Computational Biology and Chemistry最新文献

{"title":"CopyMix: Mixture model based single-cell clustering and copy number profiling using variational inference","authors":"Negar Safinianaini ,&nbsp;Camila P.E. De Souza ,&nbsp;Andrew Roth ,&nbsp;Hazal Koptagel ,&nbsp;Hosein Toosi ,&nbsp;Jens Lagergren","doi":"10.1016/j.compbiolchem.2024.108257","DOIUrl":"10.1016/j.compbiolchem.2024.108257","url":null,"abstract":"<div><div>Investigating tumor heterogeneity using single-cell sequencing technologies is imperative to understand how tumors evolve since each cell subpopulation harbors a unique set of genomic features that yields a unique phenotype, which is bound to have clinical relevance. Clustering of cells based on copy number data obtained from single-cell DNA sequencing provides an opportunity to identify different tumor cell subpopulations. Accordingly, computational methods have emerged for single-cell copy number profiling and clustering; however, these two tasks have been handled sequentially by applying various ad-hoc pre- and post-processing steps; hence, a procedure vulnerable to introducing clustering artifacts. We avoid the clustering artifact issues in our method, CopyMix, a Variational Inference for a novel mixture model, by jointly inferring cell clusters and their underlying copy number profile. Our probabilistic graphical model is an improved version of the mixture of hidden Markov models, which is designed uniquely to infer single-cell copy number profiling and clustering. For the evaluation, we used likelihood-ratio test, CH index, Silhouette, V-measure, total variation scores. CopyMix performs well on both biological and simulated data. Our favorable results indicate a considerable potential to obtain clinical impact by using CopyMix in studies of cancer tumor heterogeneity.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108257"},"PeriodicalIF":2.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142578223","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":"Computer-aided diagnosis of liver cancer with improved SegNet and deep stacking ensemble model","authors":"Vinnakota Sai Durga Tejaswi,&nbsp;Venubabu Rachapudi","doi":"10.1016/j.compbiolchem.2024.108243","DOIUrl":"10.1016/j.compbiolchem.2024.108243","url":null,"abstract":"<div><div>Liver cancer is a leading cause of cancer-related deaths, often diagnosed at advanced stages due to reliance on traditional imaging methods. Existing computer-aided diagnosis systems struggle with noise, anatomical complexity, and ineffective feature integration, leading to inaccuracies in lesion segmentation and classification. By effectively addressing these challenges, the model aims to enhance early detection and assist clinicians in making informed decisions. Ultimately, this research seeks to contribute to more efficient and accurate liver cancer diagnosis. This paper presents a novel model for liver cancer classification, called SegNet-based Liver Cancer Classification via SqueezeNet (SgN-LCC-SqN). The model effectively executes liver cancer segmentation and classification through four key steps: preprocessing, segmentation, feature extraction, and classification. During preprocessing, Quadratic Mean Estimated Wiener Filtering (QMEWF) is utilized to minimize image noise. Segmentation divides the image into segments using Enhanced Feature Pyramid SegNet (EFP-SgN), which is essential for precise diagnosis. Feature extraction encompasses color features, Local Directional Pattern Variance, and Correlation Filtering-Local Gradient Increasing Pattern (CF-LGIP) features. The extracted features are then processed through an ensemble model, Deep Convolutional, Recurrent, Long Short Term Memory with SqueezeNet (DCR-LSTM-SqN), which includes Deep Convolutional Neural Network (DCNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Modified Loss Function in SqueezeNet (MLF-SqN) classifiers, sequentially analyzing the feature sets through DCNN, RNN, and LSTM before classification by MLF-SqN. The performance of the suggested DCR-LSTM-SqN model is evaluated over conventional methods for positive, negative and other metrics. The DCR-LSTM-SqN model consistently demonstrates superior accuracy, ranging from 0.947 to 0.984, across all training data percentages. Thus, the proposed model effectively segments liver lesions and classifies cancerous areas, demonstrating its potential as a valuable resource for clinicians to enhance the efficiency and accuracy of liver cancer diagnosis.