MultiModRLBP: A Deep Learning Approach for Multi-Modal RNA-Small Molecule Ligand Binding Sites Prediction.

This study aims to tackle the intricate challenge of predicting RNA-small molecule binding sites to explore the potential value in the field of RNA drug targets. To address this challenge, we propose the MultiModRLBP method, which integrates multi-modal features using deep learning algorithms. These features include 3D structural properties at the nucleotide base level of the RNA molecule, relational graphs based on overall RNA structure, and rich RNA semantic information. In our investigation, we gathered 851 interactions between RNA and small molecule ligand from the RNAglib dataset and RLBind training set. Unlike conventional training sets, this collection broadened its scope by including RNA complexes that have the same RNA sequence but change their respective binding sites due to structural differences or the presence of different ligands. This enhancement enables the MultiModRLBP model to more accurately capture subtle changes at the structural level, ultimately improving its ability to discern nuances among similar RNA conformations. Furthermore, we evaluated MultiModRLBP on two classic test sets, Test18 and Test3, highlighting its performance disparities on small molecules based on metal and non-metal ions. Additionally, we conducted a structural sensitivity analysis on specific complex categories, considering RNA instances with varying degrees of structural changes and whether they share the same ligands. The research results indicate that MultiModRLBP outperforms the current state-of-the-art methods on multiple classic test sets, particularly excelling in predicting binding sites for non-metal ions and instances where the binding sites are widely distributed along the sequence. MultiModRLBP also can be used as a potential tool when the RNA structure is perturbed or the RNA experimental tertiary structure is not available. Most importantly, MultiModRLBP exhibits the capability to distinguish binding characteristics of RNA that are structurally diverse yet exhibit sequence similarity. These advancements hold promise in reducing the costs associated with the development of RNA-targeted drugs.

RPEMHC: improved prediction of MHC-peptide binding affinity by a deep learning approach based on residue-residue pair encoding.

MOTIVATION: Binding of peptides to major histocompatibility complex (MHC) molecules plays a crucial role in triggering T cell recognition mechanisms essential for immune response. Accurate prediction of MHC-peptide binding is vital for the development of cancer therapeutic vaccines. While recent deep learning-based methods have achieved significant performance in predicting MHC-peptide binding affinity, most of them separately encode MHC molecules and peptides as inputs, potentially overlooking critical interaction information between the two. RESULTS: In this work, we propose RPEMHC, a new deep learning approach based on residue-residue pair encoding to predict the binding affinity between peptides and MHC, which encode an MHC molecule and a peptide as a residue-residue pair map. We evaluate the performance of RPEMHC on various MHC-II-related datasets for MHC-peptide binding prediction, demonstrating that RPEMHC achieves better or comparable performance against other state-of-the-art baselines. Moreover, we further construct experiments on MHC-I-related datasets, and experimental results demonstrate that our method can work on both two MHC classes. These extensive validations have manifested that RPEMHC is an effective tool for studying MHC-peptide interactions and can potentially facilitate the vaccine development. AVAILABILITY: The source code of the method along with trained models is freely available at https://github.com/lennylv/RPEMHC.

'Let's Talk About Children' family focused practice for children of parents with schizophrenia and bipolar disorder: protocol for a randomized controlled trial.

INTRODUCTION: 'Let's Talk About Children' is a brief family focused intervention developed to improve mental health outcomes of children of parents with mental illness (COPMI). This study aims to assess the efficacy of LTC in improving mental health of children of parents with schizophrenia or bipolar disorder in China. METHODS: The planned study is a multicentre parallel group randomized wait-list controlled trial. A total of 400 eligible families with children aged 8 to 18 years will be recruited, 200 each for families with parental schizophrenia or bipolar disorder. The intervention group will receive Let's Talk About Children delivered by a trained therapist, while the control group will receive treatment as usual. The primary outcomes are child mental health measured by the strengths and difficulties questionnaire and parent-child communication measured using the parent-adolescent communication scale. Parental mental health and family functioning are secondary outcomes. This study also plans to explore mediating factors for the effect of Let's Talk About Children on child mental health, as well as conduct a cost-effectiveness analysis on using Let's Talk About Children in China. CONCLUSION: The present study will provide evidence for the efficacy of Let's Talk About Children in families with parental schizophrenia and bipolar disorder in China. In addition, it will evaluate potential mechanisms of action and cost-effectiveness of Let's Talk About Children, providing a basis for future implementation. TRIAL REGISTRATION: ChiCTR2300073904.

