Discovering Mental Health Research Topics with Topic Modeling (preprint)

Mental health significantly influences various aspects of our daily lives, and its importance has been increasingly recognized by the research community and the general public, particularly in the wake of the COVID-19 pandemic. This heightened interest is evident in the growing number of publications dedicated to mental health in the past decade. In this study, our goal is to identify general trends in the field and pinpoint high-impact research topics by analyzing a large dataset of mental health research papers. To accomplish this, we collected abstracts from various databases and trained a customized Sentence-BERT based embedding model leveraging the BERTopic framework. Our dataset comprises 96,676 research papers pertaining to mental health, enabling us to examine the relationships between different topics using their abstracts. To evaluate the effectiveness of the model, we compared it against two other state-of-the-art methods: Top2Vec model and LDA-BERT model. The model demonstrated superior performance in metrics that measure topic diversity and coherence. To enhance our analysis, we also generated word clouds to provide a comprehensive overview of the machine learning models applied in mental health research, shedding light on commonly utilized techniques and emerging trends. Furthermore, we provide a GitHub link* to the dataset used in this paper, ensuring its accessibility for further research endeavors.

Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI (preprint)

Heterogeneous data is endemic due to the use of diverse models and settings of devices by hospitals in the field of medical imaging. However, there are few open-source frameworks for federated heterogeneous medical image analysis with personalization and privacy protection simultaneously without the demand to modify the existing model structures or to share any private data. In this paper, we proposed PPPML-HMI, an open-source learning paradigm for personalized and privacy-preserving federated heterogeneous medical image analysis. To our best knowledge, personalization and privacy protection were achieved simultaneously for the first time under the federated scenario by integrating the PerFedAvg algorithm and designing our novel cyclic secure aggregation with the homomorphic encryption algorithm. To show the utility of PPPML-HMI, we applied it to a simulated classification task namely the classification of healthy people and patients from the RAD-ChestCT Dataset, and one real-world segmentation task namely the segmentation of lung infections from COVID-19 CT scans. For the real-world task, PPPML-HMI achieved $\sim$5\% higher Dice score on average compared to conventional FL under the heterogeneous scenario. Meanwhile, we applied the improved deep leakage from gradients to simulate adversarial attacks and showed the solid privacy-preserving capability of PPPML-HMI. By applying PPPML-HMI to both tasks with different neural networks, a varied number of users, and sample sizes, we further demonstrated the strong robustness of PPPML-HMI.

Computational Network Analysis of Host Genetic Risk Variants of Severe COVID-19 (preprint)

Background: Genome-wide association studies have identified numerous human host genetic risk variants that play a substantial role in the host immune response to SARS-CoV-2. Although these genetic risk variants significantly increase the severity of COVID-19, their influence on body systems is poorly understood. Therefore, we aim to interpret the biological mechanisms and pathways associated with the genetic risk factors and immune responses in severe COVID-19. We perform a deep analysis of previously identified risk variants and infer the hidden interactions between their molecular networks through disease mapping and the similarity of the molecular functions between constructed networks. Results: We designed a four-stage computational workflow for systematic genetic analysis of the risk variants. We integrated the molecular profiles of the risk factors with associated diseases, then constructed protein-protein interaction networks. We identified 24 protein-protein interaction networks with 939 interactions derived from 109 filtered risk variants in 60 risk genes and 56 proteins. The majority of molecular functions, interactions and pathways are involved in immune responses; several interactions and pathways are related to the metabolic and cardiovascular systems, which could lead to multi-organ complications and dysfunction. Conclusions: This study highlights the importance of analyzing molecular interactions and pathways to understand the heterogeneous susceptibility of the host immune response to SARS-CoV-2. We propose new insights into pathogenicity analysis of infections by including genetic risk information as essential factors to predict future complications during and after infection. This approach may assist more precise clinical decisions and accurate treatment plans to reduce COVID-19 complications. tions. Following SARS-CoV-2 infection, host genetic variations contribute to the development of illnesses that require critical care or hospitalization [1, 2]. Genome-wide association studies (GWAS) have been conducted to identify and validate risk tergenic, intronic, and transcript variants that are distributed in 60 genes in the 64 host genome. We found two gene clusters that have an impact on severe outcomes

The Association between Post-Traumatic Stress Disorder and Psychological Distress among Primary School and Middle School Teachers during the COVID-19 Epidemic: A Moderated Mediation Analysis

Background: The outbreak of the coronavirus disease (COVID-19) and its rapid spread may have led to individuals developing post-traumatic stress disorder (PTSD) and psychological distress. Under this context, teachers merit more attention as a group with high levels of work stress. The purpose of this study was to verify the relationship between PTSD and psychological distress and to explore sleep problems as a possible mediator in the relationship between PTSD and psychological distress, as well as the moderator of internet gaming disorders (IGD) in the relationship between sleep problems and psychological distress. Methods: A total of 11,014 Chinese primary and middle school teachers participated in this study. The survey was conducted online between 25 May and 30 June 2020. Results: PTSD was shown to have both a direct and indirect effect on teachers' psychological distress. The indirect effect was mediated by sleep problems. IGD played a moderating role between sleep problems and psychological distress. Conclusions: During the COVID-19 pandemic, PTSD has been shown to have had a serious impact on the psychological stress of teachers, which was mediated by sleep problems. In addition, IGD raised the harm brought from sleep problems on teachers' mental health.

