AMPActiPred: A three-stage framework for predicting antibacterial peptides and activity levels with deep forest.

The emergence and spread of antibiotic-resistant bacteria pose a significant public health threat, necessitating the exploration of alternative antibacterial strategies. Antibacterial peptide (ABP) is a kind of antimicrobial peptide (AMP) that has the potential ability to fight against bacteria infection, offering a promising avenue for developing novel therapeutic interventions. This study introduces AMPActiPred, a three-stage computational framework designed to identify ABPs, characterize their activity against diverse bacterial species, and predict their activity levels. AMPActiPred employed multiple effective peptide descriptors to effectively capture the compositional features and physicochemical properties of peptides. AMPActiPred utilized deep forest architecture, a cascading architecture similar to deep neural networks, capable of effectively processing and exploring original features to enhance predictive performance. In the first stage, AMPActiPred focuses on ABP identification, achieving an Accuracy of 87.6% and an MCC of 0.742 on an elaborate dataset, demonstrating state-of-the-art performance. In the second stage, AMPActiPred achieved an average GMean at 82.8% in identifying ABPs targeting 10 bacterial species, indicating AMPActiPred can achieve balanced predictions regarding the functional activity of ABP across this set of species. In the third stage, AMPActiPred demonstrates robust predictive capabilities for ABP activity levels with an average PCC of 0.722. Furthermore, AMPActiPred exhibits excellent interpretability, elucidating crucial features associated with antibacterial activity. AMPActiPred is the first computational framework capable of predicting targets and activity levels of ABPs. Finally, to facilitate the utilization of AMPActiPred, we have established a user-friendly web interface deployed at https://awi.cuhk.edu.cn/∼AMPActiPred/.

A two-stage computational framework for identifying antiviral peptides and their functional types based on contrastive learning and multi-feature fusion strategy.

Antiviral peptides (AVPs) have shown potential in inhibiting viral attachment, preventing viral fusion with host cells and disrupting viral replication due to their unique action mechanisms. They have now become a broad-spectrum, promising antiviral therapy. However, identifying effective AVPs is traditionally slow and costly. This study proposed a new two-stage computational framework for AVP identification. The first stage identifies AVPs from a wide range of peptides, and the second stage recognizes AVPs targeting specific families or viruses. This method integrates contrastive learning and multi-feature fusion strategy, focusing on sequence information and peptide characteristics, significantly enhancing predictive ability and interpretability. The evaluation results of the model show excellent performance, with accuracy of 0.9240 and Matthews correlation coefficient (MCC) score of 0.8482 on the non-AVP independent dataset, and accuracy of 0.9934 and MCC score of 0.9869 on the non-AMP independent dataset. Furthermore, our model can predict antiviral activities of AVPs against six key viral families (Coronaviridae, Retroviridae, Herpesviridae, Paramyxoviridae, Orthomyxoviridae, Flaviviridae) and eight viruses (FIV, HCV, HIV, HPIV3, HSV1, INFVA, RSV, SARS-CoV). Finally, to facilitate user accessibility, we built a user-friendly web interface deployed at https://awi.cuhk.edu.cn/∼dbAMP/AVP/.

Identifying Antitubercular Peptides via Deep Forest Architecture with Effective Feature Representation.

Tuberculosis (TB) is a severe disease caused by Mycobacterium tuberculosis that poses a significant threat to human health. The emergence of drug-resistant strains has made the global fight against TB even more challenging. Antituberculosis peptides (ATPs) have shown promising results as a potential treatment for TB. However, conventional wet lab-based approaches to ATP discovery are time-consuming and costly and often fail to discover peptides with desired properties. To address these challenges, we propose a novel machine learning-based framework called ATPfinder that can significantly accelerate the discovery of ATP. Our approach integrates various efficient peptide descriptors and utilizes the deep forest algorithm to construct the model. This neural network-like cascading structure can effectively process and mine features without complex hyperparameter tuning. Our experimental results show that ATPfinder outperforms existing ATP prediction tools, achieving state-of-the-art performance with an accuracy of 89.3% and an MCC of 0.70. Moreover, our framework exhibits better robustness than baseline algorithms commonly used for other sequence analysis tasks. Additionally, the excellent interpretability of our model can assist researchers in understanding the critical features of ATP. Finally, we developed a downloadable desktop application to simplify the use of our framework for researchers. Therefore, ATPfinder can facilitate the discovery of peptide drugs and provide potential solutions for TB treatment. Our framework is freely available at https://github.com/lantianyao/ATPfinder/ (data sets and code) and https://awi.cuhk.edu.cn/dbAMP/ATPfinder.html (software).

