Patterns in Biomedical Data - How do we find them?

Motivation

With great technological advances and numerous ‘big data’ initiatives targeted at generating and acquiring large amounts of biomedical information, there has been an astonishing growth in the volume of data in recent years. Considering sequencing alone, the size of data has approximately doubled every six months in the last decade. Continuing at this rate, we can expect to reach a zettabyte of sequencing data generated per year by 2025. In addition to the challenges associated with ever increasing data size, biomedical data is often multidimensional, i.e. it may include clinical measurements from electronic health records (EHRs), drug usage data, mRNA expression levels, environmental exposures, and others. Furthermore, this data is often incomplete, noisy, and heterogeneous (categorical, continuous, or binary), which introduces significant difficulties in analysis. Data-driven methods, such as pattern recognition, embrace and leverage data complexity through reduction, classification, and clustering to help elucidate features and structures necessary for interpretation. The PSB 2017 session titled “Patterns in Biomedical Data - How do we find them?” is dedicated to the presentation of innovative, data-driven pattern recognition methods and their applications to biomedical research and precision medicine. We encourage submissions of novel pattern recognition approaches, applications of existing methods to a wide range of biomedical data types, as well as manuscripts on combating current challenges in big data analysis and interpretation.

Session Topics

Topics within the scope of this session include:

Deep learning and machine learning methods for pattern recognition in big data (e.g. EHR, medical imaging, natural language processing)
Statistical pattern recognition: data clustering, classification, and dimensionality reduction.
Methods and applications of graph theory, network-based modeling and visualisation (tools such as Cytoscape, Gephi) to analyze complex biological systems (e.g. protein interactions, metabolic networks, complex diseases).
Using topological data analysis (e.g. using Mapper to discover patterns in complex data like phenotypic, EHR, epidemiological, and genomic data).
Pattern recognition in phenotypic data: discovering subtypes of heterogenous phenotypes or endophenotypes, and patterns of co-occurring diseases in EHR-derived clinical data (ICD-9 codes, clinical measurements etc.).
Visualization of patterns in big data and novel approaches to enhance its reproducibility
Current challenges in pattern recognition: missing data, integration of various data types, scalability
Other related topics

Session Organizers

Anna Basile

The Pennsylvania State University
azo121@psu.edu

Submission Information

Paper Submission Deadline: August 1, 2016 August 7, 2016
Notification of Acceptance: September 12, 2016
Revised Papers Due: October 3, 2016
Poster/Abstract Submission Deadline: November 14, 2016
Conference Date: January 3 - 7, 2017

Papers must be submitted to the PSB paper management system. Please note that the submitted papers are reviewed and accepted on a competitive basis. At least three reviewers will be assigned to each submitted manuscript.

The accepted file formats are: postscript (*.ps) and Adobe Acrobat (*.pdf). Attached files should be named with the last name of the first author (e.g. altman.ps or altman.pdf). Hardcopy submissions or unprocessed TEX or LATEX files or electronic submissions not submitted through the paper management system will be rejected without review.

Each paper must be accompanied by a cover letter. The cover letter should be the first page of your paper submission. The cover letter must state the following:

  • The email address of the corresponding author
  • The specific PSB session that should review the paper or abstract
  • The submitted paper contains original, unpublished results, and is not currently under consideration elsewhere
  • All co-authors concur with the contents of the paper

Submitted papers are limited to twelve (12) pages (not including the cover letter) in our publication format. Please format your paper according to the instructions. If figures can not be easily resized and placed precisely in the text, then it should be clear that with appropriate modifications, the total manuscript length would be within the page limit.