CCSBase2: A Unified Benchmark Dataset and Machine Learning Framework for Robust CCS Prediction.
- 1Department of Medicinal Chemistry, University of Washington, Seattle, Washington98195, United States.
Abstract
The identification of unknown analytes remains a persistent challenge in untargeted mass spectrometry-based analyses. Ion mobility-mass spectrometry (IM-MS) has expanded identification capabilities by enabling the use of collision cross section (CCS) as an orthogonal molecular identifier, but experimentally measured CCS values remain sparse relative to the breadth of known chemical space. Machine learning (ML) approaches have emerged as a complementary strategy for CCS prediction. Many existing models, however, suffer from poor generalizability and accuracy across structurally diverse chemical classes. Here, we present CCSBase2, a large, unified CCS database comprising 66,153 measurements assembled by integrating multiple public datasets, along with a classical ML framework for CCS prediction using Morgan count fingerprints. CCSBase2 achieved a mean relative error of 1.73%, median relative error of 1.23%, and root mean squared error of 4.89 Å2 on a held-out test set. CCSBase2 was trained on a consumer-grade Apple Silicon M4 Pro CPU, demonstrating that accurate CCS prediction can be achieved with minimal computational resources while maintaining fair performance when tested against out-of-distribution compounds. The final model is available at https://ccsbase.net/ccsbase2, and the codebase and datasets are freely available on GitHub (https://github.com/libinxulab/ccsbase2).
Related
- Topology-Guided Multi-Level Graph Learning: A Unified Framework for Molecular Property Prediction
- Machine Learning for Ionic Conductivity Prediction in Polymer Electrolytes: A Benchmark on Lithium Systems and a Feasibility Study on the Data-Scarce Multivalent (Mg, Zn, Na) Frontier
- Benchmark Label Definition, Not Model Capability, Explains a Machine-Learning Advantage over TD-DFT for λmax Prediction
- When Do Models Win? A Learning Curve Benchmark for Molecular Property Prediction in Low-Data Regimes
- NephroTox AI: an explainable machine learning framework with uncertainty quantification for drug-induced nephrotoxicity prediction
BibTeX
@article{bantwal2026ccsbase2,
title = {{CCSBase2: A Unified Benchmark Dataset and Machine Learning Framework for Robust CCS Prediction.}},
author = {Amogh Bantwal and Reuben Santoso and Ryan Nguyen and Griffin Rangel and Libin Xu},
journal = {Analytical chemistry},
year = {2026},
month = oct,
doi = {10.1021/acs.analchem.6c03711},
url = {https://europepmc.org/article/MED/42916131},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - CCSBase2: A Unified Benchmark Dataset and Machine Learning Framework for Robust CCS Prediction.
AU - Amogh Bantwal
AU - Reuben Santoso
AU - Ryan Nguyen
AU - Griffin Rangel
AU - Libin Xu
PY - 2026
DA - 2026/10/01
JO - Analytical chemistry
DO - 10.1021/acs.analchem.6c03711
UR - https://europepmc.org/article/MED/42916131
AB - The identification of unknown analytes remains a persistent challenge in untargeted mass spectrometry-based analyses. Ion mobility-mass spectrometry (IM-MS) has expanded identification capabilities by enabling the use of collision cross section (CCS) as an orthogonal molecular identifier, but experimentally measured CCS values remain sparse relative to the breadth of known chemical space. Machine learning (ML) approaches have emerged as a complementary strategy for CCS prediction. Many existing models, however, suffer from poor generalizability and accuracy across structurally diverse chemical classes. Here, we present CCSBase2, a large, unified CCS database comprising 66,153 measurements assembled by integrating multiple public datasets, along with a classical ML framework for CCS prediction using Morgan count fingerprints. CCSBase2 achieved a mean relative error of 1.73%, median relative error of 1.23%, and root mean squared error of 4.89 Å2 on a held-out test set. CCSBase2 was trained on a consumer-grade Apple Silicon M4 Pro CPU, demonstrating that accurate CCS prediction can be achieved with minimal computational resources while maintaining fair performance when tested against out-of-distribution compounds. The final model is available at https://ccsbase.net/ccsbase2, and the codebase and datasets are freely available on GitHub (https://github.com/libinxulab/ccsbase2).
SN - 0003-2700
SN - 1520-6882
ER -