DeepMPSF: A Deep Learning Network for Predicting General Protein Phosphorylation Sites Based on Multiple Protein Sequence Features.

Phosphorylation, as one of the most important post-translational modifications, plays a key role in various cellular physiological processes and disease occurrences. In recent years, computer technology has been gradually applied to the prediction of protein phosphorylation sites. However, most existing methods rely on simple protein sequence features that provide limited contextual information. To overcome this limitation, we propose DeepMPSF, a phosphorylation site prediction model based on multiple protein sequence features. There are two types of features: sequence semantic features, which comprise protein residue type information and relative position information within protein sequence, and protein background biophysical features, which include global semantic information containing more comprehensive protein background information obtained from pretrained models. To extract these features, DeepMPSF employs two separate subnetworks: the S71SFE module and the BBFE module, which automatically extract high-level semantic features. Our model incorporates a learning strategy for handling imbalanced datasets through ensemble learning during training and prediction. DeepMPSF is trained and evaluated on a well-established dataset of human proteins. Comparing the analysis with other benchmark methods reveals that DeepMPSF outperforms in predicting both S/T residues and Y residues. In particular, DeepMPSF showed excellent generalization performance in cross-species blind test performance, with an average improvement of 5.63%/5.72%, 22.28%/25.94%, 20.11%/17.49%, and 26.40%/28.33% for Mus musculus/Rattus norvegicus test sets in area under curves (AUCs) of ROC curve, AUC of the PR curve, F1-score, and MCC metrics, respectively. Furthermore, it also shows excellent performance in the latest updated case of natural proteins with functional phosphorylation sites. Through an ablation study and visual analysis, we uncover that the design of different feature modules significantly contributes to the accurate classification of DeepMPSF, which provides valuable insights for predicting phosphorylation sites and offers effective support for future downstream research.

TransRNAm: Identifying Twelve Types of RNA Modifications by an Interpretable Multi-Label Deep Learning Model Based on Transformer.

Accurate identification of RNA modification sites is of great significance in understanding the functions and regulatory mechanisms of RNAs. Recent advances have shown great promise in applying computational methods based on deep learning for accurate prediction of RNA modifications. However, those methods generally predicted only a single type of RNA modification. In addition, such methods suffered from the scarcity of the interpretability for their predicted results. In this work, a new Transformer-based deep learning method was proposed to predict multiple RNA modifications simultaneously, referred to as TransRNAm. More specifically, TransRNAm employs Transformer to extract contextual feature and convolutional neural networks to further learn high-latent feature representations of RNA sequences relevant for RNA modifications. Importantly, by integrating the self-attention mechanism in Transformer with convolutional neural network, TransRNAm is capable of not only capturing the critical nucleotide sites that contribute significantly to RNA modification prediction, but also revealing the underlying association among different types of RNA modifications. Consequently, this work provided an accurate and interpretable predictor for multiple RNA modification prediction, which may contribute to uncovering the sequence-based forming mechanism of RNA modification sites.

Factors that influence family-focused practice in Chinese mental health workers: A cross-sectional survey.

