One year. Real data. A career in AI‑driven drug discovery.
A one year, full time advanced diploma, taught jointly by SilicoScientia and the School of Pharmacy and Research at Dr. D. Y. Patil Dnyan Prasad University, Pune. You learn to apply artificial intelligence to real drug discovery problems, on real data, with the people who do this work every day.
The diploma gives you a working understanding of where artificial intelligence meets drug discovery. You apply machine learning and data analytics to real problems of discovery and development, and you learn by using the methods, not by reading about them.
Teaching is shared between an academic institution and an industry partner. The School of Pharmacy and Research brings the pharmaceutical science. SilicoScientia brings live software, real datasets and the working practices of a discovery company. Ethics is taught as part of the science, and graduates leave able to work across AI and pharmaceutical science and to lead rather than assist.
Six things the programme sets out to give you, in the order they tend to arrive.
A working command of artificial intelligence, machine learning and data analytics as they are actually applied in discovery, so that you can predict interactions, identify therapeutic targets and shorten the design loop.
Hands on training in Python and JAVA, and in the computational platforms used daily in discovery, including the data analytics and simulation techniques needed to evaluate complex molecular properties.
Computational science, chemistry, biology and pharmacology taught as one subject rather than four, through collaborative projects that need all of them at once.
The ethical frameworks and regulatory guidelines that govern AI in pharmaceuticals, including responsible data handling and the dilemmas that arise once a model starts influencing decisions.
The habit of interrogating a model rather than trusting it. You will analyse large datasets, judge model output critically, and build strategies that hold up under scrutiny.
An individual research project carried through from question to result, supervised by scientists who publish, and assessed on the same standards their own work is held to.
Ten theory courses and six laboratory courses across two semesters, followed by an individual research project carried through to a result.
| Code | Course title | Hours | Credits |
|---|---|---|---|
| AICDD 101 | Introduction to Artificial Intelligence in Healthcare and Medicine | 15 | 1 |
| AICDD 102 | Introduction to Python programming and applications | 30 | 2 |
| AICDD 103 | Genomics, Proteomics and Structural Bioinformatics in Drug Discovery | 30 | 2 |
| AICDD 104 | Introduction to Machine learning and Deep learning | 15 | 1 |
| AICDD 105 | Machine Learning and Deep learning Applications in Advanced Drug Discovery | 30 | 2 |
| PAICDD 101 | Python programming | 30 | 2 |
| PAICDD 102 | Structure prediction and drug design | 60 | 2 |
| PAICDD 103 | Machine learning model development using Python | 60 | 2 |
| Semester total | 270 | 14 | |
| Code | Course title | Hours | Credits |
|---|---|---|---|
| AICDD 201 | Foundations in Biostatistics: Principles and Methods | 30 | 2 |
| AICDD 202 | Advanced molecular modelling techniques in drug development | 30 | 2 |
| AICDD 203 | JAVA programming | 30 | 2 |
| AICDD 204 | Data Analysis and Machine Learning in Drug Discovery, and integrating AI into clinical workflows | 30 | 2 |
| AICDD 205 | Ethics and Regulatory Aspects of AI in Pharmaceuticals | 30 | 2 |
| PAICDD 201 | Deep learning model development | 60 | 2 |
| PAICDD 202 | JAVA programming | 60 | 2 |
| PAICDD 203 | Molecular modelling | 60 | 2 |
| Semester total | 450 | 16 | |
Every student completes a supervised research project, assessed on the same basis as the taught courses. Projects are drawn from live computational problems rather than set exercises. Recent examples of the kind of work offered:
You are assessed continuously through internal examinations, assignments and project work, and again at the end of each course in a term end examination conducted jointly by the School of Pharmacy and Research and SilicoScientia.
Across the two semesters the programme carries 2100 marks and 42 credits. A student must pass both continuous assessment and the term end examination separately, each with a minimum grade point of 4. Anyone scoring below 40 per cent in any head of passing is declared fail and reappears.
The Advanced Diploma is awarded at the end of semester two on the performance of all semester examinations, subject to a minimum CGPA of 4.00 out of 10.
Assessment is relative. The maximum grade point is 10, corresponding to O for outstanding.
| Marks | Grade | Points |
|---|---|---|
| 80 to 100 | O, Outstanding | 10 |
| 70 to below 80 | A+, Excellent | 9 |
| 60 to below 70 | A, Very Good | 8 |
| 55 to below 60 | B+, Good | 7 |
| 50 to below 55 | B, Above Average | 6 |
| 45 to below 50 | C, Average | 5 |
| 40 to below 45 | P, Pass | 4 |
| Below 40 | F, Fail | 0 |
Any one of the following qualifications, with a minimum of 50 per cent marks in the qualifying examination.
Selection is by personal interview. Thirty seats are sanctioned. For the reservation position, ask the University admissions office at admissions@dypdpu.edu.in.
Tell us your qualification and what you want to do afterwards, and we will tell you honestly whether this programme is the right route. Enquiries reach SilicoScientia directly.
Ask SilicoScientia about the content and the computational work. Ask the School of Pharmacy and Research about applications, documents and fees.
Batch 2 admissions are open. If you want to work where artificial intelligence meets drug discovery, this is the shortest honest route into it.
