生物医学工程学杂志 Pub Date : 2025-08-25 DOI: 10.7507/1001-5515.202410062

Yutao Men, Lele Wei, Baibing Hu, Pujun Hao, Chunqiu Zhang

{"title":"[Simulation research on the influence of regular porous lattice scaffolds on bone growth].","authors":"Yutao Men, Lele Wei, Baibing Hu, Pujun Hao, Chunqiu Zhang","doi":"10.7507/1001-5515.202410062","DOIUrl":"10.7507/1001-5515.202410062","url":null,"abstract":"To assess the implantation effectiveness of porous scaffolds, it is essential to consider not only their mechanical properties but also their biological performance. Given the high cost, long duration and low reproducibility of biological experiments, simulation studies as a virtual alternative, have become a widely adopted and efficient evaluation method. In this study, based on the secondary development environment of finite element analysis software, the strain energy density growth criterion for bone tissue was introduced to simulate and analyze the cell proliferation-promoting effects of four different lattice porous scaffolds under cyclic compressive loading. The biological performance of these scaffolds was evaluated accordingly. The computational results indicated that in the early stages of bone growth, the differences in bone tissue formation among the scaffold groups were not significant. However, as bone growth progressed, the scaffold with a porosity of 70% and a pore size of 900 μm demonstrated markedly superior bone formation compared to other porosity groups and pore size groups. These results suggested that the scaffold with a porosity of 70% and a pore size of 900 μm was most conducive to bone tissue growth and could be regarded as the optimal structural parameter for bone repair scaffold. In conclusion, this study used a visualized simulation approach to pre-evaluate the osteogenic potential of porous scaffolds, aiming to provide reliable data support for the optimized design and clinical application of implantable scaffolds.","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"42 4","pages":"808-816"},"PeriodicalIF":0.0,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12409508/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144972888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

[Research progress on predicting radiation pneumonia based on four-dimensional computed tomography ventilation imaging in lung cancer radiotherapy]. [肺癌放疗中基于四维计算机断层通气成像预测放射性肺炎的研究进展]。

生物医学工程学杂志 Pub Date : 2025-08-25 DOI: 10.7507/1001-5515.202405008

Yuyu Liu, Li Wang, Yanping Gao, Xiang Pan, Meifang Yuan, Bingbing He, Han Bai, Wenbing Lyu

{"title":"[Research progress on predicting radiation pneumonia based on four-dimensional computed tomography ventilation imaging in lung cancer radiotherapy].","authors":"Yuyu Liu, Li Wang, Yanping Gao, Xiang Pan, Meifang Yuan, Bingbing He, Han Bai, Wenbing Lyu","doi":"10.7507/1001-5515.202405008","DOIUrl":"10.7507/1001-5515.202405008","url":null,"abstract":"Lung cancer is the leading cause of cancer-related deaths worldwide. Radiation pneumonitis is a major complication in lung cancer radiotherapy. Four-dimensional computed tomography (4DCT) imaging provides dynamic ventilation information, which is valuable for lung function assessment and radiation pneumonitis prevention. Many methods have been developed to calculate lung ventilation from 4DCT, but a systematic comparison is lacking. Prediction of radiation pneumonitis using 4DCT-based ventilation is still in an early stage, and no comprehensive review exists. This paper presented the first systematic comparison of functional lung ventilation algorithms based on 4DCT over the past 15 years, highlighting their clinical value and limitations. It then reviewed multimodal approaches combining 4DCT ventilation imaging, dose metrics, and clinical data for radiation pneumonitis prediction. Finally, it summarized current research and future directions of 4DCT in lung cancer radiotherapy, offering insights for clinical practice and further studies.","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"42 4","pages":"863-870"},"PeriodicalIF":0.0,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12409506/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144973106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

[Multi-source adversarial adaptation with calibration for electroencephalogram-based classification of meditation and resting states]. [基于脑电图的冥想和静息状态分类校正的多源对抗适应]。

生物医学工程学杂志 Pub Date : 2025-08-25 DOI: 10.7507/1001-5515.202504044

Mingyu Gou, Haolong Yin, Tianzhen Chen, Fei Cheng, Jiang Du, Baoliang Lyu, Weilong Zheng