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108243"},"PeriodicalIF":2.6,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514745","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":"Batch effects correction in scRNA-seq based on biological-noise decoupling autoencoder and central-cross loss","authors":"Zhangjie Di ,&nbsp;Bo Yang ,&nbsp;Meng Li ,&nbsp;Yue Wu ,&nbsp;Hong Ji","doi":"10.1016/j.compbiolchem.2024.108261","DOIUrl":"10.1016/j.compbiolchem.2024.108261","url":null,"abstract":"<div><div>Technical or biologically irrelevant differences caused by different experiments, times, or sequencing platforms can generate batch effects that mask the true biological information. Therefore, batch effects are typically removed when analyzing single-cell RNA sequencing (scRNA-seq) datasets for downstream tasks. Existing batch correction methods usually mitigate batch effects by reducing the data from different batches to a lower dimensional space before clustering, potentially leading to the loss of rare cell types. To address this problem, we introduce a novel single-cell data batch effect correction model using Biological-noise Decoupling Autoencoder (BDA) and Central-cross Loss termed BDACL. The model initially reconstructs raw data using an auto-encoder and conducts preliminary clustering. We then construct a similarity matrix and a hierarchical clustering tree to delineate relationships within and between different batches. Finally, we introduce a Central-cross Loss (CL). This loss leverages cross-entropy loss to prompt the model to better distinguish between different cluster labels. Additionally, it employs the Central Loss to encourage samples to form more compact clusters in the embedding space, thereby enhancing the consistency and interpretability of clustering results to mitigate differences between different batches. The primary innovation of this model lies in reconstructing data with an auto-encoder and gradually merging smaller clusters into larger ones using a hierarchical clustering tree. By using reallocated cluster labels as training labels and employing the Central-cross Loss, the model effectively eliminates batch effects in an unsupervised manner. Compared to current methods, BDACL can mitigate batch effects without losing rare cell types.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108261"},"PeriodicalIF":2.6,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514742","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":"Construction and validation of a prognostic model based on immune-metabolic-related genes in oral squamous cell carcinoma","authors":"Bo Yang,&nbsp;Yu Wan,&nbsp;Jieqiong Wang,&nbsp;Yun Liu,&nbsp;Shaohua Wang","doi":"10.1016/j.compbiolchem.2024.108258","DOIUrl":"10.1016/j.compbiolchem.2024.108258","url":null,"abstract":"<div><div>Oral squamous cell carcinoma (OSCC), a significant type of head and neck cancer, has witnessed increasing incidence and mortality rates. Immune-related genes (IRGs) and metabolic-related genes (MRGs) play essential roles in the pathogenesis, metastasis, and progression of OSCC. This study exploited data from The Cancer Genome Atlas (TCGA) to identify IRGs and MRGs related to OSCC through differential analysis. Univariate Cox analysis was utilized to determine immune-metabolic-related genes (IMRGs) associated with patient prognosis. A prognostic model for OSCC was constructed using Lasso-Cox regression and subsequently validated with datasets from the Gene Expression Omnibus (GEO). Non-Negative Matrix Factorization (NMF) clustering identified three molecular subtypes of OSCC, among which the C2 subtype showed better overall survival (OS) and progression-free survival (PFS). A prognostic model based on nine IMRGs was developed to categorize OSCC patients into high- and low-risk groups, with the low-risk group demonstrating significantly longer OS in both training and testing cohorts. The model showed strong predictive capabilities, and the risk score served as an independent prognostic factor. Additionally, expression levels of programmed death 1 (PD1) and cytotoxic T-lymphocyte-associated antigen 4 (CTLA4) differed between the risk groups. Gene Set Enrichment Analysis (GSEA) indicated distinct enriched pathways between high-risk and low-risk groups, highlighting the crucial roles of immune and metabolic processes in OSCC. The nine IMRGs prognostic model presented excellent predictive performance and has potential for clinical application.