Certificate Course on AI in Drug Development
Conducted by
SOPHAS in Collaboration with Pumas-AI Inc
Duration
8 months (September 2025 to April 2026)
Teaching Methodology
Flipped Classroom approach
Target Audience
Background in statistics, evidence by academic coursework or certification in statistical methods relevant to pharmaceutical sector.
Objectives
- Understand the fundamental concepts of machine learning and their applications in drug development use cases.
- Understand and apply machine learning techniques for covariate modeling and prognostic factor identification.
- Understand and use explainable machine learning techniques to address drug development questions.
- Combine scientific knowledge and neural networks to build scientific machine learning (SciML) pharmacodynamic models.
- Understand the conditional variational autoencoder generative machine learning model and its relationship to nonlinear mixed-effects models.
- Compare pure machine learning, traditional scientific modeling, and hybrid SciML approaches when analyzing longitudinal clinical trial data, with and without random effects.
- Build and use DeepNLME models to analyze disease progression and biomarker data across multiple realistic case studies.
Course Structure
Phase 1:
Structured Virtual Learning
Duration: 5 months (1 Sep 2025 to 30 Jan 2026)
Format: Online, self-paced with guided materials
This phase focuses on building a strong foundational understanding through structured self-paced learning.
Participants will gain:
- Access to recorded lectures, course materials, and licensed software tools for independent study and practice
- Curated readings and learning resources aligned with course outcomes
- Assignments and exercises designed to reinforce core concepts and prepare participants for advanced, hands-on work in later phases
By the end of this phase, learners will be well-equipped with the theoretical background and tools needed for the application-oriented stages of the program.
Phase 2:
Project-Based Learning (In-Person Workshop)
Duration: 10 days (Feb 2026)
Location: Venue in South India (Details to be announced)
An immersive, ten-day in-person workshop combining theoretical instruction with hands-on, project-based learning.
This phase includes:
- In-depth training sessions with Pumas and DeepPumas, advanced software for pharmacometric modeling and scientific machine learning
- Expert-led sessions to reinforce Phase 1 topics with a special focus on applications for drug development.
- A capstone hands-on project and case studies
This intensive workshop equips participants with the practical experience and confidence to apply their knowledge effectively in professional drug development environments.
Phase 3:
Submission and Certification
Duration: 1 month (Dates TBD)
Final Submission: 2nd Week of April 2026
In the final phase of the program, learners will complete their learning journey through project submissions and final assessments.
This phase concludes the program, recognizing participants based on their engagement and performance:
- Certificate of Attendance: For those who complete the virtual learning and attend the in-person workshop.
- Certificate of Completion: For those who submit the capstone project and meet performance criteria.
These certificates formally acknowledge the participant’s proficiency in leveraging artificial intelligence techniques to advance drug development processes and make data-driven decisions.
Topics to be Covered:
Machine learning tasks
Categorical and continuous data imputation and pre-processing
Hyperparameters
Cross-validation and model evaluation
One-hot encoding
Supervised Learning
Decision tree
k-nearest neighbors
Random forest
Gradient boosting
Unsupervised Learning
Principal component analysis for dimension reduction
k-means clustering
k-medoids clustering
Neural Network Essentials
Perceptron
Activation functions
MLP (Multi-Layer Perceptron)
Regularization
Ridge regression
LASSO (Least Absolute Shrinkage and Selection Operator)
NN in Low Data Regime
Transfer Learning
Fine-tuning
Pre-training and self-supervision
Data synthesis and augmentation
Time Series Modeling
Recurrent NNs (RNN, LSTM, GRU)
NeuralODE (Neural Ordinary Differential Equations)
Scientific ODE Models
SciML Neural ODE
Explainability
LIME (Local Interpretable Model-agnostic Explanations)
SHAPELY (SHapley Additive exPlanations)
Generative models
Probabilistic principal component analysis
Nonlinear mixed effects (NLME) models as generative models
Variational autoencoder (VAE) as NLME + amortized learning
Dimension reduction and clustering using generative models
Normalizing flows
Conditional Generative Models
Conditional VAE
Scientific NLME models as conditional generative models
Generative neural ODEs
DeepNLME and SciML generative models
Model fitting and evaluation
Understanding the marginal likelihood
Information criteria vs cross-validation
Advanced model fitting and evaluation methods
Adversarial learning
Wasserstein distance
Instructors
Mohamed Tarek, PhD
Senior Product Engineer, Pumas-AI Inc. Research Affiliate, University of Sydney Business School
Vijay Ivaturi, PhD
Co-Founder & CEO, Pumas-AI Inc. Endowed Chair, Center for Pharmacometrics, Manipal
Fee Structure
|
Category
|
Full Course Fee
|
|---|---|
|
Students
|
₹2,00,000
|
|
Academics
|
₹2,50,000
|
|
Industry
|
₹4,00,000
|
Registration Form
Call for Sponsors: Advancing the Integration of AI in Drug Development
We are pleased to invite sponsorship for the upcoming eight-months hybrid certificate program in AI in Drug Development. This initiative brings together early-career researchers, professionals, and students from across various countries to build essential, hands-on expertise in a critical area of AI in drug development.
Sponsorship contributions will be directed toward supporting travel and accommodation for course participants attending the in-person workshop (Phase 2) at a Venue in South India (Details to be announced), ensuring broader access and inclusion.
Sponsor Benefits
In recognition of your support, sponsors will receive prominent visibility across all phases of the course through:
- Inclusion of sponsor logos on all official course communications—both digital and print (brochures, certificates, presentation decks, etc.)
- Dedicated shoutouts and acknowledgments on our social media platforms
- On-site recognition during the in-person workshop through banners, displays, and verbal mentions
- Optional engagement opportunities, such as addressing participants or distributing branded materials during the event
We believe that your partnership will not only help foster the next generation of scientific talent but also highlight your organization’s commitment to education and innovation in drug development.
For sponsorship inquiries and customized partnership options, please contact us at connect@sophas.net