Computational Biology and Chemistry最新文献

{"title":"Exploring a novel four-gene system as a diagnostic and prognostic biomarker for triple-negative breast cancer, using clinical variables","authors":"Faisal Ali ,&nbsp;Azhar Iqbal ,&nbsp;Iqra Azhar ,&nbsp;Adiba Qayyum ,&nbsp;Syed Ali Hassan ,&nbsp;Md. Sakib Al Hasan ,&nbsp;Motasim Jawi ,&nbsp;Hesham M. Hassan ,&nbsp;Ahmed Al-Emam ,&nbsp;Muhammad Sajid","doi":"10.1016/j.compbiolchem.2024.108247","DOIUrl":"10.1016/j.compbiolchem.2024.108247","url":null,"abstract":"<div><div>Triple-negative breast cancer (TNBC) is a subtype of breast cancer with a poor prognosis. This research aims to find real hub genes for prognostic biomarkers of TNBC therapy. The GEO datasets GSE27447 and GSE233242 were analyzed using R package limma to explore DEGs. The PPI was generated using the STRING database. Cytoscape software plug-ins were used to screen the hub genes. Using the DAVID database, GO functional enrichment and KEGG pathway enrichment analysis were performed. Different online expression databases were employed to investigate the functions of real hub genes in tumor driving, diagnosis, and prognosis in TNBC patients with various clinicopathologic characteristics. A total of one hundred DEGs were identified between both datasets. The seven hub genes were identified after the topological parameter analysis of the PPI network. The KEGG pathway and GO analysis suggest that four genes (PSMB1, PSMC1, PSMF1, and PSMD8) are highly enriched in proteasome and were finally considered as real hub genes. Additionally, the expression analysis demonstrated that hub genes were notably up-regulated in TNBC patients compared to controls. Furthermore, correlational analyses revealed the positive and negative correlations among the expression of the real hub genes and various ancillary data, including tumor purity, promoter methylation status, overall survival (OS), genetic alterations, infiltration of CD8+ T and CD4+ immune cells, and a few more, across TNBC samples. Finally, our analysis identified a couple of significant chemotherapeutic drugs, miRNAs and transcription factors (TFS) with intriguing curative potential. In conclusion, we identified four real hub genes as novel biomarkers to overcome heterogenetic-particular challenges in diagnosis, prognosis, and therapy for TNBC patients.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108247"},"PeriodicalIF":2.6,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142483223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"E-pharmacophore based virtual screening of potent lead molecules against Cystic Fibrosis: An in silico study","authors":"Sabareeswari Jeyaraman ,&nbsp;Jeyanthi Sankar ,&nbsp;Ling Shing Wong ,&nbsp;Karthikeyan Muthusamy","doi":"10.1016/j.compbiolchem.2024.108249","DOIUrl":"10.1016/j.compbiolchem.2024.108249","url":null,"abstract":"<div><div>Cystic fibrosis is an autosomal recessive condition caused by mutations in the CFTR gene, which encodes the CFTR protein. Currently, CF is a life-limiting illness that has a limited cure. The present study aimed to identify top leads against CFTR protein with F508del in comparison with Lumacaftor. In this study, a homology model of the NBD domain of CFTR protein was developed using the available NBD domain crystal structure. The protein model was refined through apo dynamics. Energy-optimized pharmacophore mapping was carried out to identify essential features for CFTR, resulting in a model with a hydrogen-bond donor, two hydrogen-bond acceptors, and three aromatic ring sites. A screening of a compound from the NPASS database using these DAARRR six-point-pharmacophore features led to the identification of potential ligands that could act against CFTR protein. Further studies such as ADME/T, molecular dynamics, MM_GBSA, and DFT were performed to identify the top-hit compound from the NPASS database. The compound Anguibactin (NPC41982) has been identified as a top lead that exhibits higher binding affinity and stability than the reference compound Lumacaftor, suggesting their potential to bind to the active site of the CFTR protein. These compounds could serve as starting points for the development of drug-like molecules for treating cystic fibrosis.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108249"},"PeriodicalIF":2.6,"publicationDate":"2024-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142483222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gene expression profiling in Venous thromboembolism: Insights from publicly available datasets","authors":"Sunanda Arya,&nbsp;Rashi Khare,&nbsp;Iti Garg,&nbsp;Swati Srivastava","doi":"10.1016/j.compbiolchem.2024.108246","DOIUrl":"10.1016/j.compbiolchem.2024.108246","url":null,"abstract":"<div><h3>Background</h3><div>Venous thromboembolism (VTE) is the third most common cardiovascular disease and is a major cause of mobility and mortality worldwide. VTE is a complex multifactorial disease and genetic mechanisms underlying its pathogenesis is yet to be completely elucidated. The aim of the present study was to identify hub genes and pathways involved in development and progression of blood clot during VTE using gene expression data from public repositories.</div></div><div><h3>Methodology</h3><div>Differential gene expression (DEG) data from two datasets, GSE48000 and GSE19151 were analysed using GEO2R tool. Gene expression data of VTE patients were compared to that of healthy controls using various bioinformatics tools.