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108258"},"PeriodicalIF":2.6,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514746","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":"Comparative in Silico study of apigenin and its dimeric forms on PIM1 kinase in glioblastoma multiform","authors":"Mohammad-Sadegh Lotfi ,&nbsp;Majid Jafari-Sabet","doi":"10.1016/j.compbiolchem.2024.108253","DOIUrl":"10.1016/j.compbiolchem.2024.108253","url":null,"abstract":"<div><div>This study aimed to investigate and compare the binding affinity of apigenin and its dimeric flavonoid forms to PIM1 kinase in glioblastoma multiforme (GBM), an aggressive and lethal brain cancer. Apigenin is a natural herbal product that has demonstrated anti-cancer effects in numerous studies, both in vitro and in vivo, on various cancers. Our in silico analysis showed that PIM1 expression was significantly higher in GBM tumor tissue compared to normal brain tissue, and high PIM1 expression correlated with worse survival rates in patients with GBM. Also, our molecular docking studies showed that apigenin and its dimeric flavonoids, such as amentoflavone and hinokiflavone, can bind to the ATP-binding site of PIM1 with significant binding affinity and form various intermolecular interactions with key amino acid residues. Notably, dimeric flavonoids have a stronger binding affinity than apigenin, indicating their potential as potent PIM1 inhibitors. Our findings demonstrated the therapeutic potential of apigenin and its dimeric flavonoid forms in treating GBM by targeting PIM1 kinase. The observed inhibitory effects of PIM1 can inhibit tumor growth, induce cell cycle arrest, and promote apoptosis. However, further in vitro and in vivo studies are needed to confirm their anticancer potentials and elucidate the underlying molecular mechanisms of these compounds in GBM treatment.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108253"},"PeriodicalIF":2.6,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514743","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 insights into human UCP1 activators through molecular docking, MM-GBSA, and molecular dynamics simulation studies","authors":"Utkarsh A. Jagtap ,&nbsp;Sanket Rathod ,&nbsp;Ravi Shukla ,&nbsp;Atish T. Paul","doi":"10.1016/j.compbiolchem.2024.108252","DOIUrl":"10.1016/j.compbiolchem.2024.108252","url":null,"abstract":"<div><div>The prevalence of obesity is rapidly increasing worldwide. Brown adipose tissue activates uncoupling protein 1 (UCP1) to generate heat through bypassing ATP synthesis, offering a potential target for obesity treatment. Targeting UCP1 activation to induce thermogenesis through small molecules presents a promising approach for obesity management. In this study, molecular docking of UCP1 activators, using 2,4-dinitrophenol (DNP) as a reference ligand (PDB ID: 8J1N, docking score: −5.343 kcal/mol), identified seven top-scoring compounds: naringin (-7.284 kcal/mol), quercetin (-6.661 kcal/mol), salsalate (-6.017 kcal/mol), rhein (-5.798 kcal/mol), mirabegron (-5.535 kcal/mol), curcumin (-5.479 kcal/mol), and formoterol (-5.451 kcal/mol). Prime MM-GBSA calculation of the top-scored molecule (i.e., naringin) in the docking study showed ΔGBind of −70.48 kcal/mol. Key interactions of these top 7 activators with UCP1 binding pocket residues Trp280, Arg276, Glu190, Arg83, and Arg91 were observed. Molecular dynamics simulations performed for 100 ns confirmed complex stability, with RMSD values below 6 Å. Additionally, most activators showed favorable intestinal absorption (&gt;90 %) and lipophilicity (LogP 2–4), with pKa values supporting their pharmacological potential as UCP1-targeting therapeutics for obesity. These findings provide a foundation for designing potent UCP1 activators by integrating docking scores, interaction profiles, statistical profiles from MD simulations, and physicochemical assessments to develop effective anti-obesity therapies.