pLM-bVAE: protein language model-enhanced binary representation improves quantum annealing-based protein sequence design
- 1Kitasato University
Abstract
Quantum annealing (QA) has been explored as an approach for protein design in vast combinatorial sequence spaces. Applying QA to protein sequence design requires amino acid sequences to be encoded as binary vectors, and optimized vectors to be decoded back into amino acid sequences. Thus, both the quality of binary encoding and sequence reconstruction accuracy are important for effective QA-based optimization. Binary variational autoencoder (bVAE) has been used to map protein sequences to binary representations in QA-based protein sequence design. However, bVAE was originally developed for natural language modeling, and its suitability for proteins has not been systematically evaluated. Here, we present pLM-bVAE, which incorporates protein representations derived from a pretrained protein language model (pLM) into the original bVAE model. In computational experiments on three public protein variant datasets, pLM-bVAE showed higher sequence reconstruction accuracy and binary encoding performance than bVAE. Moreover, we incorporated pLM-bVAE into a QA-based protein sequence design framework. Across all three datasets, pLM-bVAE generated more high-scoring sequences with greater sequence dissimilarity from the training and validation data than bVAE. Our results demonstrate that pLM-bVAE provides an effective binary representation for improving QA-based protein sequence design. Availability The source code used in this manuscript is available at https://github.com/hueda8/pLM-bVAE.
Related
- Language-guided domain adaptation improves protein sequence rep-resentations for antimicrobial resistance analysis
- Standing in unperturbed balance improves spatial memory and facilitates allocentric representation
- Sequence-aware genotyping improves the accuracy of molecular markers associated with cassava mosaic disease resistance loci
- Few-shot regulatory sequence design with a genomic language model
- Sequence-only antigen context improves modeling of antibody hypervariable regions
BibTeX
@misc{ueda2026plmbvae,
title = {{pLM-bVAE: protein language model-enhanced binary representation improves quantum annealing-based protein sequence design}},
author = {H. H. Ueda and A. Tucs and K. Tsuda and M. Umetsu and Y. Saito},
howpublished = {bioRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.05.764447},
url = {https://www.biorxiv.org/content/10.64898/2026.11.05.764447v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - pLM-bVAE: protein language model-enhanced binary representation improves quantum annealing-based protein sequence design
AU - H. H. Ueda
AU - A. Tucs
AU - K. Tsuda
AU - M. Umetsu
AU - Y. Saito
PY - 2026
DA - 2026/11/05
PB - bioRxiv
DO - 10.64898/2026.11.05.764447
UR - https://www.biorxiv.org/content/10.64898/2026.11.05.764447v1
AB - Quantum annealing (QA) has been explored as an approach for protein design in vast combinatorial sequence spaces. Applying QA to protein sequence design requires amino acid sequences to be encoded as binary vectors, and optimized vectors to be decoded back into amino acid sequences. Thus, both the quality of binary encoding and sequence reconstruction accuracy are important for effective QA-based optimization. Binary variational autoencoder (bVAE) has been used to map protein sequences to binary representations in QA-based protein sequence design. However, bVAE was originally developed for natural language modeling, and its suitability for proteins has not been systematically evaluated. Here, we present pLM-bVAE, which incorporates protein representations derived from a pretrained protein language model (pLM) into the original bVAE model. In computational experiments on three public protein variant datasets, pLM-bVAE showed higher sequence reconstruction accuracy and binary encoding performance than bVAE. Moreover, we incorporated pLM-bVAE into a QA-based protein sequence design framework. Across all three datasets, pLM-bVAE generated more high-scoring sequences with greater sequence dissimilarity from the training and validation data than bVAE. Our results demonstrate that pLM-bVAE provides an effective binary representation for improving QA-based protein sequence design. Availability The source code used in this manuscript is available at https://github.com/hueda8/pLM-bVAE.
ER -