Benchmarking community drug response prediction models: datasets, models, tools, and metrics for cross-dataset generalization analysis

2025-03-18

AI Summary

Current drug response prediction (DRP) models lack standardized evaluation of cross-dataset generalization, hindering fair and reproducible assessment. Method: We introduce the first open-source benchmark framework for DRP generalization evaluation, integrating five public drug screening datasets and six uniformly implemented models—RF, XGBoost, GCN, MPNN, DeepSynergy, and DNN—and proposing a novel evaluation metric system balancing absolute performance (R², RMSE) and relative degradation (ΔR²). Contribution/Results: Empirical analysis reveals that all models suffer >40% average R² degradation across datasets; CTRPv2 emerges as the optimal source dataset, yielding highest generalization scores on most target datasets; MPNN and DeepSynergy demonstrate relatively robust cross-dataset performance. The framework supports multi-source data fusion and transfer-based evaluation, enabling rigorous, transparent, and reproducible generalization assessment in DRP research.

Technology Category

• Machine Learning: Evaluation and Analysis
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Deep learning (DL) and machine learning (ML) models have shown promise in drug response prediction (DRP), yet their ability to generalize across datasets remains an open question, raising concerns about their real-world applicability. Due to the lack of standardized benchmarking approaches, model evaluations and comparisons often rely on inconsistent datasets and evaluation criteria, making it difficult to assess true predictive capabilities. In this work, we introduce a benchmarking framework for evaluating cross-dataset prediction generalization in DRP models. Our framework incorporates five publicly available drug screening datasets, six standardized DRP models, and a scalable workflow for systematic evaluation. To assess model generalization, we introduce a set of evaluation metrics that quantify both absolute performance (e.g., predictive accuracy across datasets) and relative performance (e.g., performance drop compared to within-dataset results), enabling a more comprehensive assessment of model transferability. Our results reveal substantial performance drops when models are tested on unseen datasets, underscoring the importance of rigorous generalization assessments. While several models demonstrate relatively strong cross-dataset generalization, no single model consistently outperforms across all datasets. Furthermore, we identify CTRPv2 as the most effective source dataset for training, yielding higher generalization scores across target datasets. By sharing this standardized evaluation framework with the community, our study aims to establish a rigorous foundation for model comparison, and accelerate the development of robust DRP models for real-world applications.

Problem

• Evaluate cross-dataset generalization in drug response prediction models.
• Standardize benchmarking for consistent model evaluation and comparison.
• Assess model transferability using comprehensive performance metrics.

Innovation

• Standardized benchmarking framework for DRP models
• Incorporates five drug screening datasets and six models
• Introduces metrics for cross-dataset generalization assessment