A machine learning method for calculating highly localized protein stabilities

Q: What does this research mean for the field?

PFNet, a machine learning method, can instantly and scalably determine the residue-level free energy of opening (∆G op) for arbitrarily large proteins and complexes from conventional peptide-level hydrogen exchange-mass spectrometry (HX-MS) datasets. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Chenlin Lu; Kyle C. Weber; Savannah K. McBride; Andrew Reckers; Anum Glasgow

doi:10.1038/s41467-026-75590-9

September 1, 2026Nature CommunicationsOpen Access

A machine learning method for calculating highly localized protein stabilities

View Full Paper

Ask AI

Bookmark

Share

Key Points

To develop a scalable machine learning framework capable of extracting residue-level thermodynamic opening free energies from standard peptide-level hydrogen exchange-mass spectrometry data.
Engineered PFNet, a machine learning method trained to quantify residue-level free energy of opening (∆G op) representing localized stability.
Processed conventional peptide-level hydrogen exchange-mass spectrometry (HX-MS) datasets across arbitrarily large proteins and macromolecular complexes.
PFNet rapidly determines residue-level ∆G op for proteins and complexes of arbitrary size using standard HX-MS datasets.
The tool establishes an accessible, scalable, and quantitative analytical pipeline that expands the utility of routine HX-MS experiments.

Ask about this paper

Answers are grounded in this paper and cite their sources.

Implication

Computational study demonstrates instant calculation of localized protein stability from mass spectrometry data, highlighting scalable and accessible structural analysis.

Abstract

The residue-level free energy of opening (∆G op ) is the thermodynamic descriptor of localized protein stability, providing valuable information about the protein ensemble at physiologically relevant timescales and conditions. PFNet instantly determines ∆G op for arbitrarily large proteins and complexes from conventional peptide-level hydrogen exchange-mass spectrometry (HX-MS) datasets. It unlocks the full potential of HX-MS, democratizing the method and establishing quantitative, scalable and accessible analysis.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Lu et al. (2026) studied this question.

synapsesocial.com/papers/6a993474636c6408cfa7c241 https://doi.org/10.1038/s41467-026-75590-9

View Full Paper

Ask AI

Bookmark

Share

A machine learning method for calculating highly localized protein stabilities

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

A machine learning method for calculating highly localized protein stabilities

Key Points

Ask about this paper

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading