Iterative Machine Learning for Classification and Discovery of Single-Molecule Unfolding Trajectories from Force Spectroscopy Data

We report the application of machine learning techniques to expedite classification and analysis of protein unfolding trajectories from force spectroscopy data. Using kernel methods, logistic regression, and triplet loss, we developed a workflow called Forced Unfolding and Supervised Iterative Online (FUSION) learning where a user classifies a small number of repeatable unfolding patterns encoded as images, and a machine is tasked with identifying similar images to classify the remaining data. We tested the workflow using two case studies on a multidomain XMod-Dockerin/Cohesin complex, validating the approach first using synthetic data generated with a Monte Carlo algorithm and then deploying the method on experimental atomic force spectroscopy data. FUSION efficiently separated traces that passed quality filters from unusable ones, classified curves with high accuracy, and identified unfolding pathways that were undetected by the user. This study demonstrates the potential of machine learning to accelerate data analysis and generate new insights in protein biophysics.

Maximizing the integration of virtual and experimental screening in hit discovery

INTRODUCTION

Experimental and virtual screening contributes to the discovery of more than 50% of clinical candidates. Considering the similar concept and goals, early-phase drug discovery would benefit from the effective integration of these approaches.

AREAS COVERED

After reviewing the recent trends in both experimental and virtual screening, the authors discuss different integration strategies from parallel, focused, sequential, and iterative screening. Strategic considerations are demonstrated in a number of real-life case studies.

EXPERT OPINION

Experimental and virtual screening are complementary approaches that should be integrated in lead discovery settings. Virtual screening can access extremely large synthetically feasible chemical space that can be effectively searched on GPU clusters or cloud architectures. Experimental screening provides reliable datasets by quantitative HTS applications, and DNA-encoded libraries (DEL) have enlarged the chemical space covered by these technologies. These developments, together with the use of artificial intelligence methods, represent new options for their efficient integration. The case studies discussed here demonstrate the benefits of complementary strategies, such as focused and iterative screening.

Changing the HTS Paradigm: AI-Driven Iterative Screening for Hit Finding

Iterative screening is a process in which screening is done in batches, with each batch filled by using machine learning to select the most promising compounds from the library based on the previous results. We believe iterative screening is poised to enhance the screening process by improving hit finding while at the same time reducing the number of compounds screened. In addition, we see this process as a key enabler of next-generation high-throughput screening (HTS), which uses more complex assays that better describe the biology but demand more resource per screened compound. To demonstrate the utility of these methods, we retrospectively analyze HTS data from PubChem with a focus on machine learning–based screening strategies that can be readily implemented in practice. Our results show that over a variety of HTS experimental paradigms, an iterative screening setup that screens a total of 35% of the screening collection over as few as three iterations has a median return rate of approximately 70% of the active compounds. Increasing the portion of the library screened to 50% yields median returns of approximately 80% of actives. Using six iterations increases these return rates to 78% and 90%, respectively. The best results were achieved with machine learning models that can be run on a standard desktop. By demonstrating that the utility of iterative screening holds true even with a small number of iterations, and without requiring significant computational resources, we provide a roadmap for the practical implementation of these techniques in hit finding.

Rapid lead discovery through iterative screening of one bead one compound libraries

Primary hits that arise from screening one bead one compound (OBOC) libraries against a target of interest rarely have high potency. However, there has been little work focused on the development of an efficient workflow for primary hit improvement. In this study, we show that by characterizing the binding constants for all of the hits that arise from a screen, structure-activity relationship (SAR) data can be obtained to inform the design of "derivative libraries" of a primary hit that can then be screened under more demanding conditions to obtain improved compounds. Here, we demonstrate the rapid improvement of a primary hit against matrix metalloproteinase-14 using this approach.