</div></div><div><h3>Results</h3><div>When the differentially expressed genes of the two datasets were compared, it was found that 19 genes were up-regulated while 134 genes were down-regulated. Gene ontology (GO) and pathway analysis revealed that pathways such as complement and coagulation cascade and B-cell receptor signalling along with DNA methylation, DNA alkylation and inflammatory genes were significantly up-regulated in VTE patients. On the other hand, differentially down-regulated genes included mitochondrial translation elongation, termination and biosysthesis along with heme biosynthesis, erythrocyte differentiation and homeostasis. The top 5 up-regulated hub genes obtained by protein-protein interaction (PPI) network analysis included MYC, FOS, SGK1, CR2 and CXCR4, whereas the top 5 down-regulated hub genes included MRPL13, MRPL3, MRPL11, RPS29 and RPL9. The up-regulated hub genes are functionally involved in maintain vascular integrity and complementation cascade while the down-regulated hub genes were mostly mitochondrial ribosomal proteins.</div></div><div><h3>Conclusion</h3><div>Present study highlights significantly enriched pathways and genes associated with VTE development and prognosis. The data hereby obtained could be used for designing newer diagnostic and therapeutic tools for VTE management.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108246"},"PeriodicalIF":2.6,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142437805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-class fundus disease classification system based on an adaptive scale discriminator and hybrid loss","authors":"Shiyu Zhou,&nbsp;Jue Wang,&nbsp;Bo Li","doi":"10.1016/j.compbiolchem.2024.108241","DOIUrl":"10.1016/j.compbiolchem.2024.108241","url":null,"abstract":"<div><div>Fundus images are crucial in the observation and detection of ophthalmic diseases. However, detecting multiple ophthalmic diseases from fundus images using deep learning techniques is a complex and challenging task One challenge is the complexity of fundus disease structures, which leads to low detection accuracy. Another challenge is the class imbalance problem common in multi-label image classification, which increases the difficulty of algorithm training and evaluation. To address these issues, this study leverages deep learning to propose an ophthalmic disease classification system. We first employ ResNet50 as the backbone network to extract image features, and then use our designed multi-dimensional attention module and adaptive scale discriminator to enhance the network's ability to detect disease features. During training, we innovatively propose a hybrid loss function method to improve the detection capability on imbalanced data. Finally, we conducted experiments on the ODRI-5K dataset with the proposed classification system. In the test set, our method achieved an AUC of 98.53 and an F1-score of 89.73. This result fully demonstrates the excellent disease classification capability of our method. In summary, the multi-label fundus image disease classification system we proposed exhibits outstanding recognition capability, providing an effective solution for the diagnosis of multi-label fundus image diseases.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108241"},"PeriodicalIF":2.6,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142433266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unraveling the biological functions of UCEC: Insights from a prognostic signature model","authors":"Qi Zhu ,&nbsp;Wulin Shan ,&nbsp;Xiaoyu Li ,&nbsp;Yao Chen ,&nbsp;Xu Huang ,&nbsp;Bairong Xia ,&nbsp;Liting Qian","doi":"10.1016/j.compbiolchem.2024.108219","DOIUrl":"10.1016/j.compbiolchem.2024.108219","url":null,"abstract":"<div><h3>Background</h3><div>Uterine corpus endometrial carcinoma (UCEC) is a prevalent gynecological tumor with a bleak prognosis. Anomalous glycosylation plays a pivotal role in tumorigenesis. Currently, there is a lack of prognostic signatures based on glycosylation-related genes for UCEC. Thus, our research aims to construct a predictive model and validate the correlation between relevant genes and biological functions.</div></div><div><h3>Methods</h3><div>Using the TCGA database, we developed prognostic models and explored their relationships with survival outcomes. We further selected key genes to verify their expression in tissues and assess their impact on cellular behavior.</div></div><div><h3>Results</h3><div>The clinical prognosis of the high-risk group was significantly worse than that of the low-risk group. The nomogram model accurately predicted UCEC patient prognosis. Additionally, we identified OLFML1 as a unique signature gene that can inhibit UCEC progression and reduce radiation resistance in vitro.</div></div><div><h3>Conclusions</h3><div>Our model, which is based on glycosylation-related genes in UCEC, effectively identifies high-risk patients and provides valuable prognostic information. In addition, OLFML1 acts as a tumor suppressor in UCEC and enhances radiosensitivity, suggesting a new potential target for improving therapeutic efficacy.