scholarly journals A cell-to-patient machine learning transfer approach uncovers novel basal-like breast cancer prognostic markers amongst alternative splice variants

BMC Biology ◽  
2021 ◽  
Vol 19 (1) ◽  
Author(s):  
Jean-Philippe Villemin ◽  
Claudio Lorenzi ◽  
Marie-Sarah Cabrillac ◽  
Andrew Oldfield ◽  
William Ritchie ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Cell Lines ◽  
Cell Invasion ◽  
Triple Negative ◽  
Splice Variants ◽  
Breast Cancer Cell Lines ◽  
Learning Approach ◽  
Machine Learning Approach ◽  
Alternative Splice Variants

Abstract Background Breast cancer is amongst the 10 first causes of death in women worldwide. Around 20% of patients are misdiagnosed leading to early metastasis, resistance to treatment and relapse. Many clinical and gene expression profiles have been successfully used to classify breast tumours into 5 major types with different prognosis and sensitivity to specific treatments. Unfortunately, these profiles have failed to subclassify breast tumours into more subtypes to improve diagnostics and survival rate. Alternative splicing is emerging as a new source of highly specific biomarkers to classify tumours in different grades. Taking advantage of extensive public transcriptomics datasets in breast cancer cell lines (CCLE) and breast cancer tumours (TCGA), we have addressed the capacity of alternative splice variants to subclassify highly aggressive breast cancers. Results Transcriptomics analysis of alternative splicing events between luminal, basal A and basal B breast cancer cell lines identified a unique splicing signature for a subtype of tumours, the basal B, whose classification is not in use in the clinic yet. Basal B cell lines, in contrast with luminal and basal A, are highly metastatic and express epithelial-to-mesenchymal (EMT) markers, which are hallmarks of cell invasion and resistance to drugs. By developing a semi-supervised machine learning approach, we transferred the molecular knowledge gained from these cell lines into patients to subclassify basal-like triple negative tumours into basal A- and basal B-like categories. Changes in splicing of 25 alternative exons, intimately related to EMT and cell invasion such as ENAH, CD44 and CTNND1, were sufficient to identify the basal-like patients with the worst prognosis. Moreover, patients expressing this basal B-specific splicing signature also expressed newly identified biomarkers of metastasis-initiating cells, like CD36, supporting a more invasive phenotype for this basal B-like breast cancer subtype. Conclusions Using a novel machine learning approach, we have identified an EMT-related splicing signature capable of subclassifying the most aggressive type of breast cancer, which are basal-like triple negative tumours. This proof-of-concept demonstrates that the biological knowledge acquired from cell lines can be transferred to patients data for further clinical investigation. More studies, particularly in 3D culture and organoids, will increase the accuracy of this transfer of knowledge, which will open new perspectives into the development of novel therapeutic strategies and the further identification of specific biomarkers for drug resistance and cancer relapse.

scholarly journals A cell-to-patient machine learning transfer approach uncovers novel basal-like breast cancer prognostic markers amongst alternative splice variants

2020 ◽  
Author(s):  
Jean-Philippe Villemin ◽  
Claudio Lorenzi ◽  
Andrew Oldfield ◽  
Marie-Sarah Cabrillac ◽  
William Ritchie ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Cell Lines ◽  
Cell Invasion ◽  
Triple Negative ◽  
Splice Variants ◽  
Breast Cancer Cell Lines ◽  
Learning Approach ◽  
Machine Learning Approach ◽  
Alternative Splice Variants

