Rprot-Vec: a deep learning approach for fast protein structure similarity calculation
Authors:
Open Access
- 10 July 2025
- journal article
- research article
- Published by Springer Nature in BMC Bioinformatics
- Vol. 26 (1) , 1-16
Abstract
Predicting protein structural similarity and detecting homologous sequences remain fundamental and challenging tasks in computational biology. Accurate identification of structural homologs enables function inference for newly discovered or unannotated proteins. Traditional approaches often require full 3D structural data, which is unavailable for most proteins. Thus, there is a need for sequence-based methods capable of inferring structural similarity efficiently and at scale. We present Rprot-Vec (Rapid Protein Vector), a deep learning model that predicts protein structural similarity and performs homology detection using only primary sequence data. The model integrates bidirectional GRU and multi-scale CNN layers with ProtT5-based encoding, enabling accurate and fast similarity estimation. Rprot-Vec achieves a 65.3% accurate similarity prediction rate in the homologous region (TM-score > 0.8), with an average prediction error of 0.0561 across all TM-score intervals. Despite having only 41% of the parameters of TM-vec, Rprot-Vec outperforms both public and locally trained TM-vec baselines in all tested settings. Additionally, we constructed and released three curated training datasets (CATH_TM_score_S/M/L), supporting further research in this area. Rprot-Vec offers a fast and lightweight solution for sequence-based structural similarity prediction. It can be applied in protein homology detection, structure-function inference, drug repurposing, and other downstream biological tasks. Its open-source availability and released datasets facilitate broader adoption and further development by the research community.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- DrugBank 6.0: the DrugBank Knowledgebase for 2024Nucleic Acids Research, 2023
- Protein remote homology detection and structural alignment using deep learningNature Biotechnology, 2023
- US-align: universal structure alignments of proteins, nucleic acids, and macromolecular complexesNature Methods, 2022
- Protein Data Bank (PDB): The Single Global Macromolecular Structure Archive2017
- The Phyre2 web portal for protein modeling, prediction and analysisNature Protocols, 2015
- The HHpred interactive server for protein homology detection and structure predictionNucleic Acids Research, 2005
- TM-align: a protein structure alignment algorithm based on the TM-scoreNucleic Acids Research, 2005
- From protein structure to functionCurrent Opinion in Structural Biology, 1999
- CATH – a hierarchic classification of protein domain structuresStructure, 1997
- Dali: a network tool for protein structure comparisonTrends in Biochemical Sciences, 1995