STATISTICAL METHODS FOR CORRELATED AND HIGH-DIMENSIONAL BIOMEDICAL DATA
Lin Xihong, Professor
Harvard University (sch Of Public Hlth)city: Boston country: United States (us)
Grant 4R37CA076404-15 from National Cancer Institute
Abstract: Correlated and high-dimensional data arise frequently in health sciences research, especially in cancer research. Correlated data arise in longitudinal studies and familial studies, while high-dimensional data have emerged in recent years as a consequence of the rapid advance of genomic and proteomic research. We propose in this application to develop nonparametric and semiparametric regression methods for clustered/longitudinal data and high-dimensional genomic and proteomic data. Specifically, we propose to develop (1) the kernel (spline) profile EM method for generalized semiparametric mixed models for clustered/longitudinal data; (2) nonparametric and semiparametric regression models for longitudinal data with dropouts; (3) the mixed model kernel machine method for generalized semiparametric regression models and semiparametric Cox models for the analysis of gene expression pathways and tag single nucleotide polymorphisms (SNPs) within a candidate gene, and the sparse kernel machine (SKM) method for selecting genes and tag SNPs from a large pool of genes or tag SNPs; (4) the joint modeling method using functional wavelet models and generalized semiparametric models for mass spectrometry proteomic data and disease outcomes. Asymptotic properties of the proposed methods will be investigated and simulation studies will be conducted to evaluate their finite sample performance. Efficient numerical algorithms and user-friendly statistical software will be developed, with the goal of disseminating these models and methods to health sciences researchers. In collaboration with biomedical investigators, we will apply the proposed models and methods to several motivating data sets on cancer research and other fields of research
Keywords: Algorithms; anticancer research; Candidate Disease Gene; Collaborations; Computer software; Cox Models; Data; Data Set; Disease Outcome; Dropout; Gene Expression; Gene Pool; Genes; Genomics; Goals; health science research; Health Sciences; Joints; Longitudinal Studies; Mass Spectrum Analysis; Methods; Modeling; Pathway interactions; Performance; Property; Proteomics; Research; Research Personnel; Sampling; simulation; Single Nucleotide Polymorphism; Statistical Methods; user-friendly
Project start date: 1997-12-15
Project end date: 2016-03-31
Budget start date: 1-APR-2011
Budget end date: 31-MAR-2012
4R37CA076404-15 (2011): $292927
Sponsored Links Excellgen http://Excellgen.com
Grants awarded to Lin Xihong
STATISTICAL INFORMATICS FOR CANCER RESEARCH
Lin Xihong, Professor
Harvard University (sch Of Public Hlth)city: Boston country: United States (us)
Grant 5P01CA134294-04 from National Cancer Institute
Abstract: We propose a Program Project, Statistical Informatics in Cancer Research, to tackle a series of problems motivated by the analysis of high dimensional data arising in population-based studies of cancer. This Program Project comprises three research projects and two cores. Project 1 focuses on spatio-temporal modeling of disease count data collected for administrative areas. The specific aims are motivated by problems encountered in epidemiological studies designed to monitor and assess health disparities. Our proposed methods address issues associated with administrative boundaries changing over time, sparse disease counts, spatial confounding, and heavy computational burdens for large data sets. Methods will be applied to data on U.S. breast cancer incidence from three state cancer registries, Boston-area premature mortality, and NCI SEER data. Project 2 is also motivated by spatially-indexed data related to cancer incidence and mortality, but the emphasis is on population surveillance and spatial cluster detection. Three of the specific aims of Project 2 are motivated by the analysis of NCI SEER data and one from a case/control study designed to assess spatial clustering in childhood leukemia. This dataset also includes individual level data on several genetic biomarkers of susceptibility. One sub-aim of this project assesses gene-space interaction by studying whether disease clustering patterns differ according to genetic polymorphisms. Project 3 focuses on methods for the analysis of very high dimensional genomic and proteomic biomarkers. Extensions to spatially indexed genomic data are also considered in Project 3. All of the aims of the three projects are closely integrated with the motivating real world cancer studies in which the investigators are involved. The three projects link thematically through a focus on population-based, observational studies in cancer, as well as technically through the consideration of high-dimensional correlated data (arising from different sources) that require advanced statistical and computing methods. Several specific techniques (e.g. spatio-temporal modeling, penalized likelihoods, False Discovery Rates, hidden Markov