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108252"},"PeriodicalIF":2.6,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514744","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 profile analysis to disclose diagnostics and therapeutics biomarkers for thyroid carcinoma","authors":"Sabkat Mahmud ,&nbsp;Alvira Ajadee ,&nbsp;Md. Bayazid Hossen ,&nbsp;Md. Saiful Islam ,&nbsp;Reaz Ahmmed ,&nbsp;Md. Ahad Ali ,&nbsp;Md. Manir Hossain Mollah ,&nbsp;Md. Selim Reza ,&nbsp;Md. Nurul Haque Mollah","doi":"10.1016/j.compbiolchem.2024.108245","DOIUrl":"10.1016/j.compbiolchem.2024.108245","url":null,"abstract":"<div><div>The most frequent endocrine cancer of the head and neck is thyroid carcinoma (THCA). Although there is increasing evidence linking THCA to genetic alterations, the exact molecular mechanism behind this relationship is not yet completely known to the researchers. There is still much to learn about THCA's molecular roots and genetic biomarkers. Though drug therapies are the best choice after metastasis, unfortunately, the majority of the patients progressively develop resistance against the therapeutic drugs after receiving them for a few years. Therefore, multi-targeted different variants of therapeutic drugs may be essential for effective treatment against THCA. To understand molecular mechanisms of THCA development and progression and explore multi-targeted different variants of therapeutic drugs, we detected 80 common differentially expressed genes (cDEGs) between THCA and non-THCA samples from six microarray gene expression datasets using the statistical LIMMA approach. Through protein-protein interaction (PPI) network analysis, we identified the top-ranked eight differentially expressed genes (TIMP1, FN1, THBS1, RUNX2, SHANK2, TOP2A, LRP2, and ACTN1) as the THCA-causing key genes (KGs), where 6 KGs (TIMP1, TOP2A, FN1, ACTN1, RUNX2, THBS1) are upregulated and 2 KGs (LRP2, SHANK2) are downregulated. The expression pattern analysis of KGs with the independent TCGA database by Box plots also confirmed their upregulated and downregulated patterns. The expression analysis of KGs in different stages of THCA development indicated that these KGs might be utilized as early diagnostic and prognostic biomarkers. The pan-cancer analysis of KGs indicated a substantial correlation of KGs with multiple cancers, including THCA. Some transcription factors (TFs) and microRNAs were detected as the key transcriptional and post-transcriptional regulators of KGs using gene regulatory network (GRN) analysis. The enrichment analysis of the cDEGs revealed several key molecular functions, biological processes, cellular components, and pathways significantly associated with THCA. These findings highlight critical mechanisms influenced by the identified key genes (KGs), providing deeper insight into their roles in THCA development. Then we detected 6 repurposable drug molecules (Entrectinib, Imatinib, Ponatinib, Sorafenib, Retevmo, and Pazopanib) by molecular docking with KGs-mediated receptor proteins, ADME/T analysis, and cross-validation with the independent receptors. Therefore, these findings might be useful resources for wet lab researchers and clinicians to consider an effective treatment strategy against THCA.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108245"},"PeriodicalIF":2.6,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514760","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":"Optimization and correction of breast dynamic optical imaging projection data based on deep learning","authors":"Tong Hu ,&nbsp;Jianguo Chen ,&nbsp;Lili Qiao","doi":"10.1016/j.compbiolchem.2024.108259","DOIUrl":"10.1016/j.compbiolchem.2024.108259","url":null,"abstract":"<div><div>Breast cancer poses a significant health threat to women, necessitating advancements in diagnostic technologies. Breast dynamic optical imaging (DOI) technology, recognized for its non-invasive and radiation-free properties, is extensively utilized for the early screening and quantitative analysis of breast tumors. The integration of deep learning, a robust technology for automatic image feature extraction, with breast DOI has the potential to enhance tumor detection and diagnosis significantly. This paper introduces a deep learning-enhanced image optimization approach to overcome challenges such as poor image quality and distorted projection data commonly encountered in existing DOI methods. The approach utilizes convolutional neural networks (CNNs) to extract features from raw images and employs generative adversarial networks (GANs) to enhance these images, thereby improving their quality and contrast. Additionally, a novel correction algorithm is developed to address projection data distortion, enabling the reconstruction and correction of this data for more accurate and reliable imaging results. Experimental findings confirm that the proposed method markedly enhances both image quality and projection data accuracy in breast DOI, offering a reliable foundation for clinical diagnosis. This study not only provides a new perspective and methodology for the early screening and diagnosis of breast cancer but also holds substantial clinical importance and prospective applications.