scholarly journals A Roadmap towards Breast Cancer Therapies Supported by Explainable Artificial Intelligence

2021 ◽  
Vol 11 (11) ◽  
pp. 4881
Author(s):  
Nicola Amoroso ◽  
Domenico Pomarico ◽  
Annarita Fanizzi ◽  
Vittorio Didonna ◽  
Francesco Giotta ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Artificial Intelligence ◽  
Dimensional Reduction ◽  
Molecular Subtype ◽  
Machine Learning Techniques ◽  
Cancer Therapies ◽  
Breast Cancer Patients ◽  
Design Data ◽  
Dimensional Reduction Method ◽  
Explainable Artificial Intelligence

In recent years personalized medicine reached an increasing importance, especially in the design of oncological therapies. In particular, the development of patients’ profiling strategies suggests the possibility of promising rewards. In this work, we present an explainable artificial intelligence (XAI) framework based on an adaptive dimensional reduction which (i) outlines the most important clinical features for oncological patients’ profiling and (ii), based on these features, determines the profile, i.e., the cluster a patient belongs to. For these purposes, we collected a cohort of 267 breast cancer patients. The adopted dimensional reduction method determines the relevant subspace where distances among patients are used by a hierarchical clustering procedure to identify the corresponding optimal categories. Our results demonstrate how the molecular subtype is the most important feature for clustering. Then, we assessed the robustness of current therapies and guidelines; our findings show a striking correspondence between available patients’ profiles determined in an unsupervised way and either molecular subtypes or therapies chosen according to guidelines, which guarantees the interpretability characterizing explainable approaches to machine learning techniques. Accordingly, our work suggests the possibility to design data-driven therapies to emphasize the differences observed among the patients.

scholarly journals Explainable Artificial Intelligence Reveals Novel Insight into Tumor Microenvironment Conditions Linked with Better Prognosis in Patients with Breast Cancer

Cancers ◽  
2021 ◽  
Vol 13 (14) ◽  
pp. 3450
Author(s):  
Debaditya Chakraborty ◽  
Cristina Ivan ◽  
Paola Amero ◽  
Maliha Khan ◽  
Cristian Rodriguez-Aguayo ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Artificial Intelligence ◽  
T Cells ◽  
Tumor Microenvironment ◽  
Cancer Patients ◽  
Immune Cell ◽  
Survival Rates ◽  
Breast Cancer Patients ◽  
Inflection Points ◽  
Explainable Artificial Intelligence

We investigated the data-driven relationship between immune cell composition in the tumor microenvironment (TME) and the ≥5-year survival rates of breast cancer patients using explainable artificial intelligence (XAI) models. We acquired TCGA breast invasive carcinoma data from the cbioPortal and retrieved immune cell composition estimates from bulk RNA sequencing data from TIMER2.0 based on EPIC, CIBERSORT, TIMER, and xCell computational methods. Novel insights derived from our XAI model showed that B cells, CD8+ T cells, M0 macrophages, and NK T cells are the most critical TME features for enhanced prognosis of breast cancer patients. Our XAI model also revealed the inflection points of these critical TME features, above or below which ≥5-year survival rates improve. Subsequently, we ascertained the conditional probabilities of ≥5-year survival under specific conditions inferred from the inflection points. In particular, the XAI models revealed that the B cell fraction (relative to all cells in a sample) exceeding 0.025, M0 macrophage fraction (relative to the total immune cell content) below 0.05, and NK T cell and CD8+ T cell fractions (based on cancer type-specific arbitrary units) above 0.075 and 0.25, respectively, in the TME could enhance the ≥5-year survival in breast cancer patients. The findings could lead to accurate clinical predictions and enhanced immunotherapies, and to the design of innovative strategies to reprogram the breast TME.

scholarly journals Expression of Phosphorylated BRD4 Is Markedly Associated with the Activation Status of the PP2A Pathway and Shows a Strong Prognostic Value in Triple Negative Breast Cancer Patients

Cancers ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 1246
Author(s):  
Marta Sanz-Álvarez ◽  
Ion Cristóbal ◽  
Melani Luque ◽  
Andrea Santos ◽  
Sandra Zazo ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Triple Negative Breast Cancer ◽  
Triple Negative ◽  
Molecular Subtype ◽  
Molecular Target ◽  
Prognostic Impact ◽  
Breast Cancer Patients ◽  
Bet Inhibitors ◽  
Brd4 Inhibition ◽  
Bet Protein

