DAY 01 — Introduction to AI in Bioinformatics & Python Fundamentals

1. Introduction to AI in Bioinformatics — scope, significance, and applications of artificial intelligence in life sciences research
2. Applications of AI in Bioinformatics — drug discovery, genomics, protein structure prediction, QSAR, and clinical data analysis
3. Introduction to BioPython — the foundational Python library for biological sequence analysis and database access
4. Introduction to Google Colab — setting up and using a cloud-based Python environment for bioinformatics workflows
5. Introduction to Jupyter Notebook — working with Python in an interactive, reproducible notebook environment
6. Executing Python codes for basic tasks in bioinformatics — writing and running Python scripts for biological data
7. Sequence retrieval from NCBI using Python — programmatically fetching nucleotide and protein sequences
8. GC content analysis using Python — calculating and interpreting GC content from retrieved sequences
9. Translate sequence — converting nucleotide sequences to protein sequences using Python
10. Sequence alignment by BLAST using Python — running and parsing BLAST results programmatically

📌 Learning Outcome: Use Python in Google Colab and Jupyter Notebook to retrieve sequences from NCBI, perform GC content analysis, translate sequences, and run BLAST alignments programmatically

DAY 02 — Introduction to QSAR & Dataset Preparation

1. Introduction to QSAR — Quantitative Structure-Activity Relationship: principles, history, and pharmaceutical applications
2. QSAR pipeline overview — the complete workflow from compound dataset to predictive model
3. Applications of QSAR in drug discovery — activity prediction, toxicity screening, and lead optimisation
4. Installation of required software — WEKA (machine learning platform), PaDEL-Descriptor, ChemSketch, and Java
5. Preparing the Excel database file — formatting and organising biological activity data for QSAR analysis
6. Creating SDF chemical structures using ChemSketch — drawing and exporting molecular structures in SDF format
7. Calculation of molecular descriptors using PaDEL — generating numerical representations of chemical structures for model input

📌 Learning Outcome: Understand the QSAR pipeline, install all required tools, build a compound dataset, draw chemical structures in ChemSketch, and calculate PaDEL molecular descriptors

DAY 03 — WEKA File Preparation, Data Processing & Machine Learning Model Building

1. Preparation of WEKA-compatible ARFF file — converting descriptor data into the format required by WEKA
2. Data processing and filtering in WEKA — handling missing values, removing low-variance features, and preprocessing the dataset
3. Machine learning model building — introduction to classification and regression approaches in QSAR
4. Linear Regression in WEKA — building a linear regression model to predict continuous biological activity values
5. Random Forest in WEKA — building a Random Forest ensemble model for robust activity classification and regression
6. Understanding and interpreting model parameters — correlation coefficient, RMSE, and cross-validation results

📌 Learning Outcome: Prepare WEKA datasets, apply data filtering, and build Linear Regression and Random Forest models for biological activity prediction

DAY 04 — Model Evaluation, New Compound Prediction & Documentation

1. Model evaluation and performance metrics — assessing model quality using R², RMSE, MAE, accuracy, sensitivity, and specificity
2. Testing the model on new data — applying the trained QSAR model to an external test set to evaluate real-world predictive performance
3. Preparation of new analogue files — creating new molecular structures and their descriptor files for prediction
4. Prediction of biological activity — using the validated QSAR model to predict the activity of novel drug-like compounds
5. Documentation — recording model parameters, performance metrics, workflow steps, and interpretation for research reporting

📌 Learning Outcome: Evaluate QSAR model performance, apply the model to predict activity of new analogues, and document the complete workflow for research and publication use

DAY 05 — Drug Binding Modelling with Python

1. Decoding drug binding — understanding the molecular basis of protein-ligand interactions and binding affinity
2. Drug binding modelling using Python — a complete step-by-step, hands-on session covering the full computational modelling workflow
3. Setting up the Python environment for drug binding analysis — required libraries and dependencies
4. Loading and preparing protein and ligand structures for binding analysis using Python
5. Running and interpreting drug binding calculations using Python-based tools
6. Visualisation and interpretation of binding results — understanding what the output means for drug discovery and lead optimisation

📌 Learning Outcome: Perform a complete drug binding modelling workflow using Python — from structure preparation to binding result interpretation — applicable to drug discovery research

