PDFBench: A Benchmark for De novo Protein Design from Function

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kuang, Jiahao, Liu, Nuowei, Wang, Jie, Sun, Changzhi, Ji, Tao, Wu, Yuanbin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908562495635456
author Kuang, Jiahao
Liu, Nuowei
Wang, Jie
Sun, Changzhi
Ji, Tao
Wu, Yuanbin
author_facet Kuang, Jiahao
Liu, Nuowei
Wang, Jie
Sun, Changzhi
Ji, Tao
Wu, Yuanbin
contents Function-guided protein design is a crucial task with significant applications in drug discovery and enzyme engineering. However, the field lacks a unified and comprehensive evaluation framework. Current models are assessed using inconsistent and limited subsets of metrics, which prevents fair comparison and a clear understanding of the relationships between different evaluation criteria. To address this gap, we introduce PDFBench, the first comprehensive benchmark for function-guided denovo protein design. Our benchmark systematically evaluates eight state-of-the-art models on 16 metrics across two key settings: description-guided design, for which we repurpose the Mol-Instructions dataset, originally lacking quantitative benchmarking, and keyword-guided design, for which we introduce a new test set, SwissTest, created with a strict datetime cutoff to ensure data integrity. By benchmarking across a wide array of metrics and analyzing their correlations, PDFBench enables more reliable model comparisons and provides key insights to guide future research.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20346
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PDFBench: A Benchmark for De novo Protein Design from Function
Kuang, Jiahao
Liu, Nuowei
Wang, Jie
Sun, Changzhi
Ji, Tao
Wu, Yuanbin
Machine Learning
Artificial Intelligence
Biomolecules
Function-guided protein design is a crucial task with significant applications in drug discovery and enzyme engineering. However, the field lacks a unified and comprehensive evaluation framework. Current models are assessed using inconsistent and limited subsets of metrics, which prevents fair comparison and a clear understanding of the relationships between different evaluation criteria. To address this gap, we introduce PDFBench, the first comprehensive benchmark for function-guided denovo protein design. Our benchmark systematically evaluates eight state-of-the-art models on 16 metrics across two key settings: description-guided design, for which we repurpose the Mol-Instructions dataset, originally lacking quantitative benchmarking, and keyword-guided design, for which we introduce a new test set, SwissTest, created with a strict datetime cutoff to ensure data integrity. By benchmarking across a wide array of metrics and analyzing their correlations, PDFBench enables more reliable model comparisons and provides key insights to guide future research.
title PDFBench: A Benchmark for De novo Protein Design from Function
topic Machine Learning
Artificial Intelligence
Biomolecules
url https://arxiv.org/abs/2505.20346