Powerful Learning Research Articles

Revolutionizing Pancreatic Cancer Diagnosis and Prognosis through Machine Learning Technology

Abstract: Pancreatic cancer presents significant challenges in terms of early detection and treatment, resulting in poor patient outcomes. This research article explores the application of random forest, a powerful machine learning algorithm, to enhance predictive modeling in pancreatic cancer research. Leveraging a dataset comprising clinical and molecular features, we trained and evaluated random forest models to predict key outcomes such as tumor progression, treatment response, and overall survival. Our findings demonstrate the effectiveness of random forest in accurately stratifying patients based on their prognosis and treatment outcomes. Furthermore, we identified key biomarkers and clinical variables contributing to predictive accuracy, providing valuable insights into the underlying biological mechanisms of pancreatic cancer progression. The integration of random forest into pancreatic cancer research holds promise for improving patient stratification, guiding treatment decisions, and ultimately, advancing personalized medicine approaches in the management of this challenging disease

21st-century stewardship: infusing environmental stewardship education with global citizenship

Environmental stewardship education, as a locally oriented concept, benefits from being recast to account for the emergent, multidimensional, and interdisciplinary nature of today’s most pressing socio-ecological issues. In an effort to infuse environmental stewardship education with global citizenship, instructional materials on community-based conservation in Peru were delivered to high school students in New York, USA. The purpose of this study was to assess the impact of instructional materials on student learning outcomes related to the practice of global citizenship in environmental stewardship education. The CLIA model for powerful learning environments was used to convey the competencies, learning conditions, interventions, and assessments that structured the delivery of the instructional materials. To evaluate learning outcomes, written student responses were analyzed, using the qualitative coding methodology. Additionally, transformative learning was assessed using the Learning Activities Survey. Results suggest a trajectory past knowledge comprehension and toward transformative, empowered action, progressing from a cognitive understanding to affective and ultimately behavioral shifts. Based on these findings, this study conceptualized and operationalized the concept 21st-century stewardship – a term coined here as an updated stewardship model that is infused with global citizenship’s multi-scalar perspectives, global compacts, and layered identities to achieve its maximum impact in our interconnected world.

Multi-scale nested UNet with transformer for colorectal polyp segmentation.

Polyp detection and localization are essential tasks for colonoscopy. U-shape network based convolutional neural networks have achieved remarkable segmentation performance for biomedical images, but lack of long-range dependencies modeling limits their receptivefields. Our goal was to develop and test a novel architecture for polyp segmentation, which takes advantage of learning local information with long-range dependenciesmodeling. A novel architecture combining with multi-scale nested UNet structure integrated transformer for polyp segmentation was developed. The proposed network takes advantage of both CNN and transformer to extract distinct feature information. The transformer layer is embedded between the encoder and decoder of a U-shape net to learn explicit global context and long-range semantic information. To address the challenging of variant polyp sizes, a MSFF unit was proposed to fuse features with multipleresolution. Four public datasets and one in-house dataset were used to train and test the model performance. Ablation study was also conducted to verify each component of the model. For dataset Kvasir-SEG and CVC-ClinicDB, the proposed model achieved mean dice score of 0.942 and 0.950 respectively, which were more accurate than the other methods. To show the generalization of different methods, we processed two cross dataset validations, the proposed model achieved the highest mean dice score. The results demonstrate that the proposed network has powerful learning and generalization capability, significantly improving segmentation accuracy and outperforming state-of-the-artmethods. The proposed model produced more accurate polyp segmentation than current methods on four different public and one in-house datasets. Its capability of polyps segmentation in different sizes shows the potential clinicalapplication.

Artificial intelligence and machine learning: Definition of terms and current concepts in critical care research

With increasing computing power, artificial intelligence (AI) and machine learning (ML) have prospered, which facilitate the analysis of large datasets, especially those found in critical care. It is important to define these terminologies, to inform a standardized approach to critical care research. This manuscript hopes to clarify these terms with examples from medical literature.Three major components that are required for a successful ML implementation: (i) reliable dataset, (ii) ML algorithm, and (iii) unbiased model evaluation, are discussed. A reliable dataset can be structured or unstructured with limited noise, outliers, and missing values. ML, a subset of AI, is typically focused on supervised or unsupervised learning tasks in which the output is based on inputs and derived from iterative pattern recognition algorithms, while AI is the overall ability of a machine to “think” or mimic human behavior; and to analyze data free from human influence.Even with successful implementation, advanced AI and ML algorithms have faced challenges in adoption into practice, mainly due to their lack of interpretability, which hinders trust, buy-in, and engagement from clinicians. Consequently, traditional algorithms, such as linear and logistic regression, that may have reduced predictive power but are highly interpretable, continue to be widely used.