Predicting Anti-inflammatory Peptides by Ensemble Machine Learning and Deep Learning.

Inflammation is a biological response to harmful stimuli, aiding in the maintenance of tissue homeostasis. However, excessive or persistent inflammation can precipitate a myriad of pathological conditions. Although current treatments such as NSAIDs, corticosteroids, and immunosuppressants are effective, they can have side effects and resistance issues. In this backdrop, anti-inflammatory peptides (AIPs) have emerged as a promising therapeutic approach against inflammation. Leveraging machine learning methods, we have the opportunity to accelerate the discovery and investigation of these AIPs more effectively. In this study, we proposed an advanced framework by ensemble machine learning and deep learning for AIP prediction. Initially, we constructed three individual models with extremely randomized trees (ET), gated recurrent unit (GRU), and convolutional neural networks (CNNs) with attention mechanism and then used stacking architecture to build the final predictor. By utilizing various sequence encodings and combining the strengths of different algorithms, our predictor demonstrated exemplary performance. On our independent test set, our model achieved an accuracy, MCC, and F1-score of 0.757, 0.500, and 0.707, respectively, clearly outperforming other contemporary AIP prediction methods. Additionally, our model offers profound insights into the feature interpretation of AIPs, establishing a valuable knowledge foundation for the design and development of future anti-inflammatory strategies.

DeepAFP: An effective computational framework for identifying antifungal peptides based on deep learning.

Fungal infections have become a significant global health issue, affecting millions worldwide. Antifungal peptides (AFPs) have emerged as a promising alternative to conventional antifungal drugs due to their low toxicity and low propensity for inducing resistance. In this study, we developed a deep learning-based framework called DeepAFP to efficiently identify AFPs. DeepAFP fully leverages and mines composition information, evolutionary information, and physicochemical properties of peptides by employing combined kernels from multiple branches of convolutional neural network with bi-directional long short-term memory layers. In addition, DeepAFP integrates a transfer learning strategy to obtain efficient representations of peptides for improving model performance. DeepAFP demonstrates strong predictive ability on carefully curated datasets, yielding an accuracy of 93.29% and an F1-score of 93.45% on the DeepAFP-Main dataset. The experimental results show that DeepAFP outperforms existing AFP prediction tools, achieving state-of-the-art performance. Finally, we provide a downloadable AFP prediction tool to meet the demands of large-scale prediction and facilitate the usage of our framework by the public or other researchers. Our framework can accurately identify AFPs in a short time without requiring significant human and material resources, and hence can accelerate the development of AFPs as well as contribute to the treatment of fungal infections. Furthermore, our method can provide new perspectives for other biological sequence analysis tasks.

StackTHPred: Identifying Tumor-Homing Peptides through GBDT-Based Feature Selection with Stacking Ensemble Architecture.

One of the major challenges in cancer therapy lies in the limited targeting specificity exhibited by existing anti-cancer drugs. Tumor-homing peptides (THPs) have emerged as a promising solution to this issue, due to their capability to specifically bind to and accumulate in tumor tissues while minimally impacting healthy tissues. THPs are short oligopeptides that offer a superior biological safety profile, with minimal antigenicity, and faster incorporation rates into target cells/tissues. However, identifying THPs experimentally, using methods such as phage display or in vivo screening, is a complex, time-consuming task, hence the need for computational methods. In this study, we proposed StackTHPred, a novel machine learning-based framework that predicts THPs using optimal features and a stacking architecture. With an effective feature selection algorithm and three tree-based machine learning algorithms, StackTHPred has demonstrated advanced performance, surpassing existing THP prediction methods. It achieved an accuracy of 0.915 and a 0.831 Matthews Correlation Coefficient (MCC) score on the main dataset, and an accuracy of 0.883 and a 0.767 MCC score on the small dataset. StackTHPred also offers favorable interpretability, enabling researchers to better understand the intrinsic characteristics of THPs. Overall, StackTHPred is beneficial for both the exploration and identification of THPs and facilitates the development of innovative cancer therapies.