models) are shared between two and in some cases all three projects. The two cores consist of an Administrative Core and a Statistical Computing Core. The Administrative Core will coordinate the overall scientific direction and programmatic activities of Program, which will include short courses, a visitor program, dissemination of research results, and an external advisory committee. A Statistical Computing Core will ensure the development and dissemination of open access, good quality, user friendly software designed to implement the statistical methods developed in the Research Projects, which is the final Specific Aim of each of the three projects. The Program Director and Co-Director, Professors Louise Ryan and Xihong Lin, respectively, are internationally known biostatisticians with strong track records of academic administration
Project start date: 2008-09-10
Project end date: 2013-08-31
Budget start date: 1-SEP-2011
Budget end date: 31-AUG-2012
5P01CA134294-04 (2011): $635114
CONFERENCES ON EMERGING STATISTICAL ISSUES IN BIOMEDICAL RESEARCH
Lin Xihong, Professor
Harvard University (sch Of Public Hlth)city: Boston country: United States (us)
Grant 2R13CA124365-06 from National Cancer Institute
Abstract: This is a renewal of the R13 application to continue the very successful annual conference series on Emerging Statistical and Quantitative Issues in Genomic Research in Health Sciences, which has been hosted by the Program in Quantitative Genomics (PQG) at Harvard School of Public Health (HSPH) in the last five years and is open to the whole research community. Modern health sciences are evolving rapidly, driven in large part by the rapid advance of high- throughput biotechnology. This changing landscape has provided researchers in health sciences, especially in cancer and other chronic diseases, with rich opportunities for new discoveries using genetic information to better understand disease biology and etiology and interplay of genes and environment, and to enhance risk prediction and personalized medicine in patient care. While such an "omics" era presents many exciting research opportunities, the explosion of massive information about the human genome presents extraordinary challenges in data processing, integration, analysis and result interpretation. Traditional statistical and computational techniques cannot meet these new demands. There is a critical need to discuss emerging quantitative issues at the forefront of scientific exploration, and to promote development of innovative statistical and quantitative methods to deal with massive high- throughput genomic and ´omics data in basic, population and clinical sciences. In this renewal application, we propose to continue hosting this conference series, where each conference focuses on emerging quantitative research areas of most current genomic research interest and the particular focus will evolve over time. A key feature of the conference series is to provide a timely and interactive platform to engage cross-discipline senior and junior investigators, such as statistical genetists, computational biologists, genetic epidemiologists, molecular biologists, and clinical scientists in cancer and other chronic diseases to critique existing quantitative methods, discuss in-depth emerging statistical and quantitative issues, identify priorities for future research and disseminate results. The 2011 conference is entitled ´´Emerging Statistical and Quantitative Issues in Genomic Medicine." The 2012 conference is on " Beyond the 1000 Genomes Project Sequencing, Complex Traits, and Population." The Conference series is cosponsored by HSPH PQG, the Department of Biostatistics of the HSPH and the Department of Biostatics and Computational Biology of the Dana Farber Cancer Institute. Serious efforts will continue to engage junior researchers, women and minorities in Conference activities. The explosion of massive information about the human genome presents extraordinary challenges in data processing, integration, analysis and result interpretation. An annual conference on Emerging Statistical and Quantitative Issues in Genomic Research in Health Sciences is proposed to continue engaging cross-disciplinary quantitative and subject-matter researchers to critique existing quantitative methods, discuss in-depth emerging statistical and quantitative issues, identify priorities for future research and disseminate results in genomic research in health sciences
Keywords: Accounting; Address; Area; Basic Science; Biology; Biomedical Research; Biometry; Biotechnology; career; Chronic Disease; Clinical; Clinical Sciences; Communities; Complex; Computational Biology; Computational Technique; computerized data processing; Critiques; Dana-Farber Cancer Institute; Data; Development; Discipline; Disease; Environment; Epidemiologist; Etiology; Explosion; Faculty; Fostering; Future; Gene Expression; Genes; Genetic; Genetic Risk; Genome; Genomics; Grant; Health; Health Sciences; high throughput technology; Human; Human Genome; innovation; Interdisciplinary Study; interest; Malignant Neoplasms; medical schools; Medicine; meetings; member; Methods; Minority; Molecular; Nature; novel; Patient Care; Population; Population Sciences; Postdoctoral Fellow; posters; programs; protein metabolite; Public Health Schools; Reproducibility; Research; Research Personnel; Risk; Science; Scientist; Series; Students; symposium; Time; trait; translational medicine; Underrepresented Minority; Validation; Woman
