DeepInsight on YouTube
Video Explanation on DeepInsight::
- 2021: Ms Wafaa Wardah: Gold Medal and Prize for the most outstanding Master of Science thesis, USP.
- 2019: Dr Shiu Kumar: Vice-Chencellor's Prize for Best Student Research, USP.
- 2019: Dr Shiu Kumar: The Vice-Chancellor's Award for Research Excellence 2019 for Higher Degree by Research, FNU.
- 2019: Dr Ronesh Sharma: The Vice-Chancellor's Award for Research Excellence for Early Career Researcher, FNU
- 2016: Mr Gaurav Raicar: Vice-Chancellor's Prize for the Best Student Research, MSc for publishing in A* ranked journal
- 2015: Mr Harsh Saini: Vice-Chancellor's Prize for the Best Student Research, MSc for publishing in A* ranked journal
- 2013: Dr Alok Sharma: Vice-Chancellor's Prize for Best Research Output
Covid-19 End Date Prediction
|Forecast of end dates for 15 countries||
|Countries||Covid-19 free forecast|
|New Zealand||4-Jan - 3-Mar 2021|
|Australia||16-Jan - 23-Feb 2021|
|USA||20-Dec-21 - 11-May, 2022|
|France||12-Mar - 4-Jun, 2021|
|Germany||19-Feb - 30-Aug, 2021|
|Italy||4-Feb - 29-Apr, 2021|
|Russia||22-Mar - 10-Oct, 2022|
|Spain||22-Mar - 30-Jun, 2021|
|UK||26-Mar - 23-Aug, 2021|
|Mexico||5-Apr - 10-Jul, 2021|
|Japan||26-Jul - 11-Dec, 2021|
|India||29-Mar - 17-Jul, 2021|
|Brazil||17-May - 11-Aug, 2021|
|Turkey||1-Apr - 3-Aug, 2021|
|Iran||26-Jan - 2-May, 2021|
*Last updated: 11-Nov-2020.
Paper related to forecasting covid-19 end date is under review.
- Harsh Saini, MSc, Exploring techniques for optimal feature and classifier selection for protein modeling, function, and fold recognition.
- Gaurav Raicar, MSc, Exploring features of protein sequences for its fold recognition and structural class prediction.
- Ronesh Sharma, PhD, Protein fold recognition, structural class prediction and MoRFs detection using computational intelligent methodologies.
- Shiu Kumar, PhD, EEG signal classification and its application to brain computer interface system using computational intelligent techniques.
- Abel Chandra, PhD, Clustering of single-cell datasets and classification of protein sequences using computationally-intelligent techniques (in preparation).
- Edwin Vans, PhD, Single-cell clustering and applications (continue).
- Vineet Singh, MSc, Accurate identification of lysine pupylation sites and its analysis in prokaryotic proteins through efficient computational techniques (in preparation).
- Hamendra Reddy, MSc,Feature engineering and exploration of machine learning tools for the prediction of glycation and sumoylations PTMs in proteins.
- Wafaa Wardah, MSc, A deep learning approach towards protein-peptide binding site prediction.
PhD Project Topics
Projects with Dr Alok Sharma
Students can enrol at UNSW Sydney or USP depending on the scholarship.
PhD Project 1: Bayesian deep learning for protein function detection
- Bayesian inference via Markov Chain Monte Carlo (MCMC) methods provide a probabilistic approach for training neural networks. Parallel tempering MCMC can feature parallel computing with enhanced exploration and exploitation capabilities that make them suitable for deep learning such as LSTMs and convolutional neural networks. Bayesian deep learning addresses the limitations of deep canonical learning by providing rigorous uncertainty quantification in modelling and predictions. This project applies advanced Bayesian deep learning methods for problems for protein function detection
PhD Project 2: Bayesian interence for MoRFs and protein peptide interactions
- Bayesian inference is typically implemented using Markov Chain Monte Carlo (MCMC) that sample from the posterior distribution to estimate and quantify the uncertainty of unknown parameters of interest. These unknown parameters are a challenge in models in the area of bioinformatics that deal with large datasets. Parallel tempering MCMC features parallelism with enhanced exploration and exploitation capabilities and hence can be applied to computationally expensive problems with the power of parallel computing. In this project, we use advanced Bayesian inference methods to estimate the model parameters in molecular recognition of features (MoRFs) in protein sequence and protein-peptide interaction.