Python

Core programming language

BioPython

Biological sequence analysis

Google Colab

Cloud Python environment

Jupyter Notebook

Interactive coding environment

WEKA

Machine learning platform

PaDEL-Descriptor

Molecular descriptor calculation

ChemSketch

Chemical structure drawing

NCBI & BLAST

Sequence retrieval & alignment

Learn Python for Biology — No Programming Background Needed

Day 1 assumes zero Python experience. The trainer walks you through Google Colab and Jupyter Notebook from scratch, executing real biological tasks — retrieving sequences from NCBI, calculating GC content, translating nucleotide sequences, and running BLAST — all in Python. By the end of Day 1, you will have written and run Python code that performs real bioinformatics analysis.

Build & Validate Real Machine Learning Models for Drug Discovery

Days 2–4 take you through the complete QSAR pipeline — drawing chemical structures in ChemSketch, calculating molecular descriptors in PaDEL, building Linear Regression and Random Forest models in WEKA, evaluating model performance, and predicting the biological activity of new drug analogues. This is the exact workflow used in published QSAR research papers and pharmaceutical R&D.

Master Drug Binding Modelling Using Python

Day 5 covers one of the most in-demand skills in computational drug discovery — drug binding modelling using Python. You will perform a complete, step-by-step workflow: preparing protein and ligand structures, running binding calculations, and interpreting the results. This skill is directly applicable to protein-ligand interaction studies, drug target validation, and computational screening workflows.

Outputs You Can Use Directly in Research & Publications

Every deliverable produced in this workshop — QSAR model performance reports, activity prediction tables for new analogues, Python scripts for sequence analysis, and drug binding results — is directly usable in your thesis, dissertation, or journal submission. These are standard components of computational biology and drug discovery publications.

Build Career-Defining Skills in the Fastest-Growing Field in Life Sciences

AI and machine learning in bioinformatics and drug discovery are among the most sought-after skills in pharmaceutical, biotech, and research job markets globally. Employers are not just looking for biologists — they are looking for biologists who can code, build models, and interpret AI-driven results. This certificate proves you can do exactly that.

Verified Certificate — A Credible, Barcoded Credential

Participants who successfully complete all tasks receive a BDG LifeSciences Certificate of Completion carrying a unique barcode for independent verification — recognized by academic institutions and employers across India, Australia, New Zealand, and internationally. Add it to your LinkedIn, portfolio, university application, or CV immediately.

Session Recordings — Revisit Every Line of Code

Every session is recorded and shared with all participants after class via YouTube. Python coding and machine learning workflows benefit enormously from repetition — with recordings you can pause, rewind, and re-run every step until the code works and the concept is clear.

No Specialised Hardware or Institutional Server Access Required

All Python sessions use Google Colab — a free, cloud-based environment that runs entirely in your browser with no installation. WEKA, PaDEL, and ChemSketch are freely downloadable. You need nothing more than a laptop with a stable internet connection. No high-performance computing, no institutional VPN, no paid software licenses.

🎓

Students

B.Sc., M.Sc., Ph.D., MBBS, M.Pharm students in Bioinformatics, Biotechnology, Biochemistry, Pharmacy, Pharmaceutical Chemistry, Life Sciences, Genetics, Biomedical Sciences, and related disciplines who want to add AI and Python skills to their academic profile

💬

Researchers & Faculty

Research scholars, post-doctoral researchers, faculty, and professors who want to incorporate AI-driven QSAR modelling, Python-based sequence analysis, and drug binding modelling into their research workflows, publications, and grant proposals

🏭

Industry Professionals

Scientists, bioinformatics analysts, computational biologists, and professionals in pharmaceutical R&D, biotech companies, CROs, genomics firms, and regulatory agencies who need practical AI and machine learning competencies for drug discovery and data-driven research

💊

Drug Discovery Scientists

Medicinal chemists, pharmacologists, and drug discovery researchers who want to build QSAR models for activity prediction, use Python for drug binding analysis, and apply machine learning to accelerate lead identification and optimisation

👔

Wet-Lab Biologists Transitioning to Computation

Experimental biologists who want to complement their wet-lab expertise with Python programming, AI modelling, and computational drug discovery skills — enabling them to independently perform in silico analyses and reduce dependence on separate computational teams

