Abstract 2671
Background
Homeobox (HOX) family consists of 39 genes which act as master regulators in embryonic development. Each of the genes is also known to play key roles in progression of breast cancer, including epithelial to mesenchymal transition, tumor angiogenesis and endocrine therapy resistance. Although there are numerous reports on individual HOX genes and cancer, none of them have comprehensively analyzed the whole gene family. Since HOX genes strongly coordinate within the family during the embryonic period, we considered that the analysis of the whole HOX family is also indispensable in breast cancer.
Methods
We collected 702 breast cancer data from four publicly available array datasets (GSE11121, GSE7390, GSE3494, GSE2990) and performed unsupervised hierarchal clustering into two clusters by the expression of HOX genes. We constructed model formulas for cluster prediction by dividing the samples into learning and validation groups. We used three machine learning methods: support-vector machine (SVM), neural network and Bayes. The model formulas were validated by validation samples. We also used 512 TCGA breast cancer data to calculate covariations of the genes in breast cancer.
Results
By the clustering of four array datasets, the DFS of the two clusters in PAM50-classified luminal B patients were statistically different (p = 0.016), and the gene ontology analysis revealed that the Wnt pathway was activated in the poor prognostic cluster. All cluster prediction models for luminal B sample achieved accuracies of over 90%. From TCGA breast cancer data, we found that HOX genes covariate the most with other HOX genes, especially within the chromosomally proximal groups.
Conclusions
Comprehensive analysis of the whole HOX family lead to the prediction of luminal B breast cancer prognosis. Considering that Wnt signaling controls HOX genes during the embryonic stage, we suppose a Wnt pathway activated, poor prognostic subgroup in luminal B breast cancer which can be identified by the expression of HOX genes. The cluster prediction model by machine learning was acceptable for its future adaptation in clinical settings. We also proved that HOX genes strongly covariate within the gene family in cancer, not only during the embryonic stage.
Clinical trial identification
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Has not received any funding.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
5517 - Molecular fingerprinting in breast cancer (BC) screening using Quantum Optics (QO) technology combined with an artificial intelligence (AI) approach applying the concept of “molecular profiles at n variables (MPnV)”: a prospective pilot study.
Presenter: Jean-Marc Nabholtz
Session: Poster Display session 3
Resources:
Abstract
2152 - Inferring the correlation between incidence rates of melanoma and the average tumor-specific epitope binding ability of HLA class I molecules in different populations
Presenter: Istvan Miklos
Session: Poster Display session 3
Resources:
Abstract
4382 - Thermal Liquid Biopsy as a Valuable Tool in Lung Cancer Screening Programs
Presenter: Alberto Rodrigo
Session: Poster Display session 3
Resources:
Abstract
2465 - Towards a screening test for cancer by circulating DNA analysis
Presenter: Rita Tanos
Session: Poster Display session 3
Resources:
Abstract
3788 - Evaluation of a successful launch of the MammaPrint and BluePrint NGS kit
Presenter: Leonie Delahaye
Session: Poster Display session 3
Resources:
Abstract
3863 - Analysis of prognostic factors on overall survival in elderly women treated for early breast cancer using data mining and machine learning
Presenter: Pierre Heudel
Session: Poster Display session 3
Resources:
Abstract
1993 - Circulating tumor cell detection in epithelial ovarian cancer using dual-component antibodies targeting EpCAM and FRα
Presenter: Na Li
Session: Poster Display session 3
Resources:
Abstract
4281 - CEUS of the breast: Is it feasible in improved performance of BI-RADS evaluation of critical breast lesions?——A multi-center prospective study in China
Presenter: Jun Luo
Session: Poster Display session 3
Resources:
Abstract
2268 - Classification of abnormal findings on ring-type dedicated breast PET for detecting breast cancer
Presenter: Shinsuke Sasada
Session: Poster Display session 3
Resources:
Abstract
4035 - Prediction of benign and malignant breast masses using digital mammograms texture features
Presenter: Cui Yanhua
Session: Poster Display session 3
Resources:
Abstract