{"title":"[Multi-source adversarial adaptation with calibration for electroencephalogram-based classification of meditation and resting states].","authors":"Mingyu Gou, Haolong Yin, Tianzhen Chen, Fei Cheng, Jiang Du, Baoliang Lyu, Weilong Zheng","doi":"10.7507/1001-5515.202504044","DOIUrl":"10.7507/1001-5515.202504044","url":null,"abstract":"Meditation aims to guide individuals into a state of deep calm and focused attention, and in recent years, it has shown promising potential in the field of medical treatment. Numerous studies have demonstrated that electroencephalogram (EEG) patterns change during meditation, suggesting the feasibility of using deep learning techniques to monitor meditation states. However, significant inter-subject differences in EEG signals poses challenges to the performance of such monitoring systems. To address this issue, this study proposed a novel model-calibrated multi-source adversarial adaptation network (CMAAN). The model first trained multiple domain-adversarial neural networks in a pairwise manner between various source-domain individuals and the target-domain individual. These networks were then integrated through a calibration process using a small amount of labeled data from the target domain to enhance performance. We evaluated the proposed model on an EEG dataset collected from 18 subjects undergoing methamphetamine rehabilitation. The model achieved a classification accuracy of 73.09%. Additionally, based on the learned model, we analyzed the key EEG frequency bands and brain regions involved in the meditation process. The proposed multi-source domain adaptation framework improves both the performance and robustness of EEG-based meditation monitoring and holds great promise for applications in biomedical informatics and clinical practice.","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"42 4","pages":"668-677"},"PeriodicalIF":0.0,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12409513/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144973075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

[Deep transcranial magnetic stimulation coil design and multi-objective slime mould algorithm]. [深经颅磁刺激线圈设计及多目标黏菌算法]。

生物医学工程学杂志 Pub Date : 2025-08-25 DOI: 10.7507/1001-5515.202412058

Hui Xiong, Jibin Zhu, Jinzhen Liu

{"title":"[Deep transcranial magnetic stimulation coil design and multi-objective slime mould algorithm].","authors":"Hui Xiong, Jibin Zhu, Jinzhen Liu","doi":"10.7507/1001-5515.202412058","DOIUrl":"10.7507/1001-5515.202412058","url":null,"abstract":"The therapeutic effects of transcranial magnetic stimulation (TMS) are closely related to the structure of the stimulation coil. Based on this, this study designed an A-word coil and proposed a multi-strategy fusion multi-objective slime mould algorithm (MSSMA) aimed at optimizing the stimulation depth, focality, and intensity of the coil. MSSMA significantly improved the convergence and distribution of the algorithm by integrating a dual-elite guiding mechanism, a hyperbolic tangent control strategy, and a hybrid polynomial mutation strategy. Furthermore, compared with other stimulation coils, the novel coil optimized by the MSSMA demonstrates superior performance in terms of stimulation depth. To verify the optimization effects, a magnetic field measurement system was established, and a comparison of the measurement data with simulation data confirmed that the proposed algorithm could effectively optimize coil performance. In summary, this study provides a new approach for deep TMS, and the proposed algorithm holds significant reference value for multi-objective engineering optimization problems.","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"42 4","pages":"716-723"},"PeriodicalIF":0.0,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12409500/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144973142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

[Prefrontal dysfunction and mismatch negativity in adolescent depression: A multimodal fNIRS-ERP study]. 青少年抑郁症的前额叶功能障碍和错配负性：一项多模态fNIRS-ERP研究。

