标杆管理
一套
水准点(测量)
计算机科学
公制(单位)
机器学习
可信赖性
数据挖掘
数据科学
软件工程
人工智能
编码(集合论)
实验数据
度量(数据仓库)
源代码
风险分析(工程)
评价方法
测试套件
标准化
模型验证
软件
作者
Hongxuan Liu,Roman Bushuiev,Ivy Lightheart,Mrunali Manjrekar,Anton Bushuiev,Magdalena Lederbauer,Filip Jozefov,Yinkai Wang,Soha Hassoun,Josef Šivic,James Taylor,Runzhong Wang,David Healey,Tomáš Pluskal,Connor W. Coley
标识
DOI:10.48550/arxiv.2606.19624
摘要
Reliable benchmarking is critical for developing machine learning models for tandem mass spectrometry (MS/MS) based molecule discovery. Subtle issues in experimental design and model evaluation procedures can degrade the trustworthiness of such benchmarks and lead to erroneous conclusions. We conduct a thorough review of model evaluation issues in the recent MS/MS machine learning literature, using the standard MassSpecGym benchmark suite as a case study to illustrate the impact of these issues. We find evaluation issues in at least 17 of 26 papers reporting MassSpecGym benchmark results in the first year of its adoption. We isolate three classes of failures: (i) data leakage, (ii) shortcut learning, and (iii) implementation bugs and metric divergence. Through extensive experimentation and code replication, we quantify the impact of these issues and show how they corrupt the evaluation standards MassSpecGym was designed to enforce. We distill our findings into recommendations generalizable to MS/MS challenges, benchmarks, and custom evaluation setups. We also release MassSpecGym v1.5, an implementation of our recommendations in the MassSpecGym benchmarking suite which addresses the failure modes identified in this audit. MassSpecGym v1.5 is publicly available at https://github.com/pluskal-lab/MassSpecGym.
科研通智能强力驱动
Strongly Powered by AbleSci AI