Resources

We gather information here on Informatics related events going on that might be of interest to you. Scroll down to the Permanent resources to see information on trainings and events we offer directly and in a permanent way. 

Workshop: Rapid Biomedical Knowledge Base Construction from Text

Do you want to automatically identify biomarkers reported within the scientific literature that are related to a particular disease?

Do you have a large collection of text-based documents (e.g., articles, webpages, reports, catalogs) from which you want to create a database of experimentally derived parameters, like P53 concentration levels or tissue stiffness?

Do you want to analyze clinical notes to extract patient-reported functional capabilities related to a given treatment?

The Mobilize Center, an NIH Big Data to Knowledge Center of Excellence, invites you to participate in our upcoming workshop on rapidly creating biomedical knowledge bases from unstructured data. You will learn how to use a tool called Snorkel to automatically extract information from data sources, such as the scientific literature and clinical notes.

DETAILS
 
When:   November 6-7, 2018
Where:  Stanford University, Stanford, CA
Registration: The workshop is free to attend, but registration is required and space is limited. 
Travel Awards: Travel awards are available. Please visit the workshop webpage for more information. 
Deadline for Applications:  Friday, September 21st, 2018
 
DESCRIPTION

Over 80% of the data available in the world today is currently unreadable by computers. These “dark data” are unstructured and include a wide range of invaluable information sources, from the text of scientific articles to the notes written by your doctor. Transforming these data into a form readable by machines is called knowledge base construction and is a vital process for unlocking the potential found in these resources.
 
Current approaches for automatically building knowledge bases require large, labeled datasets for training. These gold standard datasets are difficult to come by, particularly in biomedicine, limiting our ability to create new knowledge bases that can be analyzed.
 
Snorkel was created in response to this challenge. Developed in Christopher Re’s lab at Stanford University, Snorkel constructs knowledge bases from “dark data.” And unlike other approaches, which require precisely labeled data to train and build the models, Snorkel can work with just a set of user-input rules. 

On the first day, participants will learn about the Snorkel workflow through brief lectures and hands-on activities. On the second day, participants will utilize their new knowledge to apply Snorkel to a real-world problem using the scientific literature or electronic health record data.

INTENDED AUDIENCE

This workshop is designed for individuals who are interested in applying state-of-the-art machine reading approaches to extracting information from the text and tables of documents. You do not need to know anything about machine reading or machine learning, but you should have some basic Python programming skills.

To learn more and apply, visit http://mobilize.stanford.edu/events/snorkelworkshop2018/
 
Application deadline:  Friday, September 21st, 2018


Georgetown ICBI 7th Annual Big Data in Biomedicine Symposium

Register Today for the Georgetown ICBI 7th Annual Big Data in Biomedicine Symposium! 

Spaces are filling up fast!  Register Today!

Click Here to Register

Georgetown ICBI 7th Annual Big Data in Biomedicine Symposium: Health Data Science & Informatics

Friday October 26th 2018

Spotlight speakers:

Melissa Haendel, PhD

Neal Meropol, MD


Science Webinar Series

New complimentary webinar from Science:

Driving precision medicine through biostatistics: Translating multiomics biomarker data into breakthrough knowledge

You are invited to hear our panel of experts on October 3, 2018, in this live, online educational seminar. For more information and complimentary registration visit: webinar.sciencemag.org

Date: Wednesday, October 3, 2018
Time: 12 noon Eastern, 9 a.m. Pacific, 5 p.m. UK, 6 p.m. Central Europe
Duration: 1 hour