生物医学工程学杂志 Pub Date : 2025-08-25 DOI: 10.7507/1001-5515.202503053

Hongyi Sun, Lin Zhang, Jing Li, Zhenhua Li, Jiaxi Huang, Zhong Zheng, Ke Zou

{"title":"[Prefrontal dysfunction and mismatch negativity in adolescent depression: A multimodal fNIRS-ERP study].","authors":"Hongyi Sun, Lin Zhang, Jing Li, Zhenhua Li, Jiaxi Huang, Zhong Zheng, Ke Zou","doi":"10.7507/1001-5515.202503053","DOIUrl":"10.7507/1001-5515.202503053","url":null,"abstract":"Early identification of adolescent depression requires objective biomarkers. This study investigated the functional near-infrared spectroscopy (fNIRS) activation patterns and mismatch negativity (MMN) characteristics in adolescents with first-episode mild-to-moderate depression. We enrolled 33 patients and 33 matched healthy controls, measuring oxyhemoglobin (Oxy-Hb) concentration in the frontal cortex during verbal fluency tasks via fNIRS, and recording MMN latency/amplitude at Fz/Cz electrodes using event-related potentials (ERP). Compared with healthy controls, the depression group showed significantly prolonged MMN latency [Fz: (227.88 ± 31.08) ms vs. (208.70 ± 25.35) ms, P < 0.01; Cz: (223.73 ± 29.03) ms vs. (204.18 ± 22.43) ms, P < 0.01], and obviously reduced Fz amplitude [(2.42 ± 2.18) μV vs. (5.65 ± 5.59) μV, P = 0.03]. A significant positive correlation was observed between MMN latencies at Fz and Cz electrodes ( P < 0.01). Oxy-Hb in left frontopolar prefrontal channels (CH15/17) was significantly decreased in patient group ( P < 0.05). Our findings suggest that adolescents with depression exhibit hypofunction in the left prefrontal cortex and impaired automatic sensory processing. The combined application of fNIRS and ERP techniques may provide an objective basis for early clinical identification.","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"42 4","pages":"701-706"},"PeriodicalIF":0.0,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12409496/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144973085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

[Study on dental image segmentation and automatic root canal measurement based on multi-stage deep learning using cone beam computed tomography]. [基于锥形束计算机断层多阶段深度学习的牙齿图像分割与自动根管测量研究]。

生物医学工程学杂志 Pub Date : 2025-08-25 DOI: 10.7507/1001-5515.202503008

Ziqing Chen, Qi Liu, Jialei Wang, Nuo Ji, Yuhang Gong, Bo Gao

{"title":"[Study on dental image segmentation and automatic root canal measurement based on multi-stage deep learning using cone beam computed tomography].","authors":"Ziqing Chen, Qi Liu, Jialei Wang, Nuo Ji, Yuhang Gong, Bo Gao","doi":"10.7507/1001-5515.202503008","DOIUrl":"10.7507/1001-5515.202503008","url":null,"abstract":"This study aims to develop a fully automated method for tooth segmentation and root canal measurement based on cone beam computed tomography (CBCT) images, providing objective, efficient, and accurate measurement results to guide and assist clinicians in root canal diagnosis grading, instrument selection, and preoperative planning. The method utilized Attention U-Net to recognize tooth descriptors, cropped regions of interest (ROIs) based on the center of mass of these descriptors, and applied an integrated deep learning method for segmentation. The segmentation results were mapped back to the original coordinates and position-corrected, followed by automatic measurement and visualization of root canal lengths and angles. The results indicated that the Dice coefficient for segmentation was 96.42%, the Jaccard coefficient was 93.11%, the Hausdorff Distance was 2.07 mm, and the average surface distance was 0.23 mm, all of which surpassed existing methods. The relative error of the root canal working length measurement was 3.15% (< 5%), the curvature angle error was 2.85 °, and the correct classification rate of the treatment difficulty coefficient was 90.48%. The proposed methods all achieved favorable results, which can provide an important reference for clinical application.","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"42 4","pages":"757-765"},"PeriodicalIF":0.0,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12409488/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144972915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

[The role and mechanisms of N,N-dimethylglycine sodium in promoting wound healing in mice]. [N，N-二甲基甘氨酸钠促进小鼠伤口愈合的作用及机制]。

生物医学工程学杂志 Pub Date : 2025-08-25 DOI: 10.7507/1001-5515.202411042

Shuchang Guo, Zhenyang Zhang, Baoying Qi, Yuxiao Zhou, Meng Li, Tianzhu Liang, Huan Yan, Qiuyu Wang, Lili Jin

