1
|
Multi-head self-attention mechanism enabled individualized hemoglobin prediction and treatment recommendation systems in anemia management for hemodialysis patients. Heliyon 2023; 9:e12613. [PMID: 36747539 PMCID: PMC9898283 DOI: 10.1016/j.heliyon.2022.e12613] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/21/2022] [Revised: 12/05/2022] [Accepted: 12/16/2022] [Indexed: 02/04/2023] Open
Abstract
Anemia is a critical complication in hemodialysis patients, but the response to erythropoietin-stimulating agents (ESA) treatment varies from patient to patient and is not linear across different time points. The aim of this study was to develop deep learning algorithms for individualized anemia management. We retrospectively collected 36,677 data points from 623 hemodialysis patients, including clinical data, laboratory values, hemoglobin levels, and previous ESA doses. To reduce the computational complexity associated with recurrent neural networks (RNN) in processing time-series data, we developed neural networks based on multi-head self-attention mechanisms in an efficient and effective hemoglobin prediction model. Our proposed model achieved a more accurate hemoglobin prediction than the state-of-the-art RNN model, as shown by the smaller mean absolute error (MAE) of hemoglobin (0.451 vs. 0.593 g/dL, p = 0.014). In ESA (including darbepoetin and epoetin) dose recommendation, the simulation results by our model revealed a higher rate of achieved hemoglobin targets (physician prescription vs. model: 86.3 % vs. 92.7 %, p < 0.001), a lower rate of hemoglobin levels below 10 g/dL (13.7 % vs. 7.3 %, p < 0.001) and smaller change in hemoglobin levels (0.6 g/dL vs. 0.4 g/dL, p < 0.001) in all patients. Our model holds great potential for individualized anemia management as a computerized clinical decision support system for hemodialysis patients. Further external validation with other datasets and prospective clinical utility studies are warranted.
Collapse
|
2
|
Dong R, Du J, Liu Y, Heidari AA, Chen H. An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms. Front Neuroinform 2023; 17:1096053. [PMID: 36756212 PMCID: PMC9899791 DOI: 10.3389/fninf.2023.1096053] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/11/2022] [Accepted: 01/02/2023] [Indexed: 01/24/2023] Open
Abstract
Aiming at the poor robustness and adaptability of traditional control methods for different situations, the deep deterministic policy gradient (DDPG) algorithm is improved by designing a hybrid function that includes different rewards superimposed on each other. In addition, the experience replay mechanism of DDPG is also improved by combining priority sampling and uniform sampling to accelerate the DDPG's convergence. Finally, it is verified in the simulation environment that the improved DDPG algorithm can achieve accurate control of the robot arm motion. The experimental results show that the improved DDPG algorithm can converge in a shorter time, and the average success rate in the robotic arm end-reaching task is as high as 91.27%. Compared with the original DDPG algorithm, it has more robust environmental adaptability.
Collapse
Affiliation(s)
- Ruyi Dong
- College of Information and Control Engineering, Jilin Institute of Chemical Technology, Jilin, China
| | - Junjie Du
- College of Information and Control Engineering, Jilin Institute of Chemical Technology, Jilin, China
| | - Yanan Liu
- College of Information and Control Engineering, Jilin Institute of Chemical Technology, Jilin, China
| | - Ali Asghar Heidari
- School of Surveying and Geospatial Engineering, College of Engineering, University of Tehran, Tehran, Iran
| | - Huiling Chen
- College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou, China
| |
Collapse
|
3
|
Dong B, Li M, Jiang B, Gao B, Li D, Zhang T. Antimicrobial Peptides Prediction method based on sequence multidimensional feature embedding. Front Genet 2022; 13:1069558. [DOI: 10.3389/fgene.2022.1069558] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2022] [Accepted: 11/02/2022] [Indexed: 11/18/2022] Open
Abstract
Antimicrobial peptides (AMPs) are alkaline substances with efficient bactericidal activity produced in living organisms. As the best substitute for antibiotics, they have been paid more and more attention in scientific research and clinical application. AMPs can be produced from almost all organisms and are capable of killing a wide variety of pathogenic microorganisms. In addition to being antibacterial, natural AMPs have many other therapeutically important activities, such as wound healing, antioxidant and immunomodulatory effects. To discover new AMPs, the use of wet experimental methods is expensive and difficult, and bioinformatics technology can effectively solve this problem. Recently, some deep learning methods have been applied to the prediction of AMPs and achieved good results. To further improve the prediction accuracy of AMPs, this paper designs a new deep learning method based on sequence multidimensional representation. By encoding and embedding sequence features, and then inputting the model to identify AMPs, high-precision classification of AMPs and Non-AMPs with lengths of 10–200 is achieved. The results show that our method improved accuracy by 1.05% compared to the most advanced model in independent data validation without decreasing other indicators.
