AI-Enabled Quantitative Phenotyping of Organoids & 3D Spheroids for Drug Discovery
Transform 3D biological images into quantitative insights for smarter drug discovery.
About This Course
This three-day workshop introduces participants to the use of artificial intelligence and quantitative imaging for analysing organoids and 3D spheroids in drug discovery. Participants will learn how to preprocess microscopy images, segment 3D cellular models, extract morphological and intensity-based features, and build phenotypic profiles that can be used to evaluate treatment response. The workshop also covers dimensionality reduction, machine-learning-based phenotype classification, drug-response prediction, and candidate prioritization through guided hands-on exercises.
Aim
To provide participants with practical knowledge of AI-enabled image analysis, quantitative phenotyping, and machine-learning-based drug-response assessment using organoid and 3D spheroid models.
Workshop Objectives
- Understand the role of organoids and 3D spheroids in modern drug discovery.
- Learn the fundamentals of microscopy image processing and quantitative phenotyping.
- Apply AI-based segmentation for organoid and spheroid detection.
- Extract morphological, intensity, texture, growth, and viability features.
- Build multiparametric phenotypic profiles from imaging data.
- Compare control and treatment-induced phenotypic changes.
- Apply PCA and UMAP for visualization of phenotype patterns.
- Use machine learning for phenotype classification and drug-response prediction.
- Interpret important features associated with treatment response.
- Prioritize drug candidates using quantitative imaging data.
Workshop Structure
Day 1: 3D Cell Models, Imaging & Preprocessing
- Organoids and 3D spheroids in drug discovery
- 2D vs 3D cellular models
- Brightfield, fluorescence and confocal imaging
- Image quality and artifact handling
- Fundamentals of quantitative phenotyping
- Morphological and intensity-based features
- Image normalization, denoising and enhancement
- Region-of-interest identification
- Hands-on: Preprocess and visualize organoid/spheroid imaging datasets
Day 2: AI-Based Segmentation & Quantitative Phenotyping
- Classical vs AI-based image segmentation
- Organoid and spheroid detection
- Object and instance segmentation
- Size, area, circularity and shape analysis
- Texture and fluorescence intensity measurements
- Growth and viability assessment
- Multiparametric phenotype extraction
- Population-level phenotype comparison
- Quantitative phenotype dataset generation
- Hands-on: Segment 3D models and extract quantitative phenotypic features
Day 3: AI-Based Drug-Response Profiling & Candidate Prioritization
- Control vs treatment phenotype comparison
- Dose-response analysis
- Morphology-based drug-response signatures
- Multiparametric phenotypic profiling
- Feature selection
- PCA/UMAP phenotype visualization
- ML-based phenotype classification
- Drug-response prediction
- Responder vs non-responder identification
- Drug candidate prioritization
- Feature importance and model interpretation
- Hands-on: Build an AI-assisted drug-response prediction and candidate-ranking workflow
Who Should Enrol?
- Biotechnology and Life Sciences students
- Biomedical Science researchers
- Pharmaceutical Sciences students and professionals
- Cancer Biology and Stem Cell researchers
- Bioinformatics and Computational Biology learners
- Drug Discovery and Pharmacology researchers
- Cell Biology and Tissue Engineering researchers
- Medical and Translational Research professionals
- PhD scholars, postdoctoral researchers, faculty, and industry professionals
Important Dates
Registration Ends
October 12, 2026
IST 4:30 PM
Workshop Dates
October 12, 2026 – October 14, 2026
IST 5:00 PM
Workshop Outcomes
- Explain how organoids and 3D spheroids are used in drug screening.
- Process and visualize microscopy-based 3D culture datasets.
- Perform image segmentation and object-level analysis.
- Quantify organoid and spheroid morphology, intensity, and viability.
- Generate structured phenotypic datasets for downstream analysis.
- Identify treatment-associated phenotypic signatures.
- Visualize complex phenotype data using PCA and UMAP.
- Build basic machine-learning models for phenotype classification.
- Evaluate and interpret drug-response patterns.
- Develop an end-to-end AI-assisted quantitative phenotyping workflow for drug discovery.
Fee Structure
Student Fee
₹2499 | $65
Ph.D. Scholar / Researcher Fee
₹3499 | $75
Academician / Faculty Fee
₹4499 | $85
Industry Professional Fee
₹5499 | $110
What You’ll Gain
- Live & recorded sessions
- e-Certificate upon completion
- Post-workshop query support
- Hands-on learning experience
View All Feedbacks →