ASCEND BY NTHRYS
Research Abroad Products

Cheminformatics Internship Topics

Browse all focused areas across all internship categories under this field.

Cheminformatics Internships with Accommodation

Choose an internship topic, then explore accommodation-enabled internship options at active NTHRYS branch locations in India.

Showing 1–12 of 40 internship topics
Generative Models for Drug-like Molecule Synthesis
Interns will develop and train generative models (VAEs, GANs, or diffusion models) to design novel drug-like molecules with desired pharmacological properties. They will work on implementing molecular generation pipelines that ensure generated compounds meet Lipinski's rule of five and other drug-likeness criteria.
AI Generative Molecular Design ResearchView internship →
Molecular Property Prediction using Deep Learning
Interns will build deep neural networks to predict molecular properties such as binding affinity, solubility, toxicity, and ADMET profiles from molecular structures. They will explore graph neural networks and transformer architectures for learning effective molecular representations from chemical data.
AI Generative Molecular Design ResearchView internship →
De Novo Drug Discovery with Reinforcement Learning
Interns will implement reinforcement learning frameworks to guide molecular generation toward specific therapeutic targets while optimizing for synthesizability and bioavailability. They will work with reward functions that incorporate chemical validity, diversity, and biological activity predictions.
AI Generative Molecular Design ResearchView internship →
Molecular Scaffold Optimization and Library Design
Interns will develop computational methods to identify, modify, and optimize molecular scaffolds for hit-to-lead optimization in drug discovery. They will create generative models capable of producing targeted molecular libraries around validated chemical scaffolds with improved potency and selectivity.
AI Generative Molecular Design ResearchView internship →
Explainable AI for Structure-Activity Relationship Modeling
Interns will build interpretable machine learning models that reveal relationships between molecular structural features and biological activities. They will implement attention mechanisms and feature importance analysis to generate actionable insights for medicinal chemists in the drug design process.
AI Generative Molecular Design ResearchView internship →
Molecular Descriptor Engineering for QSAR Model Development
Interns will learn to compute and engineer molecular descriptors (physicochemical, topological, and fingerprint-based) from chemical structures using RDKit and other cheminformatics tools. They will evaluate descriptor importance for predicting drug properties and optimize descriptor selection to improve QSAR model performance across different molecular datasets.
Machine Learning QSAR/QSPR ResearchView internship →
Machine Learning Algorithm Optimization for QSPR Predictions
Interns will implement and compare multiple ML algorithms (Random Forest, Support Vector Machines, Neural Networks, Gradient Boosting) for quantitative structure-property relationship modeling. They will perform hyperparameter tuning, cross-validation, and feature selection to develop robust predictive models for compound properties like solubility, binding affinity, or toxicity.
Machine Learning QSAR/QSPR ResearchView internship →
Dataset Curation and Validation for Cheminformatics Modeling
Interns will collect, clean, and validate chemical datasets from public repositories (PubChem, ChEMBL, ZINC) for machine learning applications. They will perform data quality assessment, handle missing values, identify and remove outliers, and standardize chemical structures to ensure dataset integrity for QSAR/QSPR model training.
Machine Learning QSAR/QSPR ResearchView internship →
Model Interpretation and Explainability in Chemical Property Prediction
Interns will apply interpretability techniques (SHAP values, LIME, permutation importance) to understand how molecular features influence QSAR model predictions. They will generate chemical insights from model outputs and develop visualization methods to identify structure-activity relationships that are meaningful to medicinal chemists.
Machine Learning QSAR/QSPR ResearchView internship →
Transfer Learning and Deep Learning for Chemical Space Exploration
Interns will develop and fine-tune deep learning models (graph neural networks, convolutional neural networks) pre-trained on large chemical datasets for downstream property prediction tasks. They will explore transfer learning approaches to improve model performance on small, specialized chemical datasets and evaluate generalization across different chemical scaffolds.
Machine Learning QSAR/QSPR ResearchView internship →
Molecular Generation Models for Drug Discovery
Interns will develop and train deep learning models (VAEs, GANs, transformers) to generate novel molecular structures with desired properties. They will work on implementing graph neural networks for molecular representation and optimizing generative models for chemical validity and diversity.
AI Virtual Compound Library Design ResearchView internship →
Virtual Screening and Molecular Docking Workflows
Interns will design automated pipelines for large-scale virtual screening of compound libraries against protein targets using docking algorithms and scoring functions. They will implement and validate molecular docking workflows to predict binding affinities and identify lead compounds.
AI Virtual Compound Library Design ResearchView internship →
Want to browse internship categories in Cheminformatics? Explore all Cheminformatics internship categories.