Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

pLM-bVAE: protein language model-enhanced binary representation improves quantum annealing-based protein sequence design

Hiromi H. Ueda, Andrejs Tučs, Koji Tsuda, Mitsuo Umetsu, Yutaka Saitō

Published Nov 6, 2026• 0 citations
PDF (CC BY)Publisher

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.

DOI
10.64898/2026.11.05.764447

Related papers

Using quantum annealing to design lattice proteins

Anders Irbäck, Lucas Knuthson, Sandipan Mohanty +1 more

Quantum annealing has shown promise for finding solutions to difficult optimization problems, including protein folding. Recently, we used the D-Wave Advantage quantum annealer to explore the folding problem in a coarse-grained lattice model, the HP model, in which amino acids are classified into two broad groups: hydrophobic (H) and polar (P). Using a set of 22 HP sequences with up to 64 amino acids, we demonstrated the fast and consistent identification of the correct HP model ground states using the D-Wave hybrid quantum-classical solver. An equally relevant biophysical challenge, called the protein design problem, is the inverse of the above, where the task is to predict protein sequences that fold to a given structure. Here, we approach the design problem by a two-step procedure implemented and executed on a D-Wave machine. In the first step, we perform a pure sequence-space search by varying the type of amino acid at each sequence position, and seek sequences which minimize the HP-model energy of the target structure. After mapping this task onto an Ising spin-glass representation, we employ a hybrid quantum-classical solver to deliver energy-optimal sequences for structures with 30–64 amino acids, with a 100% success rate. In the second step, we filter the optimized sequences from the first step according to their ability to fold to the intended structure. In addition, we try solving the sequence optimization problem using only the quantum processing unit (QPU), which confines us to sizes ≤20 , due to exponentially decreasing success rates. To shed light on the pure QPU results, we investigate the effects of control errors caused by an imperfect implementation of the intended Hamiltonian on the QPU, by numerically analyzing the Schrödinger equation. We find that the simulated success rates in the presence of control noise semiquantitatively reproduce the modest pure QPU results for larger chains. Published by the American Physical Society 2024

arXiv:2402.09069•Physical Review Research•Feb 13, 2024•29 citations

Variational Quantum Approach for QUBO Lattice Protein Folding model

Ayushi, Madhvi Shakya

Protein folding is a fundamental biological process in which a linear chain of amino acids spontaneously adopts a unique three-dimensional structure essential for proper biological function, molecular recognition and transport of nutrients. Protein misfolding, on the other hand can lead to severe neurodegenerative disorders such as Alzheimer’s, Parkinson’s and cystic fibrosis. Traditional approaches to protein folding, such as knowledge-based and statistical methods, often face limitations in scalability and physical accuracy. To overcome these challenges, the problem has been reformulated as a combinatorial optimization problem classified as NP-hard. In this work, we implement the CVaR-VQE algorithm to solve a previously proposed QUBO formulation of lattice protein folding within a gate-based quantum computing framework. We demonstrate that, compared to the quantum annealing approach, this method significantly reduces qubit requirements and improves scalability, enabling more efficient and practical implementations on NISQ devices. Additionally, we benchmarked our results against classical optimization using IBM CPLEX, we observed that the proposed quantum approach yields high-quality solutions across multiple peptide instances.

IEEE International Conference on Recent Advances in Electronics, Communication, Computing, Automation and Power (RECCAP)•May 1, 2026•0 citations

Protein Folding and Design using Quantum Annealing

Sandipan Mohanty

Using a simple lattice model with a 2 letter amino acid alphabet (H: hydrophobic and P: polar), we have explored the important biophysical problems of protein folding and protein design. Our formulation of these problems features a simple algebraic form for the Hamiltonian irrespective of the system size and composition. Since exact results are available from for lattice HP chains up to a size of 30, we were able to thoroughly validate our approach. The D-Wave advantage quantum annealer successfully identifies the ground state of the HP model protein chain in 100% of cases. For a few longer protein chains with up to 64 amino acids, where exact enumerations were not available but extensive Monte Carlo studies exist, the D-Wave hybrid annealer found the correct ground states within minutes, once again with a 100% success rate. Applying the same technique to the protein design problem, we found novel HP protein sequences with the same ground state as the largest systems we studied for folding. In contrast to the sequences used for folding, some of our newly found sequences had unique rather than degenerate ground states.

