Ensure you enter your valid MODELLER key via the BioSerf tab.

You input looks like it may be a multiple sequence alignment, please ensure it is in valid fasta format and that all sequences are the same length

Current Projects

• David Jones
My main research interests are in protein structure prediction and analysis, simulations of protein folding, Hidden Markov Model methods, transmembrane protein analysis, machine learning applications in bioinformatics, de novo protein design methodology, and genome analysis including the application of intelligent software agents. New areas of research include the use of high throughput computing and very large scale machine learning for bioinformatics applications, analysis and prediction of protein disorder, expression data analysis and the analysis and prediction of protein function and protein-protein interactions using deep learning techniques. Over the years I have authored a number of widely-used bioinformatics tools such as PSIPRED, GenTHREADER, MEMSAT and DISOPRED.
• Daniel Buchan
PSIPRED Website: A complete ground up rebuild of our website and server infrastructure http://bioinf.cs.ucl.ac.uk/psipred_beta/ BioD3 : A library of functions for drawing protein annotation diagrams on the web https://github.com/psipred/biod3 Analystics Automated: A lightweight, workflow management framework for delivering Data Science analyses over the web. https://analyticsautomated.github.io/
BioD3: A library of functions for drawing protein annotation diagrams on the web https://github.com/psipred/biod3
Analystics Automated: A lightweight, workflow management framework for delivering Data Science analyses over the web. https://analyticsautomated.github.io/
• Domenico Cozzetto
BBSRC Responsive mode grant: “New Developments of Large-scale Automatic Protein Function Prediction using Graphical Learning Techniques”
Surveys of public resources show that functional information is still completely missing for a considerable fraction of known proteins and is clearly incomplete for an even larger portion. Moreover, these estimates do not include metagenomics sequences, which pose even tougher challenges to existing functional annotation tools. Bioinformatics methods have long made use of very diverse data sources alone or in combination to predict protein function, with the understanding that different data types help elucidate complementary biological roles. in fact, the evaluation results of recent community-wide challenges in the field of protein function prediction have actually shown that the most effective methods integrate different data sources.
This project aims at improving the integrative function prediction system that we tested at CAFA and that was ranked at either the top or near the top across a range of benchmarks and evaluation metrics. The main objectives are: (i) making better use of existing sources of information, by studying how informative each data source can be relative to a functional category; (ii) adding gene expression profiles and protein-protein interaction network data to make more confident biological process assignments; (iii) exploring new ways of combining component predictions into a single unified probabilistic framework, employing graphical machine learning approaches; and (iv) delivering user-friendly Web tools.
• Rai Fa
Dr Rui Fa is working on the project funded by Elsevier, which is a world leading information analytics company. One goal of the project is to improve current protein function prediction methods and analyse the value of protein function predictions in the scope of drug discovery. Another goal of the project is to evaluate how much the predictions are improved by using Elsevier Pathway Studio database of biological relationships. The project aims to leverage both academic and industrial resources to prioritize potentially promising drug targets. Dr Fa's current research focuses on protein function prediction using machine learning methods, particularly deep learning techniques.
• Shaun Kandathil
ProCovar: Methods and applications of covariation in protein sequence alignments
Proteins play many important roles in the body's cells. This array of functions is made possible by the diverse three-dimensional structures that these molecules adopt. Obtaining structural information about proteins in the 'wet' laboratory is expensive, time-consuming, and doesn't always work. On the other hand, obtaining the sequence of amino acids in a given protein is much easier. Many researchers have therefore taken to trying to predict the three-dimensional structures of proteins computationally. Recently, it has been shown that the accuracy of such predictions can be greatly improved if one knows or can predict beforehand which amino acid pairs will be in close contact in the structure. These contacting residue pairs can be inferred by looking at closely related sequences of a given protein and looking for patterns in the way the sequences change during evolution. My current research is focused on formulating and improving techniques for protein contact prediction. I am using cutting-edge machine learning methods such as deep learning, which have recently been shown to excel at such complex pattern-recognition tasks. I will also be applying similar methods to related problems in protein structure, and protein-protein and protein-nucleic acid interactions. My project is funded by the European Research Council.
• Cen Wan
Project title: BBSRC Flagship Strategic LoLa Drosophila Development Interactome Project
Project description: This project aims to quantify protein dynamics during embryonic development of Drosophila melanogaster. The specific focus of UCL Bioinformatics group is to develop novel machine learning-based approaches for predicting changes in gene function and changes in the protein-protein network. We also aim to develop novel machine learning methods to investigate the new hypotheses are generated across the project as a whole.

Completed Projects

An informatics platform for proteomics using Grid-based technologies
Functional and structural resources for bioinformatics
Information extraction for biological research
A European virtual institute for genome annotation
Fully automated distributed pipeline for large-scale structural and functional annotation
Bioinformatics for Stem Cell Transcriptics
Software agent based genome annotation