Interaction Information Research Articles

Informeasure: an R/bioconductor package for quantifying nonlinear dependence between variables in biological networks from an information theory perspective

BackgroundUsing information measures to infer biological regulatory networks can capture nonlinear relationships between variables. However, it is computationally challenging, and there is a lack of convenient tools.ResultsWe introduce Informeasure, an R package designed to quantify nonlinear dependencies in biological regulatory networks from an information theory perspective. This package compiles a comprehensive set of information measurements, including mutual information, conditional mutual information, interaction information, partial information decomposition, and part mutual information. Mutual information is used for bivariate network inference, while the other four estimators are dedicated to trivariate network analysis.ConclusionsInformeasure is a turnkey solution, allowing users to utilize these information measures immediately upon installation. Informeasure is available as an R/Bioconductor package at https://bioconductor.org/packages/Informeasure.

Advancing a biomechanical framework for cellular interaction and mechanotransduction analysis using data mining techniques

As biomechanics advances, understanding the structural and functional dynamics of biological systems at molecular and cellular levels becomes increasingly critical. This study investigates a biomechanical framework for analyzing cellular interaction forces and information flow in mechanotransduction processes. Leveraging Data Mining (DM) technology, we evaluate cellular system efficiency and adaptation mechanisms under varying biomechanical stimuli, simulating stress conditions akin to high parallel processing loads. The proposed algorithm achieves an accuracy of 95.27% in predicting cellular response behaviors, with system stability maintained above 90% under simulated mechanical stress. These findings highlight the potential of computational methods to enhance our understanding of cellular resilience and adaptation in biomechanical contexts. Ultimately, this work contributes to the development of robust, adaptive models for studying the mechanobiology of cells and tissues, advancing diagnostic and therapeutic approaches in molecular and cellular biomechanics.

A distributed algorithm for the multi-robot minimum time task allocation problem

Purpose The purpose of this study is to address the challenge of task allocation in multi-robot systems by getting the minimum overall task completion time and task allocation scheme while also minimizing robot energy consumption. This study aims to move away from traditional centralized methods and validate a more scalable distributed approach. Design/methodology/approach This paper proposes a distributed algorithm for the multi-robot task allocation problem, aimed at getting the minimum task completion time along with the task allocation scheme. The algorithm operates based on local interaction information rather than global information. By using the Consensus-Based Auction Algorithm (CBAA), it seeks to effectively minimize energy consumption without affecting the minimum completion time required for overall task allocation. Findings The proposed distributed algorithm successfully reduces robot energy consumption while effectively obtaining the shortest overall task completion time and corresponding task allocation scheme. Numerical simulations conducted using MATLAB software demonstrated its superior performance, and empirical testing on the Turtlebot3-Burger robot platform further substantiated these findings. Originality/value The original contribution of this study lies in the development of an enhanced distributed task allocation strategy using CBAA to improve efficiency in multi-robot environments. Its value extends to applications that require rapid and resource-aware coordination, such as automated logistics or search-and-rescue operations.

Rapid Vehicle Trajectory Prediction Based on Multi-Attention Mechanism for Fusing Multimodal Information

Trajectory prediction plays a crucial role in autonomous driving tasks, as accurately and rapidly predicting the future trajectories of traffic participants can significantly enhance the safety and robustness of autonomous driving systems. This paper presents a novel trajectory prediction model that follows the encoder–decoder paradigm, achieving precise and rapid predictions of future vehicle trajectories by efficiently aggregating the spatiotemporal and interaction information of agents in traffic scenarios. We propose an agent–agent interaction information extraction module based on a sparse graph attention mechanism, which enables the efficient aggregation of interaction information between agents. Additionally, we introduce a non-autoregressive query generation method that accelerates the model inference speed by generating the decoding queries in parallel. Comparative experiments with the existing advanced algorithms show that our method improves the multimodal trajectory prediction metrics for the Minimum Average Displacement Error (minADE), the Minimum Final Displacement Error (minFDE), and the Miss Rate (MR) by an average of 9.1%, 11.8%, and 14.6%, respectively, while the inference time is only 33.7% of the average time taken by the other algorithms. Finally, we demonstrate the effectiveness of the various modules proposed in this paper through ablation studies.

