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 13–24 of 40 internship topics
Chemical Space Exploration and QSAR Modeling
Interns will develop quantitative structure-activity relationship (QSAR) models to predict compound properties and biological activities from molecular descriptors and fingerprints. They will analyze high-dimensional chemical space using dimensionality reduction and clustering techniques to identify structurally diverse compound classes.
AI Virtual Compound Library Design ResearchView internship →
Synthetic Accessibility Assessment and Retrosynthesis Planning
Interns will implement machine learning models to predict synthetic accessibility (SA) scores and develop retrosynthetic pathways for computationally designed compounds. They will integrate retrosynthesis prediction algorithms to ensure designed molecules are practically synthesizable.
AI Virtual Compound Library Design ResearchView internship →
Cheminformatics Database Development and Curation
Interns will build and curate large-scale virtual compound libraries with standardized molecular descriptors, toxicity predictions, and pharmacokinetic properties. They will develop data pipelines for processing, validating, and organizing chemical data from multiple sources into searchable databases.
AI Virtual Compound Library Design ResearchView internship →
Molecular Property Prediction using Graph Neural Networks
Interns will develop and train GNN models to predict chemical properties (solubility, toxicity, binding affinity) from molecular graphs. They will work with datasets like ZINC and ChEMBL, implementing architectures such as Graph Convolutional Networks and Message Passing Neural Networks to optimize prediction accuracy.
AI Chemical Graph Neural Network ResearchView internship →
Drug Discovery Pipeline Optimization with GNNs
Interns will design neural network systems to screen large chemical libraries for drug candidates, focusing on structure-activity relationship learning. They will integrate GNNs with virtual screening workflows to identify promising compounds and validate predictions against experimental data.
AI Chemical Graph Neural Network ResearchView internship →
Chemical Reaction Outcome Prediction
Interns will build graph neural network models that predict reaction products and selectivity from reactant molecular graphs and reaction conditions. This involves working with reaction databases, implementing reaction-specific GNN architectures, and evaluating prediction performance on synthetic chemistry workflows.
AI Chemical Graph Neural Network ResearchView internship →
Molecular Graph Generation and De Novo Drug Design
Interns will develop generative GNN models and variational autoencoders to design novel molecules with desired properties. They will work on constraint satisfaction, validity checking of generated structures, and optimization techniques to ensure synthesizability of computationally designed compounds.
AI Chemical Graph Neural Network ResearchView internship →
Attention Mechanisms in Chemical Graph Networks
Interns will research and implement attention-based graph neural network architectures to improve interpretability of chemical predictions. They will focus on understanding which molecular substructures contribute most to model decisions, with applications in feature attribution and explainable AI for chemistry.
AI Chemical Graph Neural Network ResearchView internship →
Fingerprint Algorithm Comparison and Benchmarking
Interns will evaluate and compare different molecular fingerprint algorithms (e.g., Morgan, ECFP, RDKit) across diverse chemical datasets to assess their performance in molecular similarity searching and virtual screening tasks. They will develop benchmarking pipelines to quantify accuracy, computational efficiency, and applicability domain of each fingerprint type.
Molecular Fingerprint Development and OptimizationView internship →
Machine Learning-Based Fingerprint Feature Selection
Interns will apply machine learning techniques to identify the most informative fingerprint bits and features for specific prediction tasks such as ADMET properties or toxicity classification. This involves feature importance analysis, dimensionality reduction, and optimization of fingerprint representations for improved model performance.
Molecular Fingerprint Development and OptimizationView internship →
Custom Fingerprint Design for Drug-Like Molecules
Interns will design and validate tailored fingerprint representations optimized for drug discovery applications, incorporating domain-specific chemical knowledge and structural patterns relevant to pharmacophores and binding interactions. They will test these custom fingerprints against standard approaches using molecular docking and binding affinity datasets.
Molecular Fingerprint Development and OptimizationView internship →
Fingerprint-Based Molecular Diversity Analysis
Interns will develop computational workflows using molecular fingerprints to analyze chemical space, assess compound library diversity, and perform scaffold hopping analysis for lead optimization. They will implement clustering and visualization techniques to identify structurally distinct molecular subsets and reduce redundancy in chemical collections.
Molecular Fingerprint Development and OptimizationView internship →
Want to browse internship categories in Cheminformatics? Explore all Cheminformatics internship categories.