🌟

Complete Beginners to Python & AI

Anyone in life sciences who knows that Python, AI, and machine learning are essential future skills but has never known where to start. Day 1 begins from zero — no prior programming, no prior AI knowledge, and no mathematics beyond what any life sciences graduate already knows

Resource Person

Sharvari Kulkarni

CTO, BDG LifeSciences  |  Bioinformatics & Computational Drug Design Expert

Sharvari Kulkarni is one of India's most respected bioinformatics trainers and a leading expert in computational drug design, AI-driven drug discovery, QSAR modelling, molecular simulations, molecular docking, and network pharmacology. As Chief Technology Officer of BDG LifeSciences, she leads the technical training division and has personally trained hundreds of participants globally — consistently receiving over 90% positive feedback across all programmes for her structured, patient, and deeply practical teaching approach.

Her expertise spans the complete spectrum of computational biology and AI applications in life sciences — from Python-based bioinformatics workflows and QSAR pipeline development, through machine learning model building with WEKA and drug binding modelling, to MD simulations using GROMACS and Schrödinger's Desmond Maestro on both Windows and Linux platforms. She is the only trainer at BDG LifeSciences conducting hands-on AI and QSAR modelling training specifically for life sciences participants, making complex machine learning concepts genuinely accessible to researchers with no prior programming background.

With over 15 research papers published in reputable peer-reviewed journals, Sharvari actively guides student research projects, serves on academic and industry panels, and speaks on international computational biology and AI platforms. Her workshops are known for combining rigorous scientific content with step-by-step practical instruction — ensuring participants at every level leave with real, applicable skills.

16+ Years of Bioinformatics Training Excellence

Since 2010, BDG LifeSciences has delivered hands-on, practical bioinformatics and computational biology training to participants across 40+ countries — with a consistent 4.7/5 participant rating. We have been integrating AI and machine learning into our bioinformatics curriculum since before it became mainstream, making us uniquely qualified to teach it in a life sciences context.

Live Trainer — Real-Time Guidance on Every Tool & Every Line of Code

Python, WEKA, and drug binding workflows are best learned with an expert present in real time — to explain errors, demonstrate correct outputs, and answer questions the moment they arise. Every session in this workshop is delivered live by Sharvari Kulkarni. You get immediate help when your code does not run and real-time explanation when model results need interpretation.

AI Made Accessible for Life Scientists — Not Just Computer Scientists

Most AI and machine learning courses are built for computer science students. This workshop is built specifically for life scientists — using biological datasets, pharmaceutical compounds, and drug discovery applications as the context for every AI tool and Python script. The terminology, the examples, and the outputs are all grounded in biology, not abstract data science.

Globally Trusted & Officially Registered

MSME-registered under the Government of India (UDYAM-UP-01-0019151) and officially authorised to operate in Australia and New Zealand via BBR Group Pty Ltd (ACN 608 550 849). Our certificates carry a unique verification barcode and are recognized by academic institutions and employers across India, Australia, New Zealand, and internationally.

From Zero to QSAR Model in 5 Days

The 5-day structure is specifically designed so that a participant who has never written a line of Python or used WEKA on Day 1 walks away on Day 5 having built, validated, and applied a complete QSAR machine learning model — and performed drug binding modelling using Python. This is one of the most complete AI in bioinformatics programmes available at this price and duration.

Verified Certificate for Your Academic & Professional Profile

Every participant who successfully completes all tasks receives a BDG LifeSciences Certificate of Completion with a unique barcode for independent verification. It is issued as a professional digital softcopy via email — printable, shareable on LinkedIn, and accepted by academic institutions and employers internationally as a credible, trainer-assessed credential.

Q. What exactly is covered in this 5-day AI in Bioinformatics workshop?

This workshop covers four structured phases: Day 1 introduces AI in bioinformatics, BioPython, Google Colab, Jupyter Notebook, and Python-based sequence analysis including NCBI retrieval, GC content, sequence translation, and BLAST. Days 2–3 cover the complete QSAR pipeline — ChemSketch, PaDEL molecular descriptors, WEKA file preparation, data processing, and machine learning model building using Linear Regression and Random Forest. Day 4 covers model evaluation, performance metrics, testing on new data, predicting biological activity of analogues, and documentation. Day 5 covers drug binding modelling using Python — a complete step-by-step hands-on session from structure preparation to result interpretation.