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108219"},"PeriodicalIF":2.6,"publicationDate":"2024-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142549485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Potential mechanisms for predicting comorbidity between multiple myeloma and femoral head necrosis based on multiple bioinformatics","authors":"Jie Li ,&nbsp;Jing Dong ,&nbsp;Ming Li ,&nbsp;Hongbo Zhu ,&nbsp;Peicheng Xin","doi":"10.1016/j.compbiolchem.2024.108220","DOIUrl":"10.1016/j.compbiolchem.2024.108220","url":null,"abstract":"<div><h3>Objective</h3><div>This study aims to utilize multiple bioinformatics tools to elucidate the potential mechanisms underlying the comorbidity of Multiple Myeloma (MM) and Osteonecrosis of the Femoral Head (ONFH).</div></div><div><h3>Method</h3><div>High-throughput microarray datasets for MM and ONFH were retrieved from the GEO database, followed by separate preprocessing. We applied Weighted Gene Co-expression Network Analysis (WGCNA) to construct co-expression networks within the MM datasets, further identifying modules and genes associated with MM clinical characteristics. Potential comorbid genes were enriched and analyzed using pathway and network analysis tools, and key genes for MM and ONFH comorbidity were preliminarily screened using Cytoscape. The gene expression capabilities and performance were validated using two disease-related datasets, and we evaluated the differences and consistencies in the immune microenvironment between the two diseases.</div></div><div><h3>Results</h3><div>Our screening identified 418 immune-related comorbid genes, showing consistent biological processes in ribosome synthesis, particularly protein synthesis across both diseases. Key genes were further identified through Protein-Protein Interaction (PPI) networks, and their performance was validated in a validation cohort, with Receiver Operating Characteristic (ROC) curve areas exceeding 0.8. The immune microenvironment analysis highlighted consistent plasma cell infiltration correlated with disease comorbidity, suggesting potential immune targets for future therapies.</div></div><div><h3>Conclusion</h3><div>MM and ONFH share common pathogenic genes that mediate changes in signaling pathways and immune cell dynamics, potentially influencing the comorbidity and progression of these diseases. Key genes identified, such as RPS19, RPL35, RPL24, RPL36, and EIF3G, along with plasma cell infiltration, may serve as central mechanisms in the development of both diseases. This study offers insights and references for further research into targeted treatments for these conditions<strong>.</strong></div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108220"},"PeriodicalIF":2.6,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142433268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integration of 3D-QSAR, molecular docking, and machine learning techniques for rational design of nicotinamide-based SIRT2 inhibitors","authors":"Aleksandra Ilic,&nbsp;Nemanja Djokovic,&nbsp;Teodora Djikic ,&nbsp;Katarina Nikolic","doi":"10.1016/j.compbiolchem.2024.108242","DOIUrl":"10.1016/j.compbiolchem.2024.108242","url":null,"abstract":"<div><div>Selective inhibitors of sirtuin-2 (SIRT2) are increasingly recognized as potential therapeutics for cancer and neurodegenerative diseases. Derivatives of 5-((3-amidobenzyl)oxy)nicotinamides have been identified as some of the most potent and selective SIRT2 inhibitors reported to date (​<span><span>Ai et al., 2016</span></span>, <span><span>Ai et al., 2023</span></span>, <span><span>Baroni et al., 2007</span></span>​). In this study, a 3D-QSAR (3D-Quantitative Structure-Activity Relationship) model was developed using a dataset of 86 nicotinamide-based SIRT2 inhibitors from the literature, along with GRIND-derived pharmacophore models for selected inhibitors. External validation parameters emphasized the reliability of the 3D-QSAR model in predicting SIRT2 inhibition within the defined applicability domain. The interpretation of the 3D-QSAR model facilitated the generation of GRIND-derived pharmacophore models, which in turn enabled the design of novel SIRT2 inhibitors. Furthermore, based on molecular docking results for the SIRT1–3 isoforms, two classification models were developed: a SIRT1/2 model using the Naive Bayes algorithm and a SIRT2/3 model using the k-nearest neighbors algorithm, to predict the selectivity of inhibitors for SIRT1/2 and SIRT2/3. External validation parameters of the selectivity models confirmed their predictive power. Ultimately, the integration of 3D-QSAR, selectivity models and prediction of ADMET properties facilitated the identification of the most promising selective SIRT2 inhibitors for further development.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108242"},"PeriodicalIF":2.6,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142433267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational analysis of natural compounds as potential phosphodiesterase type 5A inhibitors","authors":"Abdullahi Ibrahim Uba ,&nbsp;Nicholas Joseph Paradis ,&nbsp;Chun Wu ,&nbsp;Gokhan Zengin","doi":"10.1016/j.compbiolchem.2024.108239","DOIUrl":"10.1016/j.compbiolchem.2024.108239","url":null,"abstract":"<div><div>Phosphodiesterase type 5 (PDE5) is a cyclic nucleotide-hydrolyzing enzyme that plays essential roles in the regulation of second messenger cyclic adenosine monophosphate (cAMP) and cyclic guanosine monophosphate (cGMP) produced in response to various stimuli. Pharmacological inhibition of PDE5 has been shown to have several therapeutic uses, including treating cardiovascular diseases and erectile dysfunction. In search of PDE5A inhibitors with safer pharmacokinetic properties, computational analyses of the binding propensity of fifty natural compounds comprising flavonoids, polyphenols, and glycosides were conducted. Molecular dynamics simulation coupled with Molecular mechanics with generalized Born and surface area solvation (MM/GBSA) showed that verbascoside may inhibit the activity of PDE5 with a comparative binding energy (ΔG) of -87.8 ± 9.2<!