Facial Classification for Autism Spectrum Disorder

Autism spectrum disorder (ASD) is a mental condition that affects people’s learning, communication, and expression in their daily lives. ASD usually makes it difficult to socialize and communicate with others, and also sometimes shows repetition of certain behaviors. ASD can be a cause of intellectual disability. ASD is a big challenge in neural development, specially in children. It is very important that it is identified at an early stage for timely guidance and intervention. This research identifies the application of deep learning and vision transformer (ViT) models for classification of facial images of autistic and non-autistic children. ViT models are powerful deep learning models used for image classification tasks. This model applies transformer architectures to analyze input image patches and connect the information to achieve global-level information. By employing these techniques, this study aims to contribute toward early ASD detection. ViT models are showing good results in identifying facial features associated with ASD, leading toward early diagnostics. Results show the ViT model’s capability in distinguishing the faces of autistic and non-autistic children.

A survey on contextual multi-armed bandits

As a powerful reinforcement learning framework, Contextual Multi-Armed Bandits have extensive applications in various domains. The models of Contextual Multi-Armed Bandits enable decision-makers to make intelligent choices in situations with uncertainty, and they find utility in fields such as online advertising, medical treatment optimization, resource allocation, and more. This paper reviews the evolution of algorithms for Contextual Multi-Armed Bandits, including traditional Bayesian approaches and the latest deep learning techniques. Successful case studies are summarized in different application domains, such as online ad click-through rate optimization and medical decision support. Furthermore, the author discusses future research directions, including more sophisticated context modeling, interpretability, fairness issues, and ethical considerations in the context of automated decision-making.

Strengths and weaknesses of the South-South Learning Exchange: a qualitative analysis of experts' perspectives.

South-South learning exchange (SSLE) refers to an interactive learning process where peers exchange knowledge and experience to work towards a beneficial change. Despite organizations having recently increased the opportunity to run SSLEs, the SSLE support mechanisms and processes are not well documented in the scientific literature. This study explored experts' perspectives on SSLEs, strengths, weaknesses and mechanisms leading to sustainable outcomes. We conducted a qualitative study using semi-structured interviews on experiences of participants and organizers of SSLEs. Data were collected between 1st September 2021 to 26th November 2021. All data were digitally recorded, transcribed verbatim, and analysed. In the analysis, we adopted an inductive approach derived from thematic analysis. Sixteen experts, who have participated in or facilitated one or more SSLE, were interviewed. The experts' accounts demonstrated an appreciation of participants' empowerment, positive peer-to-peer "mind change" and convincing and powerful hands-on learning of this approach as strengths in the implementation of the SSLE. Being resource heavy, participant and donor reluctance and absence of a validated methodology emerged as main weaknesses of the South-South learning approach, which could impair the effectiveness of this scheme. The strengths of SSLEs are anchored in the theories of experiential and social learning, highlighting SSLE's potential to create an environment that enhances knowledge exchange. the study highlights the challenges SSLE initiatives face. In particular, these include limited commitment and funds, limited evidence of impact, disparate approaches, and the absence of standardized guidelines and evaluation practices.

Improved dual-aggregation polyp segmentation network combining a pyramid vision transformer with a fully convolutional network.

Automatic and precise polyp segmentation in colonoscopy images is highly valuable for diagnosis at an early stage and surgery of colorectal cancer. Nevertheless, it still posed a major challenge due to variations in the size and intricate morphological characteristics of polyps coupled with the indistinct demarcation between polyps and mucosas. To alleviate these challenges, we proposed an improved dual-aggregation polyp segmentation network, dubbed Dua-PSNet, for automatic and accurate full-size polyp prediction by combining both the transformer branch and a fully convolutional network (FCN) branch in a parallel style. Concretely, in the transformer branch, we adopted the B3 variant of pyramid vision transformer v2 (PVTv2-B3) as an image encoder for capturing multi-scale global features and modeling long-distant interdependencies between them whilst designing an innovative multi-stage feature aggregation decoder (MFAD) to highlight critical local feature details and effectively integrate them into global features. In the decoder, the adaptive feature aggregation (AFA) block was constructed for fusing high-level feature representations of different scales generated by the PVTv2-B3 encoder in a stepwise adaptive manner for refining global semantic information, while the ResidualBlock module was devised to mine detailed boundary cues disguised in low-level features. With the assistance of the selective global-to-local fusion head (SGLFH) module, the resulting boundary details were aggregated selectively with these global semantic features, strengthening these hierarchical features to cope with scale variations of polyps. The FCN branch embedded in the designed ResidualBlock module was used to encourage extraction of highly merged fine features to match the outputs of the Transformer branch into full-size segmentation maps. In this way, both branches were reciprocally influenced and complemented to enhance the discrimination capability of polyp features and enable a more accurate prediction of a full-size segmentation map. Extensive experiments on five challenging polyp segmentation benchmarks demonstrated that the proposed Dua-PSNet owned powerful learning and generalization ability and advanced the state-of-the-art segmentation performance among existing cutting-edge methods. These excellent results showed our Dua-PSNet had great potential to be a promising solution for practical polyp segmentation tasks in which wide variations of data typically occurred.