The bromodomain-containing protein 4 (BRD4), a member of the bromodomain and extra-terminal domain (BET) protein family, has emerged in the last years as a promising molecular target in many tumors including breast cancer. The triple negative breast cancer (TNBC) represents the molecular subtype with the worst prognosis and a current therapeutic challenge, and TNBC cells have been reported to show a preferential sensitivity to BET inhibitors. Interestingly, BRD4 phosphorylation (pBRD4) was found as an alteration that confers resistance to BET inhibition and PP2A proposed as the phosphatase responsible to regulate pBRD4 levels. However, the potential clinical significance of pBRD4, as well as its potential correlation with the PP2A pathway in TNBC, remains to be investigated. Here, we evaluated the expression levels of pBRD4 in a series of 132 TNBC patients. We found high pBRD4 levels in 34.1% of cases (45/132), and this alteration was found to be associated with the development of patient recurrences (p = 0.007). Interestingly, BRD4 hyperphosphorylation predicted significantly shorter overall (p < 0.001) and event-free survival (p < 0.001). Moreover, multivariate analyses were performed to confirm its independent prognostic impact in our cohort. In conclusion, our findings show that BRD4 hyperphosphorylation is an alteration associated with PP2A inhibition that defines a subgroup of TNBC patients with unfavorable prognosis, suggesting the potential clinical and therapeutic usefulness of the PP2A/BRD4 axis as a novel molecular target to overcome resistance to treatments based on BRD4 inhibition.

Laboratory indicators predict axillary nodal pathologic complete response after neoadjuvant therapy in breast cancer

2021 ◽  
Author(s):  
Peng Chen ◽  
Tong Zhao ◽  
Zhao Bi ◽  
Zhao-Peng Zhang ◽  
Li Xie ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Multivariate Analysis ◽  
Neoadjuvant Therapy ◽  
Predictive Factors ◽  
Molecular Subtype ◽  
Treatment Options ◽  
Pathologic Complete Response ◽  
Complete Response ◽  
Breast Cancer Patients ◽  
Logistic Analysis

 The purpose was to integrate clinicopathological and laboratory indicators to predict axillary nodal pathologic complete response (apCR) after neoadjuvant therapy (NAT). The pretreatment clinicopathological and laboratory indicators of 416 clinical nodal-positive breast cancer patients who underwent surgery after NAT were analyzed from April 2015 to 2020. Predictive factors of apCR were examined by logistic analysis. A nomogram was built according to logistic analysis. Among the 416 patients, 37.3% achieved apCR. Multivariate analysis showed that age, pathological grading, molecular subtype and neutrophil-to-lymphocyte ratio were independent predictors of apCR. A nomogram was established based on these four factors. The area under the curve (AUC) was 0.758 in the training set. The validation set showed good discrimination, with AUC of 0.732. In subtype analysis, apCR was 23.8, 47.1 and 50.8% in hormone receptor-positive/HER2-, HER2+ and triple-negative subgroups, respectively. According to the results of the multivariate analysis, pathological grade and fibrinogen level were independent predictors of apCR after NAT in HER2+ patients. Except for traditional clinicopathological factors, laboratory indicators could also be identified as predictive factors of apCR after NAT. The nomogram integrating pretreatment indicators demonstrated its distinguishing capability, with a high AUC, and could help to guide individualized treatment options.

scholarly journals Karakteristik Klinikopatologik Pasien Kanker Payudara dengan Metastasis Tulang di RSUP Sanglah pada Tahun 2014 - 2018

e-CliniC ◽  
2019 ◽  
Vol 8 (1) ◽  
Author(s):  
Putu Krishna B. S. Putra ◽  
I Wayan J. Sumadi ◽  
Ni Putu Sriwidyani ◽  
IG Budhi Setiawan
Keyword(s):  
Breast Cancer ◽  
Metastatic Breast Cancer ◽  
Bone Metastasis ◽  
Cancer Patients ◽  
Invasive Carcinoma ◽  
Molecular Subtype ◽  
Metastatic Breast ◽  
Breast Cancer Patients ◽  
Luminal B ◽  
Histopathological Type

