Multimodal Neural Network Research Articles

The Research of Intra-Pulse Modulated Signal Recognition of Radar Emitter under Few-Shot Learning Condition Based on Multimodal Fusion

Radar radiation source recognition is critical for the reliable operation of radar communication systems. However, in increasingly complex electromagnetic environments, traditional identification methods face significant limitations. These methods often struggle with high noise levels and diverse modulation types, making it difficult to maintain accuracy, especially when the Signal-to-Noise Ratio (SNR) is low or the available training data are limited. These difficulties are further intensified by the necessity to generalize in environments characterized by a substantial quantity of noisy, low-quality signal samples while being constrained by a limited number of desirable high-quality training samples. To more effectively address these issues, this paper proposes a novel approach utilizing Model-Agnostic Meta-Learning (MAML) to enhance model adaptability in few-shot learning scenarios, allowing the model to quickly learn with limited data and optimize parameters effectively. Furthermore, a multimodal fusion neural network, DCFANet, is designed, incorporating residual blocks, squeeze and excitation blocks, and a multi-scale CNN, to fuse I/Q waveform data and time–frequency image data for more comprehensive feature extraction. Our model enables more robust signal recognition, even when the signal quality is severely degraded by noise or when only a few examples of a signal type are available. Testing on 13 intra-pulse modulated signals in an Additive White Gaussian Noise (AWGN) environment across SNRs ranging from −20 to 10 dB demonstrated the approach’s effectiveness. Particularly, under a 5−way5−shot setting, the model achieves high classification accuracy even at −10dB SNR. Our research underscores the model’s ability to address the key challenges of radar emitter signal recognition in low-SNR and data-scarce conditions, demonstrating its strong adaptability and effectiveness in complex, real-world electromagnetic environments.

Hierarchical graph contrastive learning framework based on quantum neural networks for sentiment analysis

Existing multi-modal sentiment analysis (MSA) methods typically achieve interaction by connecting different layers or designing special structures, but rarely consider the synergistic effects among data. Moreover, most sentiment analysis research tends to focus solely on single sentiment polarity analysis, without considering the intensity and directional attributes of emotions. Addressing these issues, we propose a framework called Hierarchical Graph Contrastive Learning based on Quantum Neural Network (HGCL-QNN) to remedy these shortcomings. Specifically, a graph structure is established within and between modalities. In the quantum fuzzy neural network module, fuzzy quantum encoding is implemented by using complex-valued, then quantum superposition and entanglement are utilized to consider the intensity and directional attributes of emotions while analyzing emotional polarity. In the quantum multi-modal fusion neural network module, methods such as amplitude encoding and quantum entanglement are employed to further integrate information from different modalities, thereby enhancing the model's power to express emotional information. To enhance the model's understanding of fine-grained and global features, and to better align and integrate features from different modalities, hierarchical graph contrastive learning is employed on different levels. The experimental results demonstrate that HGCL-QNN outperforms the existing baseline methods on MOSI and MOSEI datasets, achieving significant efficacy improvements.

Integrating Data Mining and Natural Language Processing to Construct a Melting Point Database for Organometallic Compounds.

As semiconductor devices are miniaturized, the importance of atomic layer deposition (ALD) technology is growing. When designing ALD precursors, it is important to consider the melting point, because the precursors should have melting points lower than the process temperature. However, obtaining melting point data is challenging due to experimental sensitivity and high computational costs. As a result, a comprehensive and well-organized database for the melting point of the OMCs has not been fully reported yet. Therefore, in this study, we constructed a database of melting points for 1,845 OMCs, including 58 metal and 6 metalloid elements. The database contains CAS numbers, molecular formulas, and structural information and was constructed through automatic extraction and systematic curation. The melting point information was extracted using two methods: 1) 1,434 materials from 11 chemical vendor databases and 2) 411 materials identified through natural language processing (NLP) techniques with an accuracy of 86.3%, based on 2,096 scientific papers published over the past 29 years. In our database, the OMCs contain up to around 250 atoms and have melting points that range from -170 to 1610 °C. The main source is the Chemsrc database, accounting for 607 materials (32.9%), and Fe is the most common central metal or metalloid element (15.0%), followed by Si (11.6%) and B (6.7%). To validate the utilization of the constructed database, a multimodal neural network model was developed integrating graph-based and feature-based information as descriptors to predict the melting points of the OMCs but moderate performance. We believe the current approach reduces the time and cost associated with hand-operated data collection and processing, contributing to effective screening of potentially promising ALD precursors and providing crucial information for the advancement of the semiconductor industry.