INTRODUCTION: Family-focused practice has become an emerging paradigm in mental health services. However, little is known about family-focused practice and associated factors in Chinese mental health workers. AIM: To examine family-focused practice and associated factors in Chinese mental health workers. METHOD: A cross-sectional survey was conducted in a convenience sample of mental health workers (n = 515) in Beijing, China. The Family-Focused Mental Health Practice Questionnaire was used to measure family-focused practice, as well as worker, workplace and client factors that might influence family-focused practice. Multiple linear regression analysis was performed to investigate the factors associated with family-focused practice. RESULTS: On average, the participants exhibited a moderate level of engagement in family-focused practice. The factors that most significantly influenced family-focused practice in Chinese mental health workers were skill and knowledge, worker confidence and time and workload. Moreover, psychiatrists were found to engage more in family-focused practice than psychiatric nurses, and community mental health workers were more active in family-focused practice than hospital-based ones. DISCUSSION: This study provided important data concerning family-focused practice and associated factors in Chinese mental health workers. IMPLICATIONS FOR PRACTICE: The varying level of Chinese mental health workers to engage in family-focused practice has advocacy, training, research and organizational implications for mental health services in China and elsewhere.

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.

Simultaneous Prediction of Interaction Sites on the Protein and Peptide Sides of Complexes through Multilayer Graph Convolutional Networks.

Identifying the binding residues of protein-peptide complexes is essential for understanding protein function mechanisms and exploring drug discovery. Recently, many computational methods have been developed to predict the interaction sites of either protein or peptide. However, to our knowledge, no prediction method can simultaneously identify the interaction sites on both the protein and peptide sides. Here, we propose a deep graph convolutional network (GCN)-based method called GraphPPepIS to predict the interaction sites of protein-peptide complexes using protein and peptide structural information. We also propose a companion method, SeqPPepIS, for assisting with the lack of structural information and the flexibility of peptides. SepPPepIS replaces the peptide structural features in GraphPPepIS by learning features from peptide sequences. We performed a comprehensive evaluation of the benchmark data sets, and the results show that our two methods outperform state-of-the-art methods on the accurate interaction sites of both protein and peptide sides. We show that our methods can help improve protein-peptide docking. For docking data sets, our methods maintain robust performance in identifying binding sites, thereby enhancing the prediction of peptide binding poses. Finally, we visualized the analysis of protein and peptide graph embedding to demonstrate the learning ability of graph convolution in predicting interaction sites, which was mainly obtained through the shared parameters of a protein graph and peptide graph.

The relevant research of adverse childhood experiences and "risky drinking" in children of alcoholics in China.

OBJECTIVE: To determine whether adverse childhood experiences (ACEs) of children of alcoholics (COA) in male were associated with their current "risky drinking". METHODS: This case-control study used the Alcohol Use Disorder Identification Test (AUDIT, cutoff is 7) to divide the participants into two groups, a "risky drinking" group (N = 53) and a "non-risky drinking" group (N = 97). Demographic data, Adverse Childhood Experiences-International Questionnaire (ACE-IQ), the Hamilton Anxiety Rating Scale (HAMA), the Hamilton Depression Rating Scale (HAMD) and the Mini-International Neuropsychiatric Interview (MINI) were used for assessment. The specific relationships between ACEs and "risky drinking" were explored. RESULTS: Respondents ranged in age from 29.70 ± 6.72 years; 74.5% were females; 94.7% were of Han nationality; 56.7% had a level of education above high school; 12% had no formal or stable job. There was difference in attitude to self-drinking between two groups (P < 0.001). The "risky drinking" group was more likely to have experienced a major depressive episode (P < 0.05), nonalcohol psychoactive substance use disorder (P < 0.01) and bulimia nervosa (P < 0.05), and they also experienced more physical abuse (P < 0.05), community violence (P < 0.001) and collective violence (P < 0.01). In a single factor logistic regression, physical abuse, community violence and collective violence were associated with a two to 11- fold increase in "risky drinking" in the adult COA, and in multiple factor logistic regression, community violence showed a graded relationship with "risky drinking". CONCLUSION: The childhood adverse experiences contribute to "risky drinking" in COA. This finding in the Chinese context have significant implications for prevention not only in China but in other cultures. There must be greater awareness of the role of ACEs in the perpetuation of alcoholism.

