Quantum Generative Models for Small Molecule Drug Discovery
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 <inline-formula><tex-math notation="LaTe...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Transactions on Quantum Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9520764/ |
| _version_ | 1818752872013103104 |
|---|---|
| author | Junde Li Rasit O. Topaloglu Swaroop Ghosh |
| author_facet | Junde Li Rasit O. Topaloglu Swaroop Ghosh |
| author_sort | Junde Li |
| collection | DOAJ |
| description | 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 <inline-formula><tex-math notation="LaTeX">$10^{60}$</tex-math></inline-formula>. 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. |
| first_indexed | 2024-12-18T04:58:21Z |
| format | Article |
| id | doaj.art-15b6705e890a430f904ab7194f5d54bb |
| institution | Directory Open Access Journal |
| issn | 2689-1808 |
| language | English |
| last_indexed | 2024-12-18T04:58:21Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Quantum Engineering |
| spelling | doaj.art-15b6705e890a430f904ab7194f5d54bb2022-12-21T21:20:12ZengIEEEIEEE Transactions on Quantum Engineering2689-18082021-01-0121810.1109/TQE.2021.31048049520764Quantum Generative Models for Small Molecule Drug DiscoveryJunde Li0https://orcid.org/0000-0003-2470-8233Rasit O. Topaloglu1Swaroop Ghosh2https://orcid.org/0000-0001-8753-490XPennsylvania State University, University Park, PA, USAIBM Inc., Armonk, NY, USAPennsylvania State University, University Park, PA, USAExisting 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 <inline-formula><tex-math notation="LaTeX">$10^{60}$</tex-math></inline-formula>. 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.https://ieeexplore.ieee.org/document/9520764/Algorithmsnoisy intermediate-scale quantum algorithms and devices |
| spellingShingle | Junde Li Rasit O. Topaloglu Swaroop Ghosh Quantum Generative Models for Small Molecule Drug Discovery IEEE Transactions on Quantum Engineering Algorithms noisy intermediate-scale quantum algorithms and devices |
| title | Quantum Generative Models for Small Molecule Drug Discovery |
| title_full | Quantum Generative Models for Small Molecule Drug Discovery |
| title_fullStr | Quantum Generative Models for Small Molecule Drug Discovery |
| title_full_unstemmed | Quantum Generative Models for Small Molecule Drug Discovery |
| title_short | Quantum Generative Models for Small Molecule Drug Discovery |
| title_sort | quantum generative models for small molecule drug discovery |
| topic | Algorithms noisy intermediate-scale quantum algorithms and devices |
| url | https://ieeexplore.ieee.org/document/9520764/ |
| work_keys_str_mv | AT jundeli quantumgenerativemodelsforsmallmoleculedrugdiscovery AT rasitotopaloglu quantumgenerativemodelsforsmallmoleculedrugdiscovery AT swaroopghosh quantumgenerativemodelsforsmallmoleculedrugdiscovery |