Supervised Protein Structure Classification Using Topological Persistence With DeltaFold

Abstract

Recent advances in protein structure prediction have considerably increased the number of available structures, underscoring the need for scalable and accurate methods to compare and classify this huge amount of data. Current approaches based on sequence alignment or structural superposition often lack sensitivity and/or are computationally expensive. Here, we introduce the DeltaFold Classifier (DFC), a fast, alignment-free, protein structure classification pipeline based on topological data analysis. Protein three-dimensional structures are encoded using fixed-length vectors derived from persistent homology applied to point clouds of their spatial representation. These vectors, known as Biotopological Markers (BTMs), capture the intrinsic topological features of protein structure geometry-such as cycles and cavities-across multiple spatial scales. BTMs are invariant under translations and rotations, thereby avoiding the need for structural superposition. The DFC pipeline uses the features of these BTMs to train machine learning models for protein structure classification at various hierarchical levels defined in the SCOP and CATH classifications. It achieves performance comparable to that of structure-based comparison methods while substantially improving computational efficiency. It also outperforms sequence-based methods in tasks involving distant homology detection. In-depth analyses confirm that most BTM features contribute significantly to classification performance. These findings highlight the potential of topological vectorisations in structural bioinformatics and support the DFC pipeline as an effective and scalable tool for automated protein structure classification and annotation.

DNA augmentations for semi-supervised learning in genomic sequence classification.
Hyunwoo Yoo, Gail L Rosen
NAR genomics and bioinformatics19 Oct 2026Peer-reviewedCC BY-NCFull textMolecular biology & gene regulationEurope PMCCrossref
CAMELLIA: an alignment-free pipeline integrating k-mer feature selection and supervised classification for genomic sequence subtyping.
Tatiana Mari Saita, Matheus Henrique Pimenta-Zanon, Artur Trancoso Lopo de Queiroz +2
NAR genomics and bioinformatics19 Oct 2026Peer-reviewedCC BY-NCFull textMolecular biology & gene regulationEurope PMCCrossref
DiST: disentangling structure via self-supervised tensors for heterophilous spatial transcriptomics.
Yaozhang Liu, Yu Hu, Jinyu Liu +6
Briefings in bioinformatics1 Sep 2026Peer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMCPMC
Rapid classification of β-lactamase activity through AI-based structure prediction and electric field analysis
D. Wang, A. H. Lima, M. W. van der Kamp
bioRxiv23 Sep 2026PreprintCC BYFull textGeneral biochemistrybioRxiv
Soybean paste functional peptides: Fermentation-driven formation, characterization, classification, structure-activity relationships, and multi-omics insights.
Shuai Pan, Changzheng Wu, Xing Tong
Food chemistry: X14 Oct 2026Peer-reviewedCC BY-NC-NDFull textMolecular biology & gene regulationEurope PMC

Cite

BibTeX RIS

BibTeX

@article{nardingennequin2026supervised,
  title = {{Supervised Protein Structure Classification Using Topological Persistence With DeltaFold}},
  author = {Joseph Nardin-Gennequin and Gabriela Ciuperca and Céline Brochier-Armanet and Philippe Malbos},
  journal = {Proteins - Structure, Function and Bioinformatics},
  year = {2026},
  month = sep,
  doi = {10.1002/prot.70163},
  url = {https://hal.science/hal-05766493v1},
  note = {CC BY-NC},
}

RIS

TY  - JOUR
TI  - Supervised Protein Structure Classification Using Topological Persistence With DeltaFold
AU  - Joseph Nardin-Gennequin
AU  - Gabriela Ciuperca
AU  - Céline Brochier-Armanet
AU  - Philippe Malbos
PY  - 2026
DA  - 2026/09/08
JO  - Proteins - Structure, Function and Bioinformatics
DO  - 10.1002/prot.70163
UR  - https://hal.science/hal-05766493v1
AB  - Recent advances in protein structure prediction have considerably increased the number of available structures, underscoring the need for scalable and accurate methods to compare and classify this huge amount of data. Current approaches based on sequence alignment or structural superposition often lack sensitivity and/or are computationally expensive. Here, we introduce the DeltaFold Classifier (DFC), a fast, alignment-free, protein structure classification pipeline based on topological data analysis. Protein three-dimensional structures are encoded using fixed-length vectors derived from persistent homology applied to point clouds of their spatial representation. These vectors, known as Biotopological Markers (BTMs), capture the intrinsic topological features of protein structure geometry-such as cycles and cavities-across multiple spatial scales. BTMs are invariant under translations and rotations, thereby avoiding the need for structural superposition. The DFC pipeline uses the features of these BTMs to train machine learning models for protein structure classification at various hierarchical levels defined in the SCOP and CATH classifications. It achieves performance comparable to that of structure-based comparison methods while substantially improving computational efficiency. It also outperforms sequence-based methods in tasks involving distant homology detection. In-depth analyses confirm that most BTM features contribute significantly to classification performance. These findings highlight the potential of topological vectorisations in structural bioinformatics and support the DFC pipeline as an effective and scalable tool for automated protein structure classification and annotation.
SN  - 0887-3585
SN  - 1097-0134
ER  -

Abstract

Related

Cite