CAPLA: improved prediction of protein-ligand binding affinity by a deep learning approach based on a cross-attention mechanism.

MOTIVATION: Accurate and rapid prediction of protein-ligand binding affinity is a great challenge currently encountered in drug discovery. Recent advances have manifested a promising alternative in applying deep learning-based computational approaches for accurately quantifying binding affinity. The structure complementarity between protein-binding pocket and ligand has a great effect on the binding strength between a protein and a ligand, but most of existing deep learning approaches usually extracted the features of pocket and ligand by these two detached modules. RESULTS: In this work, a new deep learning approach based on the cross-attention mechanism named CAPLA was developed for improved prediction of protein-ligand binding affinity by learning features from sequence-level information of both protein and ligand. Specifically, CAPLA employs the cross-attention mechanism to capture the mutual effect of protein-binding pocket and ligand. We evaluated the performance of our proposed CAPLA on comprehensive benchmarking experiments on binding affinity prediction, demonstrating the superior performance of CAPLA over state-of-the-art baseline approaches. Moreover, we provided the interpretability for CAPLA to uncover critical functional residues that contribute most to the binding affinity through the analysis of the attention scores generated by the cross-attention mechanism. Consequently, these results indicate that CAPLA is an effective approach for binding affinity prediction and may contribute to useful help for further consequent applications. AVAILABILITY AND IMPLEMENTATION: The source code of the method along with trained models is freely available at https://github.com/lennylv/CAPLA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

ctP2ISP: Protein-Protein Interaction Sites Prediction Using Convolution and Transformer With Data Augmentation.

Protein-protein interactions are the basis of many cellular biological processes, such as cellular organization, signal transduction, and immune response. Identifying protein-protein interaction sites is essential for understanding the mechanisms of various biological processes, disease development, and drug design. However, it remains a challenging task to make accurate predictions, as the small amount of training data and severe imbalanced classification reduce the performance of computational methods. We design a deep learning method named ctP2ISP to improve the prediction of protein-protein interaction sites. ctP2ISP employs Convolution and Transformer to extract information and enhance information perception so that semantic features can be mined to identify protein-protein interaction sites. A weighting loss function with different sample weights is designed to suppress the preference of the model toward multi-category prediction. To efficiently reuse the information in the training set, a preprocessing of data augmentation with an improved sample-oriented sampling strategy is applied. The trained ctP2ISP was evaluated against current state-of-the-art methods on six public datasets. The results show that ctP2ISP outperforms all other competing methods on the balance metrics: F1, MCC, and AUPRC. In particular, our prediction on open tests related to viruses may also be consistent with biological insights. The source code and data can be obtained from https://github.com/lennylv/ctP2ISP.

How Deepbics Quantifies Intensities of Transcription Factor-DNA Binding and Facilitates Prediction of Single Nucleotide Variant Pathogenicity With a Deep Learning Model Trained On ChIP-Seq Data Sets.

The binding of DNA sequences to cell type-specific transcription factors is essential for regulating gene expression in all organisms. Many variants occurring in these binding regions play crucial roles in human disease by disrupting the cis-regulation of gene expression. We first implemented a sequence-based deep learning model called deepBICS to quantify the intensity of transcription factors-DNA binding. The experimental results not only showed the superiority of deepBICS on ChIP-seq data sets but also suggested deepBICS as a language model could help the classification of disease-related and neutral variants. We then built a language model-based method called deepBICS4SNV to predict the pathogenicity of single nucleotide variants. The good performance of deepBICS4SNV on 2 tests related to Mendelian disorders and viral diseases shows the sequence contextual information derived from language models can improve prediction accuracy and generalization capability.

Multisource Attention-Mechanism-Based Encoder-Decoder Model for Predicting Drug-Drug Interaction Events.

