PubChem

PubChem is a comprehensive chemical database that contains molecular data used to evaluate the drug-likeness and validity of generated compounds in drug discovery research.

Papers using PubChem (17)

How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehension2025 · 4 citesA Large Encoder-Decoder Family of Foundation Models For Chemical Language2024 · 4 citesFine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition2026 · 1 citesEfficient Machine Learning Approach for Yield Prediction in Chemical Reactions2025 · 2 citesChemical Language Model Linker: blending text and molecules with modular adapters2024 · 2 citesBenchmarking Retrieval-Augmented Generation for Chemistry2025 · 1 citesA Personalized Generative AI Model for Diabetes Drug Discovery: Integrating Molecular and Clinical Data Using Variational Autoencoders (VAE)2026GIP-RAG: An Evidence-Grounded Retrieval-Augmented Framework for Interpretable Gene Interaction and Pathway Impact Analysis2026Accelerating Large-Scale Cheminformatics Using a Byte-Offset Indexing Architecture for Terabyte-Scale Data Integration2026Diagnosing Heteroskedasticity and Resolving Multicollinearity Paradoxes in Physicochemical Property Prediction2025STAR-VAE: Latent Variable Transformers for Scalable and Controllable Molecular Generation2025ChemBERTa-2: Towards Chemical Foundation Models2022 · 150 citesChemNLP: A Natural Language Processing based Library for Materials Chemistry Text Data2022 · 3 citesSubstructure-Atom Cross Attention for Molecular Representation Learning2022 · 2 citesMachine Learning Co-pilot for Screening of Organic Molecular Additives for Perovskite Solar Cells2024 · 1 citesTailoring Molecules for Protein Pockets: a Transformer-based Generative Solution for Structured-based Drug Design2022Predicting the activity of chemical compounds based on machine learning approaches2024