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

arXiv:2104.00746

Drug Discovery Approaches using Quantum Machine Learning

Junde Li, Mahabubul Alam, Congzhou Mike Sha, Jian Wang, Nikolay V. Dokholyan, Swaroop Ghosh

Published Apr 1, 2021• 15 citations
arXivHTMLPDF

Abstract

Traditional drug discovery pipeline takes several years and cost billions of dollars. Deep generative and predictive models are widely adopted to assist in drug development. Classical machines cannot efficiently produce atypical patterns of quantum computers which might improve the training quality of learning tasks. We propose a suite of quantum machine learning techniques e.g., generative adversarial network (GAN), convolutional neural network (CNN) and variational auto-encoder (VAE) to generate small drug molecules, classify binding pockets in proteins, and generate large drug molecules, respectively.

DOI
10.48550/arxiv.2104.00746

Related papers

Invited: Drug Discovery Approaches using Quantum Machine Learning

Junde Li, Mahabubul Alam, Congzhou Mike Sha +3 more

Traditional drug discovery pipelines can require multiple years and billions of dollars of investment. Deep generative and discriminative models are widely adopted to assist in drug development. Classical machines cannot efficiently reproduce the atypical patterns of quantum computers, which may improve the quality of learned tasks. We propose a suite of quantum machine learning techniques: incorporating generative adversarial networks (GAN), convolutional neural networks (CNN) and variational auto-encoders (VAE) to generate small drug molecules, classify binding pockets in proteins, and generate large drug molecules, respectively.

ACM/IEEE Design Automation Conference (DAC)•Nov 8, 2021•34 citations

Quantum Generative Models for Small Molecule Drug Discovery

Junde Li, Rasit Onur Topaloglu, Swaroop Ghosh

Existing drug discovery pipelines take 5–10 years and cost billions of dollars. Computational approaches aim to sample from regions of the whole molecular and solid-state compounds called chemical space, which could be on the order of$10^{60}$. Deep generative models can model the underlying probability distribution of both the physical structures and property of drugs and relate them nonlinearly. By exploiting patterns in massive datasets, these models can distill salient features that characterize the molecules. Generative adversarial networks (GANs) discover drug candidates by generating molecular structures that obey chemical and physical properties and show affinity toward binding with the receptor for a target disease. However, classical GANs cannot explore certain regions of the chemical space and suffer from training instabilities. The practical utility of such models is limited due to the vast size of the search space, characterized by millions of parameters. A full quantum GAN may require more than 90 qubits even to generate small molecules with up to nine heavy atoms. The proposed quantum GAN with a hybrid generator (QGAN-HG) model is composed of a hybrid quantum generator that supports various number of qubits and quantum circuit layers, and a classical discriminator. The QGAN-HG with less than 20% of the original parameters can learn molecular distributions as efficiently as its classical counterpart. Another extended version of the proposed QGAN-HG, which utilizes multiple quantum subcircuits, considerably accelerates our standard QGAN-HG training process and avoids the potential gradient vanishing issue of deep neural networks.

arXiv:2101.03438•IEEE Transactions on Quantum Engineering•Jan 1, 2021•121 citations

Exploring the Advantages of Quantum Generative Adversarial Networks in Generative Chemistry

Po-Yu Kao, Ya-Chu Yang, Wei-Yin Chiang +8 more

De novo drug design with desired biological activities is crucial for developing novel therapeutics for patients. The drug development process is time- and resource-consuming, and it has a low probability of success. Recent advances in machine learning and deep learning technology have reduced the time and cost of the discovery process and therefore, improved pharmaceutical research and development. In this paper, we explore the combination of two rapidly developing fields with lead candidate discovery in the drug development process. First, artificial intelligence has already been demonstrated to successfully accelerate conventional drug design approaches. Second, quantum computing has demonstrated promising potential in different applications, such as quantum chemistry, combinatorial optimizations, and machine learning. This article explores hybrid quantum-classical generative adversarial networks (GAN) for small molecule discovery. We substituted each element of GAN with a variational quantum circuit (VQC) and demonstrated the quantum advantages in the small drug discovery. Utilizing a VQC in the noise generator of a GAN to generate small molecules achieves better physicochemical properties and performance in the goal-directed benchmark than the classical counterpart. Moreover, we demonstrate the potential of a VQC with only tens of learnable parameters in the generator of GAN to generate small molecules. We also demonstrate the quantum advantage of a VQC in the discriminator of GAN. In this hybrid model, the number of learnable parameters is significantly less than the classical ones, and it can still generate valid molecules. The hybrid model with only tens of training parameters in the quantum discriminator outperforms the MLP-based one in terms of both generated molecule properties and the achieved KL divergence. However, the hybrid quantum-classical GANs still face challenges in generating unique and valid molecules compared to their classical counterparts.