GeneAI 3.0: powerful, novel, generalized hybrid and ensemble deep learning frameworks for miRNA species classification of stationary patterns from nucleotides

Due to the intricate relationship between the small non-coding ribonucleic acid (miRNA) sequences, the classification of miRNA species, namely Human, Gorilla, Rat, and Mouse is challenging. Previous methods are not robust and accurate. In this study, we present AtheroPoint’s GeneAI 3.0, a powerful, novel, and generalized method for extracting features from the fixed patterns of purines and pyrimidines in each miRNA sequence in ensemble paradigms in machine learning (EML) and convolutional neural network (CNN)-based deep learning (EDL) frameworks. GeneAI 3.0 utilized five conventional (Entropy, Dissimilarity, Energy, Homogeneity, and Contrast), and three contemporary (Shannon entropy, Hurst exponent, Fractal dimension) features, to generate a composite feature set from given miRNA sequences which were then passed into our ML and DL classification framework. A set of 11 new classifiers was designed consisting of 5 EML and 6 EDL for binary/multiclass classification. It was benchmarked against 9 solo ML (SML), 6 solo DL (SDL), 12 hybrid DL (HDL) models, resulting in a total of 11 + 27 = 38 models were designed. Four hypotheses were formulated and validated using explainable AI (XAI) as well as reliability/statistical tests. The order of the mean performance using accuracy (ACC)/area-under-the-curve (AUC) of the 24 DL classifiers was: EDL > HDL > SDL. The mean performance of EDL models with CNN layers was superior to that without CNN layers by 0.73%/0.92%. Mean performance of EML models was superior to SML models with improvements of ACC/AUC by 6.24%/6.46%. EDL models performed significantly better than EML models, with a mean increase in ACC/AUC of 7.09%/6.96%. The GeneAI 3.0 tool produced expected XAI feature plots, and the statistical tests showed significant p-values. Ensemble models with composite features are highly effective and generalized models for effectively classifying miRNA sequences.

Deep Learning on Graphs: A Data-Centric Exploration

Many learning tasks in Artificial Intelligence (AI) require dealing with graph data, ranging from biology and chemistry to finance and education. As powerful deep learning tools for graphs, graph neural networks (GNNs) have demonstrated remarkable performance in various graph-related applications. Despite the significant accomplishments of GNNs, recent studies have highlighted that their efficiency and effectiveness face significant challenges such as adversarial robustness and scalability, which are fundamentally linked to data. While major attention has been devoted to improving GNNs from the model perspective, the potential of directly enhancing data has often been overlooked. It underscores a critical gap in GNN research---while model improvements are undoubtedly important, we also need to recognize and address the data-related factors contributing to the challenges. Hence, my research is to investigate solutions for these challenges from the data perspective, employing strategies such as data characterization, reduction, augmentation, transformation, and detection.

An Empirical Study of CLIP for Text-Based Person Search

Text-based Person Search (TBPS) aims to retrieve the person images using natural language descriptions. Recently, Contrastive Language Image Pretraining (CLIP), a universal large cross-modal vision-language pre-training model, has remarkably performed over various cross-modal downstream tasks due to its powerful cross-modal semantic learning capacity. TPBS, as a fine-grained cross-modal retrieval task, is also facing the rise of research on the CLIP-based TBPS. In order to explore the potential of the visual-language pre-training model for downstream TBPS tasks, this paper makes the first attempt to conduct a comprehensive empirical study of CLIP for TBPS and thus contribute a straightforward, incremental, yet strong TBPS-CLIP baseline to the TBPS community. We revisit critical design considerations under CLIP, including data augmentation and loss function. The model, with the aforementioned designs and practical training tricks, can attain satisfactory performance without any sophisticated modules. Also, we conduct the probing experiments of TBPS-CLIP in model generalization and model compression, demonstrating the effectiveness of TBPS-CLIP from various aspects. This work is expected to provide empirical insights and highlight future CLIP-based TBPS research.