MMF-NNs: Multi-modal Multi-granularity Fusion Neural Networks for brain networks and its application to epilepsy identification

Structural and functional brain networks are generated from two scan sequences of magnetic resonance imaging data, which can provide different perspectives for describing pathological changes caused by brain diseases. Recent studies found that fusing these two types of brain networks improves performance in brain disease identification. However, traditional fusion models combine these brain networks at a single granularity, ignoring the natural multi-granularity structure of brain networks that can be divided into the edge, node, and graph levels. To this end, this paper proposes a Multi-modal Multi-granularity Fusion Neural Networks (MMF-NNs) framework for brain networks, which integrates the features of the multi-modal brain network from global (i.e., graph-level) and local (i.e., edge-level and node-level) granularities to take full advantage of the topological information. Specifically, we design an interactive feature learning module at the local granularity to learn feature maps of structural and functional brain networks at the edge-level and the node-level, respectively. In that way, these two types of brain networks are fused during the feature learning process. At the global granularity, a multi-modal decomposition bilinear pooling module is designed to learn the graph-level joint representation of these brain networks. Experiments on real epilepsy datasets demonstrate that MMF-NNs are superior to several state-of-the-art methods in epilepsy identification.

Evaluating deep neural networks in optimizing drug discovery and precision medicine: A review

Introduction/Background: Deep neural networks have shown great promise in advancing drug discovery and precision medicine. By leveraging large amounts of complex biomedical and chemical data, deep learning approaches can identify novel targets, predict drug-target and drug-drug interactions, generate new molecular structures, and assist in personalized treatment selection and development. However, fully utilizing deep learning techniques for optimization across the drug development pipeline remains an ongoing challenge. Materials and Methods: A comprehensive literature review was conducted using major bibliographic databases including PubMed, Web of Science, and Scopus. Search terms included combinations of "deep learning", "drug discovery", "precision medicine", "biomedical data", and "neural networks". Over 200 papers published between 2010-2023 related to deep learning applications in pharmacology and genomics were identified and reviewed. Results: Deep learning has been widely applied at various stages of the drug discovery process including target identification/prioritization, lead generation/optimization, and prediction of molecular properties. Convolutional neural networks are commonly used for the representation and classification of biological sequence and image data for tasks such as gene expression analysis and pathogen detection from microscopy images. Graph neural networks effectively model compound structures and interactome networks to predict molecular bindings and disease associations. Multi-modal neural networks integrate diverse data types for personalized treatment response prediction and biomarker discovery. Challenges remain around data and model interpretation, generalization to new targets/diseases, and integration across domains. Discussion: While deep learning has shown promise, rigorous benchmarking and validation on real-world clinical endpoints are still needed to establish usefulness in decision-making. Data and model transparency must be improved to enable scientific insights. Privacy and security risks accompanying "real world" biomedical big data will require ethical practices. Standardization and sharing of resources/protocols could accelerate progress by enabling comparison of techniques. Combining deep learning with other AI paradigms like causal inference may further improve utility in drug discovery and precision healthcare. Conclusion: Deep neural networks demonstrate potential for optimizing drug development and precision medicine applications. Continued advancement relies on addressing challenges around data, models, validation, and ethics. Multi-disciplinary collaborations integrating machine learning, molecular biology, medicine, and other domains are needed to fully realize benefits to patients.

Multimodal Deep Representation Learning for Quantum Cross-Platform Verification.

Cross-platform verification, a critical undertaking in the realm of early-stage quantum computing, endeavors to characterize the similarity of two imperfect quantum devices executing identical algorithms, utilizing minimal measurements. While the random measurement approach has been instrumental in this context, the quasiexponential computational demand with increasing qubit count hurdles its feasibility in large-qubit scenarios. To bridge this knowledge gap, here we introduce an innovative multimodal learning approach, recognizing that the formalism of data in this task embodies two distinct modalities: measurement outcomes and classical description of compiled circuits on explored quantum devices, both containing unique information about the quantum devices. Building upon this insight, we devise a multimodal neural network to independently extract knowledge from these modalities, followed by a fusion operation to create a comprehensive data representation. The learned representation can effectively characterize the similarity between the explored quantum devices when executing new quantum algorithms not present in the training data. We evaluate our proposal on platforms featuring diverse noise models, encompassing system sizes up to 50 qubits. The achieved results demonstrate an improvement of 3 orders of magnitude in prediction accuracy compared to the random measurements and offer compelling evidence of the complementary roles played by each modality in cross-platform verification. These findings pave the way for harnessing the power of multimodal learning to overcome challenges in wider quantum system learning tasks.