•Jan 1, 2025•0 citations

Decoding Protein Sequences as a 'Quantum Language'… Demonstration of a QNLP-Based Classification Pipeline

inquantio

A study published on bioRxiv demonstrates for the first time the technique of treating protein sequences like sentences in natural language processing (NLP) and parsing them into parameterized quantum circuits using the Quantum Natural Language (QNLP) framework. It establishes a scheme that converts protein sequences into tensor networks represented by wires and boxes, and maps them onto actual quantum circuits through semantic functors. By generating protein syntax trees with a neural network-based parser and converting them into string diagrams optimized for quantum processor execution, the study proves that 'Quantum Tensor Networks (QTN)' achieve overwhelming computational accuracy in classifying vast protein sequences. [Quantum Biology Society] An innovative approach has been proposed to decode protein sequences—the most fundamental and complex codes of living organisms—by converting them into a natural language that quantum computers can comprehend. The paper titled "Application of Quantum Tensor Networks for Protein Classification", published in the preprint repository bioRxiv, introduces a groundbreaking pipeline that applies Quantum Natural Language Processing (QNLP) technology to protein sequence classification, opening a new horizon for next-generation bioinformatics. A research team from Pennsylvania State University, including Debarshi Kundu, Jian Wang, Archisman Ghosh, and Nikolay Dokholyan, led this innovative study. ■ QNLP: Reading Protein Sequences as Sentences The researchers introduced a unique perspective of treating protein sequences, which are arrays of amino acids, as if they were sentences composed in human language. To achieve this, they adopted the 'Quantum Natural Language (QNLP)' framework, which combines state-of-the-art computational natural language processing (NLP) techniques with quantum computing. Within this framework, protein sequences are parsed into syntax trees with grammatical structures through a neural network-based parser, laying the foundation for their direct conversion into parameterized quantum circuits. ■ Transformation into Tensor Networks and String Diagrams In this process, protein sequences are converted into a tensor network scheme, geometrically represented by wires and boxes. The researchers defined a sophisticated semantic function (functor) that perfectly maps this abstract network to the operational structure of actual quantum circuits. The generated syntax trees are ultimately transformed into string diagrams, a format optimized for execution on quantum processors. Consequently, the constructed Quantum Tensor Networks (QTN) demonstrated overwhelming computational accuracy in machine learning tasks that involve extracting features and functionally classifying highly diverse and complex protein sequences, even in environments with a limited number of available qubits. This demonstration is highly significant as it establishes a powerful workflow in drug discovery and biotechnology, enabling rapid and accurate analysis of massive genomic data and protein interaction structures through quantum algorithms, transcending the limits of conventional classical computers. #QuantumTensorNetworks #QNLP #ProteinClassification #QuantumMachineLearning #QuantumLanguageModel #ProteinSequenceAnalysis #QuantumBiology #Biophysics #ArtificialIntelligence #KoreanQuantumBiologySociety https://www.biorxiv.org/content/10.1101/2024.03.11.584501v1

•Jul 10, 2026•0 citations

Quantum Boltzmann Machine Enhanced Variational Autoencoder for Cds Sequence Modeling