Many computational methods have been proposed to predict drug-drug interactions (DDIs), which can occur when combining drugs to treat various diseases, but most mainly utilize single-source features of drugs, which is inadequate for drug representation. To fill this gap, we propose two attention-mechanism-based encoder-decoder models that incorporate multisource information: one is MAEDDI, which can predict DDIs, and the other is MAEDDIE, which can make further DDI-associated event predictions for drug pairs with DDIs. To better express the drug feature, we used three encoding methods to encode the drugs, integrating the self-attention mechanism, cross-attention mechanism, and graph attention network to construct a multisource feature fusion network. Experiments showed that both MAEDDI and MAEDDIE performed better than some state-of-the-art methods in various validation attempts at different experimental tasks. The visualization analysis showed that the semantic features of drug pairs learned from our models had a good drug representation. In practice, MAEDDIE successfully screened 43 DDI events on favipiravir, an influenza antiviral drug, with a success rate of nearly 50%. Our model achieved competitive results, mainly owing to the design of sequence-based, structural, biochemical, and statistical multisource features. Moreover, different encoders constructed based on different features learn the interrelationship information between drug pairs, and the different representations of these drug pairs are incorporated to predict the target problem. All of these encoders were designed to better characterize the complex DDI relationships, allowing us to achieve high generalization in DDI and DDI-associated event predations.

DeepNup: Prediction of Nucleosome Positioning from DNA Sequences Using Deep Neural Network.

Nucleosome positioning is involved in diverse cellular biological processes by regulating the accessibility of DNA sequences to DNA-binding proteins and plays a vital role. Previous studies have manifested that the intrinsic preference of nucleosomes for DNA sequences may play a dominant role in nucleosome positioning. As a consequence, it is nontrivial to develop computational methods only based on DNA sequence information to accurately identify nucleosome positioning, and thus intend to verify the contribution of DNA sequences responsible for nucleosome positioning. In this work, we propose a new deep learning-based method, named DeepNup, which enables us to improve the prediction of nucleosome positioning only from DNA sequences. Specifically, we first use a hybrid feature encoding scheme that combines One-hot encoding and Trinucleotide composition encoding to encode raw DNA sequences; afterwards, we employ multiscale convolutional neural network modules that consist of two parallel convolution kernels with different sizes and gated recurrent units to effectively learn the local and global correlation feature representations; lastly, we use a fully connected layer and a sigmoid unit serving as a classifier to integrate these learned high-order feature representations and generate the final prediction outcomes. By comparing the experimental evaluation metrics on two benchmark nucleosome positioning datasets, DeepNup achieves a better performance for nucleosome positioning prediction than that of several state-of-the-art methods. These results demonstrate that DeepNup is a powerful deep learning-based tool that enables one to accurately identify potential nucleosome sequences.

Factor Structure of an ICF-Based Measure of Activity and Participations for Adults in Taiwan's Disability Eligibility Determination System.

To assess activity and participation for adults in Taiwan's Disability Eligibility Determination System (DEDS), we developed a measure, the Functioning Disability Evaluation Scale-Adult version (FUNDES-Adult), based on the 36-item interviewer-administered version of the WHO Disability Assessment Schedule 2.0. The purpose of this study was to examine the factor structures of performance and capability dimensions of the FUNDES-Adult. This study followed a methodology research design to investigate the construct validity of the two dimensions of the FUNDES-Adult. Two samples were randomly stratified from the databank of adults with disabilities to examine structural validity by the exploratory factor analysis (EFA) (n = 8,730, mean age of 52.9 ± 16.81) and the confirmatory factor analysis (CFA) (n = 500, mean age of 54.3 ± 16.81). The results demonstrated that the EFA yielded 5-factor structures for both performance dimension (73.5% variance explained) and capability dimension (75.9% variance explained). The CFA indicated that the second-order factor structures of both dimensions were more parsimonious with adequate fit indices (GFI, NFI, CFI, and TLI ≥ 0.95, RMSEA < 0.09). The results of this study provide evidence that the FUNDES-Adult has acceptable structural validity for use in Taiwan's DEDS. Utility of the FUNDES-Adult in rehabilitation, employment, welfare, and long-term care services needs further study.