A model for investment type recommender system based on the potential investors based on investors and experts feedback using ANFIS and MNN

This article presents an investment recommender system based on an Adaptive Neuro-Fuzzy Inference System (ANFIS) and pre-trained weights from a Multimodal Neural Network (MNN). The model is designed to support the investment process for the customers and takes into consideration seven factors to implement the proposed investment system model through the customer or potential investor data set. The system takes input from a web-based questionnaire that collects data on investors' preferences and investment goals. The data is then preprocessed and clustered using ETL tools, JMP, MATLAB, and Python. The ANFIS-based recommender system is designed with three inputs and one output and trained using a hybrid approach over three epochs with 188 data pairs and 18 fuzzy rules. The system's performance is evaluated using metrics such as RMSE, accuracy, precision, recall, and F1-score. The system is also designed to incorporate expert feedback and opinions from investors to customize and improve investment recommendations. The article concludes that the proposed ANFIS-based investment recommender system is effective and accurate in generating investment recommendations that meet investors' preferences and goals.Graphical abstract

Multimodal Social Sensing for the Spatio-Temporal Evolution and Assessment of Nature Disasters.

Social sensing, using humans as sensors to collect disaster data, has emerged as a timely, cost-effective, and reliable data source. However, research has focused on the textual data. With advances in information technology, multimodal data such as images and videos are now shared on media platforms, aiding in-depth analysis of social sensing systems. This study proposed an analytical framework to extract disaster-related spatiotemporal information from multimodal social media data. Using a pre-trained multimodal neural network and a location entity recognition model, the framework integrates disaster semantics with spatiotemporal information, enhancing situational awareness. A case study of the April 2024 heavy rain event in Guangdong, China, using Weibo data, demonstrates that multimodal content correlates more strongly with rainfall patterns than textual data alone, offering a dynamic perception of disasters. These findings confirm the utility of multimodal social media data and offer a foundation for future research. The proposed framework offers valuable applications for emergency response, disaster relief, risk assessment, and witness discovery, and presents a viable approach for safety risk monitoring and early warning systems.

A multimodal neural network with gradient blending improves predictions of survival and metastasis in sarcoma

The objective of this study is to develop a multimodal neural network (MMNN) model that analyzes clinical variables and MRI images of a soft tissue sarcoma (STS) patient, to predict overall survival and risk of distant metastases. We compare the performance of this MMNN to models based on clinical variables alone, radiomics models, and an unimodal neural network. We include patients aged 18 or older with biopsy-proven STS who underwent primary resection between January 1st, 2005, and December 31st, 2020 with complete outcome data and a pre-treatment MRI with both a T1 post-contrast sequence and a T2 fat-sat sequence available. A total of 9380 MRI slices containing sarcomas from 287 patients are available. Our MMNN accepts the entire 3D sarcoma volume from T1 and T2 MRIs and clinical variables. Gradient blending allows the clinical and image sub-networks to optimally converge without overfitting. Heat maps were generated to visualize the salient image features. Our MMNN outperformed all other models in predicting overall survival and the risk of distant metastases. The C-Index of our MMNN for overall survival is 0.77 and the C-Index for risk of distant metastases is 0.70. The provided heat maps demonstrate areas of sarcomas deemed most salient for predictions. Our multimodal neural network with gradient blending improves predictions of overall survival and risk of distant metastases in patients with soft tissue sarcoma. Future work enabling accurate subtype-specific predictions will likely utilize similar end-to-end multimodal neural network architecture and require prospective curation of high-quality data, the inclusion of genomic data, and the involvement of multiple centers through federated learning.

