Machine-Learning-Based Data Analysis Method for Cell-Based Selection of DNA-Encoded Libraries

Abstract

DNA-encoded library (DEL) is a powerful ligand discovery technology that has been widely adopted in the pharmaceutical industry. DEL selections are typically performed with a purified protein target immobilized on a matrix or in solution phase. Recently, DELs have also been used to interrogate the targets in the complex biological environment, such as membrane proteins on live cells. However, due to the complex landscape of the cell surface, the selection inevitably involves significant nonspecific interactions, and the selection data are much noisier than the ones with purified proteins, making reliable hit identification highly challenging. Researchers have developed several approaches to denoise DEL datasets, but it remains unclear whether they are suitable for cell-based DEL selections. Here, we report the proof-of-principle of a new machine-learning (ML)-based approach to process cell-based DEL selection datasets by using a Maximum A Posteriori (MAP) estimation loss function, a probabilistic framework that can account for and quantify uncertainties of noisy data. We applied the approach to a DEL selection dataset, where a library of 7,721,415 compounds was selected against a purified carbonic anhydrase 2 (CA-2) and a cell line expressing the membrane protein carbonic anhydrase 12 (CA-12). The extended-connectivity fingerprint (ECFP)-based regression model using the MAP loss function was able to identify true binders and also reliable structure−activity relationship (SAR) from the noisy cell-based selection datasets. In addition, the regularized enrichment metric (known as MAP enrichment) could also be calculated directly without involving the specific machine-learning model, effectively suppressing low-confidence outliers and enhancing the signal-to-noise ratio. Future applications of this method will focus on de novo ligand discovery from cell-based DEL selections.

Discovering Cell-targeting Ligands and the Cell Surface Receptors via Selection of DNA-encoded Chemical Libraries (DELs) against Cancer Cells without Predefined Targets

“…Here, we used a "BB-centric" approach and relied on the normalized z-score as the metric for data analysis. In future, more sophisticated data analysis modalities, such as machine learning, [93][94][95][96][97][98][99] is expected to facilitate hit identification or even generate enrichment "fingerprints" for specific cell types or properties.…”

Evolution of chemistry and selection technology for DNA-encoded library

“…These ML methods have facilitated the analysis of DEL selection data with purified proteins, however, approaches for the processing of the much noisier cell-based selection data have not yet been reported. Recently, Li's group 154 described an ML-based method to process cell-based DEL selection datasets. They used the Maximum A Posteriori (MAP)-based enrichment metric to denoise the datasets, thereby facilitating to obtain high-confidence enrichment values.…”