Clinical Trial Outcome Prediction: Benchmark for Approval Probability

Published in Cell Patterns (2022) by futianfan, this benchmark dataset provides structured data for predicting the probability of clinical trial approval. It was developed to standardize performance evaluation for deep learning models, specifically the Hierarchical Interaction Network (HINT), within the therapeutic drug development domain.

Use Cases

• Predicting approval probability using drug molecule and disease indication features
• Benchmarking Graph Neural Networks on clinical trial success outcomes
• Evaluating Hierarchical Interaction Network (HINT) performance against baseline models

Strengths

• Peer-reviewed publication in Cell Patterns 2022
• Designed specifically as a benchmark for the HINT architecture
• Focuses on the high-stakes domain of therapeutic drug development

Limitations

• Metadata lacks explicit row counts and column definitions
• Temporal bias limited to trials available up to the 2022 publication date

Provenance

Source

Cell Patterns 2022 publication by futianfan

Collection Method

Dataset generation for benchmarking

Freshness

Last updated June 2025 on GitHub, though the core data corresponds to the 2022 Cell Patterns publication.