技术报告：改进 LIMO 生成的分子的特性

arXiv - QuanBio - Biomolecules Pub Date : 2024-07-20 DOI:arxiv-2407.14968

Vineet Thumuluri, Peter Eckmann, Michael K. Gilson, Rose Yu

{"title":"技术报告：改进 LIMO 生成的分子的特性","authors":"Vineet Thumuluri, Peter Eckmann, Michael K. Gilson, Rose Yu","doi":"arxiv-2407.14968","DOIUrl":null,"url":null,"abstract":"This technical report investigates variants of the Latent Inceptionism on\nMolecules (LIMO) framework to improve the properties of generated molecules. We\nconduct ablative studies of molecular representation, decoder model, and\nsurrogate model training scheme. The experiments suggest that an autogressive\nTransformer decoder with GroupSELFIES achieves the best average properties for\nthe random generation task.","PeriodicalId":501022,"journal":{"name":"arXiv - QuanBio - Biomolecules","volume":"26 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Technical report: Improving the properties of molecules generated by LIMO\",\"authors\":\"Vineet Thumuluri, Peter Eckmann, Michael K. Gilson, Rose Yu\",\"doi\":\"arxiv-2407.14968\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This technical report investigates variants of the Latent Inceptionism on\\nMolecules (LIMO) framework to improve the properties of generated molecules. We\\nconduct ablative studies of molecular representation, decoder model, and\\nsurrogate model training scheme. The experiments suggest that an autogressive\\nTransformer decoder with GroupSELFIES achieves the best average properties for\\nthe random generation task.\",\"PeriodicalId\":501022,\"journal\":{\"name\":\"arXiv - QuanBio - Biomolecules\",\"volume\":\"26 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuanBio - Biomolecules\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2407.14968\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuanBio - Biomolecules","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2407.14968","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

本技术报告研究了分子上的潜在感知（LIMO）框架的变体，以改进生成分子的特性。我们对分子表示、解码器模型和代理模型训练方案进行了模拟研究。实验结果表明，在随机生成任务中，采用 GroupSELFIES 的自进式变换器解码器可以获得最佳的平均特性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Technical report: Improving the properties of molecules generated by LIMO

This technical report investigates variants of the Latent Inceptionism on Molecules (LIMO) framework to improve the properties of generated molecules. We conduct ablative studies of molecular representation, decoder model, and surrogate model training scheme. The experiments suggest that an autogressive Transformer decoder with GroupSELFIES achieves the best average properties for the random generation task.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

arXiv - QuanBio - Biomolecules

自引率

0.00%

发文量