Predicting the antigenic evolution of SARS-COV-2 with deep learning (preprint)

The severe acute respiratory syndrome coronavirus 2 (SARS-COV-2) antigenic profile evolves in response to the vaccine and natural infection-derived immune pressure, resulting in immune escape and threatening public health. Exploring the possible antigenic evolutionary potentials improves public health preparedness, but it is limited by the lack of experimental assays as the sequence space is exponentially large. Here we introduce the Machine Learning-guided Antigenic Evolution Prediction (MLAEP), which combines structure modeling, multi-task learning, and genetic algorithm to model the viral fitness landscape and explore the antigenic evolution via in silico directed evolution. As demonstrated by existing SARS-COV-2 variants, MLEAP can infer the order of variants along antigenic evolutionary trajectories, which is also strongly correlated with their sampling time. The novel mutations predicted by MLEAP are also found in immunocompromised covid patients and newly emerging variants, like BA. 4/5. In sum, our approach enables profiling existing variants and forecasting prospective antigenic variants, thus may help guide the development of vaccines and increase preparedness against future variants.

Modeling COVID-19 vaccine-induced immunological memory development and its links to antibody level and infectiousness (preprint)

COVID-19 vaccines have proven to be effective against SARS-CoV-2 infection. However, the dynamics of vaccine-induced immunological memory development and neutralizing antibodies generation are not fully understood, limiting vaccine development and vaccination regimen determination. Herein, we constructed a mathematical model to characterize the vaccine-induced immune response based on fitting the viral infection and vaccination datasets. With the example of CoronaVac, we revealed the association between vaccine-induced immunological memory development and neutralizing antibody levels. The establishment of the intact immunological memory requires more than 6 months after the first and second doses, after that a booster shot can induce high levels neutralizing antibodies. By introducing the maximum viral load and recovery time after viral infection, we quantitatively studied the protective effect of vaccines against viral infection. Accordingly, we optimized the vaccination regimen, including dose and vaccination timing, and predicted the effect of the fourth dose. Last, by combining the viral transmission model, we showed the suppression of virus transmission by vaccination, which may be instructive for the development of public health policies.

SenWave: Monitoring the Global Sentiments under the COVID-19 Pandemic (preprint)

Since the first alert launched by the World Health Organization (5 January, 2020), COVID-19 has been spreading out to almost 200 countries and territories. As of January 23, 2022, in total, over 346 million confirmed cases and over 5.5 million deaths have been reported worldwide. This causes massive losses in the economy and jobs globally and confining about 58% of the global population. In this paper, we introduce SenWave, a novel sentimental analysis work using 106+ million collected tweets and Weibo messages to evaluate the global rise and falls of sentiments during the COVID-19 pandemic. To make a fine-grained analysis on the feeling when we face this global health crisis, we annotate 10K tweets in English and 10K tweets in Arabic in 10 categories, including optimistic, thankful, empathetic, pessimistic, anxious, sad, annoyed, denial, official report, and joking. We then utilize an integrated transformer framework, called simpletransformer, to conduct multi-label sentimental classification by fine-tuning the pre-trained language model on the labeled data. Meanwhile, in order for a more complete analysis, we also translate the annotated English tweets into different languages (Spanish, Italian, and French) to generated training data for building sentiment analysis models for these languages. We provide detailed analysis and interesting discoveries on how the emotions evolve overtime. SenWave thus reveals the sentiment of global conversation in six different languages on COVID-19 (covering English, Spanish, French, Italian, Arabic and Chinese), followed the spread of the epidemic. The conversation showed a remarkably similar pattern of rapid rise and slow decline over time across all nations, as well as on special topics like the herd immunity strategies, to which the global conversation reacts strongly negatively. Overall, SenWave shows that optimistic and positive sentiments increased over time, foretelling a desire to seek, together, a reset for an improved COVID-19 world. We share the dataset with public to help other social impact studies of Covid-19, and fine-grained sentimental analysis tasks.

Self-supervised contrastive learning for integrative single cell RNA-seq data analysis (preprint)

Single-cell RNA-sequencing (scRNA-seq) has become a powerful tool to reveal the complex biological diversity and heterogeneity among cell populations. However, the technical noise and bias of the technology still have negative impacts on the downstream analysis. Here, we present a self-supervised Contrastive LEArning framework for scRNA-seq (CLEAR) profile representation and the downstream analysis. CLEAR overcomes the heterogeneity of the experimental data with a specifically designed representation learning task and thus can handle batch effects and dropout events. In the task, the deep learning model learns to pull together the representations of similar cells while pushing apart distinct cells, without manual labeling. It achieves superior performance on a broad range of fundamental tasks, including clustering, visualization, dropout correction, batch effect removal, and pseudo-time inference. The proposed method successfully identifies and illustrates inflammatory-related mechanisms in a COVID-19 disease study with 43,695 single cells from peripheral blood mononuclear cells. Further experiments to process a million-scale single-cell dataset demonstrate the scalability of CLEAR. This scalable method generates effective scRNA-seq data representation while eliminating technical noise, and it will serve as a general computational framework for single-cell data analysis.