Junya Wang, Qi Gao, Yin Ma +2 more

Coding sequences (CDSs) are high-dimensional discrete biological sequences with recognizable sequence-level statistics such as GC content and codon usage. In this paper, CDS data are used as a structured sequence-modeling benchmark to study whether a quantum Boltzmann-machine-enhanced VAE (QVAE) can learn latent dependencies in discrete biological sequences. The QBM prior uses a diagonal Ising-type Hamiltonian to model dependencies among binary latent variables, and converts the negative-phase update into an Ising-type sampling task suitable for quantum or coherent-Ising samplers. Compared with Gaussian VAE and Bernoulli DVAE baselines, QVAE+Mamba achieves high decoded-sequence diversity with a mean normalized pairwise edit distance of 0.691, while preserving selected dataset statistics including GC-content and codon-frequency trends. The reported QVAE+Mamba result is obtained using a physical coherent Ising machine, while classical simulation gives similar behavior in our additional checks. These results suggest that a quantum structured prior can support high-dimensional discrete sequence modeling. The generated sequences should not be interpreted as protein-preserving or therapeutically optimized mRNA designs without additional biological constraints and functional validation.

International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC)•Jul 1, 2026•0 citations

Application of Quantum Tensor Networks for Protein Classification

Debarshi Kundu, Archisman Ghosh, Srinivasan Ekambaram +3 more

Computational methods in drug discovery significantly reduce both time and experimental costs. Nonetheless, certain computational tasks in drug discovery can be daunting with classical computing techniques which can be potentially overcome using quantum computing. A crucial task within this domain involves the functional classification of proteins. However, a challenge lies in adequately representing lengthy protein sequences given the limited number of qubits available in existing noisy quantum computers. We show that protein sequences can be thought of as sentences in natural language processing and can be parsed using the existing Quantum Natural Language framework into parameterized quantum circuits of reasonable qubits, which can be trained to solve various protein-related machine-learning problems. We classify proteins based on their sub-cellular locations—a pivotal task in bioinformatics that is key to understanding biological processes and disease mechanisms. Leveraging the quantum-enhanced processing capabilities, we demonstrate that Quantum Tensor Networks (QTN) can effectively handle the complexity and diversity of protein sequences. We present a detailed methodology that adapts QTN architectures to the nuanced requirements of protein data, supported by comprehensive experimental results. We demonstrate two distinct QTNs, inspired by classical recurrent neural networks (RNN) and convolutional neural networks (CNN), to solve the binary classification task mentioned above. Our top-performing quantum model has achieved a 94% accuracy rate, which is comparable to the performance of a classical model that uses the ESM2 protein language model embeddings. It’s noteworthy that the ESM2 model is extremely large, containing 8 million parameters in its smallest configuration, whereas our best quantum model requires only around 800 parameters. We demonstrate that these hybrid models exhibit promising performance, showcasing their potential to compete with classical models of similar complexity.