A Lightweight Transformer-Based Spatiotemporal Analysis Prediction Algorithm for High-Dimensional Meteorological Data

High-dimensional meteorological data offer a comprehensive overview of meteorological conditions. Nevertheless, predicting regional high-dimensional meteorological data poses challenges due to the vast scale and rapid changes. Apart from slow conventional numerical weather prediction methods, recently developed deep learning methods often fail to fully integrate spatial information of the high-dimensional data and require a significant amount of computational resources. This paper presents the spatiotemporal analysis fitting prediction algorithm (SA-Fit), an approximation algorithm for regional high-dimensional meteorological data prediction. SA-Fit proposes two key designs to achieve efficient prediction of the high-dimensional data. SA-Fit introduces a lightweight Transformer-based spatiotemporal analysis network to encode spatiotemporal information, which can integrate the interaction information between different coordinates in the data. Furthermore, SA-Fit introduces explicit functions with a lasso penalty to fit variations in high-dimensional meteorological data, achieving the prediction of a large amount of data with minimal prediction values. We performed experiments using the ERA5 dataset from the Shanghai and Xi’an regions. The experimental results show that SA-Fit is comparable to other advanced deep learning prediction methods in overall prediction performance. SA-Fit shortens training time and significantly reduces model parameters while using the Transformer structure to ensure prediction accuracy.

Fuzzy multi-neighborhood entropy-based interactive feature selection for unsupervised outlier detection

Unsupervised feature selection is one of the important techniques for unsupervised knowledge discovery, which aims to reduce the dimensionality of conditional feature sets as much as possible to improve the efficiency and accuracy of the algorithm. However, existing methods have the following two challenges: (1) They are mainly applicable to select numerical or nominal features and cannot effectively select heterogeneous features; (2) The relevance and redundancy are primarily considered to construct feature evaluation indexes, ignoring the interaction information of heterogeneous features. To solve the challenges mentioned above, this paper proposes an unsupervised heterogeneous feature selection method based on fuzzy multi-neighborhood entropy, which also considers the multi-correlation of features to select heterogeneous features. First, the fuzzy multi-neighborhood granule is constructed by considering the distribution characteristics of the data. Then, the concept of fuzzy entropy is introduced to define the fuzzy multi-neighborhood entropy and its associated uncertainty measures, and the relationship between them is discussed. Next, the relevance, redundancy, and interactivity among attributes are defined, and the idea of maximum relevance-minimum redundancy-maximum interactivity is used to construct the evaluation indexes of heterogeneous features. Finally, experiments are conducted on several publicly unbalanced datasets, and the results are in comparison with existing algorithms. The experimental results show that the proposed algorithm can select fewer heterogeneous features to improve the efficiency of outlier detection tasks. The code is publicly available online at https://github.com/BELLoney/MNIFS.

Resan: A Residual Dual‐Attention Network for Abnormal Cardiac Activity Detection

ABSTRACTCardiovascular disease is one of the leading causes of death worldwide. Early and accurate detection of abnormal cardiac activity can be an effective way to prevent serious cardiovascular events. Electrocardiogram (ECG) and phonocardiogram (PCG) signals provide an objective evaluation of the heart's electrical and acoustic functions, enabling medical professionals to make an accurate diagnosis. Therefore, the cardiologists often use them to make a preliminary diagnosis of abnormal cardiac activity in clinical practice. For this reason, many diagnostic models have been proposed. However, these models fail to utilize the interaction information within and between the signals to aid the diagnosis of disease. To address this issue, we designed a residual dual‐attention network (ResAN) for the detection of abnormal cardiac activity using synchronized ECG and PCG signals. First, ResAN uses a feature learning module with two parallel residual networks, for example, ECG‐ResNet and PCG‐ResNet to automatically learn the deep modal‐specific features from the ECG and PCG sequences, respectively. Second, to fully utilize the available information of different modal signals, ResAN uses a dual‐attention fusion module to capture the salient features of the integrated ECG and PCG features learned by the feature learning module, as well as the alternating features between them based on the attention mechanisms. Finally, these fused features are merged and fed to the classification module to detect abnormal cardiac activity. Our model achieves an accuracy of 96.1%, surpassing the performances of comparison models by 1.0% to 9.9% when using synchronized ECG and PCG signals. Furthermore, the ablation study confirmed the efficacy of the components in ResAN and also showed that ResAN performs better with synchronized ECG and PCG signals compared to using single‐modal signals. Overall, ResAN provides a valid solution for the early detection of abnormal cardiac activity using ECG and PCG signals.

Robust graph mutual-assistance convolutional networks for semi-supervised node classification tasks

Graph convolutional networks (GCNs) have made substantial progress in semi-supervised learning. However, GCNs are sensitive to graph noise, making the reconstruction of imperfect graph structures essential for adapting GCNs to complex scenarios. Prevalent GCNs employ graph augmentation to generate reliable augmented graphs, thereby mining potential graph information. Since traditional GCN layers can only perform message passing independently within each graph, GCNs primarily concentrate on fusing information from the node embeddings independently learned by the reliable augmented graphs. Nevertheless, the neglect of cross-graph information exchange during message passing limits the model's inter-graph interactions ability. In this paper, we propose a GCN framework called Robust graph mutual-assistance convolutional networks (RamNet), which introduces cross-graph information exchange mechanisms into the GCN layers. First, RamNet employs a multi-metric topology augmentation strategy to generate a synthesized graph, thereby exploring more reliable information. Second, it learns inter-graph interaction information by achieving information exchange between the raw graph and the synthesized graph during message passing. Finally, in addition to utilizing a small amount of supervised information, it also captures rich self-supervision information by maximizing consistency relationship between input graphs. We conduct comprehensive experiments in both standard and noisy scenarios, highlighting the superior performance of RamNet.

Characteristics of 1D CRL position sensitive SiPM and its performance in acquiring 2D radiation imaging

The characteristics of one-dimensional (1D) position sensitive SiPM with an intrinsic continuous cap resistive layer (CRL) and its performance in acquiring two-dimensional (2D) radiation imaging are reported in this paper. The device, with an active size of 6.14 mm × 6.14 mm, demonstrated the position measurement error of 32.0 ± 24.0 µm without correction, which accounted for 0.5% of the length of the SiPM at a mean response photoelectron number around 230 and the reverse bias voltage of 40 V. Under the same condition, it demonstrated a position resolution of 128.7 ± 20.1 µm and a time resolution of 96.0 ± 33.2 ps. A 3D scintillation detector for acquiring 2D radiation imaging with depth information of interaction (DOI) is proposed by implementing two 1D CRL SiPMs in a perpendicular orientation on the two ends of a scintillator. Using this configuration, the 2D imaging of a pixelated 10 × 10 lutetium yttrium orthosilicate (LYSO) array, with each element having a volume of 0.52 mm × 0.52 mm × 20 mm, was successfully resolved by utilizing the natural radioactive radiation of lutetium element in LYSO without distortions at the edges and corners.

The characterization and structural basis of a human broadly binding antibody to HBV core protein.

Hepatitis B virus (HBV) core protein (HBc) plays a crucial role in the virus life cycle, making it an important detection marker for HBV infection and a potential target for treatment. However, several commercially available monoclonal antibodies (mAbs) or polyclonal antibodies (pAbs) targeting HBc have certain limitations in detecting HBV across different genotypes in various biochemical assays, such as enzyme-linked immunosorbent assay, western blot, immunofluorescence assay, flow cytometry, and immune spot assay. In this study, we identified 12 human anti-HBc mAbs and evaluated their potential application in multiple biochemical assays. These mAbs mainly recognized the epitopes near residues 20-22 amino acids (a.a.) and 77-78 a.a. of HBc, demonstrating a broadly cross-genotypic activity. Notably, three Group II mAbs, named cAbA1, cAbD4, and cAbF9, displayed excellent capacities for the detection of HBV infection in all tested biochemical assays. Furthermore, we determined a 3.22 Å of cryo-electron microscopy (cryo-EM) structure of the fragment of antigen binding (Fab) of cAbD4 complexed with HBc dimer, which was the highest resolution of the structural model for Fab-HBc to date. Collectively, our findings provided excellent and reliable antibody candidates for live HBV detection and revealed the recognition mechanism and the detailed interaction information of a potent human anti-HBc mAb binding to the spike tips of HBc dimer.IMPORTANCEThe lack of excellent detection Abs for live hepatitis B virus (HBV) infection and high-resolution structures of the Ab-HBV core protein (HBc) complex largely limited the development of HBV-related research. This study reports a panel of anti-HBc monoclonal antibodies (mAbs) with excellent capacities for detecting HBV infection in multiple biochemical assays and determines a 3.22 Å of cryo-EM structure of HBc with a potent binding mAb. These findings provide excellent and reliable detecting tools for HBV-related research and promote the understanding of the recognition mechanism of anti-HBc mAbs to HBc particles.

PHI-base - the multi-species pathogen-host interaction database in 2025.

The Pathogen-Host Interactions Database (PHI-base) has, since 2005, provided manually curated genes from fungal, bacterial and protist pathogens that have been experimentally verified to have important pathogenicity, virulence and/or effector functions during different types of interactions involving human, animal, plant, invertebrate and fungal hosts. PHI-base provides phenotypic annotation and genotypic information for both native and model host interactions, including gene alterations that do not alter the phenotype of the interaction. In this article, we describe major updates to PHI-base. The latest version of PHI-base, 4.17, contains a 19% increase in genes and a 23% increase in interactions relative to version 4.12 (released September 2022). We also describe the unification of data in PHI-base 4 with the data curated from a new curation workflow (PHI-Canto), which forms the first complete release of PHI-base version 5.0. Additionally, we describe adding support for the Frictionless Data framework to PHI-base 4 datasets, new ways of sharing interaction data with the Ensembl database, an analysis of the conserved orthologous genes in PHI-base, and the increasing variety of research studies that make use of PHI-base. PHI-base version 4.17 is freely available at www.phi-base.org and PHI-base version 5.0 is freely available at phi5.phi-base.org.

Clinical, Research, and Educational Applications of ChatGPT in Dentistry: A Narrative Review

Artificial intelligence (AI), specifically Generative Pre-trained Transformer (GPT) technology, has revolutionized various fields, including medicine and dentistry. The AI model ChatGPT, developed by OpenAI, mimics human language on a large scale, generating coherent and contextually appropriate responses. ChatGPT serves as an auxiliary resource for diagnosis and decision-making across various medical disciplines. This comprehensive narrative review aims to explore how ChatGPT can assist the dental sector, highlighting its potential to enhance various aspects of the discipline. This review includes a literature search on the application of ChatGPT in dentistry, with a focus on the differences between the free version, ChatGPT 3.5, and the more advanced subscription-based version, ChatGPT 4. Specifically, ChatGPT has proven to be effective in enhancing user interaction, providing fast and accurate information and improving the accessibility of knowledge. However, despite these advantages, several limitations are identified, including concerns regarding the accuracy of responses in complex scenarios, ethical considerations surrounding its use, and the need for improved training to handle highly specialized queries. In conclusion, while ChatGPT offers numerous benefits in terms of efficiency and scalability, further research and development are needed to address these limitations, particularly in areas requiring greater precision, ethical oversight, and specialized expertise.

ViTGaze: gaze following with interaction features in vision transformers

Gaze following aims to interpret human-scene interactions by predicting the person’s focal point of gaze. Prevailing approaches often adopt a two-stage framework, whereby multi-modality information is extracted in the initial stage for gaze target prediction. Consequently, the efficacy of these methods highly depends on the precision of the previous modality extraction. Others use a single-modality approach with complex decoders, increasing network computational load. Inspired by the remarkable success of pre-trained plain vision transformers (ViTs), we introduce a novel single-modality gaze following framework called ViTGaze. In contrast to previous methods, it creates a novel gaze following framework based mainly on powerful encoders (relative decoder parameters less than 1%). Our principal insight is that the inter-token interactions within self-attention can be transferred to interactions between humans and scenes. Leveraging this presumption, we formulate a framework consisting of a 4D interaction encoder and a 2D spatial guidance module to extract human-scene interaction information from self-attention maps. Furthermore, our investigation reveals that ViT with self-supervised pre-training has an enhanced ability to extract correlation information. Many experiments have been conducted to demonstrate the performance of the proposed method. Our method achieves state-of-the-art performance among all single-modality methods (3.4% improvement in the area under curve score, 5.1% improvement in the average precision) and very comparable performance against multi-modality methods with 59% fewer parameters.

