pACP-HybDeep: predicting anticancer peptides using binary tree growth based transformer and structural feature encoding with deep-hybrid learning

pACPs-DNN: Predicting anticancer peptides using novel peptide transformation into evolutionary and structure matrix-based images with self-attention deep learning model

Globally, cancer remains a major health challenge due to its high mortality rates. Traditional experimental approaches and therapies are resource-intensive and often cause significant side effects. Anticancer peptides (ACPs) have emerged as alternative therapeutic agents owing to their selectivity, safety, and potential to mitigate drug resistance. In this paper, we propose pACPs-DNN, a novel attention mechanism-based deep learning model developed for the accurate prediction of ACPs and non-ACPs. The pACPs-DNN model transforms input peptides into image representations using residue-wise energy contact matrix (RECM), substitution Matrix Representation (SMR), and Position Specific Scoring Matrix (PSSM) embeddings, followed by local binary pattern (LBP)-based decomposition to capture enhanced structural and local semantic features. These transformations generate novel feature sets, including RECM_LBP, LBP_SMR, and LBP_PSSM. Subsequently, a two-tier feature selection approach is employed to identify a high-ranking optimal feature set, which is then used to train an attention-based deep neural network. The proposed pACPs-DNN model achieves an impressive training accuracy of 96.91 % and an AUC of 0.98. To evaluate its generalization capability, the model was validated on independent datasets, demonstrating significant improvements of 5 % and 3.5 % in accuracy over existing models on the Ind-I and Ind-II datasets, respectively. The demonstrated efficacy and robustness of pACPs-DNN highlight its potential as a valuable tool for advancing drug discovery and academic research in cancer-related therapeutic development.

Transforming breast cancer diagnosis and treatment with large language Models: A comprehensive survey

Breast cancer (BrCa), being one of the most prevalent forms of cancer in women, poses many challenges in the field of treatment and diagnosis due to its complex biological mechanisms. Early and accurate diagnosis plays a fundamental role in improving survival rates, but the limitations of existing imaging methods and clinical data interpretation often prevent optimal results. Large Language Models (LLMs), which are developed based on advanced architectures such as transformers, have brought about a significant revolution in data processing and medical decision-making. By analyzing a large volume of medical and clinical data, these models enable early diagnosis by identifying patterns in images and medical records and provide personalized treatment strategies by integrating genetic markers and clinical guidelines. Despite the transformative potential of these models, their use in BrCa management faces challenges such as data sensitivity, algorithm transparency, ethical considerations, and model compatibility with the details of medical applications that need to be addressed to achieve reliable results. This review systematically reviews the impact of LLMs on BrCa treatment and diagnosis. This study's objectives include analyzing the role of LLM technology in diagnosing and treating this disease. The findings indicate that the application of LLMs has resulted in significant improvements in various aspects of BrCa management, such as a 35% increase in the Efficiency of Diagnosis and BrCa Treatment (EDBC), a 30% enhancement in the System's Clinical Trust and Reliability (SCTR), and a 20% improvement in the quality of patient education and information (IPEI). Ultimately, this study demonstrates the importance of LLMs in advancing precision medicine for BrCa and paves the way for effective patient-centered care solutions.

A machine learning-based glycolysis and fatty acid metabolism-related prognostic signature is constructed and identified ACSL5 as a novel marker inhibiting the proliferation of breast cancer

INTRODUCTION

A new perspective on cancer metabolism suggests that it varies by context and is diverse. Cancer metabolism reprogramming can create a heterogeneous microenvironment that affects immune cell infiltration and function, complicating the selection of treatment methods. However, the specifics of this relationship remain unclear in breast cancer. This research aims to explore how glycolysis and fatty acid metabolism (GF) influence the immune microenvironment and their predictive capabilities for immunotherapy responses and overall survival.

METHODS

We at first time identified 602 GF-related genes. Utilizing multiple datasets from various centers and employing 10 different machine learning algorithms, we developed a GF-related signature called GFSscore, driven by artificial intelligence.

RESULTS

The GFSscore served as an independent prognostic indicator and demonstrated greater robustness than other models. Its validity was validated through multiple databases. Our study found that breast cancer patients with a high GFSscore, indicative of a greater tendency towards glycolytic activity, experienced poorer prognosis due to immunosuppression from distinct immune evasion mechanisms. Conversely, those with a low GFSscore, more inclined towards fatty acid metabolism, had better outcomes. Additionally, the GFSscore has the potential to forecast how well a patient might respond to immunotherapy and their susceptibility to chemotherapy medications. Moreover, we found that the overexpressed ACSL5 gene inhibits the proliferation of BRCA through experiments.

