FiTMuSiC: leveraging structural and (co)evolutionary data for protein fitness prediction.

Systematically predicting the effects of mutations on protein fitness is essential for the understanding of genetic diseases. Indeed, predictions complement experimental efforts in analyzing how variants lead to dysfunctional proteins that in turn can cause diseases. Here we present our new fitness predictor, FiTMuSiC, which leverages structural, evolutionary and coevolutionary information. We show that FiTMuSiC predicts fitness with high accuracy despite the simplicity of its underlying model: it was among the top predictors on the hydroxymethylbilane synthase (HMBS) target of the sixth round of the Critical Assessment of Genome Interpretation challenge (CAGI6) and performs as well as much more complex deep learning models such as AlphaMissense. To further demonstrate FiTMuSiC's robustness, we compared its predictions with in vitro activity data on HMBS, variant fitness data on human glucokinase (GCK), and variant deleteriousness data on HMBS and GCK. These analyses further confirm FiTMuSiC's qualities and accuracy, which compare favorably with those of other predictors. Additionally, FiTMuSiC returns two scores that separately describe the functional and structural effects of the variant, thus providing mechanistic insight into why the variant leads to fitness loss or gain. We also provide an easy-to-use webserver at https://babylone.ulb.ac.be/FiTMuSiC , which is freely available for academic use and does not require any bioinformatics expertise, which simplifies the accessibility of our tool for the entire scientific community.

Evaluation of enzyme activity predictions for variants of unknown significance in Arylsulfatase A.

Continued advances in variant effect prediction are necessary to demonstrate the ability of machine learning methods to accurately determine the clinical impact of variants of unknown significance (VUS). Towards this goal, the ARSA Critical Assessment of Genome Interpretation (CAGI) challenge was designed to characterize progress by utilizing 219 experimentally assayed missense VUS in the Arylsulfatase A (ARSA) gene to assess the performance of community-submitted predictions of variant functional effects. The challenge involved 15 teams, and evaluated additional predictions from established and recently released models. Notably, a model developed by participants of a genetics and coding bootcamp, trained with standard machine-learning tools in Python, demonstrated superior performance among submissions. Furthermore, the study observed that state-of-the-art deep learning methods provided small but statistically significant improvement in predictive performance compared to less elaborate techniques. These findings underscore the utility of variant effect prediction, and the potential for models trained with modest resources to accurately classify VUS in genetic and clinical research.

Transcranial direct current stimulation enhances motor learning in Parkinson's disease: a randomized controlled trial.

Writing training has shown clinical benefits in Parkinson's disease (PD), albeit with limited retention and insufficient transfer effects. It is still unknown whether anodal transcranial direct current stimulation (atDCS) can boost consolidation in PD and how this interacts with medication. To investigate the effects of training + atDCS versus training + sham stimulation on consolidation of writing skills when ON and OFF medication. Second, to examine the intervention effects on cortical excitability. In this randomized sham-controlled double-blind study, patients underwent writing training (one session) with atDCS (N = 20) or sham (N = 19) over the primary motor cortex. Training was aimed at optimizing amplitude and assessed during online practice, pre- and post-training, after 24-h retention and after continued learning (second session) when ON and OFF medication (interspersed by 2 months). The primary outcome was writing amplitude at retention. Cortical excitability and inhibition were assessed pre- and post-training. Training + atDCS but not training + sham improved writing amplitudes at retention in the ON state (p = 0.017, g = 0.75). Transfer to other writing tasks was enhanced by atDCS in both medication states (g between 0.72 and 0.87). Also, training + atDCS improved continued learning. However, no online effects were found during practice and when writing with a dual task. A post-training increase in cortical inhibition was found in the training + atDCS group (p = 0.039) but not in the sham group, irrespective of medication. We showed that applying atDCS during writing training boosted most but not all consolidation outcomes in PD. We speculate that atDCS together with medication modulates motor learning consolidation via inhibitory processes ( https://osf.io/gk5q8/ , 2018-07-17).