Motivation: DNA-encoded library (DEL) technology has been developed as a powerful platform for drug development. Live cell-based selection methodologies were recently developed to expedite drug candidate discovery with higher biological relevance. Nevertheless, hit characterization is challenged by prominent background signals of cell-based selections. Therefore, automated data processing streamline compatible with noisy sequencing output is highly desirable. Results: Herein, we report an innovative automatic method that enables the most promising hit identification from large quantities of cell-based DEL datasets with improved accuracy and efficiency. This processing workflow is based on a comprehensive unsupervised algorithm incorporating data pre-processing, feature extracting and outlier filtering, descriptor-based classification, similarity score ranking, and active compound prediction. We performed methodology development with two DEL selection datasets targeting insulin receptor (INSR) on live cells, from both ∼30 million- and 1.033 billion-membered libraries. The automated scheme has demonstrated high consistency with experimental results as well as self-adaptivity to on-cell DEL datasets with varied library scales. Extended methodology application to cellular thrombopoietin receptor (TPOR) further substantiated the algorithmic generalization capability regarding target proteins. Thus, this approach can serve as a widely applicable workflow automatically differentiating hit compounds and thereby facilitates drug development from candidate discovery. Availability and implementation: The complete datasets, source code, and pre-trained models are made available at https://doi.org/10.5281/zenodo.17452392 and https://doi.org/10.5281/zenodo.17569557.
DNA-encoded libraries (DELs) have undergone significant development and are being widely adopted in drug discovery. As part of the evolution of DEL selections, the introduction of the DNA-programmed affinity labelling (DPAL) technique has extended the scope to include more-complex target systems beyond purified proteins immobilized on a solid matrix. In this review, detailed procedures for the application of DPAL-assisted DEL selections are compiled as a guide to the technique. Methods based on selections against in-solution proteins, DNA-encoded dynamic library (DEDL) selections, and selections against membrane proteins on a cell surface are included.
DNA-encoded chemical libraries (DELs) provide a powerful high-throughput screening platform that is used in both academia and industry. High-quality DELs lay the foundation for reliable DEL selection outcomes, and most pharmaceutical companies would prefer double-stranded DELs (dsDELs) because of their superior stability. Here, we summarize the experimental details for encoding a dsDEL, including the overall encoding strategy, synthetic chemistry of building-block addition, ligation strategies of code elongation, and quality control of the resulting libraries, exemplified with a 320-million-membered benzimidazole dsDEL from GlaxoSmithKline (GSK). We also briefly review the successful selection cases involving the presented libraries to highlight the great potential of dsDELs in drug discovery.