Dataset Information

Toward Addiction Prediction: An Overview of Cross-Validated Predictive Modeling Findings and Considerations for Future Neuroimaging Research.

ABSTRACT: Substance use is a leading cause of disability and death worldwide. Despite the existence of evidence-based treatments, clinical outcomes are highly variable across individuals, and relapse rates following treatment remain high. Within this context, methods to identify individuals at particular risk for unsuccessful treatment (i.e., limited within-treatment abstinence), or for relapse following treatment, are needed to improve outcomes. Cumulatively, the literature generally supports the hypothesis that individual differences in brain function and structure are linked to differences in treatment outcomes, although anatomical loci and directions of associations have differed across studies. However, this work has almost entirely used methods that may overfit the data, leading to inflated effect size estimates and reduced likelihood of reproducibility in novel clinical samples. In contrast, cross-validated predictive modeling (i.e., machine learning) approaches are designed to overcome limitations of traditional approaches by focusing on individual differences and generalization to novel subjects (i.e., cross-validation), thereby increasing the likelihood of replication and potential translation to novel clinical settings. Here, we review recent studies using these approaches to generate brain-behavior models of treatment outcomes in addictions and provide recommendations for further work using these methods.

SUBMITTER: Yip SW

PROVIDER: S-EPMC8274215 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:One of the unaddressed challenges in drug discovery is that drug potency determined in vitro is not a reliable indicator of drug activity in vivo. Accumulated evidence suggests that in vivo activity is more strongly correlated with the binding/unbinding kinetics than the equilibrium thermodynamics of protein-ligand interactions (PLIs). However, existing experimental and computational techniques are insufficient in studying the molecular details of kinetics processes of PLIs on a large scale. Consequently, we not only have limited mechanistic understanding of the kinetic processes but also lack a practical platform for high-throughput screening and optimization of drug leads on the basis of their kinetic properties. For the first time, we address this unmet need by integrating coarse-grained normal mode analysis with multitarget machine learning (MTML). To test our method, HIV-1 protease is used as a model system. We find that computational models based on the residue normal mode directionality displacement of PLIs can not only recapitulate the results from all-atom molecular dynamics simulations but also predict protein-ligand binding/unbinding kinetics accurately. When this is combined with energetic features, the accuracy of combined kon and koff prediction reaches 74.35%. Furthermore, our integrated model provides us with new insights into the molecular determinants of the kinetics of PLIs. We propose that the coherent coupling of conformational dynamics and thermodynamic interactions between the receptor and the ligand may play a critical role in determining the kinetic rate constants of PLIs. In conclusion, we demonstrate that residue normal mode directionality displacement can serve as a kinetic fingerprint to capture long-time-scale conformational dynamics of the binding/unbinding kinetics. When this is coupled with MTML, it is possible to screen and optimize compounds on the basis of their binding/unbinding kinetics in a high-throughput fashion. The further development of such computational tools will bridge one of the critical missing links between in vitro compound screening and in vivo drug activity.

Dataset Information

Toward Addiction Prediction: An Overview of Cross-Validated Predictive Modeling Findings and Considerations for Future Neuroimaging Research.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets