DGCddG: Deep Graph Convolution for Predicting Protein-Protein Binding Affinity Changes Upon Mutations.

Effectively and accurately predicting the effects of interactions between proteins after amino acid mutations is a key issue for understanding the mechanism of protein function and drug design. In this study, we present a deep graph convolution (DGC) network-based framework, DGCddG, to predict the changes of protein-protein binding affinity after mutation. DGCddG incorporates multi-layer graph convolution to extract a deep, contextualized representation for each residue of the protein complex structure. The mined channels of the mutation sites by DGC is then fitted to the binding affinity with a multi-layer perceptron. Experiments with results on multiple datasets show that our model can achieve relatively good performance for both single and multi-point mutations. For blind tests on datasets related to angiotensin-converting enzyme 2 binding with the SARS-CoV-2 virus, our method shows better results in predicting ACE2 changes, may help in finding favorable antibodies. Code and data availability: https://github.com/lennylv/DGCddG.

Children of parents with mental illness in the COVID-19pandemic: A cross-sectional survey in China.

OBJECTIVE: Children of parents with mental illness (COPMI) are vulnerable during the COVID-19 pandemic. The study aimed to assess the psychosocial impacts of the pandemic and identify potential factors influencing their mental health. METHOD: 665 COPMI from six sites including Wuhan in China were enrolled. COPMI's mental health and the impacts of COVID-19 were assessed by an online survey. Univariate and multivariate analyses were performed to examine the association between impact factors and participants' mental health. RESULTS: 16.1 % of participants were in abnormal range of mental health, with interpersonal relationship being the most common problem. 48.6 % of participants reported quite worried about the epidemic. All aspects of adverse effects of COVID-19 were more prevalent among COPMI in Wuhan than in other sites. Concerns about COVID-19 (OR = 1.7, p = 0.02), decreased family income (OR = 2.0, p = 0.02), being physically abused (OR = 2.1, p = 0.04), witnessing family members being physically abused (OR = 2.0, p = 0.03), and needs for promoting family members' mental health (OR = 2.2, p < 0.01) were independent risk factors for participants' mental health. CONCLUSION: The findings raise our awareness of the impacts of COVID-19 pandemic on the wellbeing of COPMI. Multifaceted psychosocial support for COPMI is urgently needed to support them live through the pandemic.