Drug–target interaction prediction by integrating heterogeneous information with mutual attention network

BackgroundIdentification of drug–target interactions is an indispensable part of drug discovery. While conventional shallow machine learning and recent deep learning methods based on chemogenomic properties of drugs and target proteins have pushed this prediction performance improvement to a new level, these methods are still difficult to adapt to novel structures. Alternatively, large-scale biological and pharmacological data provide new ways to accelerate drug–target interaction prediction.MethodsHere, we propose DrugMAN, a deep learning model for predicting drug–target interaction by integrating multiplex heterogeneous functional networks with a mutual attention network (MAN). DrugMAN uses a graph attention network-based integration algorithm to learn network-specific low-dimensional features for drugs and target proteins by integrating four drug networks and seven gene/protein networks collected by a certain screening conditions, respectively. DrugMAN then captures interaction information between drug and target representations by a mutual attention network to improve drug–target prediction.ResultsDrugMAN achieved the best performance compared with cheminformation-based methods SVM, RF, DeepPurpose and network-based deep learing methods DTINet and NeoDT in four different scenarios, especially in real-world scenarios. Compared with SVM, RF, deepurpose, DTINet, and NeoDT, DrugMAN showed the smallest decrease in AUROC, AUPRC, and F1-Score from warm-start to Both-cold scenarios. This result is attributed to DrugMAN’s learning from heterogeneous data and indicates that DrugMAN has a good generalization ability. Taking together, DrugMAN spotlights heterogeneous information to mine drug–target interactions and can be a powerful tool for drug discovery and drug repurposing.

MOHGCN: A trustworthy multi-omics data integration framework based on specificity-aware heterogeneous graph convolutional neural networks for disease diagnosis

With the advancement of cutting-edge sequencing methodologies, the integration of multi-omics data provides invaluable opportunities for researchers to study complex diseases from a molecular perspective while at the same time being challenged by the deployment of safety-critical applications such as computer-aided diagnostics. However, existing methods in multi-omics data integration primarily explore interactions between omics or samples, neglecting high-order interaction information among biomolecules specific to certain diseases. In this work, we propose MOHGCN, a trustworthy multi-omics data integration framework based on specificity-aware heterogeneous graph convolutional neural networks for disease diagnosis, aiming to maximize the utilization of biomolecular interactions in patients with specific diseases for precise diagnosis to enhance the model’s credibility. In the approach, we constructed a heterogeneous graph of samples and genes and devised the HGCN graph convolution model specifically tailored to the sample–gene heterogeneous graph. Concurrently, techniques such as trustworthy attention weights and self-attention mechanisms were incorporated to unveil relationships between different omics, facilitating the efficient integration of multi-omics data. Through comprehensive experimentation on four publicly available multi-omics medical datasets, our proposed framework consistently demonstrates superior performance across various classification tasks. Simultaneously, the experimental results substantiate the model’s effectiveness in extracting features from multi-omics data and unveiling latent associations among different omics.

Multimodal Trajectory Prediction for Diverse Vehicle Types in Autonomous Driving with Heterogeneous Data and Physical Constraints.

The accurate prediction of vehicle behavior is crucial for autonomous driving systems, impacting their safety and efficiency in complex urban environments. To address the challenge of multi-agent trajectory prediction, we propose a novel model integrating multiple input modalities, including historical trajectories, map data, vehicle features, and interaction information. Our approach employs a Conditional Variational Autoencoder (CVAE) framework with a decoder that predicts control actions using the Gaussian Mixture Model (GMM) and then converts these actions into dynamically feasible trajectories through a bicycle model. Evaluated on the nuScenes dataset, the model achieves great performance across key metrics, including minADE5 of 1.26 and minFDE5 of 2.85, demonstrating robust performance across various vehicle types and prediction horizons. These results indicate that integrating multiple data sources, physical models, and probabilistic methods significantly improves trajectory prediction accuracy and reliability for autonomous driving. Our approach generates diverse yet realistic predictions, capturing the multimodal nature of future outcomes while adhering to Physical Constraints and vehicle dynamics.