Methods and Impact for Using Federated Learning to Collaborate on Clinical Research.

BACKGROUND: The development of accurate machine learning algorithms requires sufficient quantities of diverse data. This poses a challenge in health care because of the sensitive and siloed nature of biomedical information. Decentralized algorithms through federated learning (FL) avoid data aggregation by instead distributing algorithms to the data before centrally updating one global model. OBJECTIVE: To establish a multicenter collaboration and assess the feasibility of using FL to train machine learning models for intracranial hemorrhage (ICH) detection without sharing data between sites. METHODS: Five neurosurgery departments across the United States collaborated to establish a federated network and train a convolutional neural network to detect ICH on computed tomography scans. The global FL model was benchmarked against a standard, centrally trained model using a held-out data set and was compared against locally trained models using site data. RESULTS: A federated network of practicing neurosurgeon scientists was successfully initiated to train a model for predicting ICH. The FL model achieved an area under the ROC curve of 0.9487 (95% CI 0.9471-0.9503) when predicting all subtypes of ICH compared with a benchmark (non-FL) area under the ROC curve of 0.9753 (95% CI 0.9742-0.9764), although performance varied by subtype. The FL model consistently achieved top three performance when validated on any site's data, suggesting improved generalizability. A qualitative survey described the experience of participants in the federated network. CONCLUSION: This study demonstrates the feasibility of implementing a federated network for multi-institutional collaboration among clinicians and using FL to conduct machine learning research, thereby opening a new paradigm for neurosurgical collaboration.

Satisfaction With Community Health Education Among Residents in China: Results From a Structural Equation Model.

Background: Although community health education has drawn lots of attention from the public, evidence on resident satisfaction is still sparse. This study aims to explore the relationships among five dimensions (perceived quality, perceived value, public expectation, public trust, and public satisfaction) of satisfaction with community health education among Chinese residents. Methods: We constructed a theoretical public satisfaction model for community health education based on the American Customer Satisfaction Index (ACSI) model. There are five dimensions in the theoretical model, including public expectation, perceived quality, perceived value, public satisfaction, and public trust. We recruited 474 respondents from a quota sampling based on gender and age, and collected information on five dimensions of satisfaction with community health education. The relationships of the five dimensions were examined using structural equation model. Results: The mean scores of public expectation, perceived quality, perceived value, public satisfaction, and public trust for the participants were 11.44 (total 15), 123.89 (total 170), 14.18 (total 20), 10.19 (total 15), and 15.61 (total 20), respectively. We obtained a structural equation model with a good fitting degree. There was a direct effect of perceived quality on perceived value (γ = 0.85, P < 0.01), public trust (γ = 0.81, P < 0.01) and public satisfaction (γ = 0.58, P < 0.01), and a direct effect of public expectation on public satisfaction (γ = 0.36, P < 0.01) and perceived value (γ = 0.25, P < 0.01). Conclusions: We provide a good tool to measure public satisfaction with community health education, which can be potentially used to measure public satisfaction and improve the effectiveness of health education.

Federated learning for predicting clinical outcomes in patients with COVID-19.

Federated learning (FL) is a method used for training artificial intelligence models with data from multiple sources while maintaining data anonymity, thus removing many barriers to data sharing. Here we used data from 20 institutes across the globe to train a FL model, called EXAM (electronic medical record (EMR) chest X-ray AI model), that predicts the future oxygen requirements of symptomatic patients with COVID-19 using inputs of vital signs, laboratory data and chest X-rays. EXAM achieved an average area under the curve (AUC) >0.92 for predicting outcomes at 24 and 72 h from the time of initial presentation to the emergency room, and it provided 16% improvement in average AUC measured across all participating sites and an average increase in generalizability of 38% when compared with models trained at a single site using that site's data. For prediction of mechanical ventilation treatment or death at 24 h at the largest independent test site, EXAM achieved a sensitivity of 0.950 and specificity of 0.882. In this study, FL facilitated rapid data science collaboration without data exchange and generated a model that generalized across heterogeneous, unharmonized datasets for prediction of clinical outcomes in patients with COVID-19, setting the stage for the broader use of FL in healthcare.

