Transcriptomics 3 is a continuation of Transcriptomics 1 and 2. In Transcriptomics 1, we learned how to convert raw reads from a Next Generation Sequencer into a table of expression and visualize the table of expression using PCA, which we then used to develop hypotheses. In Transcriptomics 2, we looked at statistical methods for determining differentially expressed elements in known groups of samples. We explored Student’s t-test, Bayesian methods such as Deseq and EdgeR, and Factor Regression Analysis to dissect the influence of multiple influential factors. Here, we will explore different methods for identifying groups of samples without prior knowledge (clustering) and then examine methods for developing classifiers from known samples to classify unknown samples.
We will be inquiring into the clustering and the classification methods using a biological example from the publication Daemen et al. (Modeling precision treatment of breast cancer, Genome Biol. 2013. We will not repeat the analysis presented in the paper; rather we will re-analyze data from the paper and consider the differences between our own analysis and those of the authors.
Passing Grade & Criteria
70% is the minimum score to pass
50% : Total quizzes
50% : Course project
- Lectures 14
- Quizzes 2
- Duration 6 hours
- Skill level All levels
- Language English
- Students 403
- Certificate Yes
- Assessments Yes
Data Details and Pre-Processing
Clustering: Unsupervised Analysis
Classification: Supervised Analysis
Introduction to Machine learning
Transcriptomics 3 encompasses the concepts of unsupervised and supervised analysis of biological data. This course contains explanations of various ML algorithms such as LDA,swLDA and SVM. We also learn about the development of classifiers from known samples to classify unknown samples. The course allows us to perform the hands-on practical on the t-bio-server platform where we can deal with a real world biological data for preparatory and other additional analysis.
Put on your Machine Learning goggles!
Transcriptomics-3 offers corresponding examples to run on the t-bio server platform along with great conceptual explanations to ML algorithms, such as; LDA, swLDA, and SVM. The course covers both supervised & unsupervised learning algorithms and uses an actual cancer-dataset to perform exploratory and predictive analysis on the same.
The ML for Biological Data
This course culminates into the actual algorithms of Machine Learning which when applied sequentially gives meaningful insight from the data. The carefully curated quiz acts as a benchmark to the learning process.
This course gave an detailed knowledge about clustering and the classification methods using a biological example from the publication .
Introduction to ML
Learn to analyze your transcriptomics data using Machine Learning techniques effectively!