Artificial Intelligence for detecting and preventing procurement fraud

The utilization of powerful machine learning models in artificial intelligence offers novel prospects for the identification of fraudulent activities. Artificial Intelligence (AI) is a revolutionary technological tool that enhances the ability to detect and prevent fraud by improving efficiency and effectiveness. This research offers a thorough examination of the utilization of artificial intelligence technology in the realm of procurement fraud prevention and detection. Additionally, it highlights the obstacles that arise when employing machine learning techniques for the purpose of identifying and preventing fraudulent activities. A mixed methods approach was employed in this study, wherein data was collected through an unstructured interview and questionnaire. We conducted a comprehensive review of relevant scholarly articles and online resources. The findings indicate that fraudsters are progressively advancing in their skills, which poses a significant challenge in detecting fraudulent activities. The advent of AI in fraud detection has demonstrated its transformative impact. AI has achieved unparalleled precision and velocity in crime detection and prevention, surpassing the capabilities of any human. Artificial intelligence (AI) enhances the capacity for automation. Accessing unstructured data in the form of spreadsheets, digital documents, and email inboxes poses a significant issue for the procurement function. In order to achieve a successful procurement transformation, businesses should prioritize the creation of essential tools, guarantee acceptance through the establishment of a superior user experience, and integrate both novel and pre-existing technology. It is imperative to disseminate knowledge to the general public regarding the escalating sophistication of artificial intelligence (AI) in the realm of fraud detection and prevention. This includes elucidating the potential benefits of AI in identifying patterns of suspicious activities, assessing its efficacy in predicting potential threats or fraudulent activities prior to their manifestation, and exploring its utility in analyzing historical data pertaining to both familiar and unfamiliar forms of fraudulent behavior.

A number sense as an emergent property of the manipulating brain

The ability to understand and manipulate numbers and quantities emerges during childhood, but the mechanism through which humans acquire and develop this ability is still poorly understood. We explore this question through a model, assuming that the learner is able to pick up and place small objects from, and to, locations of its choosing, and will spontaneously engage in such undirected manipulation. We further assume that the learner’s visual system will monitor the changing arrangements of objects in the scene and will learn to predict the effects of each action by comparing perception with a supervisory signal from the motor system. We model perception using standard deep networks for feature extraction and classification. Our main finding is that, from learning the task of action prediction, an unexpected image representation emerges exhibiting regularities that foreshadow the perception and representation of numbers and quantity. These include distinct categories for zero and the first few natural numbers, a strict ordering of the numbers, and a one-dimensional signal that correlates with numerical quantity. As a result, our model acquires the ability to estimate numerosity, i.e. the number of objects in the scene, as well as subitization, i.e. the ability to recognize at a glance the exact number of objects in small scenes. Remarkably, subitization and numerosity estimation extrapolate to scenes containing many objects, far beyond the three objects used during training. We conclude that important aspects of a facility with numbers and quantities may be learned with supervision from a simple pre-training task. Our observations suggest that cross-modal learning is a powerful learning mechanism that may be harnessed in artificial intelligence.

Using Artificial Intelligence Algorithms to Detect Hate Speech in Social Media Posts

Detecting hate speech on social media is of great importance to prevent negative impacts on people and communities and to remove such content. However, detecting hate speech is a complex and challenging process due to linguistic and cultural diversity. Therefore, it is important to develop powerful and effective machine learning algorithms. Since detecting such content using traditional methods can be time-consuming and costly, it is stated that artificial intelligence-based machine learning algorithms have great potential in this regard. The aim of this study is to evaluate the performance of artificial intelligence-based machine learning algorithms used in detecting posts containing hate speech on social media. The study focuses on the problem of detecting and managing hate speech on social media platforms. In this study, we will compare the performances of different algorithms and determine the most suitable methods. Additionally, the effects of the dataset and feature extraction methods on algorithm performance will be analyzed. Algorithms are often based on natural language processing techniques and try to detect hate speech by learning features in texts. The performance of these algorithms can vary depending on factors such as language, culture, the attributes they use, and the training dataset, so a comprehensive analysis is required. In the research, the performance of the algorithms used in detecting hate speech was compared with the dataset and feature extraction methods. In this process, the algorithms' linguistic and cross-cultural effectiveness, feature selection and representation, false positive and false negative rates, and overall accuracy will be analyzed.