About This Webinar 

In order to provide better treatment for patients and more effective, targeted drugs, it is vital to understand disease mechanisms and to identify informative markers for patient susceptibility, disease progression, treatment response, and individual drug tolerance. The move to more stratified medicine is a key paradigm for global health care, but also an enormous challenge for biologists and data scientists. Technological developments are enabling larger studies that can rapidly deliver huge quantities of data—their translation into meaningful, actionable biological understanding is essential, but often difficult. Genomics and proteomics are increasingly combined to characterize the role of specific biomarkers in disease, uncover novel biological pathways, provide rationales for drug target selection, and develop new, more efficacious therapies. These large-scale, multiomics studies generate complex datasets that highlight an important example of the big-data problem. At the same time, the credibility of scientific research is facing challenges from the so-called “replication crisis,” raising questions about how we judge the significance of the data we obtain. Thus, biostatisticians play an increasingly critical role in interpreting and quality-assuring the outcome of such studies, throughout the process of biomarker discovery, validation, clinical implementation, and drug development. Our panelists will share their experiences in applying biostatistics to large datasets in order to facilitate more confident development of novel therapeutics, and to drive precision medicine.  

During the webinar, the speakers will:

• Describe their biostatistical approaches to analyzing large, complex datasets
• Illustrate how biostatistical analysis can translate complex data into biological insights
• Discuss how biomarkers can be leveraged to identify unique underlying biological mechanisms and personalize patient treatment
• Answer your questions during the live broadcast!


Participants:

Eric Fauman, Ph.D.
Pfizer
Cambridge, MA

Jasper Tromp, M.D., Ph.D.
University Medical Centre Groningen
Groningen, Netherlands

Register at:
webinar.sciencemag.org

Questions? E-mail: webinar@aaas.org

Produced by the Science/AAAS Custom Publishing Office and sponsored by Olink Proteomics.

MEEGID XIV: 14th International Conference on Molecular Epidemiology and Evolutionary Genetics of Infectious Diseases

Upcoming MEEGID XIV: 14th International Conference on Molecular Epidemiology and Evolutionary Genetics of Infectious Diseases. Our very own Dr. Keith Crandall will be speaking about "Computational approaches to microbiome characterization and infectious disease dynamics" at the conference!

Dates: 6-9 November 2018

Location: Sitges, Spain

Register: www.elsevier.com/meegid-conference/



Permanent Resources

REDCap All-Hands Training

Research Electronic Data Capture (REDCap) is a mature, secure, HIPAA compliant, web-based application for building and managing online surveys and databases. It is the database platform of choice in all CTSA awarded institutions and for other institutions across the globe. There is no charge for current Children’s National and George Washington University (GW) faculty, staff, sponsored students, and sponsored affiliates conducting clinical and translational research.

We provide free monthly training sessions, take a look at our Events page for the next dates.

Check out our Extended REDCap Consultations in our Services page for your ongoing REDCap Project.

Click here to register for a Training!

For more information: https://ctsicn.org/redcap

 


Informatics Seminar Series

Every first Tuesday of the month*, the Informatics Core brings an expert over to share his/her expertise on new Informatics developments, applied research Informatics projects, and new areas of potential cross-fertilization with Informatics and other areas in health-related research. You can find us at the Science & Engineering Hall, Conference room 2000*. 

Take a look at our Events page to find out more.

If you missed one, you can find the recording on our Archives page.

*Please see details on our Events page, as dates/location may vary


ResearchMatch / i2b2 Training

We offer free training sessions on the basics of these recruitment tools:

ResearchMatch, which is an NIH-funded national registry that brings together researchers and 130,000+ volunteers who are interested in learning more about research studies. Used nationally by over 6,000 researchers this novel platform has been helpful in recruiting research participants across many research areas, and has been particularly useful for research involving rare disease, surveys, and healthy volunteers.

i2b2 (Informatics for Integrating Biology and the Bedside) a scalable informatics framework that facilitates self-service exploration and query of the clinical data at Children's National Health System that has been de-identified and aggregated. i2b2 helps with study feasibility and cohort discovery by allowing a researcher to query various inclusion/exclusion criteria, as well as ascertain the potential for recruitment.

Take a look at our Events page for the next dates.

Need another resource? Let us know!
— www.bioinformatics.gwu.edu