Abstract: Breast cancer is the most common cancer in woman. Metastasis often occurs especially to the bones. This study was aimed to determine the characteristics of breast cancer patients with bone metastasis. This was a descriptive study with a cross-sectional design. Samples were 46 breast cancer patients with bone metastasis recorded at Sanglah Hospital from 2014 until 2018. Data of pathological examination archives of Oncology Surgery Division Medical Faculty of Udayana University/Sanglah General Hospital were used to obtain the clinicopathological characteristics of metastatic breast cancer patients based on age, lateralization, histopathological type, and tumor molecular subtype. The results showed that most cases of metastatic breast cancer were aged 40-49 years as many 21 patients (45.7%), minimal difference in lateralization between right breast as many 22 patients (47.8%) and left breast 23 patients (50%). The most common histopathological type was invasive carcinoma of no special type as many 34 patients (73.9%). The most common tumor subtype was the luminal B subtype as many 21 patients (45.7%). In conclusion, most patients of breast cancer with bone metastasis were 40-49 years old, invasive carcinoma of no special type, molecular subtype of luminal B, and no significant difference between lateralization to the right and left breast.Keywords: breast cancer, bone, metastasis, clinicopathological caharacteristics Abstrak: Kanker payudara merupakan jenis kanker yang paling sering dijumpai pada wanita. Metastasis sering terjadi terutama pada tulang. Penelitian ini bertujuan untuk mengetahui karakteristik pasien kanker payudara dengan metastasis tulang di RSUP Sanglah Denpasar. Jenis penelitian ialah deskriptif dengan desain potong lintang. Sampel penelitian ialah 46 pasien kanker payudara dengan metastasis tulang yang tercatat di RSUP Sanglah tahun 2014-2018. Data diambil dari arsip hasil pemeriksaan patologi di Subdivisi Bedah Onkologi, Departemen/Kelompok Staf Medis (KSM) Bedah Fakultas Kedokteran Universitas Udayana (FK UNUD)/RSUP Sanglah untuk mendapatkan karakteristik klinikopatologi pasien kanker payudara metastasis tulang berdasarkan usia, lateralisasi, tipe histopatologik, dan subtipe molekuler tumor. Hasil penelitian menunjukkan kasus terbanyak terjadi pada rentang usia 40-49 tahun sebanyak 21 orang (45,7%), dengan lateralisasi tidak jauh berbeda antara payudara kanan sebanyak 22 orang (47,8) dan kiri sebanyak 23 orang (50%). Tipe histopatologik yang lebih sering ditemukan yaitu invasive carcinoma of no special type sebanyak 34 orang (73,9%). Subtipe molekuler yang paling banyak ditemukan ialah subtipe luminal B sebanyak 21 orang (45,7%). Simpulan penelitian ini pasien kanker payudara dengan metastasis tulang berada pada rentang usia 40-49 tahun, invasive carcinoma of no special type, subtipe molekuler luminal B. dan lateralisasi payudara kanan dan kiri tidak jauh berbeda.Kata kunci: kanker payudara, metastasis, tulang, karakteristik klinikopatologik

scholarly journals VPS52 expression associates with survival in triple negative breast cancer.

2021 ◽  
Author(s):  
Shahan Mamoor
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Triple Negative Breast Cancer ◽  
Triple Negative ◽  
Molecular Subtype ◽  
Breast Cancer Patients ◽  
Primary Tumors ◽  
Free Survival ◽  
Significant Gene ◽  
Vacuolar Protein

We mined published microarray data (1) to understand the most significant gene expression differences in the tumors of triple negative breast cancer patients based on survival following treatment: dead or alive. We observed significant transcriptome-wide differential expression of vacuolar protein sorting 52, encoded by VPS52 when comparing the primary tumors of triple negative breast cancer patients dead or alive. Importantly, VPS52 expression was correlated with recurrence-free survival in basal subtype breast cancer, a molecular subtype sharing significant overlap with triple negative breast cancer. VPS52 may be of relevance as a biomarker or as a molecule of interest in understanding the etiology or progression of triple negative breast cancer.

scholarly journals MAP4K2 expression associates with survival in triple negative breast cancer.

2021 ◽  
Author(s):  
Shahan Mamoor
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Triple Negative Breast Cancer ◽  
Triple Negative ◽  
Molecular Subtype ◽  
Mitogen Activated Protein Kinase ◽  
Breast Cancer Patients ◽  
Primary Tumors ◽  
Mitogen Activated Protein ◽  
Significant Gene

We mined published microarray data (1) to understand the most significant gene expression differences in the tumors of triple negative breast cancer patients based on survival following treatment: dead or alive. We observed significant transcriptome-wide differential expression of mitogen-activated protein kinase kinase kinase kinase 2, encoded by MAP4K2 when comparing the primary tumors of triple negative breast cancer patients dead or alive. Importantly, MAP4K2 expression was correlated with distant metastasis-free survival in basal subtype breast cancer, a molecular subtype sharing significant overlap with triple negative breast cancer. MAP4K2 may be of relevance as a biomarker or as a molecule of interest in understanding the etiology or progression of triple negative breast cancer.

scholarly journals PAX5 expression associates with survival in triple negative breast cancer.