Multi-Modal Machine Learning to Predict the Energy Discharge Levels from a Multi-Cell Mechanical Draft Cooling Tower

An artificial neural network was developed to augment the accuracy of a physically based computer model in relating heat discharge to visible plume volume of a 12-cell mechanical draft cooling tower. In a previous study, Savannah River National Laboratory developed a 1D model to capture the average power plant discharge levels via analysis of a series of visual images but was unable to accurately predict individual cases, resulting in an overall average error of about 5%, but individual comparisons resulted in an R2 of 0.36. Three optimization algorithms were applied to better fit the entrainment coefficients, and the artificial neural network model was applied to 289 cases of a 12-cell mechanical draft cooling tower power generation facility. Two artificial neural networks configurations consisted of 10 and 47 nodes that used as input readily available plant data, observed cooling tower plume conditions, observed operational conditions, local and regional weather, and the predicted plume volume from the physical model; the individual predictions’ accuracy improved to R2>0.95. This article concludes the sensitivities for the 1D model and additional actions to progress this field of study as well as applications for cooling tower monitoring. This strategy demonstrated an encouraging first step towards using multi-modal artificial neural network machine learning technology for information fusion to estimate power levels from external observations.

Multimodal Transformers and Their Applications in Drug Target Discovery for Aging and Age-Related Diseases.

Given the unprecedented rate of global aging, advancing aging research and drug discovery to support healthy and productive longevity is a pressing socioeconomic need. Holistic models of human and population aging that account for biomedical background, environmental context, and lifestyle choices are fundamental to address these needs, but integration of diverse data sources and large data sets into comprehensive models is challenging using traditional approaches. Recent advances in artificial intelligence and machine learning, and specifically multimodal transformer-based neural networks, have enabled the development of highly capable systems that can generalize across multiple data types. As such, multimodal transformers can generate systemic models of aging that can predict health status and disease risks, identify drivers, or breaks of physiological aging, and aid in target discovery against age-related disease. The unprecedented capacity of transformers to extract and integrate information from large and diverse data modalities, combined with the ever-increasing availability of biological and medical data, has the potential to revolutionize healthcare, promoting healthy longevity and mitigating the societal and economic impacts of global aging.

Multimodal Convolutional Neural Network-Based Algorithm for Real-Time Detection and Differentiation of Malignant and Inflammatory Biliary Strictures in Cholangioscopy: a Proof of Concept Study with Video

Deep learning algorithms gained attention for detection (CADe) of biliary tract cancer (BTC) in digital single-operator cholangioscopy (dSOC). We developed a multimodal convolutional neural network (CNN) for detection (CADe) characterization and discriminating (CADx) between malignant, inflammatory and normal biliary tissue in raw dSOC videos. In addition, clinical metadata was included in the CNN algorithm to overcome limitations of image-only models. Based on dSOC videos and images of 111 patients (total of 15,158 still frames), we developed and validated a real-time CNN-based algorithm for CADe and CADx. We established an image-only model and metadata injection approach. In addition, we validated frame-wise and case-based predictions on complete dSOC video sequences. Model embeddings were visualized and class-activation maps highlighted relevant image regions. The concatenation-based CADx approach achieved a per-frame AUC of 0.871, sensitivity of 0.809 (95% CI: [0.784-0.832]), specificity of 0.773 [0.761-0.785], PPV of 0.450 [0.423-0.467], and NPV of 0.946 [0.940-0.954] with respect to malignancy on 5,715 test frames from complete videos of 20 patients. For case-based diagnosis using average prediction scores, six out of eight malignant cases and all twelve benign cases were identified correctly. Our algorithm distinguishes malignant and inflammatory bile duct lesions in dSOC videos, indicating the potential of CNN-based diagnostic support systems for both, CADe and CADx. The integration of non-image data can improve CNN based support systems, targeting current challenges in the assessment of biliary strictures.

SG-Fusion: A swin-transformer and graph convolution-based multi-modal deep neural network for glioma prognosis

The integration of morphological attributes extracted from histopathological images and genomic data holds significant importance in advancing tumor diagnosis, prognosis, and grading. Histopathological images are acquired through microscopic examination of tissue slices, providing valuable insights into cellular structures and pathological features. On the other hand, genomic data provides information about tumor gene expression and functionality. The fusion of these two distinct data types is crucial for gaining a more comprehensive understanding of tumor characteristics and progression. In the past, many studies relied on single-modal approaches for tumor diagnosis. However, these approaches had limitations as they were unable to fully harness the information from multiple data sources. To address these limitations, researchers have turned to multi-modal methods that concurrently leverage both histopathological images and genomic data. These methods better capture the multifaceted nature of tumors and enhance diagnostic accuracy. Nonetheless, existing multi-modal methods have, to some extent, oversimplified the extraction processes for both modalities and the fusion process. In this study, we presented a dual-branch neural network, namely SG-Fusion. Specifically, for the histopathological modality, we utilize the Swin-Transformer structure to capture both local and global features and incorporate contrastive learning to encourage the model to discern commonalities and differences in the representation space. For the genomic modality, we developed a graph convolutional network based on gene functional and expression level similarities. Additionally, our model integrates a cross-attention module to enhance information interaction and employs divergence-based regularization to enhance the model’s generalization performance. Validation conducted on glioma datasets from the Cancer Genome Atlas unequivocally demonstrates that our SG-Fusion model outperforms both single-modal methods and existing multi-modal approaches in both survival analysis and tumor grading.

Identifying chaotic dynamics in noisy time series through multimodal deep neural networks

Abstract Chaos detection is the problem of identifying whether a series of measurements is being sampled from an underlying set of chaotic dynamics. The unavoidable presence of measurement noise significantly affects the performance of chaos detectors, as discerning chaotic dynamics from stochastic signals becomes more challenging. This paper presents a computationally efficient multi-modal deep neural network tailored for chaos detection by combining information coming from the analysis of time series, recurrence plots and spectrograms. The proposed approach is the first one suitable for multi-class classification of chaotic systems while being robust with respect to measurement noise, and is validated on a dataset of 15 different chaotic and non-chaotic dynamics subject to white, pink or brown coloured noise.

Improving Interpretability of Leucocyte Classification with Multimodal Network.

White blood cell classification plays a key role in the diagnosis of hematologic diseases. Models can perform classification either from images or based on morphological features. Image-based classification generally yields higher performance, but feature-based classification is more interpretable for clinicians. In this study, we employed a Multimodal neural network to classify white blood cells, utilizing a combination of images and morphological features. We compared this approach with image-only and feature-only training. While the highest performance was achieved with image-only training, the Multimodal model provided enhanced interpretability by the computation of SHAP values, and revealed crucial morphological features for biological characterization of the cells.

The Zwicky Transient Facility Bright Transient Survey. III. BTSbot: Automated Identification and Follow-up of Bright Transients with Deep Learning

The Bright Transient Survey (BTS) aims to obtain a classification spectrum for all bright (m peak ≤ 18.5 mag) extragalactic transients found in the Zwicky Transient Facility (ZTF) public survey. BTS critically relies on visual inspection (“scanning”) to select targets for spectroscopic follow-up, which, while effective, has required a significant time investment over the past ∼5 yr of ZTF operations. We present BTSbot, a multimodal convolutional neural network, which provides a bright transient score to individual ZTF detections using their image data and 25 extracted features. BTSbot is able to eliminate the need for daily human scanning by automatically identifying and requesting spectroscopic follow-up observations of new bright transient candidates. BTSbot recovers all bright transients in our test split and performs on par with scanners in terms of identification speed (on average, ∼1 hr quicker than scanners). We also find that BTSbot is not significantly impacted by any data shift by comparing performance across a concealed test split and a sample of very recent BTS candidates. BTSbot has been integrated into Fritz and Kowalski, ZTF’s first-party marshal and alert broker, and now sends automatic spectroscopic follow-up requests for the new transients it identifies. Between 2023 December and 2024 May, BTSbot selected 609 sources in real time, 96% of which were real extragalactic transients. With BTSbot and other automation tools, the BTS workflow has produced the first fully automatic end-to-end discovery and classification of a transient, representing a significant reduction in the human time needed to scan.

Multimodal Recipe Recommendation with Heterogeneous Graph Neural Networks

Recipe recommendation is the process of recommending suitable recipes to users based on factors such as user preferences and dietary needs. Recipes typically involve multiple modalities, with text and images being common, while most typical recipe recommendation methods recommend recipes to users based on text. Obviously, the expressiveness of a single modal is often not enough, and the semantic information of images is more abundant. Moreover, it is difficult to grasp the feature fusion granularity of different kinds of modal information and the relationship between recipes and users. To solve the above problem, this paper proposes a Multimodal Heterogeneous Graph Neural Network Recipe Recommendation (MHGRR) architecture, which aims to fully fuse the various kinds of modal information of recipes and handle the relationship between users and recipes. We use embedding and shallow Convolutional Neural Networks (CNNs) to extract original text and image information for unifying feature fusion granularity, and use Heterogeneous Graph Neural Networks based on GraphSAGE to capture the complex relationship between users and recipes. To verify the effectiveness of our proposed model, we perform some comparative experiments on a real dataset; the experiments show that our method outperforms most popular recipe recommendation methods. Through an ablation experiment, we found that adding image information to recipe recommendation is more effective, and we additionally found that as the output dimensions of GraphSAGE increased, the performance of the model varied little.

