scRNA seq Data Analysis
From Raw Reads to Biological Insights with AI-Driven Workflows
Course Description
Unlock the power of single-cell resolution with our comprehensive scRNA-seq Data Analysis course. Designed for the 2026 bioinformatic landscape, this program bridges the gap between traditional transcriptomics and cutting-edge AI-driven genomics. You will navigate the entire computational pipeline, from processing raw FASTQ files and UMI deduplication to advanced deep learning applications for cell-type annotation. Through hands-on sessions using Seurat (R) and Scanpy (Python), you will learn to tackle cellular heterogeneity, correct batch effects, and perform trajectory inference. Whether you are looking to identify rare cell populations or model complex disease progression, this course provides the technical mastery and machine learning frameworks necessary to transform high-dimensional data into publication-quality biological discoveries.
What You'll Learn
How to perform rigorous Quality Control (QC) to filter doublets and mitochondrial noise.
Techniques for Data Integration and Batch Effect Correction using CCA and Harmony.
The math behind Dimensionality Reduction (PCA, JackStraw analysis).
Differential Expression Analysis to identify cluster-specific marker genes.
Advanced downstream tasks: Pseudotime analysis, RNA velocity, and cell-cell communication modeling.
Curriculum
-
Module 1: Introduction to Single-Cell Technologies and Raw Data Processing (FASTQ to Matrix).
Lesson -
Module 2: Pre-processing Pipelines: Normalization, Scaling, and Feature Selection.
Lesson -
Module 3: Exploratory Data Analysis: PCA, UMAP, and Cluster Optimization.
Lesson -
Module 4: Biological Interpretation: Differential Expression and Pathway Enrichment.
Lesson -
Module 5: Advanced Workflows: Data Integration and Multi-modal (CITE-seq) Analysis.
Lesson -
Module 6: The AI Frontier: Deep Learning for Denoising and Generative Models in Genomics.
Lesson
