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 bacteriumEscherichia colimay 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 ofE. coliamong 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, anE. coliisolate 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 inE. coligenotypic 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 dyadicE. colisimilarity 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 thatE. coliisolated 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.

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.

Drug–target interactions is essential for advancing pharmaceuticals. Traditional drug–target interaction studies rely on labor-intensive laboratory techniques. Still, recent advancements in computing power have elevated the importance of deep learning methods, offering faster, more precise, and cost-effective screening and prediction. Nonetheless, general deep learning methods often yield low-confidence results due to the complex nature of drugs and proteins, bias, limited labeled data, and feature extraction challenges. To address these challenges, a novel two-stage pre-trained framework is proposed for drug–target interactions prediction. In the first stage, pre-trained molecule and protein models develop a comprehensive feature representation, enhancing the framework’s ability to handle drug and protein diversity. This also reduces bias, improving prediction accuracy. In the second stage, a transformer with bilinear pooling and a fully connected layer enables predictions based on feature vectors. Comprehensive experiments were conducted using public datasets from DrugBank and Epigenetic-regulators datasets to evaluate the framework’s effectiveness. The results demonstrate that the proposed framework outperforms the state-of-the-art methods regarding accuracy, area under the receiver operating characteristic curve, recall, and area under the precision-recall curve. The code is available at: https://github.com/DHCGroup/MocFormer.

The emergence of drug resistance among pathogens has become a major challenge to human health on a global scale. Among them, antibiotic resistance is already a critical issue, and finding new therapeutic agents to address this problem is therefore urgent. One of the most promising alternatives to antibiotics are antibacterial peptides (ABPs), i.e., short peptides with antibacterial activity. In this study, we propose a novel ABP recognition method, called ABPCaps. It integrates a convolutional neural network (CNN), a long short-term memory (LSTM), and a new type of neural network named the capsule network. The capsule network can extract critical features automatically from both positive and negative samples, leading to superior performance of ABPCaps over all baseline models built on hand-crafted peptide descriptors. Evaluated on independent test sets, ABPCaps achieves an accuracy of 93.33% and an F1-score of 91.34%, and consistently outperforms the baseline models in other extensive experiments as well. Our study demonstrates that the proposed ABPCaps, built on the capsule network method, is a valuable addition to the current state-of-the-art in the field of ABP recognition and has significant potential for further development.