On the Tuning of the Computation Capability of Spiking Neural Membrane Systems with Communication on Request.

Spiking neural P systems (abbreviated as SNP systems) are models of computation that mimic the behavior of biological neurons. The spiking neural P systems with communication on request (abbreviated as SNQP systems) are a recently developed class of SNP system, where a neuron actively requests spikes from the neighboring neurons instead of passively receiving spikes. It is already known that small SNQP systems, with four unbounded neurons, can achieve Turing universality. In this context, 'unbounded' means that the number of spikes in a neuron is not capped. This work investigates the dependency of the number of unbounded neurons on the computation capability of SNQP systems. Specifically, we prove that (1) SNQP systems composed entirely of bounded neurons can characterize the family of finite sets of numbers; (2) SNQP systems containing two unbounded neurons are capable of generating the family of semilinear sets of numbers; (3) SNQP systems containing three unbounded neurons are capable of generating nonsemilinear sets of numbers. Moreover, it is obtained in a constructive way that SNQP systems with two unbounded neurons compute the operations of Boolean logic gates, i.e., OR, AND, NOT, and XOR gates. These theoretical findings demonstrate that the number of unbounded neurons is a key parameter that influences the computation capability of SNQP systems.

Identifying modifications on DNA-bound histones with joint deep learning of multiple binding sites in DNA sequence.

MOTIVATION: Histone modifications are epigenetic markers that impact gene expression by altering the chromatin structure or recruiting histone modifiers. Their accurate identification is key to unraveling the mechanisms by which they regulate gene expression. However, the solutions for this task can be improved by exploiting multiple relationships from dataset and exploring designs of learning models, for example jointly learning technology. RESULTS: This article proposes a deep learning-based multi-objective computational approach, iHMnBS, to identify which of the seven typical histone modifications a DNA sequence may choose to bind, and which parts of the DNA sequence bind to them. iHMnBS employs a customized dataset that allows the marking of modifications contained in histones that may bind to any position in the DNA sequence. iHMnBS tries to mine the information implicit in this richer data by means of deep neural networks. In comprehensive comparisons, iHMnBS outperforms a baseline method, and the probability of binding to modified histones assigned to a representative nucleotide of a DNA sequence can serve as a reference for biological experiments. Since the interaction between transcription factors and histone modifications has an important role in gene expression, we extracted a number of sequence patterns that may bind to transcription factors, and explored their possible impact on disease. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/lennylv/iHMnBS. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The Personality Traits and P300 of Offspring of Parents With Alcohol Dependence Differ Depending on Current Risky Drinking: A Preliminary Case-Control Study.

Aims: The aim of this study was to investigate the personality traits, and P300 component in the offspring of parents with alcohol dependence (OPAD) currently engaged in risky drinking and those not engaged in risky drinking, and to further explore the correlates of problematic alcohol use. Methods: A case-control study was conducted according to the cutoff of the Alcohol Use Disorder Identification Test (AUDIT). The frequency of the TaqIA polymorphism of the dopamine receptor D2 gene associated with alcohol dependence was compared between the two OPAD groups. Tridimensional Personality Questionnaire (TPQ), The Alcohol, Smoking, and Substance Involvement Screening Test (ASSIST), and the MINI-International Neuropsychiatric Interview (M.I.N.I.) were measured or interviewed in OPAD not engaged in risky drinking (resilient; n = 35) and those currently engaged in risky drinking (vulnerable; n = 20). P300 was measured to test the possible electrophysiological differences. The correlates of alcohol use were analyzed. Results: Vulnerable OPAD showed higher novelty seeking subscale scores (NS4; 4.45 ± 2.012 vs. 3.31 ± 1.728, P < 0.05) and harm avoidance subscale scores (HA4; 5.3 ± 2.319 vs. 3.66 ± 2.461, P < 0.05) than resilient OPAD, while the total scores of each dimension showed no significant difference. OPAD engaged in risky drinking showed more tobacco use than OPAD resistant to risky drinking. OPAD with risky drinking showed a shorter P300 latency than resilient OPAD on Fz electrodes. AUDIT scores of OPAD were correlated with P300 latency. Conclusions: P300 differed between OPAD with and without risky drinking and alcohol use was associated with P300 latency, indicating that P300 may be used in the early detection of vulnerable OPAD and early intervention in the future.