Revolutionizing the used car market: Predicting prices with XGBoost

In contemporary dynamic automobile industry, informed decision-making is crucial for success. Accurate sales predictions are essential for optimizing operations and resource allocation in the used car market. This article explores the application of machine learning, specifically the eXtreme Gradient Boosting(XGBoost) algorithm, in predicting used car prices in the UK. The dataset consists of over 110,000 data points from various brands, including features like model, year, mileage, and more. Data preprocessing, including outlier removal and feature scaling, is performed to prepare the dataset. XGBoost, a powerful machine learning algorithm, is selected for price prediction and compared with traditional regression models. The results show that eXtreme Gradient Boosting(XGBoost) outperforms other models in terms of R2 score, Mean Absolute Error, and Mean Square Error. Its accuracy and efficiency make it a valuable tool for both buyers and sellers in the used car market. However, challenges such as data quality, feature engineering complexity, and model interpretability remain. Future research directions include improving data quality, exploring advanced feature engineering techniques, and integrating external data sources. This study highlights the potential of machine learning in enhancing decision-making in the dynamic used car market.

Advancements in EEG Emotion Recognition: Leveraging Multi-Modal Database Integration

This paper addresses the limitations of relying solely on facial expressions for emotion recognition by proposing an advanced approach that emphasizes continuous monitoring of electroencephalography (EEG) signals. Recognizing the potential for deception in facial expressions, our study leverages the growing interest in EEG signals, tapping into advancements in deep learning and machine learning. By optimizing the configuration of EEG electrodes, our approach enhances the accuracy of emotion classification systems, offering a streamlined solution. The proposed multi-input system refines EEG-based emotion recognition efficiency and integrates facial expression analysis to enhance overall system effectiveness. Through the application of brain heat map topographies and facial expression recognition, our system, employing just nine electrodes, outperforms basic emotion recognition setups. Experimental results validate that combining facial expression analysis with EEG signals provides a more comprehensive and accurate understanding of human emotions. This innovative approach holds significance across various sectors, including healthcare, psychology, and human–computer interaction. The paper introduces a novel multi-input system approach, collaboratively fusing two powerful deep learning algorithms: two Convolutional Neural Networks (CNNs). The proposed EEG-based CNN algorithm achieves an efficiency of 87.43%, rising to 91.21% when integrated with the DeepFace CNN. The seamless integration of facial expressions and brain topographies enables the system to efficiently harness abundant information from both modalities, ensuring a thorough comprehension of human emotions. By capitalizing on the combined advantages of analyzing facial expressions and EEG-derived brain topography, this avant-garde technique substantially improves both precision and efficiency in emotion recognition systems. This enhancement establishes a foundation for the introduction of innovative applications across a spectrum of fields.

The prediction of residual stress of welding process based on deep neural network

The welding process has been an efficient method for producing essential and complex manufacturing parts in various industrial design fields. The post-weld residual stress can have detrimental effects on welded components. Therefore, systematic studies of residual stress are essential for evaluating welding behaviors and mechanisms in welded structures. They can provide a valuable reference and optimization for addressing residual stress relief. Numerical finite element analyses based on thermal-mechanical models offer a comprehensive approach to simulate real welding, providing a reliable means to determine and quantify the distribution of residual stress based on welding parameters and material properties. Furthermore, the finite element analysis is capable of generating adequate and dependable datasets in relation to the classical experiment. However, the finite element simulation is not considered an efficient method for predicting the magnitude and distortion of residual stress due to its high computational cost. A deep learning framework with powerful automatic learning abilities could potentially be used as an alternative method to efficiently predict residual stress. The purpose of the current study is to propose an innovative modeling approach for accurately and effectively predicting residual stress. A deep network model with Convolutional Neural Network using Adam optimization is integrated with numerical finite element analyses of a single-pass beam weld in SUS304 stainless steel. Finite element analysis is used to generate extensive residual stress datasets, which are partly used to train the deep network model and partly used for model validation. The deep network model aligns closely with the finite element analysis results, with a root-mean-square error (RMSE) of less than 12, an absolute fraction of variation (R2) of greater than 0.95, a mean absolute error (MAE) of less than 6.8 and a mean absolute percentage error (MAPE) of less than 1.1. Furthermore, this study highlights the potential advantage of using a deep network model with strong memory capabilities to directly predict residual stress for identical structural components and welding processes.

