The following content is based on the practice set of OmicsLogic BioML(Py) course. The main focus area of the lessons are, data wrangling, data visualization, statistical analysis and machine learning with omics data.
The lessons:
-
Loading Data - Getting started
-
Data wrangling and visualization
-
Descriptive statistical analysis
-
Dimentionality reduction methods - PCA, MDS, NMDS
-
Clustering methods - K-means and Heirarchial clustering
-
Machine learning classification
-
Visualization with t-SNE and UMAP
-
Dimentionality reduction with deep learning
-
Deep learning predictive model
-
Interactive plotiing with 'plotly' of python (Part- I)
-
Interactive plotiing with 'plotly' of python (Part- II)
-
T-test and Heatmap with python
Recently developed 'molplotly' package will also be used for molecular data analysis. For image settings, an R-script is written to manipulate pixel and changing contrast, brightness and color of images generated.