A multi-center study of COVID-19 patient prognosis using deep learning-based CT image analysis and electronic health records.

PURPOSE: As of August 30th, there were in total 25.1 million confirmed cases and 845 thousand deaths caused by coronavirus disease of 2019 (COVID-19) worldwide. With overwhelming demands on medical resources, patient stratification based on their risks is essential. In this multi-center study, we built prognosis models to predict severity outcomes, combining patients' electronic health records (EHR), which included vital signs and laboratory data, with deep learning- and CT-based severity prediction. METHOD: We first developed a CT segmentation network using datasets from multiple institutions worldwide. Two biomarkers were extracted from the CT images: total opacity ratio (TOR) and consolidation ratio (CR). After obtaining TOR and CR, further prognosis analysis was conducted on datasets from INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3. For each data cohort, generalized linear model (GLM) was applied for prognosis prediction. RESULTS: For the deep learning model, the correlation coefficient of the network prediction and manual segmentation was 0.755, 0.919, and 0.824 for the three cohorts, respectively. The AUC (95 % CI) of the final prognosis models was 0.85(0.77,0.92), 0.93(0.87,0.98), and 0.86(0.75,0.94) for INSTITUTE-1, INSTITUTE-2 and INSTITUTE-3 cohorts, respectively. Either TOR or CR exist in all three final prognosis models. Age, white blood cell (WBC), and platelet (PLT) were chosen predictors in two cohorts. Oxygen saturation (SpO2) was a chosen predictor in one cohort. CONCLUSION: The developed deep learning method can segment lung infection regions. Prognosis results indicated that age, SpO2, CT biomarkers, PLT, and WBC were the most important prognostic predictors of COVID-19 in our prognosis model.

Federated Learning used for predicting outcomes in SARS-COV-2 patients.

'Federated Learning' (FL) is a method to train Artificial Intelligence (AI) models with data from multiple sources while maintaining anonymity of the data thus removing many barriers to data sharing. During the SARS-COV-2 pandemic, 20 institutes collaborated on a healthcare FL study to predict future oxygen requirements of infected patients using inputs of vital signs, laboratory data, and chest x-rays, constituting the "EXAM" (EMR CXR AI Model) model. EXAM achieved an average Area Under the Curve (AUC) of over 0.92, an average improvement of 16%, and a 38% increase in generalisability over local models. The FL paradigm was successfully applied to facilitate a rapid data science collaboration without data exchange, resulting in a model that generalised across heterogeneous, unharmonized datasets. This provided the broader healthcare community with a validated model to respond to COVID-19 challenges, as well as set the stage for broader use of FL in healthcare.

Efficient degradation of ivermectin by newly isolated Aeromonas taiwanensis ZJB-18,044.

Ivermectin (IVM) is a widely used antiparasitic agent and acaricide. Despite its high efficiency against nematodes and arthropods, IVM may pose a threat to the environment due to its ecotoxcity. In this study, degradation of IVM by a newly isolated bacterium Aeromonas taiwanensis ZJB-18,044 was investigated. Strain ZJB-18,044 can completely degrade 50 mg/L IVM in 5 d with a biodegradation ability of 0.42 mg/L/h. Meanwhile, it exhibited high tolerance (50 mg/L) to doramectin, emamectin, rifampicin, and spiramycin. It can also efficiently degrade doramectin, emamectin, and spiramycin. The IVM degradation of strain ZJB-18,044 can be inhibited by erythromycin, azithromycin, spiramycin or rifampicin. However, supplement of carbonyl cyanide m-chlorophenylhydrazone, an uncoupler of oxidative phosphorylation, can partially recover the IVM degradation. Moreover, strain ZJB-18,044 cells can pump out excess IVM to maintain a low intracellular IVM concentration. Therefore, the IVM tolerance of strain ZJB-18,044 may be due to the regulation of the intracellular IVM concentration by the activated macrolide efflux pump(s). With the high IVM degradation efficiency, A. taiwanensis ZJB-18,044 may serve as a bioremediation agent for IVM and other macrolides in the environment.