ACM Great Lakes Symposium on VLSI (GLSVLSI)•Jun 10, 2024•10 citations
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.
Quantum annealing has shown promise for finding solutions to difficult optimization problems, including protein folding. Recently, we used the D-Wave Advantage quantum annealer to explore the folding problem in a coarse-grained lattice model, the HP model, in which amino acids are classified into two broad groups: hydrophobic (H) and polar (P). Using a set of 22 HP sequences with up to 64 amino acids, we demonstrated the fast and consistent identification of the correct HP model ground states using the D-Wave hybrid quantum-classical solver. An equally relevant biophysical challenge, called the protein design problem, is the inverse of the above, where the task is to predict protein sequences that fold to a given structure. Here, we approach the design problem by a two-step procedure implemented and executed on a D-Wave machine. In the first step, we perform a pure sequence-space search by varying the type of amino acid at each sequence position, and seek sequences which minimize the HP-model energy of the target structure. After mapping this task onto an Ising spin-glass representation, we employ a hybrid quantum-classical solver to deliver energy-optimal sequences for structures with 30–64 amino acids, with a 100% success rate. In the second step, we filter the optimized sequences from the first step according to their ability to fold to the intended structure. In addition, we try solving the sequence optimization problem using only the quantum processing unit (QPU), which confines us to sizes ≤20 , due to exponentially decreasing success rates. To shed light on the pure QPU results, we investigate the effects of control errors caused by an imperfect implementation of the intended Hamiltonian on the QPU, by numerically analyzing the Schrödinger equation. We find that the simulated success rates in the presence of control noise semiquantitatively reproduce the modest pure QPU results for larger chains. Published by the American Physical Society 2024
Protein folding is a fundamental biological process in which a linear chain of amino acids spontaneously adopts a unique three-dimensional structure essential for proper biological function, molecular recognition and transport of nutrients. Protein misfolding, on the other hand can lead to severe neurodegenerative disorders such as Alzheimer’s, Parkinson’s and cystic fibrosis. Traditional approaches to protein folding, such as knowledge-based and statistical methods, often face limitations in scalability and physical accuracy. To overcome these challenges, the problem has been reformulated as a combinatorial optimization problem classified as NP-hard. In this work, we implement the CVaR-VQE algorithm to solve a previously proposed QUBO formulation of lattice protein folding within a gate-based quantum computing framework. We demonstrate that, compared to the quantum annealing approach, this method significantly reduces qubit requirements and improves scalability, enabling more efficient and practical implementations on NISQ devices. Additionally, we benchmarked our results against classical optimization using IBM CPLEX, we observed that the proposed quantum approach yields high-quality solutions across multiple peptide instances.
Using a simple lattice model with a 2 letter amino acid alphabet (H: hydrophobic and P: polar), we have explored the important biophysical problems of protein folding and protein design. Our formulation of these problems features a simple algebraic form for the Hamiltonian irrespective of the system size and composition. Since exact results are available from for lattice HP chains up to a size of 30, we were able to thoroughly validate our approach. The D-Wave advantage quantum annealer successfully identifies the ground state of the HP model protein chain in 100% of cases. For a few longer protein chains with up to 64 amino acids, where exact enumerations were not available but extensive Monte Carlo studies exist, the D-Wave hybrid annealer found the correct ground states within minutes, once again with a 100% success rate. Applying the same technique to the protein design problem, we found novel HP protein sequences with the same ground state as the largest systems we studied for folding. In contrast to the sequences used for folding, some of our newly found sequences had unique rather than degenerate ground states.
A study published on bioRxiv demonstrates for the first time the technique of treating protein sequences like sentences in natural language processing (NLP) and parsing them into parameterized quantum circuits using the Quantum Natural Language (QNLP) framework. It establishes a scheme that converts protein sequences into tensor networks represented by wires and boxes, and maps them onto actual quantum circuits through semantic functors. By generating protein syntax trees with a neural network-based parser and converting them into string diagrams optimized for quantum processor execution, the study proves that 'Quantum Tensor Networks (QTN)' achieve overwhelming computational accuracy in classifying vast protein sequences. [Quantum Biology Society] An innovative approach has been proposed to decode protein sequences—the most fundamental and complex codes of living organisms—by converting them into a natural language that quantum computers can comprehend. The paper titled "Application of Quantum Tensor Networks for Protein Classification", published in the preprint repository bioRxiv, introduces a groundbreaking pipeline