Q. Do I need prior Python or programming experience to attend this workshop?

No. Day 1 is specifically designed for participants who have never used Python before. The trainer introduces Google Colab and Jupyter Notebook from scratch and guides you through every line of code step by step. The workshop uses Google Colab — a free, browser-based Python environment — which means there is no complex installation required. All you need is a Gmail account and a stable internet connection.

Q. What is QSAR and why is it important in drug discovery?

QSAR stands for Quantitative Structure-Activity Relationship. It is a computational methodology that uses mathematical models to establish a relationship between the chemical structure of a molecule and its biological activity — allowing researchers to predict how active a new compound will be before synthesising it in the laboratory. QSAR is widely used in pharmaceutical R&D for lead identification, toxicity prediction, and compound optimisation. Days 2–4 of this workshop take you through the complete QSAR pipeline — from drawing structures to building, validating, and applying a machine learning QSAR model to predict the activity of new drug analogues.

Q. What software do I need to install for this workshop?

For Python sessions (Days 1 and 5), you use Google Colab — which runs entirely in your web browser and requires no installation. You only need a Gmail account. For QSAR sessions (Days 2–4), you will install WEKA (free, open-source machine learning platform), PaDEL-Descriptor (free descriptor calculator), ChemSketch (free chemical structure drawing tool), and Java (required to run WEKA and PaDEL). The trainer guides the installation of all software live on Day 2. All tools are freely available and work on Windows, Mac, and Linux.

Q. What is the difference between Linear Regression and Random Forest in this workshop context?

Both are machine learning algorithms used to build QSAR predictive models in this workshop, and both are implemented in WEKA. Linear Regression predicts continuous biological activity values by fitting a straight-line relationship between molecular descriptors and activity — it is interpretable, fast, and widely used in regression QSAR studies. Random Forest is an ensemble method that builds multiple decision trees and aggregates their predictions — it handles non-linear relationships, is more robust to overfitting, and generally produces higher-accuracy predictions on complex biological datasets. Day 3 covers both methods in full, and Day 4 covers how to evaluate and compare their performance using standard metrics.

Q. Are sessions recorded? What if I miss a day?

Yes. Every session is recorded and shared with all registered participants after each class via YouTube, using the Gmail ID you provide during registration. If you miss a session, you can still complete all assigned tasks by watching the recording at your own pace. Python and QSAR workflows particularly benefit from recordings — you can pause and rerun every step as many times as needed until the code executes correctly. Please register with the Gmail ID you actively use on YouTube for seamless access.

Q. Will I receive a certificate on completion?

Yes. A BDG LifeSciences Certificate of Completion is awarded to every participant who successfully completes all tasks assigned by the trainer across the 5 days. The certificate is issued as a professional digital softcopy via email, carrying a unique barcode for independent verification by employers and academic institutions. You may print it, laminate it, add it to your LinkedIn profile, or include it in job applications and academic submissions. It will be issued exactly as per the name and details provided during registration.

Q. How will this AI in Bioinformatics workshop help my PhD research or publications?

This workshop produces research-ready outputs at every stage. Your Python scripts for NCBI sequence retrieval, GC content analysis, and BLAST are directly usable in computational methods sections. Your QSAR model — including descriptor dataset, model performance metrics (R², RMSE), and activity predictions for new analogues — forms the core of a complete computational drug discovery publication. Your drug binding modelling results contribute directly to molecular interaction studies. All of these are standard components of papers in journals covering computational chemistry, bioinformatics, and medicinal chemistry.

Q. What platform will live sessions be conducted on?

Live sessions are conducted on Zoom or Google Meet. The Zoom meeting link will be sent to all registered participants after the registration period closes. You will need a stable internet connection, a Gmail account for accessing Google Colab (Day 1 and 5), and the Gmail ID provided during registration to access session recordings on YouTube.

Q. Is the registration fee refundable or transferable?

No. The registration fee is non-refundable and non-transferable. Please read the full Terms & Conditions carefully before completing registration and ensure you register under the correct participant category — India or Outside India. Registering under the wrong category will result in cancellation with no refund. BDG LifeSciences reserves the right of admission to all its programmes.