biostudies-literatureZhao ZResearch Grants Council of the Hong Kong SAR Government of Chinabbaf680https://www.ebi.ac.uk/biostudies/studies/S-EPMC12713628biostudies-literatureUnknown26(6)The efficient discovery of high-affinity small-molecule aptamers via the Systematic Evolution of Ligands by EXponential enrichment (SELEX) is often constrained by challenges in navigating vast sequence spaces and rationally designing initial libraries. In this study, we introduce Deep Learning-assisted SELEX (DL-SELEX), a novel two-step framework that employs variational autoencoders (VAEs) to accelerate and refine small-molecule aptamer selection. This approach is the first to integrate deep learning to design initial aptamer libraries, marking a significant advancement in SELEX workflows. DL-SELEX leverages shared structural features within molecular families (e.g. steroids) to guide aptamer design: AptaVAE, the first VAE enriched with transfer learning from foundation models, generates Briefings in bioinformaticsStructure-enhanced deep learning accelerates aptamer selection for small molecule families like steroids.PMC12713628CRF#6107-20GGRF#16303522Hsing IMLin HChen HZhao ZLau HYfalseStructure-enhanced deep learning accelerates aptamer selection for small molecule families like steroids.The efficient discovery of high-affinity small-molecule aptamers via the Systematic Evolution of Ligands by EXponential enrichment (SELEX) is often constrained by challenges in navigating vast sequence spaces and rationally designing initial libraries. In this study, we introduce Deep Learning-assisted SELEX (DL-SELEX), a novel two-step framework that employs variational autoencoders (VAEs) to accelerate and refine small-molecule aptamer selection. This approach is the first to integrate deep learning to design initial aptamer libraries, marking a significant advancement in SELEX workflows. DL-SELEX leverages shared structural features within molecular families (e.g. steroids) to guide aptamer design: AptaVAE, the first VAE enriched with transfer learning from foundation models, generates 2025-01-01T00:00:00Z2025 Nov2026-06-08T05:31:52.926Z2026-06-08T03:08:58.453ZS-EPMC127136284142839110.1093/bib/bbaf680