Collapse
|
4
|
Identification of Nine mRNA Signatures for Sepsis Using Random Forest. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022; 2022:5650024. [PMID: 35345523 PMCID: PMC8957445 DOI: 10.1155/2022/5650024] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/09/2022] [Accepted: 02/28/2022] [Indexed: 11/17/2022]
Abstract
Sepsis has high fatality rates. Early diagnosis could increase its curating rates. There were no reliable molecular biomarkers to distinguish between infected and uninfected patients currently, which limit the treatment of sepsis. To this end, we analyzed gene expression datasets from the GEO database to identify its mRNA signature. First, two gene expression datasets (GSE154918 and GSE131761) were downloaded to identify the differentially expressed genes (DEGs) using Limma package. Totally 384 common DEGs were found in three contrast groups. We found that as the condition worsens, more genes were under disorder condition. Then, random forest model was performed with expression matrix of all genes as feature and disease state as label. After which 279 genes were left. We further analyzed the functions of 279 important DEGs, and their potential biological roles mainly focused on neutrophil threshing, neutrophil activation involved in immune response, neutrophil-mediated immunity, RAGE receptor binding, long-chain fatty acid binding, specific granule, tertiary granule, and secretory granule lumen. Finally, the top nine mRNAs (MCEMP1, PSTPIP2, CD177, GCA, NDUFAF1, CLIC1, UFD1, SEPT9, and UBE2A) associated with sepsis were considered as signatures for distinguishing between sepsis and healthy controls. Based on 5-fold cross-validation and leave-one-out cross-validation, the nine mRNA signature showed very high AUC.
Collapse
|
5
|
Xia W, Zheng L, Fang J, Li F, Zhou Y, Zeng Z, Zhang B, Li Z, Li H, Zhu F. PFmulDL: a novel strategy enabling multi-class and multi-label protein function annotation by integrating diverse deep learning methods. Comput Biol Med 2022; 145:105465. [PMID: 35366467 DOI: 10.1016/j.compbiomed.2022.105465] [Citation(s) in RCA: 36] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2022] [Revised: 03/22/2022] [Accepted: 03/25/2022] [Indexed: 02/06/2023]
Abstract
Bioinformatic annotation of protein function is essential but extremely sophisticated, which asks for extensive efforts to develop effective prediction method. However, the existing methods tend to amplify the representativeness of the families with large number of proteins by misclassifying the proteins in the families with small number of proteins. That is to say, the ability of the existing methods to annotate proteins in the 'rare classes' remains limited. Herein, a new protein function annotation strategy, PFmulDL, integrating multiple deep learning methods, was thus constructed. First, the recurrent neural network was integrated, for the first time, with the convolutional neural network to facilitate the function annotation. Second, a transfer learning method was introduced to the model construction for further improving the prediction performances. Third, based on the latest data of Gene Ontology, the newly constructed model could annotate the largest number of protein families comparing with the existing methods. Finally, this newly constructed model was found capable of significantly elevating the prediction performance for the 'rare classes' without sacrificing that for the 'major classes'. All in all, due to the emerging requirements on improving the prediction performance for the proteins in 'rare classes', this new strategy would become an essential complement to the existing methods for protein function prediction. All the models and source codes are freely available and open to all users at: https://github.com/idrblab/PFmulDL.
Collapse
Affiliation(s)
- Weiqi Xia
- College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, 310058, China
| | - Lingyan Zheng
- College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, 310058, China; Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Alibaba-Zhejiang University Joint Research Center of Future Digital Healthcare, Hangzhou, 330110, China
| | - Jiebin Fang
- College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, 310058, China
| | - Fengcheng Li
- College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, 310058, China
| | - Ying Zhou
- College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, 310058, China
| | - Zhenyu Zeng
- Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Alibaba-Zhejiang University Joint Research Center of Future Digital Healthcare, Hangzhou, 330110, China
| | - Bing Zhang
- Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Alibaba-Zhejiang University Joint Research Center of Future Digital Healthcare, Hangzhou, 330110, China
| | - Zhaorong Li
- Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Alibaba-Zhejiang University Joint Research Center of Future Digital Healthcare, Hangzhou, 330110, China
| | - Honglin Li
- School of Pharmacy, East China University of Science and Technology, Shanghai, 200237, China.
| | - Feng Zhu
- College of Pharmaceutical Sciences, The Second Affiliated Hospital, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, 310058, China; Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University, Alibaba-Zhejiang University Joint Research Center of Future Digital Healthcare, Hangzhou, 330110, China.
| |
Collapse
|