CONCLUSIONS

The GFSscore may offer patients personalized therapy by identifying new therapeutic targets for tumors. By understanding the relationship between cancer metabolism and the immune microenvironment, we can better tailor treatments to individual patients.

An optimized transformer model for efficient detection of thoracic diseases in chest X-rays with multi-scale feature fusion

This study presents the development and application of an optimized Detection Transformer (DETR) model, known as CD-DETR, for the detection of thoracic diseases from chest X-ray (CXR) images. The CD-DETR model addresses the challenges of detecting minor pathologies in CXRs, particularly in regions with uneven medical resource distribution. In the central and western regions of China, due to a shortage of radiologists, CXRs from township hospitals are concentrated in central hospitals for diagnosis. This requires processing a large number of CXRs in a short period of time to obtain results. The model integrates a multi-scale feature fusion approach, leveraging Efficient Channel Attention (ECA-Net) and Spatial Attention Upsampling (SAU) to enhance feature representation and improve detection accuracy. It also introduces a dedicated Chest Diseases Intersection over Union (CDIoU) loss function to optimize the detection of small targets and reduce class imbalance. Experimental results on the NIH Chest X-ray dataset demonstrate that CD-DETR achieves a precision of 88.3% and recall of 86.6%, outperforming other DETR variants by an average of 5% and CNN-based models like YOLOv7 by 6-8% in these metrics, showing its potential for practical application in medical imaging diagnostics.

Towards precision oncology: a multi-level cancer classification system integrating liquid biopsy and machine learning

BACKGROUND

Millions of people die from cancer every year. Early cancer detection is crucial for ensuring higher survival rates, as it provides an opportunity for timely medical interventions. This paper proposes a multi-level cancer classification system that uses plasma cfDNA/ctDNA mutations and protein biomarkers to identify seven distinct cancer types: colorectal, breast, upper gastrointestinal, lung, pancreas, ovarian, and liver.

RESULTS

The proposed system employs a multi-stage binary classification framework where each stage is customized for a specific cancer type. A majority vote feature selection process is employed by combining six feature selectors: Information Value, Chi-Square, Random Forest Feature Importance, Extra Tree Feature Importance, Recursive Feature Elimination, and L1 Regularization. Following the feature selection process, classifiers-including eXtreme Gradient Boosting, Random Forest, Extra Tree, and Quadratic Discriminant Analysis-are customized for each cancer type individually or in an ensemble soft voting setup to optimize predictive accuracy. The proposed system outperformed previously published results, achieving an AUC of 98.2% and an accuracy of 96.21%. To ensure reproducibility of the results, the trained models and the dataset used in this study are made publicly available via the GitHub repository ( https://github.com/SaraEl-Metwally/Towards-Precision-Oncology ).

CONCLUSION

The identified biomarkers enhance the interpretability of the diagnosis, facilitating more informed decision-making. The system's performance underscores its effectiveness in tissue localization, contributing to improved patient outcomes through timely medical interventions.

pNPs-CapsNet: Predicting Neuropeptides Using Protein Language Models and FastText Encoding-Based Weighted Multi-View Feature Integration with Deep Capsule Neural Network

Neuropeptides (NPs) are critical signaling molecules that are essential in numerous physiological processes and possess significant therapeutic potential. Computational prediction of NPs has emerged as a promising alternative to traditional experimental methods, often labor-intensive, time-consuming, and expensive. Recent advancements in computational peptide models provide a cost-effective approach to identifying NPs, characterized by high selectivity toward target cells and minimal side effects. In this study, we propose a novel deep capsule neural network-based computational model, namely pNPs-CapsNet, to predict NPs and non-NPs accurately. Input samples are numerically encoded using pretrained protein language models, including ESM, ProtBERT-BFD, and ProtT5, to extract attention mechanism-based contextual and semantic features. A differential evolution-based weighted feature integration method is utilized to construct a multiview vector. Additionally, a two-tier feature selection strategy, comprising MRMD and SHAP analysis, is developed to identify and select optimal features. Finally, the novel capsule neural network (CapsNet) is trained using the selected optimal feature set. The proposed pNPs-CapsNet model achieved a remarkable predictive accuracy of 98.10% and an AUC of 0.98. To validate the generalization capability of the pNPs-CapsNet model, independent samples reported an accuracy of 95.21% and an AUC of 0.96. The pNPs-CapsNet model outperforms existing state-of-the-art models, demonstrating 4% and 2.5% improved predictive accuracy for training and independent data sets, respectively. The demonstrated efficacy and consistency of pNPs-CapsNet underline its potential as a valuable and robust tool for advancing drug discovery and academic research.