Big Data Science with the BD2KLINCS Data Coordination and Integration Center
Coursera
Course Summary
Learn various methods of analysis including: unsupervised clustering, gene-set enrichment analyses, Bayesian integration, network visualization, and supervised machine learning applications to LINCS data and other relevant Big Data.
-
+
Course Description
The Library of Integrative Network-based Cellular Signatures (LINCS) is an NIH Common Fund project that was recently expanded to its second phase. The idea is to perturb different types of human cells with many different types of perturbations such as: drugs and other small molecules; genetic manipulations such as knockdown or overexpression of genes, manipulation of the extracellular microenvironment conditions, i.e., growing cells on different surfaces, and more. These perturbations are applied to various types of human cells including induced pluripotent stem cells from patients, differentiated into various lineages such as neuron or cardiomyocytes. Then, to better understand the molecular networks that are affected by these perturbations, changes in levels of many different variables are measured including: mRNA, protein, and metabolites, as well as cellular phenotypic changes such as changes in cell morphology. In most cases, the data that is collected is genome-wide and from across different regulatory layers.
The BD2K-LINCS Data Coordination and Integration Center (DCIC) is commissioned to organize, analyze, visualize and integrate this with other publicly available relevant resources. In this course we will introduce the various Centers that collect data for LINCS, describing the experimental data procedures and the various data types. We will then cover the design and collection of meta-data and how meta-data is linked to ontologies. We will then describe data processing and data normalization methods to clean and harmonize LINCS data. This will follow a discussion about how the data is served as RESTful APIs and JSON, and for this we will cover concepts from client-server computing. Most importantly, the course will focus on various methods of analysis including: unsupervised clustering, gene-set enrichment analyses, Bayesian integration, network visualization, and supervised machine learning applications to LINCS data and other relevant Big Data. The course will be taught by members of the Ma'ayan Lab at the Icahn School of Medicine Mount Sinai, Medvedovic Lab at the University of Cincinnati, Schurer Lab at the University of Miami, and other members of the BD2K-LINCS Team as well as members of other BD2K and LINCS NIH funded centers.
-
+
Course Syllabus
- Overview of the NIH Common Fund LINCS Program
- Overview of the Data Signature Generation Centers (experiments and data)
- Meta-Data and Ontologies
- Data Normalization
- Unsupervised Learning Methods: Data Clustering
- Supervised Learning Methods
- Enrichment Analyses
- Bayesian Data Integration
- Network Analysis and Network Visualization
- Cheminformatics
- Serving data through RESTful APIs and JSON
- Interactive Data Visualization of LINCS Data
-
+
Recommended Background
Basic courses in statistics and molecular biology are useful but not required. Ability to write short scripts in languages such as Python would be useful but not necessary.
-
+
Course Format
The class will consist of lecture videos, which are between 8 and 12 minutes in length. The course will be divided into segments where each segment will have a quiz and a homework assignment. For evaluation, students will be graded through their participation in the assignments and quiz completion.
-
+
Suggested Reading
Review articles and selected original research articles will be discussed in the lectures and can enhance understanding, but these are not required to complete the course. All materials will be from open access journals or will be provided as links to e-reprints, so there will be no cost to the student.
1 Review
Able to learn quickly.