that applies Quantum Natural Language Processing (QNLP) technology to protein sequence classification, opening a new horizon for next-generation bioinformatics. A research team from Pennsylvania State University, including Debarshi Kundu, Jian Wang, Archisman Ghosh, and Nikolay Dokholyan, led this innovative study. ■ QNLP: Reading Protein Sequences as Sentences The researchers introduced a unique perspective of treating protein sequences, which are arrays of amino acids, as if they were sentences composed in human language. To achieve this, they adopted the 'Quantum Natural Language (QNLP)' framework, which combines state-of-the-art computational natural language processing (NLP) techniques with quantum computing. Within this framework, protein sequences are parsed into syntax trees with grammatical structures through a neural network-based parser, laying the foundation for their direct conversion into parameterized quantum circuits. ■ Transformation into Tensor Networks and String Diagrams In this process, protein sequences are converted into a tensor network scheme, geometrically represented by wires and boxes. The researchers defined a sophisticated semantic function (functor) that perfectly maps this abstract network to the operational structure of actual quantum circuits. The generated syntax trees are ultimately transformed into string diagrams, a format optimized for execution on quantum processors. Consequently, the constructed Quantum Tensor Networks (QTN) demonstrated overwhelming computational accuracy in machine learning tasks that involve extracting features and functionally classifying highly diverse and complex protein sequences, even in environments with a limited number of available qubits. This demonstration is highly significant as it establishes a powerful workflow in drug discovery and biotechnology, enabling rapid and accurate analysis of massive genomic data and protein interaction structures through quantum algorithms, transcending the limits of conventional classical computers. #QuantumTensorNetworks #QNLP #ProteinClassification #QuantumMachineLearning #QuantumLanguageModel #ProteinSequenceAnalysis #QuantumBiology #Biophysics #ArtificialIntelligence #KoreanQuantumBiologySociety https://www.biorxiv.org/content/10.1101/2024.03.11.584501v1
Coding sequences (CDSs) are high-dimensional discrete biological sequences with recognizable sequence-level statistics such as GC content and codon usage. In this paper, CDS data are used as a structured sequence-modeling benchmark to study whether a quantum Boltzmann-machine-enhanced VAE (QVAE) can learn latent dependencies in discrete biological sequences. The QBM prior uses a diagonal Ising-type Hamiltonian to model dependencies among binary latent variables, and converts the negative-phase update into an Ising-type sampling task suitable for quantum or coherent-Ising samplers. Compared with Gaussian VAE and Bernoulli DVAE baselines, QVAE+Mamba achieves high decoded-sequence diversity with a mean normalized pairwise edit distance of 0.691, while preserving selected dataset statistics including GC-content and codon-frequency trends. The reported QVAE+Mamba result is obtained using a physical coherent Ising machine, while classical simulation gives similar behavior in our additional checks. These results suggest that a quantum structured prior can support high-dimensional discrete sequence modeling. The generated sequences should not be interpreted as protein-preserving or therapeutically optimized mRNA designs without additional biological constraints and functional validation.
Computational methods in drug discovery significantly reduce both time and experimental costs. Nonetheless, certain computational tasks in drug discovery can be daunting with classical computing techniques which can be potentially overcome using quantum computing. A crucial task within this domain involves the functional classification of proteins. However, a challenge lies in adequately representing lengthy protein sequences given the limited number of qubits available in existing noisy quantum computers. We show that protein sequences can be thought of as sentences in natural language processing and can be parsed using the existing Quantum Natural Language framework into parameterized quantum circuits of reasonable qubits, which can be trained to solve various protein-related machine-learning problems. We classify proteins based on their sub-cellular locations—a pivotal task in bioinformatics that is key to understanding biological processes and disease mechanisms. Leveraging the quantum-enhanced processing capabilities, we demonstrate that Quantum Tensor Networks (QTN) can effectively handle the complexity and diversity of protein sequences. We present a detailed methodology that adapts QTN architectures to the nuanced requirements of protein data, supported by comprehensive experimental results. We demonstrate two distinct QTNs, inspired by classical recurrent neural networks (RNN) and convolutional neural networks (CNN), to solve the binary classification task mentioned above. Our top-performing quantum model has achieved a 94% accuracy rate, which is comparable to the performance of a classical model that uses the ESM2 protein language model embeddings. It’s noteworthy that the ESM2 model is extremely large, containing 8 million parameters in its smallest configuration, whereas our best quantum model requires only around 800 parameters. We demonstrate that these hybrid models exhibit promising performance, showcasing their potential to compete with classical models of similar complexity.