Novel hybrid protein scaffold gap filling using weighted machine learning ensemble, beam search, and mass-constrained reranking
Abstract
Protein scaffold gap filling is an important computational task in protein sequence reconstruction, where missing amino acid regions must be inferred from incomplete scaffold information. This study proposes a hybrid machine learning and mass constrained reranking framework for protein scaffold gap filling under known-gap-size and known-gapmass settings. Homologous protein sequences from MabCampath, P5A proteoform, and carbonic anhydrase 2 were used to generate masked 11-mer residue-level samples and fullgap evaluation cases. The residue prediction task was formulated as a 20-class amino acid classification problem using first-, middle-, and last-position masking. Multiple classical machine learning models were trained using raw encoded, row-average, and SVD-reduced features, and the strongest models were combined through a validation-accuracy-weighted ensemble. For known-size gap reconstruction, beam search was used to generate complete missing peptide sequences from residue-level probability estimates. For known-mass reconstruction, mass-constrained homologous candidate retrieval was combined with hybrid reranking based on mass validity, homologous frequency, context support, ensemble likelihood, mass error, and length penalty. The proposed framework achieved 95.41% residue-level validation accuracy, 87.50% known-size exact-match accuracy, and 100% top-5 recovery on seven CAH2 known-mass benchmark cases. These results indicate that the proposed framework can effectively reconstruct missing protein regions by integrating local sequence learning, homologous evidence, peptide mass constraints, and biochemical validation.
Related
- cryoWEight: Conformational ensembles from cryo-EM particle images with weighted ensemble simulations
- METANet: a supervised ensemble learning framework for reconstructing direct and functional tissue-specific transcription factor networks.
- Deciphering isonicotinylation and mast cell-associated pathogenic patterns in Duchenne muscular dystrophy: evidence from ensemble learning-driven multi-omics and in vitro validation
- An Interpretable Ensemble-Learning Framework for Decoding Multi-Component–Multi-Bioactivity Relationships in Salvia miltiorrhiza Based on 1H NMR Metabolomics and Lifecycle-Oriented Bioassays
- Multi-source data integration and ensemble machine learning analysis of the role of Corilagin in regulating endoplasmic reticulum stress and alleviating intestinal ischemia reperfusion injury in mice
BibTeX
@misc{shrestha2026novel,
title = {{Novel hybrid protein scaffold gap filling using weighted machine learning ensemble, beam search, and mass-constrained reranking}},
author = {Tahmid Enam Shrestha and Md. Manzurul Hasan and Md. Rafiqul Islam},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.05436},
eprint = {2609.05436},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.05436},
}
RIS
TY - UNPB
TI - Novel hybrid protein scaffold gap filling using weighted machine learning ensemble, beam search, and mass-constrained reranking
AU - Tahmid Enam Shrestha
AU - Md. Manzurul Hasan
AU - Md. Rafiqul Islam
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.05436
UR - https://arxiv.org/abs/2609.05436
AB - Protein scaffold gap filling is an important computational task in protein sequence reconstruction, where missing amino acid regions must be inferred from incomplete scaffold information. This study proposes a hybrid machine learning and mass constrained reranking framework for protein scaffold gap filling under known-gap-size and known-gapmass settings. Homologous protein sequences from MabCampath, P5A proteoform, and carbonic anhydrase 2 were used to generate masked 11-mer residue-level samples and fullgap evaluation cases. The residue prediction task was formulated as a 20-class amino acid classification problem using first-, middle-, and last-position masking. Multiple classical machine learning models were trained using raw encoded, row-average, and SVD-reduced features, and the strongest models were combined through a validation-accuracy-weighted ensemble. For known-size gap reconstruction, beam search was used to generate complete missing peptide sequences from residue-level probability estimates. For known-mass reconstruction, mass-constrained homologous candidate retrieval was combined with hybrid reranking based on mass validity, homologous frequency, context support, ensemble likelihood, mass error, and length penalty. The proposed framework achieved 95.41% residue-level validation accuracy, 87.50% known-size exact-match accuracy, and 100% top-5 recovery on seven CAH2 known-mass benchmark cases. These results indicate that the proposed framework can effectively reconstruct missing protein regions by integrating local sequence learning, homologous evidence, peptide mass constraints, and biochemical validation.
ER -