ABSTRACTBackgroundBreast cancer is amongst the 10 first causes of death in women worldwide. Around 20% of patients are misdiagnosed leading to early metastasis, resistance to treatment and relapse. Many clinical and gene expression profiles have been successfully used to classify breast tumours into 5 major types with different prognosis and sensitivity to specific treatments. Unfortunately, these profiles have failed to subclassify breast tumours into more subtypes to improve diagnostics and survival rate. Alternative splicing is emerging as a new source of highly specific biomarkers to classify tumours in different grades. Taking advantage of extensive public transcriptomics datasets in breast cancer cell lines (CCLE) and breast cancer tumours (TCGA), we have addressed the capacity of alternative splice variants to subclassify highly aggressive breast cancers.ResultsTranscriptomics analysis of alternative splicing events between luminal, basal A and basal B breast cancer cell lines identified a unique splicing signature for a subtype of tumours, the basal B, whose classification is not in use in the clinic yet. Basal B cell lines, in contrast with luminal and basal A, are highly metastatic and express epithelial-to-mesenchymal (EMT) markers, which are hallmarks of cell invasion and resistance to drugs. By developing a semi-supervised machine learning approach, we transferred the molecular knowledge gained from these cell lines into patients to subclassify basal-like triple negative tumours into basal A- and basal B-like categories. Changes in splicing of 25 alternative exons, intimately related to EMT and cell invasion such as ENAH, CD44 and CTNND1, were sufficient to identify the basal-like patients with the worst prognosis. Moreover, patients expressing this basal B-specific splicing signature also expressed newly identified biomarkers of metastasis-initiating cells, like CD36, supporting a more invasive phenotype for this basal B-like breast cancer subtype.ConclusionsUsing a novel machine learning approach, we have identified an EMT-related splicing signature capable of subclassifying the most aggressive type of breast cancer, which are basal-like triple negative tumours. This proof-of-concept demonstrates that the biological knowledge acquired from cell lines can be transferred to patients data for further clinical investigation. More studies, particularly in 3D culture and organoids, will increase the accuracy of this transfer of knowledge, which will open new perspectives into the development of novel therapeutic strategies and the further identification of specific biomarkers for drug resistance and cancer relapse.

Small Molecular Leads Differentially Active Against HER2 Positive and Triple Negative Breast Cancer Cell Lines

2019 ◽  
Vol 15 (7) ◽  
pp. 738-742 ◽  
Author(s):  
Adnan Badran ◽  
Atia-tul-Wahab ◽  
Sharmeen Fayyaz ◽  
Elias Baydoun ◽  
Muhammad Iqbal Choudhary
Keyword(s):  
Breast Cancer ◽  
Cancer Cells ◽  
Cell Lines ◽  
Cancer Cell ◽  
Breast Cancer Cell ◽  
Triple Negative ◽  
Cancer Cell Lines ◽  
Breast Cancer Cell Lines ◽  
Cancer Type

Background:Breast cancer is the most prevalent cancer type in women globally. It is characterized by distinct subtypes depending on different gene expression patterns. Oncogene HER2 is expressed on the surface of cell and is responsible for cell growth regulation. Increase in HER2 receptor protein due to gene amplification, results in aggressive growth, and high metastasis in cancer cells.Methods:The current study evaluates and compares the anti-breast cancer effect of commercially available compounds against HER2 overexpressing BT-474, and triple negative MDA-MB-231 breast cancer cell lines.Results:Preliminary in vitro cell viability assays on these cell lines identified 6 lead molecules active against breast cancer. Convallatoxin (4), a steroidal lactone glycoside, showed the most potent activity with IC50 values of 0.63 ± 0.56, and 0.69 ± 0.59 µM against BT-474 and MDA-MB-231, respectively, whereas 4-[4-(Trifluoromethyl)-phenoxy] phenol (3) a phenol derivative, and Reserpine (5) an indole alkaloid selectively inhibited the growth of BT-474, and MDA-MB-231 breast cancer cells, respectively.Conclusion:These results exhibited the potential of small molecules in the treatment of HER2 amplified and triple negative breast cancers in vitro.

scholarly journals A machine learning approach to predict healthcare cost of breast cancer patients

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Pratyusha Rakshit ◽  
Onintze Zaballa ◽  
Aritz Pérez ◽  
Elisa Gómez-Inhiesto ◽  
Maria T. Acaiturri-Ayesta ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Cancer Patients ◽  
Healthcare Cost ◽  
Percentage Error ◽  
Learning Approach ◽  
Early Prediction ◽  
Breast Cancer Patients ◽  
Machine Learning Approach ◽  
Clinical Records

