Position-wise Fold-Switch Prediction in Metamorphic Proteins: A Comparison of Handcrafted and Language Model Features
- 1Indian Institute of Technology Bombay
Abstract
In this work, we focus on predicting fold-switching phenomena observed in certain protein structures. Proteins that undergo fold-switching are called metamorphic proteins. We model fold-switch prediction in proteins as a position/residue-wise classification task. We use various features extracted from a protein's sequence as well as structure to train the classifiers. We propose a novel class of handcrafted parametrised features that encode the structural context of a residue. We also use embeddings from existing protein language models (PLMs) to train the classifiers. We train binary and 3-class classifiers, with the 3-class classifiers providing granular information on the type of fold-switch. In our computations, higher classification performance is achieved for binary prediction as compared to 3-class granular prediction. The handcrafted features perform comparably with the PLM embeddings on our standard test set. A rigorous error analysis by us during the review period revealed a critical data-leakage vulnerability in the metamorphic protein test data. This analysis also revealed that the PLM-based classifier suffers sequence-memorisation bias and fails to generalise to novel fold-switching sequences. On the other hand, one of our domain-informed handcrafted feature based classifier detects fold-switching without relying on sequence memory.
Related
- GraphTFactor: A graph-based approach for proteins transcription factor prediction
- EdiProPred: Prediction of Edible Plant Tissue-Associated Proteins Using Large Language Models
- Computational design of protein conformational landscapes for metamorphic behavior
- A post-embryonic specific and ecologically selective network underlies metamorphic remodelling in teleosts
- Comparison of data mining algorithms and regression method for prediction of live body weight using biometric traits of non-descript indigenous chickens.
BibTeX
@misc{machingal2026positionwise,
title = {{Position-wise Fold-Switch Prediction in Metamorphic Proteins: A Comparison of Handcrafted and Language Model Features}},
author = {P. Machingal and N. Hemachandra and P. V. Balaji},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.30.755750},
url = {https://www.biorxiv.org/content/10.64898/2026.09.30.755750v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Position-wise Fold-Switch Prediction in Metamorphic Proteins: A Comparison of Handcrafted and Language Model Features
AU - P. Machingal
AU - N. Hemachandra
AU - P. V. Balaji
PY - 2026
DA - 2026/09/30
PB - bioRxiv
DO - 10.64898/2026.09.30.755750
UR - https://www.biorxiv.org/content/10.64898/2026.09.30.755750v1
AB - In this work, we focus on predicting fold-switching phenomena observed in certain protein structures. Proteins that undergo fold-switching are called metamorphic proteins. We model fold-switch prediction in proteins as a position/residue-wise classification task. We use various features extracted from a protein's sequence as well as structure to train the classifiers. We propose a novel class of handcrafted parametrised features that encode the structural context of a residue. We also use embeddings from existing protein language models (PLMs) to train the classifiers. We train binary and 3-class classifiers, with the 3-class classifiers providing granular information on the type of fold-switch. In our computations, higher classification performance is achieved for binary prediction as compared to 3-class granular prediction. The handcrafted features perform comparably with the PLM embeddings on our standard test set. A rigorous error analysis by us during the review period revealed a critical data-leakage vulnerability in the metamorphic protein test data. This analysis also revealed that the PLM-based classifier suffers sequence-memorisation bias and fails to generalise to novel fold-switching sequences. On the other hand, one of our domain-informed handcrafted feature based classifier detects fold-switching without relying on sequence memory.
ER -