Optimizing glaucoma diagnosis using fundus and optical coherence tomography image fusion based on multi-modal convolutional neural network approach

A novel approach that combines segmented fundus images (FIs) and optical coherence tomography image (OCTIs) are presented here, by incorporating deep learning network (DLN) techniques, to address the imperative need for advanced diagnostic algorithms in detecting and classifying glaucoma. By combining these two images, glaucoma diagnoses are made to improve the accuracy with more reliability. Multi modal convolutional neural networks (MMCNNs) are proposed for automatically extracting discriminatory features from both segmented FIs and OCTIs, allowing for comprehensive ocular analysis. A significant improvement in glaucoma diagnosis is achieved through segmentation of both FIs and OCTIs, ensuring robustness generalization to diverse clinical scenarios, DLN models are trained on datasets encompassing a wide range of glaucoma cases. The integrated approach outperforms individual modalities in terms of early detection of glaucoma and accurate classification. This method demonstrates promising potential in early glaucoma detection due to its effectiveness. By combining segmented features from both FIs and OCTIs through MMCNNs, improved efficiency in diagnosing predominant ocular glaucoma disorder is achieved compared to existing methods. Within the scope of this research, GoogLeNet (GN) is applied to independently classify glaucoma (uni-modal) in segmented FIs and OCTIs, providing a basis for comparison with the evaluation of MMCNNs.

Identifying Sample Provenance From SEM/EDS Automated Particle Analysis via Few-Shot Learning Coupled With Similarity Graph Clustering.

Automated particle analysis (APA) provides a vast amount of compositional data via energy-dispersive X-ray spectroscopy along with size and shape data via scanning electron microscopy for individual particles in a sample. In many instances, APA data are leveraged to support identification of the source of a sample based on the detection of particles of a specific composition. Often, the particles that provide context make up a minuscule portion of the sample. Additionally, the interpretation of complex samples can be difficult due to the diversity of compositions both in the mixture and within a particle. In this work, we demonstrate a method to compute and cluster similarity graphs that describe inter-particle relationships within a sample using a multi-modal few-shot learning neural network. As a proof-of-concept, we show that samples known to have been exposed to gunshot residue can be distinguished from samples occasionally mistaken for gunshot residue. Our workflow builds upon standard APA techniques and data processing methods to unveil additional information in a readily interpretable and quantitatively comparable format.

MuCoCP: a priori chemical knowledge-based multimodal contrastive learning pre-trained neural network for the prediction of cyclic peptide membrane penetration ability.

There has been a burgeoning interest in cyclic peptide therapeutics due to their various outstanding advantages and strong potential for drug formation. However, it is undoubtedly costly and inefficient to use traditional wet lab methods to clarify their biological activities. Using artificial intelligence instead is a more energy-efficient and faster approach. MuCoCP aims to build a complete pre-trained model for extracting potential features of cyclic peptides, which can be fine-tuned to accurately predict cyclic peptide bioactivity on various downstream tasks. To maximize its effectiveness, we use a novel data augmentation method based on a priori chemical knowledge and multiple unsupervised training objective functions to greatly improve the information-grabbing ability of the model. To assay the efficacy of the model, we conducted validation on the membrane-permeability of cyclic peptides which achieved an accuracy of 0.87 and R-squared of 0.503 on CycPeptMPDB using semi-supervised training and obtained an accuracy of 0.84 and R-squared of 0.384 using a model with frozen parameters on an external dataset. This result has achieved state-of-the-art, which substantiates the stability and generalization capability of MuCoCP. It means that MuCoCP can fully explore the high-dimensional information of cyclic peptides and make accurate predictions on downstream bioactivity tasks, which will serve as a guide for the future de novo design of cyclic peptide drugs and promote the development of cyclic peptide drugs. All code used in our proposed method can be found at https://github.com/lennonyu11234/MuCoCP.