AbstractThis paper presents a novel machine learning approach to perform an early prediction of the healthcare cost of breast cancer patients. The learning phase of our prediction method considers the following two steps: (1) in the first step, the patients are clustered taking into account the sequences of actions undergoing similar clinical activities and ensuring similar healthcare costs, and (2) a Markov chain is then learned for each group to describe the action-sequences of the patients in the cluster. A two step procedure is undertaken in the prediction phase: (1) first, the healthcare cost of a new patient’s treatment is estimated based on the average healthcare cost of its k-nearest neighbors in each group, and (2) finally, an aggregate measure of the healthcare cost estimated by each group is used as the final predicted cost. Experiments undertaken reveal a mean absolute percentage error as small as 6%, even when half of the clinical records of a patient is available, substantiating the early prediction capability of the proposed method. Comparative analysis substantiates the superiority of the proposed algorithm over the state-of-the-art techniques.

scholarly journals Integrative analysis of mRNA and miRNA profiles identifies miR-193 and miR-210 as potential regulatory biomarkers in different molecular subtypes of breast cancer

2020 ◽  
Author(s):  
Adriane Feijo Evangelista ◽  
Renato J Oliveira ◽  
Viviane A O Silva ◽  
Rene A D C Vieira ◽  
Rui M Reis ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cell Proliferation ◽  
Cell Line ◽  
Cell Lines ◽  
Breast Cancer Cell ◽  
Cancer Progression ◽  
Triple Negative ◽  
Molecular Subtypes ◽  
Breast Cancer Cell Lines ◽  
Mcf 7

Abstract Introduction: Breast cancer is the most frequently diagnosed malignancy among women. However, the role of microRNA expression in breast cancer progression is not fully understood. In this study we examined predictive interactions between differentially expressed miRNAs and mRNAs in breast cancer cell lines representative of the common molecular subtypes. Integrative bioinformatics analysis identified miR-193 and miR-210 as potential regulatory biomarkers of mRNA in breast cancer. Several recent studies have investigated these miRNAs in a broad range of tumors, but the mechanism of their involvement in cancer progression has not previously been investigated. Methods: The miRNA-mRNA interactions in breast cancer cell lines were identified by parallel expression analysis and miRNA target prediction programs. The expression profiles of mRNA and miRNAs from luminal (MCF-7, MCF-7/AZ and T47D), HER2 (BT20 and SK-BR3) and triple negative subtypes (Hs578T e MDA-MB-231) could be clearly separated by unsupervised analysis using HB4A cell line as a control. Breast cancer miRNA data from TCGA patients were grouped according to molecular subtypes and then used to validate these findings. Expression of miR-193 and miR-210 was investigated by miRNA transient silencing assays using the MCF7, BT20 and MDA-MB-231 cell lines. Functional studies included, xCELLigence system, ApoTox-Glo triplex, flow cytometry and transwell assays were performed to determine cell proliferation, cytotoxicity, apoptosis, migration and invasion, respectively. Results: The most evident effects were associated with cell proliferation after miR-210 silencing in triple negative subtype cell line MDA-MB-231. Using in silico prediction algorithms, TNFRSF10 was identified as one of the potential downstream targets for both miRNAs. The TNFRSF10C and TNFRSF10D mRNA expression inversely correlated with the expression levels of miR-193 and miR210 in breast cell lines and breast cancer patients, respectively. Other potential regulated genes whose expression also inversely correlated with both miRNAs were CCND1, a mediator on invasion and metastasis, and the tumor suppressor gene RUNX3. Conclusion: In summary, our findings identify miR-193 and miR-210 as potential regulatory miRNA in different molecular subtypes of breast cancer and suggest that miR-210 may have specific role in MDA-MB-231 proliferation. Our results highlight important new downstream regulated targets that may serve as promising therapeutic pathways for aggressive breast cancers.

Sign in / Sign up

Export Citation Format

Share Document