Prevalence and Correlates of Risky Drinking Among the Oldest-Old in China: A National Community-Based Survey.

Aims: To investigate the prevalence and correlates of risky drinking in Chinese elderly people aged 80 and over. Methods: Data were obtained from the Chinese Longitudinal Healthy Longevity Survey (CLHLS) conducted in 2018. A total of 10,141 respondents aged 80 years or older were included in this analysis. Risky drinking was defined as drinking > 2 drinks per day. The participants were divided into no risky drinking, past risky drinking, and current risky drinking groups. The prevalence of risky drinking, daily dosage, and type of alcohol beverages were assessed. The correlates of risky drinking were analyzed using logistic regression. Results: The prevalence of past and current risky drinking was 6.2 and 4.4%, respectively. A total of 12.2% of males and 2.1% of females reported past risky drinking, and 8.9% of males and 1.4% of females reported current risky drinking. The median of the daily dosage of the past risky drinking group was 4.5 and 4 drinks in males and females, respectively, and were 4 and 3.3, respectively, of the current risky drinking group. Strong liquor was the most popular alcohol beverage in all groups. Men who were older or had white-collar work were less likely to be past risky drinkers, while those with smoking in past or current or heart disease were more likely to be past risky drinkers. Women who smoked in the past were more likely to be past risky drinkers. Men with older age or living in the urban areas or with heart disease were less likely to be current risky drinkers. Women with higher education or with heart disease were less likely to be current risky drinkers. Women with current smoking were more likely to have current risky drinking. Conclusions: Our findings indicated that risky drinking among the oldest-old was not rare in China. The correlates of past and current risky drinking were different. Men and women had various correlates of risky drinking as well. Those with higher socioeconomic status seemed less likely to be risky drinking. More attention should be given to risky drinking among the oldest old, and sex-specific intervention may be needed.

TransPPMP: predicting pathogenicity of frameshift and non-sense mutations by a Transformer based on protein features.

MOTIVATION: Protein structure can be severely disrupted by frameshift and non-sense mutations at specific positions in the protein sequence. Frameshift and non-sense mutation cases can also be found in healthy individuals. A method to distinguish neutral and potentially disease-associated frameshift and non-sense mutations is of practical and fundamental importance. It would allow researchers to rapidly screen out the potentially pathogenic sites from a large number of mutated genes and then use these sites as drug targets to speed up diagnosis and improve access to treatment. The problem of how to distinguish between neutral and potentially disease-associated frameshift and non-sense mutations remains under-researched. RESULTS: We built a Transformer-based neural network model to predict the pathogenicity of frameshift and non-sense mutations on protein features and named it TransPPMP. The feature matrix of contextual sequences computed by the ESM pre-training model, type of mutation residue and the auxiliary features, including structure and function information, are combined as input features, and the focal loss function is designed to solve the sample imbalance problem during the training. In 10-fold cross-validation and independent blind test set, TransPPMP showed good robust performance and absolute advantages in all evaluation metrics compared with four other advanced methods, namely, ENTPRISE-X, VEST-indel, DDIG-in and CADD. In addition, we demonstrate the usefulness of the multi-head attention mechanism in Transformer to predict the pathogenicity of mutations-not only can multiple self-attention heads learn local and global interactions but also functional sites with a large influence on the mutated residue can be captured by attention focus. These could offer useful clues to study the pathogenicity mechanism of human complex diseases for which traditional machine learning methods fall short. AVAILABILITY AND IMPLEMENTATION: TransPPMP is available at https://github.com/lennylv/TransPPMP. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.