Association between serum HER2/ErbB2 levels and coronary artery disease: a case-control study.

BACKGROUND: Research has associated human epidermal growth factor receptor (HER2) with glucose and lipid metabolism. However, the association between circulating HER2 levels and coronary artery disease (CAD) remains to be elucidated. METHODS: We performed a case-control study with 435 participants (237 CAD patients and 198 controls) who underwent diagnostic coronary angiography from September 2018 to October 2019. Adjusted odds ratios (ORs) and 95% confidence intervals (CIs) for CAD were calculated with multiple logistic regression models after adjustment for confounders. RESULTS: Overall, increased serum HER2 levels were independently associated with the presence of CAD (OR per 1-standard deviation (SD) increase: 1.438, 95% CI 1.13-1.83; P = 0.003) and the number of stenotic vessels (OR per 1-SD increase: 1.399, 95% CI 1.15-1.71; P = 0.001). In the subgroup analysis, a significant interaction of HER2 with body mass index (BMI) on the presence of CAD was observed (adjusted interaction P = 0.046). Increased serum HER2 levels were strongly associated with the presence of CAD in participants with BMI ≥ 25 kg/m2 (OR per 1-SD increase: 2.143, 95% CI 1.37-3.35; P = 0.001), whereas no significant association was found in participants with BMI < 25 kg/m2 (OR per 1-SD increase: 1.225, 95% CI 0.90-1.67; P = 0.201). CONCLUSION: Elevated HER2 level is associated with an increased risk of CAD, particularly in people with obesity. This finding yields new insight into the pathological mechanisms underlying CAD, and warrants further research regarding HER2 as a preventive and therapeutic target of CAD.

Association between serum angiopoietin-2 concentrations and periprocedural myocardial injury in patients undergoing elective percutaneous coronary intervention.

Angiopoietin-2 (Ang-2) is a proangiogenic factor that mediates inflammation and atherosclerosis. We evaluated the predictive value of circulating Ang-2 levels for periprocedural myocardial injury (PMI) in 145 patients undergoing elective percutaneous coronary intervention (PCI), and investigated whether post-PCI Ang-2 levels are influenced by PMI. PMI was defined as a post-procedural troponin elevation above the 5×99th percentile upper reference limit. Blood samples for Ang-2 analysis were collected at admission and on postoperative days 1 and 3. PMI occurred in 40 patients (28%). At baseline, there was no difference in Ang-2 levels between PMI and non-PMI patients (P=0.554). However, a significant interaction effect between PMI occurrence and time on Ang-2 levels was observed (interaction P=0.036). Although serum Ang-2 levels in non-PMI patients gradually decreased, Ang-2 levels in PMI patients did not change between different time-points. Multiple logistic regression analysis revealed that age, total stent length, and serum levels of N-terminal pro-brain natriuretic peptide were independent PMI predictors. These findings indicate that pre-procedural Ang-2 levels do not impact PMI occurrence after elective PCI. However, changes in Ang-2 levels after the procedure are closely related to PMI.

DCG++: A data-driven metric for geometric pattern recognition.

Clustering large and complex data sets whose partitions may adopt arbitrary shapes remains a difficult challenge. Part of this challenge comes from the difficulty in defining a similarity measure between the data points that captures the underlying geometry of those data points. In this paper, we propose an algorithm, DCG++ that generates such a similarity measure that is data-driven and ultrametric. DCG++ uses Markov Chain Random Walks to capture the intrinsic geometry of data, scans possible scales, and combines all this information using a simple procedure that is shown to generate an ultrametric. We validate the effectiveness of this similarity measure within the context of clustering on synthetic data with complex geometry, on a real-world data set containing segmented audio records of frog calls described by mel-frequency cepstral coefficients, as well as on an image segmentation problem. The experimental results show a significant improvement on performance with the DCG-based ultrametric compared to using an empirical distance measure.

Serum angiopoietin-2 concentrations of post-PCI are correlated with the parameters of renal function in patients with coronary artery disease.

