Sequence Analysis

Oct 1, 2015
Photo by Miguel Á. Padriñán from Pexels

Working on the development of machine-learning-based approaches to predict a series of protein identities and functions, including bacterial secreted substrates, bacterial virulence factors, phage anti-CRISPR proteins, phage virion proteins and lysine malonylation sites across multiple species. Based on the proposed methodologies, public services and standalone toolkits are developed to maximally facilitate the scientific community.

Machine Learning Web Server Linux/MAC JAVA Python R Perl Perl CGI Distributed Framework
Jiawei Wang
Jiawei Wang
Marie Curie Fellow
EMBO Non-Stipendiary Fellow

My research interests include computational biology, computer science, machine learning and single cell omics.

Related

Publications

AcrHub: an integrative hub for investigating, predicting and mapping anti-CRISPR proteins
Cite Project Project DOI PDF Server User map Dataset Guidance
AcrHub: an integrative hub for investigating, predicting and mapping anti-CRISPR proteins
BastionHub: a universal platform for integrating and analyzing substrates secreted by Gram-negative bacteria
Cite Project Project DOI PDF Server User map Dataset Guidance
BastionHub: a universal platform for integrating and analyzing substrates secreted by Gram-negative bacteria
Component Parts of Bacteriophage Virions Accurately Defined by a Machine-Learning Approach Built on Evolutionary Features
Cite Project Project
DeepVF: a deep learning-based hybrid framework for identifying virulence factors using the stacking strategy
Cite Project Project
Mapping bacterial effector arsenals: in vivo and in silico approaches to defining the protein features dictating effector secretion by bacteria
Cite Project
PaCRISPR: a server for predicting and visualizing anti-CRISPR proteins
A server for predicting and visualizing anti-CRISPR proteins. Predicted anti-CRISPRs can be further explored by interactive data visualizations on anti-CRISPR relationships, highlighting sequence similarity and phylogenetic considerations.
Cite Project DOI PDF Supplementary file Server User map Dataset Guidance
PaCRISPR: a server for predicting and visualizing anti-CRISPR proteins
PeNGaRoo, a combined gradient boosting and ensemble learning framework for predicting non-classical secreted proteins
Cite Project Project
Bastion3: a two-layer ensemble predictor of type III secreted effectors
Cite Project
Computational analysis and prediction of lysine malonylation sites by exploiting informative features in an integrative machine-learning framework
Cite Project Project
Systematic analysis and prediction of type IV secreted effector proteins by machine learning approaches
Cite Project
Systematic analysis and prediction of type IV secreted effector proteins by machine learning approaches
Bastion6: a bioinformatics approach for accurate prediction of type VI secreted effectors
Cite Project DOI PDF Supplementary file Server User map Dataset Guidance
Bastion6: a bioinformatics approach for accurate prediction of type VI secreted effectors
Comprehensive assessment and performance improvement of effector protein predictors for bacterial secretion systems III, IV and VI
Cite Project
POSSUM: a bioinformatics toolkit for generating numerical sequence feature descriptors based on PSSM profiles
Cite Project Project DOI PDF Supplementary file Server User map Standalone toolkit Guidance
POSSUM: a bioinformatics toolkit for generating numerical sequence feature descriptors based on PSSM profiles
SecretEPDB: a comprehensive web-based resource for secreted effector proteins of the bacterial types III, IV and VI secretion systems
Cite Project

Events

Machine learning based prediction and analysis of anti-CRISPR proteins
A talk to introduce our work in machine learning based phage protein analysis.
May 1, 2021 1:00 PM — 1:30 PM School of Mathematics and Statistics, University of Sydney (Online)
Project Project Slides Follow
Machine learning based prediction and analysis of anti-CRISPR proteins