SenWave: Monitoring the Global Sentiments under the COVID-19 Pandemic (preprint)

Since the first alert launched by the World Health Organization (5 January, 2020), COVID-19 has been spreading out to over 180 countries and territories. As of June 18, 2020, in total, there are now over 8,400,000 cases and over 450,000 related deaths. This causes massive losses in the economy and jobs globally and confining about 58% of the global population. In this paper, we introduce SenWave, a novel sentimental analysis work using 105+ million collected tweets and Weibo messages to evaluate the global rise and falls of sentiments during the COVID-19 pandemic. To make a fine-grained analysis on the feeling when we face this global health crisis, we annotate 10K tweets in English and 10K tweets in Arabic in 10 categories, including optimistic, thankful, empathetic, pessimistic, anxious, sad, annoyed, denial, official report, and joking. We then utilize an integrated transformer framework, called simpletransformer, to conduct multi-label sentimental classification by fine-tuning the pre-trained language model on the labeled data. Meanwhile, in order for a more complete analysis, we also translate the annotated English tweets into different languages (Spanish, Italian, and French) to generated training data for building sentiment analysis models for these languages. SenWave thus reveals the sentiment of global conversation in six different languages on COVID-19 (covering English, Spanish, French, Italian, Arabic and Chinese), followed the spread of the epidemic. The conversation showed a remarkably similar pattern of rapid rise and slow decline over time across all nations, as well as on special topics like the herd immunity strategies, to which the global conversation reacts strongly negatively. Overall, SenWave shows that optimistic and positive sentiments increased over time, foretelling a desire to seek, together, a reset for an improved COVID-19 world.

Role of 1'-Ribose Cyano Substitution for Remdesivir to Effectively Inhibit both Nucleotide Addition and Proofreading in SARS-CoV-2 Viral RNA Replication (preprint)

COVID-19 has recently caused a global health crisis and an effective interventional therapy is urgently needed. SARS-CoV-2 RNA-dependent RNA polymerase (RdRp) provides a promising but challenging drug target due to its intrinsic proofreading exoribonuclease (ExoN) function. Nucleoside triphosphate (NTP) analogues added to the growing RNA chain should supposedly terminate viral RNA replication, but ExoN can cleave the incorporated compounds and counteract their efficacy. Remdesivir targeting SARS-CoV-2 RdRp exerts high drug efficacy in vitro and in vivo. However, its underlying inhibitory mechanisms remain elusive. Here, we performed all-atom molecular dynamics (MD) simulations with an accumulated simulation time of 12.6 microseconds to elucidate the molecular mechanisms underlying the inhibitory effects of remdesivir in nucleotide addition (RdRp complex: nsp12-nsp7-nsp8) and proofreading (ExoN complex: nsp14-nsp10). We found that the 1-cyano group of remdesivir possesses the dual role of inhibiting both nucleotide addition and proofreading. For nucleotide addition, we showed that incorporation of one remdesivir is not sufficient to terminate RNA synthesis. Instead, the presence of the polar 1-cyano group of remdesivir at an upstream site causes instability via its electrostatic interactions with a salt bridge formed by Asp865 and Lys593, rendering translocation unfavourable. This may eventually lead to a delayed chain termination of RNA extension by three nucleotides. For proofreading, remdesivir can inhibit cleavage via the steric clash between the 1-cyano group and Asn104. To further examine the role of 1-cyano group in remdesivirs inhibitory effects, we studied three additional NTP analogues with other types of modifications: favipiravir, vidarabine, and fludarabine. Our simulations suggest that all three of them are prone to ExoN cleavage. Our computational findings were further supported by an in vitro assay in Vero E6 cells using live SARS-CoV-2. The dose-response curves suggest that among tested NTP analogues, only remdesivir exerts significant inhibitory effects on viral replication. Our work provides plausible mechanisms at molecular level on how remdesivir inhibits viral RNA replication, and our findings may guide rational design for new treatments of COVID-19 targeting viral replication.

Computational Drug Repositioning and Elucidation of Mechanism of Action of Compounds against SARS-CoV-2 (preprint)

The COVID-19 crisis called for rapid reaction from all the fields of biomedical research. Traditional drug development involves time consuming pipelines that conflict with the urgence of identifying effective therapies during a health and economic emergency. Drug repositioning, that is the discovery of new clinical applications for drugs already approved for different therapeutic contexts, could provide an effective shortcut to bring COVID-19 treatments to the bedside in a timely manner. Moreover, computational approaches can help accelerate the process even further. Here we present the application of computational drug repositioning tools based on transcriptomics data to identify drugs that are potentially able to counteract SARS-CoV-2 infection, and also to provide insights on their mode of action. We believe that mucolytics and HDAC inhibitors warrant further investigation. In addition, we found that the DNA Mismatch repair pathway is strongly modulated by drugs with experimental in vitro activity against SARS-CoV-2 infection. Both full results and methods are publicly available.