{"title":"[The role and mechanisms of N,N-dimethylglycine sodium in promoting wound healing in mice].","authors":"Shuchang Guo, Zhenyang Zhang, Baoying Qi, Yuxiao Zhou, Meng Li, Tianzhu Liang, Huan Yan, Qiuyu Wang, Lili Jin","doi":"10.7507/1001-5515.202411042","DOIUrl":"10.7507/1001-5515.202411042","url":null,"abstract":"N,N-Dimethylglycine (DMG) is a glycine derivative, and its sodium salt (DMG-Na) has been demonstrated to possess various biological activities, including immunomodulation, free radical scavenging, and antioxidation, collectively contributing to the stability of tissue and cellular functions. However, its direct effects and underlying mechanisms in wound healing remain unclear. In this study, a full-thickness excisional wound model was established on the dorsal skin of mice, and wounds were treated locally with DMG-Na. Wound healing progression was assessed by calculating wound closure rates. Histopathological analysis was conducted using hematoxylin-eosin (HE) staining, and keratinocyte proliferation, migration, and differentiation were evaluated using CCK-8 assays, scratch wound assays, and quantitative reverse transcription PCR (qRT-PCR). Inflammation-related cytokine expression in keratinocytes was analyzed via ELISA and qRT-PCR. Results revealed that DMG-Na treatment significantly accelerated wound healing in mice and improved overall wound closure quality. The wound healing rates on days 3, 6, and 9 were 49.18%, 68.87%, and 90.55%, respectively, with statistically significant differences compared to the control group ( P<0.05). DMG-Na treatment downregulated the mRNA levels of keratinocyte differentiation markers while enhancing cell proliferation and migration ( P<0.05). Furthermore, DMG-Na decreased the secretion of LPS-induced keratinocyte inflammatory cytokines, including IL-1β, IL-6, IL-8, TNF-α, and CXCL10 ( P<0.05). These findings indicate that DMG-Na regulates inflammatory responses and promotes keratinocyte proliferation and migration, thereby facilitating the healing of skin wounds.","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"42 4","pages":"824-831"},"PeriodicalIF":0.0,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12409491/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144972945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

[Preparation and application of conductive fiber coated with liquid metal]. [液态金属包覆导电纤维的制备与应用]。

生物医学工程学杂志 Pub Date : 2025-08-25 DOI: 10.7507/1001-5515.202507019

Chengfeng Liu, Jiabo Tang, Ming Li, Shihao Zhang, Yang Zou, Yonggang Lyu

{"title":"[Preparation and application of conductive fiber coated with liquid metal].","authors":"Chengfeng Liu, Jiabo Tang, Ming Li, Shihao Zhang, Yang Zou, Yonggang Lyu","doi":"10.7507/1001-5515.202507019","DOIUrl":"10.7507/1001-5515.202507019","url":null,"abstract":"Flexible conductive fibers have been widely applied in wearable flexible sensing. However, exposed wearable flexible sensors based on liquid metal (LM) are prone to abrasion and significant conductivity degradation. This study presented a high-sensitivity LM conductive fiber with integration of strain sensing, electrical heating, and thermochromic capabilities, which was fabricated by coating eutectic gallium-indium (EGaIn) onto spandex fibers modified with waterborne polyurethane (WPU), followed by thermal curing to form a protective polyurethane sheath. This fiber, designated as Spandex/WPU/EGaIn/Polyurethane (SWEP), exhibits a four-layer coaxial structure: spandex core, WPU modification layer, LM conductive layer, and polyurethane protective sheath. The SWEP fiber had a diameter of (458.3 ± 10.4) μm, linear density of (2.37 ± 0.15) g/m, and uniform EGaIn coating. The fiber had excellent conductivity with an average value of (3 716.9 ± 594.2) S/m. The strain sensing performance was particularly noteworthy. A 5 cm × 5 cm woven fabric was fabricated using polyester warp yarns and SWEP weft yarns. The fabric exhibited satisfactory moisture permeability [(536.06 ± 33.15) g/(m 2·h)] and maintained stable thermochromic performance after repeated heating cycles. This advanced conductive fiber development is expected to significantly promote LM applications in wearable electronics and smart textile systems.","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"42 4","pages":"724-732"},"PeriodicalIF":0.0,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12409498/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144973053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

[Effect of 40 Hz pulsed magnetic field on mitochondrial dynamics and heart rate variability in dementia mice]. [40 Hz脉冲磁场对痴呆小鼠线粒体动力学和心率变异性的影响]。