2021 ◽  
Author(s):  
Shahan Mamoor
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Cancer Patients ◽  
Triple Negative Breast Cancer ◽  
Microarray Data ◽  
Triple Negative ◽  
Molecular Subtype ◽  
Breast Cancer Patients ◽  
Primary Tumors ◽  
Significant Gene

We mined published microarray data (1) to understand the most significant gene expression differences in the tumors of triple negative breast cancer patients based on survival following treatment: dead or alive. We observed significant transcriptome-wide differential expression of paired box 5, encoded by PAX5 when comparing the primary tumors of triple negative breast cancer patients dead or alive. Importantly, PAX5 expression was significantly correlated with overall survival in basal subtype breast cancer, a molecular subtype sharing significant overlap with triple negative breast cancer. PAX5 may be of relevance as a biomarker or as a molecule of interest in understanding the etiology or progression of triple negative breast cancer.

scholarly journals GBP5 expression associates with survival in triple negative breast cancer.

2021 ◽  
Author(s):  
Shahan Mamoor
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Triple Negative Breast Cancer ◽  
Triple Negative ◽  
Molecular Subtype ◽  
Breast Cancer Patients ◽  
Primary Tumors ◽  
Significant Gene ◽  
Inflammasome Component ◽  
Guanylate Binding Protein

We mined published microarray data (1) to understand the most significant gene expression differences in the tumors of triple negative breast cancer patients based on survival at time of analysis: dead or alive. The inflammasome component and guanylate-binding protein GBP5 emerged as among the most significant differences, transcriptome-wide, when comparing the primary tumors of triple negative breast cancer patients dead or alive. Importantly, GBP5 expression was significantly correlated with overall survival in basal subtype breast cancer, a molecular subtype sharing significant overlap with triple negative breast cancer. GBP5 may be of relevance as a biomarker or as a molecule of interest in understanding the etiology or progression of triple negative breast cancer.

scholarly journals PD-L2 (PDCD1LG2) expression associates with survival in triple negative breast cancer.

2021 ◽  
Author(s):  
Shahan Mamoor
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Triple Negative Breast Cancer ◽  
Microarray Data ◽  
Triple Negative ◽  
Molecular Subtype ◽  
Breast Cancer Patients ◽  
Primary Tumors ◽  
Programmed Cell Death 1 ◽  
Significant Gene

We mined published microarray data (1) to understand the most significant gene expression differences in the tumors of triple negative breast cancer patients based on survival following treatment: dead or alive. We observed significant transcriptome-wide differential expression of programmed cell death 1 ligand 2, encoded by PDCD1LG2, also known as PD-L2, when comparing the primary tumors of triple negative breast cancer patients dead or alive. Importantly, PD-L2 expression was significantly correlated with overall survival in basal subtype breast cancer, a molecular subtype sharing significant overlap with triple negative breast cancer. PD-L2 may be of relevance as a biomarker or as a molecule of interest in understanding the etiology or progression of triple negative breast cancer.

scholarly journals HES1 expression associates with survival in triple negative breast cancer.

2021 ◽  
Author(s):  
Shahan Mamoor
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Triple Negative Breast Cancer ◽  
Triple Negative ◽  
Molecular Subtype ◽  
Breast Cancer Patients ◽  
Primary Tumors ◽  
Hes1 Expression ◽  
Significant Gene ◽  
Enhancer Of Split

We mined published microarray data (1) to understand the most significant gene expression differences in the tumors of triple negative breast cancer patients based on survival following treatment: dead or alive. We observed significant transcriptome-wide differential expression of hairy and enhancer of split 1, encoded by HES1 when comparing the primary tumors of triple negative breast cancer patients dead or alive. Importantly, HES1 expression was significantly correlated with overall survival in basal subtype breast cancer, a molecular subtype sharing significant overlap with triple negative breast cancer. HES1 may be of relevance as a biomarker or as a molecule of interest in understanding the etiology or progression of triple negative breast cancer.

Sign in / Sign up

Export Citation Format

Share Document