Relevance: The explosion of massive information about the human genome presents extraordinary challenges in data processing, integration, analysis and result interpretation. An annual conference on Emerging Statistical and Quantitative Issues in Genomic Research in Health Sciences is proposed to continue engaging cross-disciplinary quantitative and subject-matter researchers to critique existing quantitative methods, discuss in-depth emerging statistical and quantitative issues, identify priorities for future research and disseminate results in genomic research in health sciences
Project start date: 2006-08-01
Project end date: 2016-08-31
Budget start date: 16-SEP-2011
Budget end date: 31-AUG-2012
PFA/PA: PA-10-071
2R13CA124365-06 (2011): $30000
RESEARCH SUPPORT CORE: ENVIRONMENTAL STATISTICS
Lin Xihong, Professor
Harvard University (sch Of Public Hlth)city: Boston country: United States (us)
Abstract: The Environmental Statistics and Bioinformatics Core will provide cutting edge biostatistical and bioinformatics design and analysis support for all projects. Core faculty are drawn from the Dept. of Biostatistics´s Environmental Statistics Program, the HSPH Program of Quantitative Genomics, the HSPH Bioinformatics Core, the Dept. of Epidemiology, and the Dept. of Environmental Health´s Program in Environmental Epidemiology. Core faculty have a strong history of collaboration and methods development for applications in environmental health research and genetic epidemiology. Specific areas of expertise include nonparametric smoothing, Bayesian methods, spatial statistics, longitudinal data analysis, environmental risk assessment, statistical genetics, bioinformatics, genome-wide association studies, and genes and environment. Students and postdoctoral fellows in Biostatistics will also provide data analysis support as needed. In addition to handling and overseeing statistical design and analysis for all projects, the core will ¿ Advise on data management and ensure that all projects adopt appropriate quality control/quality assurance for data collection, entry, storage and retrieval; ¿ Provide training in statistical methods and supervise doctoral students working on related research projects; ¿ Arrange for workshops, seminars and reading groups to ensure that all program faculty and researchers have access to state of the art statistical methods, programs and techniques related to bioinformatics; ¿ Conduct mission-related statistical research
Keywords: Adopted; Area; Basic Science; Bayesian Method; Bioinformatics; biomarker; Biometry; Case Study; Collaborations; Computer software; Data Analyses; Data Collection; data management; design; Development; Educational workshop; Ensure; Environment; Environmental Epidemiology; Environmental Health; Environmental Risk Factor; Epidemiology; Faculty; Genes; Genetic; genetic epidemiology; genome wide association study; Genomics; Internet; Metals; method development; Methods; Mission; neurodevelopment; Postdoctoral Fellow; pre-doctoral; programs; Public Health Schools; quality assurance; Quality Control; Reading; Recording of previous events; Research; Research Design; Research Personnel; Research Project Grants; Research Support; Retrieval; Risk Assessment; sound; Statistical Methods; statistics; Students; success; Superfund; Techniques; Training; Training and Education; Work
Relevance: The Environmental Statistics and Bioinformatics Core is critical to rigorous study design and analysis of all the projects and ensures the success of the scientific discovery of the Harvard Superfund Center
Budget start date: 1-APR-2011
Budget end date: 31-MAR-2012
5P42ES016454-02_8769 (2011): $279799
STATISTICAL METHODS FOR GENOMICS AND PROTEOMIC DATA IN POPULATION-BASED STUDIES
Lin Xihong, Professor
Harvard University (sch Of Public Hlth)city: Boston country: United States (us)
Abstract: Large-scale genomic, proteomic and other "omic" research has become increasingly important and common for discovering disease genes and "omic" biomarkers for cancer prevention and intervention, and for studying gene-environment interactions in population-based studies. Such high-dimensional "omic" data present fundamental statistical and computational challenges in data analysis and result interpretation. Limited statistical developments have been made on analysis of high-dimensional "omic" data in populationbased studies. Such a methodological shortage limits the speed of using genomic and proteomic data to effectively advance population sciences. The purpose of this proposal is to respond to this need by developing advanced statistical methods in conjunction with other advanced quantitative methods for analysis of high-dimensional