The Centre for Bioinformatics, Biomarker Discovery and Information-Based Medicine is committed to shortening the process of obtaining novel discoveries to achieve distinctively better outcomes in clinical practice and translational individualised medicine

Priority Research Centre for


The Centre for Bioinformatics, Biomarker Discovery and Information-Based Medicine (CIBM) brings together academics from the Faculty of Health and the Faculty of Engineering and Built Environment and works in collaboration with the Hunter Medical Research Institute's Information Based Medicine Program. The Centre draws together the disciplines of bioinformatics, and molecular and genetic analysis with clinical information and population data analysis.

Researchers in the Centre utilise computer technology and mathematical methods to extract meaningful information from vast amounts of clinical and molecular data to identify disease-related genetic patterns. The aim is to inform the development of patient-tailored treatment to a host of diseases which are influenced by genetic aspects, such as breast cancer, prostate cancer, melanoma, schizophrenia and potential applications for chronic obstructive pulmonary disease.

Research themes

  • Large-scale data analytics
  • Predictive analytics
  • Artificial intelligence and pattern recognition
  • Supercomputing and multi-objective optimisation
  • Biotechnology and "-omics" (genomics, proteomics, metabolomics)

Cancer Treatment: An Illustrative Example of a Real World Application

There are many challenging issues facing medical practice and none more so than in the field of cancer treatment. Currently, whilst a set of therapies exist for people diagnosed with cancer, some treatments have a broader spectrum of use and others are designed to target specific types of the disease. In addition, those therapies will typically work on some people, while for others they might not work at all. The primary goal is to provide patients with an optimal treatment to maximise their chances of having a good outcome. The Centre's focus on personalised medicine, which individualises patient treatment, maximises benefits and minimises adverse side effects, and potentially saves the healthcare industry millions of dollars in the future.

Professor Pablo Moscato: Unlocking the power of personalised medicine

Through the application of Computer Science and the development of new algorithms, Professor Pablo Moscato and his research team are driving the push for personalised medicine. His team uses mathematical methods to interpret genetic data for diseases such as melanoma, prostate, breast and brain cancer. Analysis of these diseases at previously unseen levels allows the identification of not only disease subtypes but also biomarkers that track the progression of cancer or neurodegeneration.

Computer Science enables researchers to address complex questions posed by 'big data' from across many fields and, in the field of medicine, has the potential to alter treatment methods.

The work of Professor Moscato and his team recently played a vital role in helping European and American scientists in confirming one biomarker as a predictor of neurodegeneration with applications for early detection of Alzheimer's Disease.

A step closer to Alzheimer's blood test

A simple blood test to identify people in the early stages of Alzheimer's Disease is on the horizon thanks to an interdisciplinary team of The University of Newcastle researchers who spent a year studying data from the international Alzheimer's Disease Neuroimaging Initiative, the most comprehensive collection of Alzheimer's data in the world.

The team assessed the levels of 190 proteins in blood from 566 people with either Alzheimer's Disease, mild cognitive impairment or normal cognition. Results of this study have shown that measuring a panel of 11 proteins in blood can provide a predictive test with more than 85 per cent accuracy. Monitoring the change in blood protein levels over time could increase accuracy to above 90 per cent.

Current Alzheimer's Disease diagnosis is based on clinical observations and testing of cognitive capacity and memory loss. The only reliable and accurate biological markers so far identified for early diagnosis require measurement by either expensive procedures such as brain imaging or invasive procedures such as spinal punctures. The current study is a large step towards the development of cheap, non-invasive testing that can facilitate early detection and effective intervention.

A new philosophy: breaking the traditional medicine mould

While there are currently a number of therapies and thousands of drugs that can be used to treat cancer, some treatments have a broad spectrum of use, others are designed to target specific types of the disease, and some will work on certain people, or certain cancers, but not on others. The challenge brought about by the huge number of possible combinations for treatment can be overcome with the use of sophisticated computer analysis. CIBM's methods have shown to be efficient in implicitly screening all possible combinations informed by specific patterns of gene activation. The aim, therefore, is that these methods would later provide patients with the optimal combinatorial drug treatment strategies which would most benefit their molecular individuality.

"Most of the policy that exists today involves patients being given a drug for a disease, where the disease categories and definitions are generally quite broad. New biotechnologies and mathematical classification methods are revealing that they are actually multiple diseases", explains Professor Moscato.

"With cancer, for instance, we are already moving away from the approaches that hope for a 'silver bullet' cure. Databases now boast thousands of drugs that can be used to treat cancers. Only with sophisticated computer analysis can you screen all of the combinations and prioritise those that may be relevant for further investigation."

"In the near future," explains Professor Moscato, "Computer Science and novel biotechnologies may allow for the analysis of the molecular profiles of affected tumours as well as normal cells. This could eventually lead to the automatic determination of which drugs are most effective for individual patients rather than using a lengthy, and potentially painful, trial-and-error process. This revolutionary approach will require the health system to re-establish itself as an adaptive, 'learning from data' business intelligence operation."

Professor Rodney Scott and Professor Pablo Moscato

Despite their differing backgrounds, geneticist Professor Rodney Scott and computer scientist Professor Pablo Moscato share a common purpose. As co-directors of the Centre for Bioinformatics, Biomarker Discover and Information-Based Medicine, they are at the forefront of research directly linking bioinformatics and molecular biology with clinical research practice.

The two eminent researchers were drawn together by the need for more efficient ways of processing and interpreting the mass of genetic research data being collected by medical researchers. There have been huge advances in knowledge and the technology that can be used to identify risk factors associated with disease. The vast amount of data, however, has created a bottleneck as there is so much data that needs to be analysed. Bioinformatics provides a mechanism to reduce the complexity of analysing, managing and interpreting data and subsequently producing new useful knowledge.

Moscato and Scott first collaborated in an ARC Discovery Project which started in 2005. In it, Moscato applied his statistical and computational skills to analyse data associated with the rare genetic disorder Xeroderma Pigmentosum. This is basic science which is necessary to understand the causes of UV ray damage with applications to skin cancer and melanoma research. They joined forces a year later towards establishing a centre of excellence in interdisciplinary research, and the university approved their project which is now the Priority Research Centre for Bioinformatics, Biomarker Discovery and Information-Based Medicine and one of the seven programs of the Hunter Medical Research Institute.

Since that time, University medical and bioinformatics researchers have successfully worked together on interpreting genetic data relating not only to cancer but a range of conditions including stroke, multiple sclerosis, macular degeneration, Alzheimer's disease and lung disease.

Data mining and supercomputing

Among the new techniques targeted at meeting the challenge of data analysis is mathematical modelling and powerful optimisation metaheuristics, in particular 'memetic algorithms' (MAs). This technique was championed by Professor Moscato for more than two decades after he introduced the seminal ideas back in 1989 while at the California Institute of Technology. MAs are currently used in many scientific and engineering fields for large-scale optimisation. In 2013, a report by Thomson Reuters ranked Memetic Computing among the top 10 ranked research fronts in all of the combined areas of Mathematics, Computer Science and Engineering. The selection was done from approximately "8,000 research fronts currently identified".

The CIBM has applied these techniques with great success to the problem of finding structure in a seemingly uninformative amount of data.

Mathematical methods developed in this field are applicable to a large variety of problems in the industrial, commercial and government areas.

The CIBM has assembled a state-of-the-art HPC computing cluster, consisting of a grid of more than 130 cores enhanced by several GPU supercomputing nodes. This allows researchers to tackle huge datasets produced by today's high throughput genomics and proteomics studies.

Data analytics

The Centre for Bioinformatics, Biomarker Discovery and Information-Based Medicine provides a data analytics service for organisations that can help them make better decisions or help prove or disprove existing theories and assumed working hypotheses. CIBM provides world-class expertise and customisable solutions based on state-of-the-art optimisation techniques linked together with innovative data mining and machine intelligence methodologies. 

Data analytics encompasses:

  • Data profiling (a mathematically driven analysis of the quality of the data)
  • Exploratory data analysis (to find new features and attributes of the data)
  • Confirmatory data analysis (a true or false hypothesis test)
  • Identification of associations of interest in the data (selection of characteristics present in the data whose joint presence suggests a higher order characteristic)
  • Path analysis of temporal events (identification of characteristics in time-stamped data)
  • Classification methods
  • Clustering (using state-of-the-art optimisation algorithms to find structures in the data and define mathematical separations between the groups)
  • Predictive analytics. 

Data mining: consumer behaviour analysis

Professor Moscato's research collaborations span all of the University's faculties. He recently worked with the Faculty of Business and Law to analyse online consumer behaviours and online customer brand engagement. Fuelled by the surge of social media platforms and applications, Professor Moscato has proposed methodology for a new, data-driven way of modelling human behaviour. Results of the proposal were published in the esteemed disciplinary journal PLoS ONE in July 2014.


CIBM can act as a solution provider for the purpose of contract research in their domain of expertise and is actively engaging in national and international partnerships. CIBM can offer tailored solutions that can be implemented via collaboration, contract research, government-sponsored linkage grants that could help business partners to develop a common IP portfolio.