Patients with coronary artery disease (CAD) frequently have comorbidity of chronic kidney disease (CKD). Their renal function may deteriorate because of the use of contrast agent after percutaneous coronary intervention (PCI). Angiopoietin-2 (Ang-2), which is highly expressed in the site of angiogenesis, plays an important role in both CAD and CKD. This study aimed to investigate the relation of serum Ang-2 concentrations with the renal function after PCI.This study enrolled 57 patients with CAD undergoing PCI. Blood samples for Ang-2 were collected in the first morning after admission and within 24 to 48 h after PCI. The parameters of renal function (serum creatinine, cystatin C and eGFR) were tested on the first day after admission and within 72 h after PCI.Overall, serum Ang-2 levels of post-PCI were significantly lower than those of pre-PCI [median, 1733 (IQR, 1100-2568) vs median, 2523 (IQR, 1702-3640) pg/mL; P < .001]. However, in patients with CKD (eGFR < 60 mL/min/1.73 m), there was no significant difference between serum Ang-2 levels of post-PCI and those of pre-PCI [median, 2851 (IQR, 1720-4286) vs. median, 2492 (IQR, 1434-4994) pg/mL; P = .925]. In addition, serum Ang-2 levels of post-PCI, but not pre-PCI, were significantly correlated with the post-PCI parameters of renal function.Serum Ang-2 concentrations of post-PCI are closely related to renal function in patients with CAD. It may have potential to be the early biomarker of contrast-induced nephropathy in the future.

PET Image Denoising Using a Deep Neural Network Through Fine Tuning.

Positron emission tomography (PET) is a functional imaging modality widely used in clinical diagnosis. In this work, we trained a deep convolutional neural network (CNN) to improve PET image quality. Perceptual loss based on features derived from a pre-trained VGG network, instead of the conventional mean squared error, was employed as the training loss function to preserve image details. As the number of real patient data set for training is limited, we propose to pre-train the network using simulation data and fine-tune the last few layers of the network using real data sets. Results from simulation, real brain and lung data sets show that the proposed method is more effective in removing noise than the traditional Gaussian filtering method.

Social network community structure and the contact-mediated sharing of commensal E. coli among captive rhesus macaques (Macaca mulatta).

In group-living animals, heterogeneity in individuals' social connections may mediate the sharing of microbial infectious agents. In this regard, the genetic relatedness of individuals' commensal gut bacterium Escherichia coli may be ideal to assess the potential for pathogen transmission through animal social networks. Here we use microbial phylogenetics and population genetics approaches, as well as host social network reconstruction, to assess evidence for the contact-mediated sharing of E. coli among three groups of captively housed rhesus macaques (Macaca mulatta), at multiple organizational scales. For each group, behavioral data on grooming, huddling, and aggressive interactions collected for a six-week period were used to reconstruct social network communities via the Data Cloud Geometry (DCG) clustering algorithm. Further, an E. coli isolate was biochemically confirmed and genotypically fingerprinted from fecal swabs collected from each macaque. Population genetics approaches revealed that Group Membership, in comparison to intrinsic attributes like age, sex, and/or matriline membership of individuals, accounted for the highest proportion of variance in E. coli genotypic similarity. Social network approaches revealed that such sharing was evident at the community-level rather than the dyadic level. Specifically, although we found no links between dyadic E. coli similarity and social contact frequencies, similarity was significantly greater among macaques within the same social network communities compared to those across different communities. Moreover, tests for one of our study-groups confirmed that E. coli isolated from macaque rectal swabs were more genotypically similar to each other than they were to isolates from environmentally deposited feces. In summary, our results suggest that among frequently interacting, spatially constrained macaques with complex social relationships, microbial sharing via fecal-oral, social contact-mediated routes may depend on both individuals' direct connections and on secondary network pathways that define community structure. They lend support to the hypothesis that social network communities may act as bottlenecks to contain the spread of infectious agents, thereby encouraging disease control strategies to focus on multiple organizational scales. Future directions includeincreasing microbial sampling effort per individual to better-detect dyadic transmission events, and assessments of the co-evolutionary links between sociality, infectious agent risk, and host immune function.