ABSTRACT
DNA-encoded libraries (DELs) provide the means to make and screen millions of diverse compounds against a target of interest in a single experiment. However, despite producing large volumes of binding data at a relatively low cost, the DEL selection process is susceptible to noise, necessitating computational follow-up to increase signal-to-noise ratios. In this work, we present a set of informatics tools to employ data from prior DEL screen(s) to gain information about which building blocks are most likely to be productive when designing new DELs for the same target. We demonstrate that similar building blocks have similar probabilities of forming compounds that bind. We then build a model from the inference that the combined behavior of individual building blocks is predictive of whether an overall compound binds. We illustrate our approach on a set of three-cycle OpenDEL libraries screened against soluble epoxide hydrolase (sEH) and report performance of more than an order of magnitude greater than random guessing on a holdout set, demonstrating that our model can serve as a baseline for comparison against other machine learning models on DEL data. Lastly, we provide a discussion on how we believe this informatics workflow could be applied to benefit researchers in their specific DEL campaigns.
Subject(s)
Drug Discovery , Small Molecule Libraries , Small Molecule Libraries/chemistry , DNA/chemistry , Machine LearningABSTRACT
OBJECTIVE: Nonsuicidal self-injury (NSSI) is a public health concern and risk factor for suicide. The Emotional Cascade Model (ECM) proposes that NSSI partially functions as a distraction from cascades of negative affect and rumination. The purpose of this study was to examine the roles of trait rumination, and momentary instability of rumination and negative emotion, in NSSI. METHOD: Experience sampling methods were used to monitor thoughts, emotions, and behaviors in 47 individuals reporting dysregulated behaviors including NSSI. Instability indices were generated for rumination and negative emotion using the momentary assessments. RESULTS: Twenty-five episodes of NSSI were reported during monitoring. Trait rumination prospectively predicted NSSI episodes, and the instability indices interacted to predict NSSI. CONCLUSIONS: Consistent with the ECM, the interaction between rumination instability and negative affect instability during monitoring significantly predicted NSSI, with the strongest effects occurring for sadness and rumination about past. These findings may enhance conceptualization and treatment of patients with NSSI.