Loading...

Cancer Prediction Using cfDNA Methylation Patterns With Deep Learning Approach

Mahdavi, Fatemeh | 2023

86 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56038 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Soleymani Baghshah, Mahdieh
  7. Abstract:
  8. Liquid biopsy includes information about the progress of the tumor, the effectiveness of the treatment and the possibility of tumor metastasis. This type of biopsy obtains this information by doing diagnosis and enumerating genetic variations in cells and cell-free DNA (cfDNA). Only a small fraction of cfDNA which might be free circulation tumor DNA (ctDNA) fragments, has mutations and is usually identified by epigenetic variations. On the other hand, the use of liquid biopsy has decreased, and tumors in the final stages are often untreatable due to the low accuracy in prediction of cancer. In this research, the aim is to predict cancer using cfDNA methylation patterns. We obtain these patterns using DNase data of the interest cancer. Then, we can find possible positions in the set of genes associated with cfDNA using DNA methylation data. So, we will be able to extract DNA pseudo-patterns without requiring the cancer cells themselves. Then, we proposed an approach in order to predict cancer using cfDNA methylation patterns data. This approach is based on deep learning methods and its purpose is to receive methylation data and learn the patterns within them. We design a convolution neural network with residual connections so that it can predict the probability of having cancer using cfDNA methylation patterns obtained from Gene Expression Omnibus (GEO) experiments using the "fine-tuning" technique. At last, we tried various experiments and methods of implementing of the proposed network using cfDNA methylation data and then we selected the best one
  9. Keywords:
  10. Cell Free Deoxyribonucleic Acid (cfDNA)Biomarker ; Cancer ; Deep Learning ; Convolutional Neural Network ; Epigenetic ; DNA Methylation ; Cancer Prediction

 Digital Object List

 Bookmark

...see more