Molecular dynamics simulations of intrinsically disordered protein regions enable biophysical interpretation of variant-effect predictors.

Predictive models for missense-variant pathogenicity offer little functional interpretation for intrinsically disordered regions (IDRs), since they mostly leverage conservation and co-evolution across homologous sequences. In our study, we use molecular dynamics (MD) simulations to model biophysics of IDRs for improved interpretation of variant effects. We develop MDmis, a method that uses biophysical features extracted from MD simulations of IDRs to predict pathogenicity. We find that pathogenic variants in IDRs longer than 800 residues manifest differently, being strongly associated with a propensity for transient order and depleted solvent access, compared to those in IDRs ≤ 800 residues in length. Using MD simulations of proteins with single missense variants, we identify evidence for local structural changes, such as an increase in solvent-accessible surface area, and global structural changes, such as increase in overall compaction, in IDRs > 800 amino acids (aa). Lastly, MDmis, when combined with conservation information, can aid predictive accuracy, especially for pathogenic variants in IDRs > 800 aa. Overall, extracting information from MD simulations can help elucidate biophysical behaviors affected by pathogenic variants in IDRs and understand the drivers of predictive performance in different models.