Developing And Applying Biologically Plausible Statistical Models For Normal And Non-normal Family Data
Funder
National Health and Medical Research Council
Funding Amount
$339,700.00
Summary
Although molecular and computing advances have enabled more detailed investigations of inherited diseases and the ability to fit realistic statistical models to these data, limitations still exist when analysing family data. Often only basic statistical analyses are performed, due to the lack of understanding of complexities within the data and-or inability of researchers to fit appropriate statistical models. These factors have hampered the search for genes and environmental factors influencing ....Although molecular and computing advances have enabled more detailed investigations of inherited diseases and the ability to fit realistic statistical models to these data, limitations still exist when analysing family data. Often only basic statistical analyses are performed, due to the lack of understanding of complexities within the data and-or inability of researchers to fit appropriate statistical models. These factors have hampered the search for genes and environmental factors influencing common diseases. This project aims to develop novel, biologically realistic statistical models for investigation of common, complex diseases, such as heart disease and cancer, in families. These models will incorporate both measured and unmeasured genetic and environmental factors, and will be applicable to both normally distributed and non-normally distributed traits. Model fitting will use computer-intensive simulation techniques. Application of the models to data from two large pre-existing studies of international renown, the Victorian Family Heart Study and the Australian Prostate Cancer Family Study, will enable a better understanding of the genetic and environmental factors influencing heart disease and cancer. The models will also be applicable to many other studies of diseases which use data from families, and allow more accurate and useful information to be obtained from data. Software will also be made freely available to other researchers. This will ultimately translate into better outcomes from familial genetic research, and eventually, better prevention, detection, and treatment of the diseases.Read moreRead less
Novel Statistical Methods For The Analysis Of Meausred Genetic And Environmental Risk Factors In Twin Studies
Funder
National Health and Medical Research Council
Funding Amount
$478,314.00
Summary
Studies on twins are an important way to determine whether the risk of disease is likely to be influenced by genetic factors but have traditionally focussed on unmeasured factors. New epidemiological studies measure thousands of genetic variants on many participants. This project will extend methods for analysing data within and between twin pairs to determine whether risk factors are likely to be causal and therefore should be the subject of further designed studies based on intervention.
Goodness-of-fit Testing And Extensions Of Relative Risk Models
Funder
National Health and Medical Research Council
Funding Amount
$380,558.00
Summary
Information about the health consequences of exposure to causal factors is obtained from mathematical models of observed data. Relative risk models are recommended for observations over time on a cohort of subjects, but it is not known how best to assess the adequacy of such models or whether they can be applied to ordered outcomes or multiple measurements on the same individuals. These research aims to address those issues, and thereby to increase the practical usefulness of these models.
Statistical Analyses Of Breast Cancer Risks For Australian BRCA1 And BRCA2 Mutation Carriers
Funder
National Health and Medical Research Council
Funding Amount
$424,628.00
Summary
About 10 years ago two genes, called BRCA1 and BRCA2, were discovered. The normal function of these genes is to prevent breast and other cancers from developing. All people have two copies of each gene, one inherited from their mother and one from their father. Women who have inherited a fault in one copy are at increased risk of breast and ovarian cancer. There has been considerable controversy about what their actual cancer risks are, especially about how those risks might depend on their age. ....About 10 years ago two genes, called BRCA1 and BRCA2, were discovered. The normal function of these genes is to prevent breast and other cancers from developing. All people have two copies of each gene, one inherited from their mother and one from their father. Women who have inherited a fault in one copy are at increased risk of breast and ovarian cancer. There has been considerable controversy about what their actual cancer risks are, especially about how those risks might depend on their age. We have already conducted studies on this and have developed the necessary statistical methods to address these issues by analysing data from the families in which there are faulty genes. In this study we propose to use two large Australian studies, one of families with multiple-cases of breast cancer (Kathleen Cuningham Consortium for Research on Familial Breast Cancer; kConFab) and the other of the families of women with breast cancer chosen, irrespective of their family cancer histories, through the Victorian and NSW Cancer Registries (Australian Breast Cancer Family Study; ABCFS). A large amount of work has already been conducted to identify these families and test them for faults in BRCA1 and BRCA2. There are over 350 families who carry faults, making this one of the largest studies of its type in the world. We will check the cancer histories of these families and determine which members have, or are likely to have, inherited a faulty gene. We will then estimate the breast and ovarian cancer risks accurately, and with much more precision, than has been done previously. We will also use these large datasets to develop a simple method to identify which Australian women are most likely to carry a fault in BRCA1 or BRCA2, based on their personal and family cancer histories. This study will assist genetic counsellors inform Australian women who consider mutation testing for BRCA1 and BRCA2 about their cancer risks, and help make breast cancer genetics more cost effective.Read moreRead less
Fast flexible feature selection for high dimensional challenging data. The project aims to provide new frameworks for fast flexible feature selection and appropriate modelling of heterogeneous data through structural varying-coefficient regression models. The outcomes will be a series of new statistical methods and concepts enabling more powerful modelling of complex bioscience data. The project will create the science for building reliable statistical models taking model uncertainty into accoun ....Fast flexible feature selection for high dimensional challenging data. The project aims to provide new frameworks for fast flexible feature selection and appropriate modelling of heterogeneous data through structural varying-coefficient regression models. The outcomes will be a series of new statistical methods and concepts enabling more powerful modelling of complex bioscience data. The project will create the science for building reliable statistical models taking model uncertainty into account, impacting how results will be interpreted, and with accompanying software. This will be a significant improvement in the assessment of model confidence in the food and health research priority areas including areas such as meat science, Huntington’s disease, and kidney transplantation.Read moreRead less
I am an NHMRC Australia Fellow and mathematical statistician by training, specializing in the design and analysis of family and twin studies. I lead or co-lead large international molecular, environmental, genetic and analytic epidemiology family resources for studying breast, bowel and other cancers. My vision is realise the full potential of these studies to improve the health and well-being people at increased familial or genetic risk of these diseases.