Project offerings 2018

Click on the supervisors name for a description of the projects they are offering.

Projects will be added over the coming weeks.

Supervisor

Project/s

Ralph Holz

Blockchain and network security projects

List of projects

Ashnil Kumar

Predicting transcription factor binding sites in gene sequence data with deep learning

Development of a computer aided diagnosis (CAD) technique for early detection of melanoma

 

Projects supervised by Ashnil Kumar

Predicting transcription factor binding sites in gene sequence data with deep learning
Ultrafast sequencing (ChIP-seq) allows genome-wide profiling of transcription factor (TF) binding sites, the locations where proteins can bind to DNA and regulate the expression of the genes. Sophisticated computational algorithms are required to accurately identify TF binding sites from massive amounts of sequencing data. Deep learning methods have demonstrated success for many bioinformatics applications. In this project, we aim to develop and apply deep learning models to predict TF binding sites by integrating ChIP-seq data with other biological knowledge. This project will allow you the opportunity to adapt, develop, and apply deep learning algorithms to solve a key biological problem. You will get involved in all aspects of the development including algorithm design, implementation, and evaluation.

Skills: Programing skills in C/C++/Python. Knowledge of machine learning concepts will be helpful.

Supervisors: Dr Ashnil Kumar (School of Information Technologies) and Dr Pengyi Yang (School of Mathematics and Statistics).

Development of a computer aided diagnosis (CAD) technique for early detection of melanoma
TheDermatologydepartment at Westmead Hospital is following patients that are at a high risk of developing melanoma with a new imaging modality called Sequential Digital Dermoscopy Imaging (SDDI), which involves full body digital photography to examine the changes in melanoma over time. However, automated methods for skin lesion detection, tracking, and classification are challenging because of variation in the size, shape, and colour of the skin lesions, as well as the differences in illumination and photography angle.This project will allow you to opportunity to build a novel CAD system that will address these challenges using state-of-the-art machine learning technologies.

Skills: Programing skills in C/C++/Python. Knowledge of machine learning concepts will be helpful.

Supervisors: Dr Ashnil Kumar , A/Prof Jinman Kim (School of Information Technologies) and A/Prof Pablo Fernandez-Penas, Dr Marina Ali (Westmead Hospital)