Multi-Peptide Personalized drugs have emerged as a prominent focus in pharmaceutical research owing to their high specificity, low toxicity, and excellent biocompatibility. They are increasingly being applied across various fields, including peptide-drug conjugates (PDCs), infectious disease vaccines, and anti-aging interventions. Immunotherapy, leveraging the immune system to combat cancer, increasingly relies on identifying neoantigens—tumor-specific proteins arising from mutations. These neoantigens, pivotal for personalized cancer vaccines, present computational challenges in their identification and binding affinity prediction to T-cell receptors. This study introduces DeepNeoAGNet, a novel sequence deep learning framework designed for gene sequence prediction. DeepNeoAGNet utilizes bidirectional long-short term memory (Bi-LSTM) neural networks to extract important features from peptide sequences by incorporating both global and local bioengineer information. Our approach incorporates new analysis techniques, including comprehensive amino acid feature engineering such as global amino acid composition strategy, dipeptide composition, local amino acid composition, and local dipeptide composition. Inter-residue sequence relationship analysis is employed to capture intricate dependencies within the sequences. In both the training and testing phases, our approach achieves higher R-square values, indicating a correlation enhancement of 46.466%, and lower RMSE, achieving an accuracy improvement of 11.147%, compared to HLAIImaster and TripHLApan models. These advancements indicate the possibility of facilitating precise identification of HLA-peptide binding, offering researchers and clinicians with a more effective and general tool for neoantigen prediction. By leveraging both global and local features within a BiLSTM architecture, DeepNeoAGNet offers interpretable prediction. Furthermore, it serves as a valuable domain-specific knowledge resource for large language models (LLMs).

AI-assisted thyroid nodule evaluation shows promise in improving thyroid nodule detection, which can be missed by ultrasound(US)-guided hand-held transducer due to the complexity of nodules segmentation. this paper proposed the paper proposes an efficient 4-level framework for ultrasound images segmentation, consisting of Dus-KFCM, Patch Learning, One Class Cross Learning, and parallel computing layer. The developed ML-OCX network considers the contributions of patches to predict the final image-level label by using a GS agent. The authors also created a novel ultrasonography dataset with 4 types of thyroid ultrasound scanning images. Extensive experiments demonstrate the effectiveness of the ML-OCX model, which outperforms other learning methods. The paper also presents an effective multi-modality learning framework to enhance segmentation performance by utilizing prior knowledge of one modality and finding a set of reliable positive and negative examples. The parallel algorithm achieves ~50% improvement in computation efficiency compared to the original serial algorithm. The model is trained on FL-TN, TI-RADS, and DDTI datasets and achieves an accuracy of 97.574%, Fmeasure of 86.150%, and precise judgement of GS-thyroid nodules location from ultrasound assessment, demonstrating its generalization ability. This can help endocrinologist more easily find missed atypia and decrease the follicular lesion miss rate. It may be applicable in daily clinical practice to reduce the burden on physicians. The technology also allows high-risk precancerous lumps to be detected, which has the clinical and biological significance analysis on thyroid nodules echotherapy finding. More prospective studies are needed to make AI-aided thyroid ultrasound diagnosis universal in thyroid nodule clinic.