GenSMILES: An enhanced validity conscious representation for inverse design of molecules

Kumar, Kurichi; Kumar, Kamal; Kumar, Neeraj

doi:10.1016/j.knosys.2023.110429

Cited by 9 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome these challenges, alternative notations like Self-Referencing Embedded Strings (SELFIES) 2,3 have been developed. SELFIES address the robustness and validity issues in deep generative modeling through a recursive approach, surpassing notations like DeepSmiles 4 and GenSMILES, 5 but come at the cost of simplicity, interpretability and compactness. None of these notations consistently uphold the integrity of scaffolds and fragments essential for several molecular generation tasks.…”

Section: Related Workmentioning

confidence: 99%

Gotta be SAFE: a new framework for molecular design

Noutahi,

Gabellini,

Craig

et al. 2024

Digital Discovery

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Gotta be SAFE: a new framework for molecular design

Noutahi,

Gabellini,

Craig

et al. 2024

Digital Discovery

View full text Add to dashboard Cite

show abstract

“…Despite their promise, these models often stumble 7 by producing invalid or irrelevant molecular structures. Furthermore, fine-tuning and retraining these models demand substantial labeled data at times, complicated training procedures, intensive computational resources, and a significant amount of time, making the process costly and sometimes impractical for many tasks.…”

Section: Introductionmentioning

confidence: 99%

Large Language Models as Molecular Design Engines

Bhattacharya,

Cassady,

Hickner

et al. 2024

Preprint

View full text Add to dashboard Cite

The design of small molecules is crucial for technological applications ranging from drug discovery to energy storage. Due to the vast design space available to modern synthetic chemistry, the community has increasingly sought to use data-driven and machine learning approaches to navigate this space. Although generative machine learning methods have recently shown potential for computational molecular design, their use is hindered by complex training procedures, and they often fail to generate valid and unique molecules. In this context, pre-trained Large Language Models (LLMs) have emerged as potential tools for molecular design, as they appear to be capable of creating and modifying molecules based on simple instructions provided through natural language prompts. In this work, we show that the Claude 3 Opus LLM can read, write, and modify molecules according to prompts, with an impressive 97% valid and unique molecules. By quantifying these modifications in a low-dimensional latent space, we systematically evaluate the model’s behavior under different prompting conditions. Notably, the model is able to perform guided molecular generation when asked to manipulate the electronic structure of molecules using simple, natural-language prompts. Our findings highlight the potential of LLMs as powerful and versatile molecular design engines.

show abstract

Nc-vae: normalised conditional diverse variational autoencoder guided de novo molecule generation

Bhadwal,

Kumar

2024

J Supercomput

View full text Add to dashboard Cite

GenSMILES: An enhanced validity conscious representation for inverse design of molecules

Cited by 9 publications

References 28 publications

Gotta be SAFE: a new framework for molecular design

Gotta be SAFE: a new framework for molecular design

Large Language Models as Molecular Design Engines

Nc-vae: normalised conditional diverse variational autoencoder guided de novo molecule generation

Contact Info

Product

Resources

About