--> <!-->kcal/mol to that of the cocrystal ligand (PDB ID: 3BJC), having ΔG = -77.7±4.5<!--> <!-->kcal/mol. However, the other top compounds studied were found to have lower binding propensities than the cocrystal ligand WAN: hesperidin (ΔG = -33.8 ± 3.4<!--> <!-->kcal/mol), rutin (ΔG = -23.6 ± 26.3<!--> <!-->kcal/mol), caftaric acid (ΔG = -21.2 ±3.6<!--> <!-->kcal/mol), and chlorogenic acid (ΔG = 6.0 ± 16.5<!--> <!-->kcal/mol). Therefore, verbascoside may serve as a potential PDE5A inhibitor while hesperidin, rutin, and caftaric acid may provide templates for further structural optimization for the designs of safer PDE5 inhibitors.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108239"},"PeriodicalIF":2.6,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142428645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Drug–target prediction through self supervised learning with dual task ensemble approach","authors":"Surabhi Mishra,&nbsp;Ashish Chinthala,&nbsp;Mahua Bhattacharya","doi":"10.1016/j.compbiolchem.2024.108244","DOIUrl":"10.1016/j.compbiolchem.2024.108244","url":null,"abstract":"<div><div>Drug–Target interaction (DTI) prediction, a transformative approach in pharmaceutical research, seeks novel therapeutic applications for computational method based virtual screening, existing drugs to address untreated diseases and discovery of existing drugs side effects. The proposed model predict DTI through Heterogeneous biological network by combining drug, genes and disease related knowledge. For the purpose of embedding extraction Self-supervised learning (SSL) has been used which, trains models through pretext tasks, eliminating the need for manual annotations. The pretext tasks are related to either structural based information or similarity based information. To mitigate GNN vulnerability to non-robustness, ensemble learning can be incorporated into GNNs, harnessing multiple models to enhance robustness. This paper introduces a Graph neural network based architecture consisting of task based module and ensemble module for link prediction of DTI. The ensemble module of dual task combinations, both in cold start and warm start scenarios achieve very good performance as it provide 0.960 in cold start and 0.970 in warm start mean AUCROC score with less deviation.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108244"},"PeriodicalIF":2.6,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Federated learning and deep learning framework for MRI image and speech signal-based multi-modal depression detection","authors":"Minakshee Patil ,&nbsp;Prachi Mukherji ,&nbsp;Vijay Wadhai","doi":"10.1016/j.compbiolchem.2024.108232","DOIUrl":"10.1016/j.compbiolchem.2024.108232","url":null,"abstract":"<div><div>Adolescence is a significant period for developing skills and knowledge and learning about managing relationships and emotions by gathering attributes for maturity. Recently, Depression arises as a common mental health issue in adolescents and this affects the daily life of the person. This leads to educational and social impairments and this acts as a major risk for suicide. As a result, the identification and treatment for this disorder are essential. By applying Deep learning (DL) algorithms to medical data, the mental condition of a person can be predicted. However, the traditional deep learning models face the challenge in processing the huge sized data. Hence, FL has emerged as an efficient solution for addressing the data size issue of DL. Here, Depression detection in adolescents is carried out by considering the FL framework, which comprises two modules, namely the local module and the Global module. The detection process is done in the local module using the proposed Exponential African Pelican Optimization based Deep Convolutional Neural Network (ExpAPO-DCNN), whereas the Global module produces the aggregated output of the local module. In this research, FL utilizes the DL model in producing the output, where the DL model considered two modalities of inputs, such as speech signal and Magnetic Resonance Imaging (MRI) image. The processing steps used for this research are pre-processing, feature extraction and detection. For MRI and speech signals, all the above processes are carried out individually. Finally, both the outputs are fused utilizing the overlap coefficient. The ExpAPO-DCNN obtained accuracy, Loss, Root mean Squared error (RMSE), Mean Squared error (MSE), True Negative rate (TNR), and True Positive rate (TPR) of 98.00 %, 0.023, 0.058, 0.240, 97.90 %, and 96.30 %, respectively.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108232"},"PeriodicalIF":2.6,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142445188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}