The i2b2 tranSMART Foundation 2017 Training Program will be expanding soon to include the i2b2 platform training and related topics
Our 2017 Program consists of training classes held on the last Monday of every month. This year, these classes will include different topics with classes starting at 11AM Eastern.
NOTE: classes for MAY and DECEMBER are one week earlier to avoid holiday conflicts.
Class instructor time is being provided at no cost to the Foundation by Member organizations Rancho Biosciences, Clarivate Analytics and the Hyve.
| Date | Title | Abstract | Trainer | Company | REGISTRATION REQUIRED |
|---|---|---|---|---|---|
| January 30th, 11AM Eastern | Intro to tranSMART | This class offers an overview of tranSMART platform and its features. We will walk through the Search and Browse interface, and the Analyze interface. The analytic capabilities will be demonstrated using use cases from publicly available datasets. | Alena Fedarovich | Rancho Biosciences | Recordings & Slides |
| February 27th, 11AM Eastern | Clinical and Biomarker data loading 101 | The first part of this training will cover basic data curation and preparing data files for loading into tranSMART. The second part will focus on installing and configuring necessary tools to transfer data files to the server and loading into the database using tMDataLoader. | Natalia Boukharov | Clarivate Analytics | Recordings & Slides |
| March 27th, 11AM Eastern | How to get started with tranSMART development | We'll show you how to set up your tranSMART development environment, give an overview of what repository does what and the basics of the the Core API, REST API and the i2b2/tranSMART database model. | Ewelina Grudzién and Ruslan Forostianov | The Hyve | Postponed |
| April 24th, 11AM Eastern | Data loading for beginners | Data Loading for Beginners" training session will start by a brief introduction of tM user interface and functionalities such as browse and search datasets loaded, variable types and patient cohort selection, saving queries, summary statistics, grid view and advanced workflow. tranSMART curation workflow will be discussed and we will use sample data (GEO data) to demonstrate how to transform and map dataset into tM navigation tree. Demonstration of the curation process required to load data types supported by tM will include clinical data curation, for which we will highlight the importance of data cleaning and mapping clinical variables using defined ontologies, and how to prepare high dimensional data files using gene expression as an example. After preparing the data files we will show the folder/file structure required to load data using tM ETL tool, and how to use the ETL tool (main commands) and how to troubleshoot data loading issues. | Monica Beato Coelho | Rancho Biosciences | Recordings & Slides |
| May 31st, 11AM Eastern (due to US Memorial Day) | SmartR | Use of the SmartT workflows will be described and examples presented. There will also be a short section on how to create a new SmartR Workflow | Sascha Herzinger | U Luxemburg | Recordings & Slides |
| June 26th, 11AM Eastern | Programmatic access to data in tranSMART 17.1: The tranSMART REST API V2 | Learn all the new REST API calls that have become available with the 17.1 version of tranSMART. Access your time series and sample data, low and high dimensional via a programmatic interface. See what is possible and how you can use this to build a REST client on top. | The Hyve | Postponed | |
| July 31st, 11AM Eastern | Advanced training for tranSMART | This webinar will cover major functionalities of tranSMART v.16.1 with focusing on Advanced workflows, preparation of VCF data for Genome Browser, analysis of RNA seq in tranSMART. | Yulia Skovpen | Rancho Biosciences | Recordings & Slides |
| Aug 28th, 11AM Eastern | How to load your data to make the most of it | This webinar will focus on practical solutions to data mapping into tranSMART tree. Examples of different ways to map variables to get the most of your data analysis using tranSMART analytics will be discussed. | Stephen Wicks | Clarivate Analytics | Re-scheduled for November 2017 (see below) |
| Sep 25th, 11AM Eastern | How to get started with modelling your data for tranSMART: Modelling and loading with the Arborist and tranSMART-batch. | The training will show you the basis of how to set up the Python package for tranSMART Arborist and work in Jupyter Notebook to transform your data and shape the tree for loading in tranSMART. Next we'll cover the basics of loading the data with transmart-batch to your tranSMART database. | Coming Soon | The Hyve | Recordings & Slides |
| Oct 30th, 11AM Eastern | TranSMART training using complex clinical dataset | An overview of tranSMART using Parkinson’s Data. The webinar will demonstrate clinical and biological data analysis using two curated Parkinson's datasets from the Michael J Fox Foundation. Clinical and biological data from more than 1,500 people with and without Parkinson's in the Parkinson's Progression Markers Initiative (PPMI), and 220 moderate to advanced Parkinson's patients and control volunteers in the Fox Investigation for New Discovery of Biomarkers (BioFIND) studies will be used to demonstrate the visualization and analysis tools. | Alena Fedarovich | Rancho Biosciences | Recordings & Slides |
| Nov 27th, 11AM Eastern | Cross-study analysis using R Interface | This training will show participants how to analyzing data with R Interface. Examples of cross-study data analysis will be discussed. | Eugene Myshkin | Clarivate Analytics | POSPONED. Replaced by the Aug class by Stephen Wicks. See next row. |
| Nov 27th, 11AM Eastern | How to load your data to make the most of it | This webinar will focus on practical solutions to data mapping into tranSMART tree. Examples of different ways to map variables to get the most of your data analysis using tranSMART analytics will be discussed. | Stephen Wicks | Clarivate Analytics | Recordings & Slides |
| Dec 18th, 11AM Eastern | TranSMART Platform basic training | The training will cover overview of basic main features of tranSMART 16.1. We will cover the principles of creating cohorts and working with different workflows. We will explore different functional analyses available in tranSMART in order to evaluate robustness of several putative biomarkers identified in two example studies of uveal melanoma. We will learn how to use correlation analyses, box plot with Anova and clustering techniques to verify reported findings and also to generate novel hypotheses in the form of new gene lists (biomarkers). We will learn how to test new hypotheses on the fly in different studies. | Oksana Tyurina | Rancho Biosciences | Register HERE |
Classes generally will be 60 to 90 minutes of training plus up to 30 minutes for Q&A.
Virtually unlimited attendance: up to 100 per session!! But you must register for each class you would like to attend.
Every class will be recorded and the recording and slide deck will be made available here within one day of the class.
Recordings and Slides from the Training Classes: slide deck and recordings