AI & Machine Learning in Bioinformatics — Hands-on

Build practical ML systems for genomics, transcriptomics, proteomics, imaging, and clinical datasets. You will learn the full lifecycle: data preparation, model training, validation, interpretation, and lightweight deployment with clear documentation and governance.

AI & Machine Learning in Bioinformatics

Help Desk · WhatsApp

Session Index

Session 1 — ML Foundations for Bio Data Session 2 — Core Algorithms & Imbalanced Learning Session 3 — Evaluation, Interpretability & Pipelines Session 4 — Mini Capstone: End-to-End Bio ML

Session 1

Fee: Rs 9800

ML Foundations for Bio Data

Problem framing & target definitions

classification/regression/ranking train/val/test splits data leakage traps

Preprocessing pipelines for omics & clinical tables

scaling/normalization missing data categoricals/encoders

Toolchain

scikit-learn pandas / numpy R (tidymodels)

Session 2

Fee: Rs 13200

Core Algorithms & Imbalanced Learning

Models & regularization

logistic/linear + L1/L2 trees, RF, XGBoost SVM, k-NN

Unsupervised & dimensionality reduction

PCA/UMAP clustering anomaly detection

Imbalanced learning & leakage control

class weights/thresholding SMOTE/under-sampling time-aware CV

Session 3

Fee: Rs 16800

Evaluation, Interpretability & Pipelines

Metrics & resampling

ROC/PR AUC F1/balanced accuracy calibration curves

Interpretability & accountability

permutation importance SHAP model cards

Pipelines, tuning & reproducibility

Grid/Random/Optuna sklearn pipelines experiment tracking

Session 4

Fee: Rs 21200

Mini Capstone: End-to-End Bio ML

From raw data to validated model on a real bio dataset

Theory + Practical

Lightweight MLOps & packaging

environment files CLI/notebook app reproducibility report

Deliverables: notebook, model artifact & model card

.ipynb/.Rmd .pkl/.rds PDF/HTML

PDF

AI & Machine Learning in Bioinformatics Training | Models, Evaluation, Interpretability, MLOps

AI & Machine Learning in Bioinformatics — Hands-on