arXiv:2210.16823•Journal of Chemical Information and Modeling•May 12, 2023•92 citations

A Next Generation Innovation in Drug Discovery Using Quantum Generative AI

Dr.C. Krishna Priya Dr.C. Krishna Priya, Nazeer Shaik, P. Chitralingappa

The convergence of Quantum Computing and Generative Artificial Intelligence (AI) marks a transformative leap in the field of drug discovery. Traditional drug development pipelines are often slow, costly, and limited by classical computational constraints. This paper presents a novel hybrid approach—QuantumGeneraDrug—that integrates quantum generative models with deep learning architectures to accelerate molecule generation, optimize binding affinities, and reduce computation time. A comprehensive literature survey highlights the evolution of both quantum algorithms and generative AI models applied to pharmaceutical research. The proposed system demonstrates improved performance over existing frameworks in key metrics such as valid molecule rate, druglikeness (QED) score, binding affinity accuracy, and processing time per compound. Comparative results are illustrated using numerical tables and visualized via bar and pie charts. The study concludes that Quantum Generative AI holds immense promise for next-generation drug discovery, especially in tackling complex diseases and enabling personalized medicine.

International Journal of Pharmaceutical Research and Applications•Apr 1, 2025•1 citation

Quantum Computing in Drug Discovery

Bancha Yingngam, Alex Khang

The drug discovery process necessitates a significant investment of time and resources. Typically, over a decade and billions of dollars are required to bring a single drug to market. However, quantum computing may provide a solution to these challenges. It not only has the potential to streamline drug discovery but also to enhance the quality and accuracy of the results. This chapter explores the innovative amalgamation of quantum computing and pharmaceutical research. Traditional drug discovery methods, due to their time-consuming and costly nature, face numerous obstacles. Quantum computing, armed with its extraordinary computational power, could surmount these hurdles by providing efficient and precise simulations of drug molecules. This could, in turn, expedite the discovery of effective drug candidates. The chapter delves into the fundamentals of quantum computing, its application in drug discovery, and specific techniques relevant to this field. It also presents case studies of successful applications and discusses prospects, taking current limitations into account. A particularly exciting development in this field is quantum machine learning, a fusion of quantum mechanics and machine learning. This synergy could accelerate scientific advances by offering robust predictive modeling for drug discovery. Consequently, this chapter provides an in-depth exploration of a potential future in which quantum technology, artificial intelligence, and robotics are fully integrated. Such integration could revolutionize drug discovery, heralding a new era in health care and reshaping the boundaries of medical science and therapeutic development.

CRC Press eBooks•Aug 2, 2024•5 citations

Quantum Machine Learning in Drug Discovery: Current State and Challenges

Maria Avramouli, Ilias Κ. Savvas, Anna Vasilaki +2 more

The drug discovery process is a time-consuming and quite expensive process. The predictive models of machine learning algorithms have been used efficiently for years in various stages of the drug discovery pipeline. The complexity of these algorithms increases as the size of the molecule increases, adding a single atom to a molecule increases the number of possible combinations. Quantum computers with quantum supremacy can play an important role in complex calculations. Combining the two technologies in practice is a complex endeavor that requires diverse, interdisciplinary teams of scientists working together to be able to integrate the two technologies with the goal of reducing cost and time in drug discovery.

