Deep neural network improves the estimation of polygenic risk scores for breast cancer

Deep Neural Network (DNN) stands for multilayered Neural Network (NN) that is capable of progressively learn the more abstract and composite representations of the raw features of the input data received, with no need for any feature engineering. They are advanced NNs having repetitious hidden layers between the initial input and the final layer. The working principle of such a standard deep classifier is based on a hierarchy formed by the composition of linear functions and a defined nonlinear Activation Function (AF). It remains uncertain (not clear) how the DNN classifier can function so well. But it is clear from many studies that within DNN, the AF choice has a notable impact on the kinetics of training and the success of tasks. In the past few years, different AFs have been formulated. The choice of AF is still an area of active study. Hence, in this study, a novel deep Feed forward NN model with four AFs has been proposed for breast cancer classification: hidden layer 1: Swish, hidden layer, 2:-LeakyReLU, hidden layer 3: ReLU, and final output layer: naturally Sigmoidal. The purpose of the study is twofold. Firstly, this study is a step toward a more profound understanding of DNN with layer-wise different AFs. Secondly, research is also aimed to explore better DNN-based systems to build predictive models for breast cancer data with improved accuracy. Therefore, the benchmark UCI dataset WDBC was used for the validation of the framework and evaluated using a ten-fold CV method and various performance indicators. Multiple simulations and outcomes of the experimentations have shown that the proposed solution performs in a better way than the Sigmoid, ReLU, and LeakyReLU and Swish activation DNN in terms of different parameters. This analysis contributes to producing an expert and precise clinical dataset classification method for breast cancer. Furthermore, the model also achieved improved performance compared to many established state-of-the-art algorithms/models.

Download Full-text

Integrating ensemble systems biology feature selection and bimodal deep neural network for breast cancer prognosis prediction

Scientific Reports ◽

10.1038/s41598-021-92864-y ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Li-Hsin Cheng ◽

Te-Cheng Hsu ◽

Che Lin

Keyword(s):

Breast Cancer ◽

Neural Network ◽

Feature Selection ◽

Systems Biology ◽

Ensemble Learning ◽

Microarray Data ◽

Deep Neural Network ◽

Prediction Models ◽

Biological Knowledge ◽

Prognosis Prediction

AbstractBreast cancer is a heterogeneous disease. To guide proper treatment decisions for each patient, robust prognostic biomarkers, which allow reliable prognosis prediction, are necessary. Gene feature selection based on microarray data is an approach to discover potential biomarkers systematically. However, standard pure-statistical feature selection approaches often fail to incorporate prior biological knowledge and select genes that lack biological insights. Besides, due to the high dimensionality and low sample size properties of microarray data, selecting robust gene features is an intrinsically challenging problem. We hence combined systems biology feature selection with ensemble learning in this study, aiming to select genes with biological insights and robust prognostic predictive power. Moreover, to capture breast cancer's complex molecular processes, we adopted a multi-gene approach to predict the prognosis status using deep learning classifiers. We found that all ensemble approaches could improve feature selection robustness, wherein the hybrid ensemble approach led to the most robust result. Among all prognosis prediction models, the bimodal deep neural network (DNN) achieved the highest test performance, further verified by survival analysis. In summary, this study demonstrated the potential of combining ensemble learning and bimodal DNN in guiding precision medicine.

Download Full-text

The importance of Ethnicity: are breast cancer Polygenic Risk Scores ready for women who are not of white European origin?

International Journal of Cancer ◽

10.1002/ijc.33782 ◽

2021 ◽

Author(s):

D. Gareth Evans ◽

Elke M Veen ◽

Helen Byers ◽

Eleanor Roberts ◽

Anthony Howell ◽

...

Keyword(s):

Breast Cancer ◽

Risk Scores ◽

European Origin ◽

Polygenic Risk

Download Full-text

New computer aided diagnostic system using deep neural network and SVM to detect breast cancer in thermography

Quantitative InfraRed Thermography Journal ◽

10.1080/17686733.2021.2025018 ◽

2022 ◽

pp. 1-16

Author(s):

Nabil Karim Chebbah ◽

Mohamed Ouslim ◽

Sorore Benabid

Keyword(s):

Breast Cancer ◽

Neural Network ◽

Deep Neural Network ◽

Diagnostic System ◽

Computer Aided ◽

Detect Breast Cancer

Download Full-text

Polygenic risk, susceptibility genes, and breast cancer over the life course

10.1101/2020.04.17.20069229 ◽

2020 ◽

Cited By ~ 1

Author(s):

Nina Mars ◽

Elisabeth Widén ◽

Sini Kerminen ◽

Tuomo Meretoja ◽

Matti Pirinen ◽

...

Keyword(s):

Breast Cancer ◽

Family History ◽

Clinical Decision Making ◽

Breast Cancer Mortality ◽

Breast Cancer Incidence ◽

Positive Family History ◽

Risk Scores ◽

Limited Information ◽

Polygenic Risk ◽

Fold Enrichment

ABSTRACTPolygenic risk scores (PRS) for breast cancer have potential to improve risk prediction, but there is limited information on their clinical applicability. We set out to study how PRS could help in clinical decision making. Among 99,969 women in the FinnGen study with 6,879 breast cancer cases, the PRS was associated not only with breast cancer incidence but also with a range of breast cancer-related endpoints. Women with a breast cancer PRS above the 90th percentile had both higher breast cancer mortality (HR 2.40, 95%CI 1.82-3.17) and higher risk for non-localized disease at diagnosis (HR 2.94, 95%CI 2.63-3.28), compared to those with PRS <80th percentile. The PRS modified the breast cancer risk of two high-impact frameshift risk variants. Women with the c.1592delT variant in PALB2 (242-fold enrichment in Finland, 263 carriers) and an average PRS (20-80th percentile) had a lifetime risk of breast cancer at 58% (95%CI 50-66%), which increased to 85% (70-100%) with a high PRS (>90th percentile), and decreased to 27% (15-39%) with a low PRS (<20th percentile). Similarly, for c.1100delC in CHEK2 (3.7-fold enrichment; 1,543 carriers), the respective lifetime risks were 27% (95%CI 25-30%), 59% (52-67%), and 18% (13-22%). Among breast cancer cases, a PRS >90th percentile was associated with risk of contralateral breast cancer with HR 1.66 (95%CI 1.24-2.22). Finally, the PRS significantly refined the risk assessment of women with first-degree relatives diagnosed with breast cancer, i.e. the combination of high PRS (>90th percentile) and a positive family-history was associated with a 2.33-fold elevated risk (95%CI 1.57-3.46) compared to a positive family history alone. These findings demonstrate opportunities for a comprehensive way of assessing genetic risk in the general population, in breast cancer patients, and in unaffected family members.

Download Full-text