生物医学工程学杂志 Pub Date : 2025-08-25 DOI: 10.7507/1001-5515.202501061

Lifan Zhang, Duyan Geng, Guizhi Xu, Hongxia An

{"title":"[Effect of 40 Hz pulsed magnetic field on mitochondrial dynamics and heart rate variability in dementia mice].","authors":"Lifan Zhang, Duyan Geng, Guizhi Xu, Hongxia An","doi":"10.7507/1001-5515.202501061","DOIUrl":"10.7507/1001-5515.202501061","url":null,"abstract":"Alzheimer's disease (AD) is the most common degenerative disease of the nervous system. Studies have found that the 40 Hz pulsed magnetic field has the effect of improving cognitive ability in AD, but the mechanism of action is not clear. In this study, APP/PS1 double transgenic AD model mice were used as the research object, the water maze was used to group dementia, and 40 Hz/10 mT pulsed magnetic field stimulation was applied to AD model mice with different degrees of dementia. The behavioral indicators, mitochondrial samples of hippocampal CA1 region and electrocardiogram signals were collected from each group, and the effects of 40 Hz pulsed magnetic field on mouse behavior, mitochondrial kinetic indexes and heart rate variability (HRV) parameters were analyzed. The results showed that compared with the AD group, the loss of mitochondrial crest structure was alleviated and the mitochondrial dynamics related indexes were significantly improved in the AD + stimulated group ( P < 0.001), sympathetic nerve excitation and parasympathetic nerve inhibition were improved, and the spatial cognitive memory ability of mice was significantly improved ( P < 0.05). The preliminary results of this study show that 40 Hz pulsed magnetic field stimulation can improve the mitochondrial structure and mitochondrial kinetic homeostasis imbalance of AD mice, and significantly improve the autonomic neuromodulation ability and spatial cognition ability of AD mice, which lays a foundation for further exploring the mechanism of ultra-low frequency magnetic field in delaying the course of AD disease and realizing personalized neurofeedback therapy for AD.","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"42 4","pages":"707-715"},"PeriodicalIF":0.0,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12409489/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144973058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

[Research on prediction model of protein thermostability integrating graph embedding and network topology features]. 结合图嵌入和网络拓扑特征的蛋白质热稳定性预测模型研究

生物医学工程学杂志 Pub Date : 2025-08-25 DOI: 10.7507/1001-5515.202501045

Shuyi Pan, Xiaoyang Xiang, Qunfang Yan, Yanrui Ding

{"title":"[Research on prediction model of protein thermostability integrating graph embedding and network topology features].","authors":"Shuyi Pan, Xiaoyang Xiang, Qunfang Yan, Yanrui Ding","doi":"10.7507/1001-5515.202501045","DOIUrl":"10.7507/1001-5515.202501045","url":null,"abstract":"Protein structure determines function, and structural information is critical for predicting protein thermostability. This study proposes a novel method for protein thermostability prediction by integrating graph embedding features and network topological features. By constructing residue interaction networks (RINs) to characterize protein structures, we calculated network topological features and utilize deep neural networks (DNN) to mine inherent characteristics. Using DeepWalk and Node2vec algorithms, we obtained node embeddings and extracted graph embedding features through a TopN strategy combined with bidirectional long short-term memory (BiLSTM) networks. Additionally, we introduced the Doc2vec algorithm to replace the Word2vec module in graph embedding algorithms, generating graph embedding feature vector encodings. By employing an attention mechanism to fuse graph embedding features with network topological features, we constructed a high-precision prediction model, achieving 87.85% prediction accuracy on a bacterial protein dataset. Furthermore, we analyzed the differences in the contributions of network topological features in the model and the differences among various graph embedding methods, and found that the combination of DeepWalk features with Doc2vec and all topological features was crucial for the identification of thermostable proteins. This study provides a practical and effective new method for protein thermostability prediction, and at the same time offers theoretical guidance for exploring protein diversity, discovering new thermostable proteins, and the intelligent modification of mesophilic proteins.","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":"42 4","pages":"817-823"},"PeriodicalIF":0.0,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12409512/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144973116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

生物医学工程学杂志最新文献