Schistocyte detection in artificial intelligence age.

Schistocytes are fragmented red blood cells produced as a result of mechanical damage to erythrocytes, usually due to microangiopathic thrombotic diseases or mechanical factors. The early laboratory detection of schistocytes has a critical impact on the timely diagnosis, effective treatment, and positive prognosis of diseases such as thrombocytopenic purpura and hemolytic uremic syndrome. Due to the rapid development of science and technology, laboratory hematology has also advanced. The accuracy and efficiency of tests performed by fully automated hematology analyzers and fully automated morphology analyzers have been considerably improved. In recent years, substantial improvements in computing power and machine learning (ML) algorithm development have dramatically extended the limits of the potential of autonomous machines. The rapid development of machine learning and artificial intelligence (AI) has led to the iteration and upgrade of automated detection of schistocytes. However, along with significantly facilitated operation processes, AI has brought challenges. This review summarizes the progress in laboratory schistocyte detection, the relationship between schistocytes and clinical diseases, and the progress of AI in the detection of schistocytes. In addition, current challenges and possible solutions are discussed, as well as the great potential of AI techniques for schistocyte testing in peripheral blood.

Predicting the Displacement Variation of Rehabilitated Foundation of Onshore Wind Turbines Using Machine Learning Models

The rehabilitation of wind turbine foundations after damage is increasingly common. However, limited research exists on the deformation of wind turbine foundations after rehabilitation. Artificial intelligence methods can be used to analyze future deformation state and predict post-rehabilitation deformation of foundations. This paper focuses on analyzing the stability of damaged wind turbine foundations after rehabilitation, as well as establishing and evaluating machine learning models. Specifically, Decision Tree (DT), Extreme Gradient Boosting (XGB), Support Vector Regression (SVR), and Long Short-Term Memory Network (LSTM) models are utilized to predict the vertical displacement of the rehabilitated foundation. Hence, the stability of the rehabilitated foundation is discussed in correlation with the measured wind speed, based on the foundation vertical displacement data. During the development of the machine learning model, the most suitable combination of hyperparameters is determined. The prediction performance of the SVR and LSTM models, which exhibit good performance, is compared to further evaluate their effectiveness. Furthermore, the models are analyzed and validated. The results indicate that the vertical displacements of the rehabilitated foundations gradually get close to a state of steady fluctuation over time. The SVR model is identified as the most effective in predicting the vertical displacements of wind turbine foundations after rehabilitation. This study aims to analyze and predict the vertical displacement of wind turbine foundations after rehabilitation based on extensive field monitoring data and powerful machine learning models.

GraphsformerCPI: Graph Transformer for Compound-Protein Interaction Prediction.

Accurately predicting compound-protein interactions (CPI) is a critical task in computer-aided drug design. In recent years, the exponential growth of compound activity and biomedical data has highlighted the need for efficient and interpretable prediction approaches. In this study, we propose GraphsformerCPI, an end-to-end deep learning framework that improves prediction performance and interpretability. GraphsformerCPI treats compounds and proteins as sequences of nodes with spatial structures, and leverages novel structure-enhanced self-attention mechanisms to integrate semantic and graph structural features within molecules for deep molecule representations. To capture the vital association between compound atoms and protein residues, we devise a dual-attention mechanism to effectively extract relational features through .cross-mapping. By extending the powerful learning capabilities of Transformers to spatial structures and extensively utilizing attention mechanisms, our model offers strong interpretability, a significant advantage over most black-box deep learning methods. To evaluate GraphsformerCPI, extensive experiments were conducted on benchmark datasets including human, C. elegans, Davis and KIBA datasets. We explored the impact of model depth and dropout rate on performance and compared our model against state-of-the-art baseline models. Our results demonstrate that GraphsformerCPI outperforms baseline models in classification datasets and achieves competitive performance in regression datasets. Specifically, on the human dataset, GraphsformerCPI achieves an average improvement of 1.6% in AUC, 0.5% in precision, and 5.3% in recall. On the KIBA dataset, the average improvement in Concordance index (CI) and mean squared error (MSE) is 3.3% and 7.2%, respectively. Molecular docking shows that our model provides novel insights into the intrinsic interactions and binding mechanisms. Our research holds practical significance in effectively predicting CPIs and binding affinities, identifying key atoms and residues, enhancing model interpretability.