Understanding anthropomorphic voice-AI chatbot continuance from a human-AI interaction perspective

ABSTRACT Although anthropomorphic AI technologies nowadays are significantly changing the human-AI interaction, the mechanism of how voice-AI chatbots’ anthropomorphism affects users’ continuance behaviour is unclear. To explore the role of human-AI interaction and privacy concerns in the continuance intention of anthropomorphic voice-AI chatbots, a research model, based on parasocial relationship theory, is developed. The research model was then empirically tested against a cross-sectional survey from 473 voice-AI chatbot users and two-wave longitudinal data collected from 271 voice-AI chatbot users. The Structural Equation Modelling (SEM) results indicate that voice-AI chatbots’ anthropomorphism affects continuance intention via both human-AI interaction fluency and human-AI rapport building. In particular, the impact of voice-AI chatbots’ anthropomorphism on voice-AI chatbots’ continuance intention is fully mediated by human-AI interaction fluency and human-AI rapport building. Moreover, the influence of human-AI interaction fluency on voice-AI chatbots’ continuance intention will decrease and the impact of human-AI rapport building on voice-AI chatbots’ continuance intention will increase when users’ privacy concerns are high. The findings provide new insights into AI chatbot research from a human-AI interaction perspective. Developers of voice AI chatbots could focus on anthropomorphism, interaction and user information collection strategies to increase user continuance intention.

A signal-diffusion-based unsupervised contrastive representation learning for spatial transcriptomics analysis.

Spatial transcriptomics allows for the measurement of high-throughput gene expression data while preserving the spatial structure of tissues and histological images. Integrating gene expression, spatial information, and image data to learn discriminative low-dimensional representations is critical for dissecting tissue heterogeneity and analyzing biological functions. However, most existing methods have limitations in effectively utilizing spatial information and high-resolution histological images. We propose a signal-diffusion-based unsupervised contrast learning method (SDUCL) for learning low-dimensional latent embeddings of cells/spots. SDUCL integrates image features, spatial relationships and gene expression information. We designed a signal diffusion microenvironment discovery algorithm, which effectively captures and integrates interaction information within the cellular microenvironment by simulating the biological signal diffusion process. By maximizing the mutual information between the local representation and the microenvironment representation of cells/spots, SDUCL learns more discriminative representations. SDUCL was employed to analyze spatial transcriptomics datasets from multiple species, encompassing both normal and tumor tissues. SDUCL performed well in downstream tasks such as clustering, visualization, trajectory inference, and differential gene analysis, thereby enhancing our understanding of tissue structure and tumor microenvironments. https://github.com/WeiMin-Li-visual/SDUCL. Supplementary data are available at Bioinformatics online.

Modeling inter-modal incongruous sentiment expressions for multi-modal sarcasm detection

Multi-modal sarcasm detection (MSD) presents a formidable and intricate endeavor. Despite strides made by extant models, two principal hurdles persist: Firstly, prevailing methodologies merely address superficial disparities between textual inputs and associated images, neglecting nuanced inter-modal combinations. Secondly, satirical instances frequently involve intricate emotional expressions, highlighting the imperative of leveraging emotional cues across modalities to discern satirical nuances. Accordingly, this research proposes the utilization of a deep graph convolutional network that integrates cross-modal mapping information to effectively identify significant incongruent sentiment expressions across various modalities for the purpose of multi-modal sarcasm detection. Specifically, we first design a cross-modal mapping network, which obtains the interaction information between these two modalities by mapping text feature vectors and image feature vectors two by two to compensate for the lack of multi-modal data in the fusion process. Additionally, we employ external knowledge of ANPS as a bridge to construct cross-correlation graphs through highly correlated satirical cues and their connection weights between image and text modalities. Afterward, the GCN architecture with retrieval-based attentional mechanisms will effectively capture satirical cues. The experiments conducted on two publicly available datasets demonstrate a significant enhancement in the performance of our method when compared to numerous contemporary models.

Joining to the web. Predation of Heterophrynus sp. (Amblypygi: Phrynidae) on a catfish Astroblepus sp. (Siluriformes: Astroblepidae), in a premontane river of the northern Andes of Colombia

Riparian food webs are linked by cross-boundary resource fluxes, including the consumption of terrestrial invertebrates and vertebrates by fish and the consumption of aquatic vertebrates by terrestrial invertebrates, mostly arachnids. Amblypygids prey upon a wide array of vertebrates, but no records on fishes are known. Here we report an interesting predation event of an adult Heterophrynus sp., upon a catfish Astroblepus sp. in the Rio Manso, northern Andes of Colombia, and summarized the published information of trophic interactions of this river in a food web framework. A high prey-size ratio (0.87) respect to Heterophrynus sp., highlight that fishes could represent an important food item for amblypygids. This datum, besides other published before, indicates that the consumption of terrestrial and aquatic vertebrates by terrestrial invertebrates can be a substantial cross-boundary flux link in tropical montane streams deserving future ecological studies.