genomic and proteomic data arising from population-based studies. The specific aims are (1) To develop regularized estimating equation-based variable selection methods for gene/biomarker discovery in the presence of a large number of SNPs or proteins and in studying gene-environment (space) interactions. The methods are developed for (a) continuous and discrete cross-sectional/case-control data, (b) longitudinal, clustered and spatial data, (c) independent, clustered, and spatial survival data; (2) To develop penalized likelihood-based methods for multiple testing for high-dimensional genomic and proteomic data subject to moderate/high correlation, such as microarrays and proteomic mass-spectrometry data, with the goal of providing higher statistical power and better false discovery rate (FDR) estimation; (3) To develop a suite of tools using contemporary advances in signal processing based on local Fourier analysis to effectively preprocess mass spectrometry (MS) proteomic data; (4) To develop supervised clustering methods for array CGH (aCGH) data to identify aCGH profiles related to survival; (5) To develop efficient user-friendly statistical software that implement these methods with the goal of disseminating them freely to health science researchers. The proposed methods will be applied to data from the motivating Harvard/MGH lung cancer genetic susceptibility and progression studies, the Harvard/MGH lung cancer proteomic study, the DFCI lung cancer LBK mutation micorarray study, the longitudinal HIV codon mutation study, and the Harvard/MGH brain tumor aCGH study. This project integrates closely with the spatial and surveillance projects 1 and 2 and the cores, as they have a common theme of analysis of high-dimensional observational study data; need advanced computing, and jointly provide tools for studying gene-space interactions
Keywords: Accounting; Algorithms; anticancer research; base; biomarker; Brain Neoplasms; cancer genetics; cancer microarray; Cancer Prevention Intervention; cancer proteomics; case control; Codon Nucleotides; Cohort Studies; Computer software; computerized data processing; Data; Data Analyses; Detection; Development; Disease; Effectiveness; Environment; Equation; Fourier Analysis; Fourier Transform; gene environment interaction; Gene Expression; Genes; Genetic Predisposition to Disease; Genomics; Goals; Health Sciences; HIV; improved; Informatics; Intervention Studies; Location; Longitudinal Studies; Malignant neoplasm of lung; Malignant Neoplasms; markov model; Mass Spectrum Analysis; Methodology; Methods; Mutation; Nature; Observational Study; population based; Population Sciences; Procedures; Proteins; Proteomics; Research; Research Personnel; Science; Speed (motion); Statistical Methods; Statistical Study; Structure; Testing; Time; tool; user-friendly
Budget start date: 1-SEP-2011
Budget end date: 31-AUG-2012
5P01CA134294-04_0003 (2011): $143347
WORKSHOP FOR JUNIOR BIOSTATISTICIANS IN HEALTH RESEARCH
Lin Xihong
University Of North Carolina Chapel Hillcity: Chapel Hill country: United States (us)
Grant 5R13CA138138-03 from National Cancer Institute
Keywords: Academia; American; anticancer research; Area; Asthma; Authorization documentation; Biometry; cancer risk; Cardiovascular system; career; career development; Clinical Trials; Codon Nucleotides; Collaborations; Communities; Data; Decision Making; design; Development; editorial; Educational workshop; Evaluation; experience; Familiarity; Funding; Funding Agency; gene environment interaction; genome wide association study; Government; Grant; Health; HIV vaccine; improved; Individual; Industry; Institutes; Institution; interdisciplinary collaboration; International; Investigation; Joints; Journals; Knowledge; Laboratory Study; Leadership; Malignant Neoplasms; Medical; meetings; member; method development; Methodology; Morbidity - disease rate; Mortality Vital Statistics; Mutation; National Heart, Lung, and Blood Institute; National Institute of Allergy and Infectious Disease; National Institute of Environmental Health Sciences; next generation; Observational Study; Participant; Play; Policies; Process; programs; public health research; Publications; Publishing; Research; Research Personnel; Research Project Grants; Risk; Role; skills; Societies; Statistical Methods; statistics; Structure; success; Time; Training; United States; United States National Institutes of Health; Validation; Work; Writing
Relevance: The Workshop for Junior Biostatisticians in Health Research is designed to enhance the skills and knowledge of junior biostatistical researchers in four key areas: interdisciplinary collaboration, publication, grant writing, and career development and promotion. Senior researchers will meet with junior investigators the day prior to the annual ENAR meeting to provide advice and tips that will help the next generation of biostatisticians meet emerging challenges in medical and public health research
Project start date: 2009-01-01
Project end date: 2012-12-31
Budget start date: 1-JAN-2012
Budget end date: 31-DEC-2012
5R13CA138138-03 (2012): $30000