Panhellenic Conference on Informatics•Nov 25, 2022•13 citations
Traditional drug discovery pipeline takes several years and cost billions of dollars. Deep generative and predictive models are widely adopted to assist in drug development. Classical machines cannot efficiently produce atypical patterns of quantum computers which might improve the training quality of learning tasks. We propose a suite of quantum machine learning techniques e.g., generative adversarial network (GAN), convolutional neural network (CNN) and variational auto-encoder (VAE) to generate small drug molecules, classify binding pockets in proteins, and generate large drug molecules, respectively.
Traditional drug discovery pipelines can require multiple years and billions of dollars of investment. Deep generative and discriminative models are widely adopted to assist in drug development. Classical machines cannot efficiently reproduce the atypical patterns of quantum computers, which may improve the quality of learned tasks. We propose a suite of quantum machine learning techniques: incorporating generative adversarial networks (GAN), convolutional neural networks (CNN) and variational auto-encoders (VAE) to generate small drug molecules, classify binding pockets in proteins, and generate large drug molecules, respectively.
Existing drug discovery pipelines take 5–10 years and cost billions of dollars. Computational approaches aim to sample from regions of the whole molecular and solid-state compounds called chemical space, which could be on the order of106010^{60}1060. Deep generative models can model the underlying probability distribution of both the physical structures and property of drugs and relate them nonlinearly. By exploiting patterns in massive datasets, these models can distill salient features that characterize the molecules. Generative adversarial networks (GANs) discover drug candidates by generating molecular structures that obey chemical and physical properties and show affinity toward binding with the receptor for a target disease. However, classical GANs cannot explore certain regions of the chemical space and suffer from training instabilities. The practical utility of such models is limited due to the vast size of the search space, characterized by millions of parameters. A full quantum GAN may require more than 90 qubits even to generate small molecules with up to nine heavy atoms. The proposed quantum GAN with a hybrid generator (QGAN-HG) model is composed of a hybrid quantum generator that supports various number of qubits and quantum circuit layers, and a classical discriminator. The QGAN-HG with less than 20% of the original parameters can learn molecular distributions as efficiently as its classical counterpart. Another extended version of the proposed QGAN-HG, which utilizes multiple quantum subcircuits, considerably accelerates our standard QGAN-HG training process and avoids the potential gradient vanishing issue of deep neural networks.
De novo drug design with desired biological activities is crucial for developing novel therapeutics for patients. The drug development process is time- and resource-consuming, and it has a low probability of success. Recent advances in machine learning and deep learning technology have reduced the time and cost of the discovery process and therefore, improved pharmaceutical research and development. In this paper, we explore the combination of two rapidly developing fields with lead candidate discovery in the drug development process. First, artificial intelligence has already been demonstrated to successfully accelerate conventional drug design approaches. Second, quantum computing has demonstrated promising potential in different applications, such as quantum chemistry, combinatorial optimizations, and machine learning. This article explores hybrid quantum-classical generative adversarial networks (GAN) for small molecule discovery. We substituted each element of GAN with a variational quantum circuit (VQC) and demonstrated the quantum advantages in the small drug discovery. Utilizing a VQC in the noise generator of a GAN to generate small molecules achieves better physicochemical properties and performance in the goal-directed benchmark than the classical counterpart. Moreover, we demonstrate the potential of a VQC with only tens of learnable parameters in the generator of GAN to generate small molecules. We also demonstrate the quantum advantage of a VQC in the discriminator of GAN. In this hybrid model, the number of learnable parameters is significantly less than the classical ones, and it can still generate valid molecules. The hybrid model with only tens of training parameters in the quantum discriminator outperforms the MLP-based one in terms of both generated molecule properties and the achieved KL divergence. However, the hybrid quantum-classical GANs still face challenges in generating unique and valid molecules compared to their classical counterparts.
The convergence of Quantum Computing and Generative Artificial Intelligence (AI) marks a transformative leap in the field of drug discovery. Traditional drug development pipelines are often slow, costly, and limited by classical computational constraints. This paper presents a novel hybrid approach—QuantumGeneraDrug—that integrates quantum generative models with deep learning architectures to accelerate molecule generation, optimize binding affinities, and reduce computation time. A comprehensive literature survey highlights the evolution of both quantum algorithms and generative AI models applied to pharmaceutical research. The proposed system demonstrates improved performance over existing frameworks in key metrics such as valid molecule rate, druglikeness (QED) score, binding affinity accuracy, and processing time per compound. Comparative results are illustrated using numerical tables and visualized via bar and pie charts. The study concludes that Quantum Generative AI holds immense promise for next-generation drug discovery, especially in tackling complex diseases and enabling personalized medicine.
The drug discovery process necessitates a significant investment of time and resources. Typically, over a decade and billions of dollars are required to bring a single drug to market. However, quantum computing may provide a solution to these challenges. It not only has the potential to streamline drug discovery but also to enhance the quality and accuracy of the results. This chapter explores the innovative amalgamation of quantum computing and pharmaceutical research. Traditional drug discovery methods, due to their time-consuming and costly nature, face numerous obstacles. Quantum computing, armed with its extraordinary computational power, could surmount these hurdles by providing efficient and precise simulations of drug molecules. This could, in turn, expedite the discovery of effective drug candidates. The chapter delves into the fundamentals of quantum computing, its application in drug discovery, and specific techniques relevant to this field. It also presents case studies of successful applications and discusses prospects, taking current limitations into account. A particularly exciting development in this field is quantum machine learning, a fusion of quantum mechanics and machine learning. This synergy could accelerate scientific advances by offering robust predictive modeling for drug discovery. Consequently, this chapter provides an in-depth exploration of a potential future in which quantum technology, artificial intelligence, and robotics are fully integrated. Such integration could revolutionize drug discovery, heralding a new era in health care and reshaping the boundaries of medical science and therapeutic development.
The drug discovery process is a time-consuming and quite expensive process. The predictive models of machine learning algorithms have been used efficiently for years in various stages of the drug discovery pipeline. The complexity of these algorithms increases as the size of the molecule increases, adding a single atom to a molecule increases the number of possible combinations. Quantum computers with quantum supremacy can play an important role in complex calculations. Combining the two technologies in practice is a complex endeavor that requires diverse, interdisciplinary teams of scientists working together to be able to integrate the two technologies with the goal of reducing cost and time in drug discovery.