Chemistry-Wide Association Studies (CWAS): A Novel Framework for Identifying and Interpreting Structure–Activity Relationships

Abstract

Quantitative Structure-Activity Relationships (QSAR) models are often seen as a “black box” because they are considered difficult to interpret. Meanwhile, qualitative approaches, e.g., structural alerts (SA) or read-across, provide mechanistic insight, which is preferred for regulatory purposes, but predictive accuracy of such approaches is often low. Herein, we introduce the Chemistry-Wide Association Study (CWAS) approach, a novel framework that both addresses such deficiencies and combines advantages of statistical QSAR and alert-based approaches. The CWAS framework consists of the following steps: (i) QSAR model building for an endpoint of interest; (ii) identification of key chemical features; (iii) determination of communities of such features disproportionately co-occurring more frequently in the active than in the inactive class; and (iv) assembling these communities to form larger (and not necessarily chemically connected) novel structural alerts with high specificity. As a proof-of-concept, we have applied CWAS to model Ames mutagenicity and Stevens-Johnson Syndrome (SJS). For the well-studied Ames mutagenicity dataset, we have identified 76 important individual fragments and assembled co-occurring fragments into SA both replicative of known as well as representing novel mutagenicity alerts. For the SJS dataset, we identified 29 important fragments and assembled co-occurring communities into SA including both known and novel alerts. In summary, we demonstrate that CWAS provides a new framework to interpret predictive QSAR models and derive refined structural alerts for more effective design and safety assessment of drugs and drug candidates.

QSAR without borders

“…114 These combined approaches were further developed by the chemistry-wide association study (CWAS) that predicted Ames mutagenicity and an adverse drug reaction known as Stevens-Johnson syndrome. 116 The identification of important chemical fragments and analysis of their co-occurrences also allows mechanistic interpretations of QSAR models without compromising their accuracy.…”

School of cheminformatics in Latin America

“…It outperforms other models and exhibits consistently high external classification accuracy and applicability to diverse chemicals. Chemistry-wide association studies (CWAS) [ 3 ] explore how chemical structures are associated with activity by integrating statistical and non-statistical modeling. This model derives alerts from validated QSAR models and validates alert-based assertions by QSAR.…”

“…GTM maps can be built with different descriptors, such as ISIDA fragment descriptors [ 3 , 4 ], which can vary by topology, size, and atom labels. Two scenarios can be considered to profile a chemical library with respect to different activities: preparation of single-task models for particular activities or construction of one universal map able to predict the entire pharmacological profile in a multitasking manner.…”