experiments, available as free open source software at http://base.thep.lu.se under the terms of the GPLv3 license.

Prediction of Lymph Node Metastasis in Breast Cancer by Gene Expression and Clinicopathological Models: Development and Validation within a Population-Based Cohort.

PURPOSE: More than 70% of patients with breast cancer present with node-negative disease, yet all undergo surgical axillary staging. We aimed to define predictors of nodal metastasis using clinicopathological characteristics (CLINICAL), gene expression data (GEX), and mixed features (MIXED) and to identify patients at low risk of metastasis who might be spared sentinel lymph node biopsy (SLNB).Experimental Design: Breast tumors (n = 3,023) from the population-based Sweden Cancerome Analysis Network-Breast initiative were profiled by RNA sequencing and linked to clinicopathologic characteristics. Seven machine-learning models present the discriminative ability of N0/N+ in development (n = 2,278) and independent validation cohorts (n = 745) stratified as ER+HER2-, HER2+, and TNBC. Possible SLNB reduction rates are proposed by applying CLINICAL and MIXED predictors. RESULTS: In the validation cohort, the MIXED predictor showed the highest area under ROC curves to assess nodal metastasis; AUC = 0.72. For the subgroups, the AUCs for MIXED, CLINICAL, and GEX predictors ranged from 0.66 to 0.72, 0.65 to 0.73, and 0.58 to 0.67, respectively. Enriched proliferation metagene and luminal B features were noticed in node-positive ER+HER2- and HER2+ tumors, while upregulated basal-like features were observed in node-negative TNBC tumors. The SLNB reduction rates in patients with ER+HER2- tumors were 6% to 7% higher for the MIXED predictor compared with the CLINICAL predictor accepting false negative rates of 5% to 10%. CONCLUSIONS: Although CLINICAL and MIXED predictors of nodal metastasis had comparable accuracy, the MIXED predictor identified more node-negative patients. This translational approach holds promise for development of classifiers to reduce the rates of SLNB for patients at low risk of nodal involvement.