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108259"},"PeriodicalIF":2.6,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142560564","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 insights into irinotecan's interaction with UBE2I in ovarian and endometrial cancers","authors":"Tamizhini Loganathan ,&nbsp;Madhulekha S. ,&nbsp;Hatem Zayed ,&nbsp;George Priya Doss C","doi":"10.1016/j.compbiolchem.2024.108250","DOIUrl":"10.1016/j.compbiolchem.2024.108250","url":null,"abstract":"<div><div>Endometrial and Ovarian cancers are two highly prevalent and fatal reproductive diseases with poor prognoses among women. Elevated estrogen levels in Ovarian Cancer (OC) stimulate the endometrium, causing Endometrial Cancer (EC). Although numerous studies have reported the crucial genes and pathways in this cancer, the pathogenesis of this disease remains unclear. In this study, used bioinformatics tools to analyse GSE63678, GSE115810, GSE36389, GSE26712, GSE36668, GSE27651, GSE6008, GSE69429, GSE69428, GSE18521, GSE185209, GSE54388 gene expression microarray datasets for both the cancers. We analyzed the differential gene expression, functional association, and structural studies. The analysis identified crucial differentially expressed genes (DEGs) in both cancers associated with DNA damage, DNA integrity, and cell-cycle checkpoint signaling pathways. <em>CLDN7, UBE2I, WT1, JAM2, FOXL2, F11R, JAM3, ZFPM2, MEF2C</em>, and <em>PIAS1</em> are the top 10 hub genes commonly identified in both cancer types. Only <em>CLDN7</em> and <em>F11R</em> are upregulated, whereas the remaining hub genes are downregulated in both cancers, suggesting a common framework for contributing to tumorigenesis. Molecular docking and dynamics were performed on the UBE2I protein with Irinotecan Hydrochloride, which could serve as the new approach for treating and managing both cancers. The study reveals the common molecular pathways, pointing out the role of cell cycle and DNA damage and integrity checkpoint signaling in the pathogenesis of both cancer types. This study explored the <em>UBE2I</em> gene as a potential biomarker in OC and EC. Further, this study concludes that the irinotecan hydrochloride drug has higher therapeutic effects on UBE2I protein through docking and dynamics studies.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108250"},"PeriodicalIF":2.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142549484","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":"Cycle-ESM: Generation-assisted classification of antifungal peptides using ESM protein language model","authors":"YiMing Wang,&nbsp;Chun Fang","doi":"10.1016/j.compbiolchem.2024.108240","DOIUrl":"10.1016/j.compbiolchem.2024.108240","url":null,"abstract":"<div><div>The rising prevalence of invasive fungal infections and the emergence of antifungal resistance highlight the urgent need for new antifungal medications. Antifungal peptides have emerged as promising alternatives to traditional antimicrobial agents. The identification of natural or synthetic antifungal peptides is crucial for advancing antifungal drug development. Typically, the availability of antifungal samples is limited, and significant sequence diversity exists among antifungal peptides, posing challenges for high-throughput screening. To address the identification challenge of antifungal peptides with limited sample availability, this study introduces the Cycle ESM method. Initially, the method utilises the ESM protein language model to generate additional data on antifungal peptides, serving as a data augmentation technique to enhance model training effectiveness. Subsequently, the ESM is employed in conjunction with a textCNN model to construct a classifier for peptide prediction, with a comprehensive exploration of peptide characteristics to improve prediction accuracy. Experimental results demonstrate that the performance of the Cycle ESM method surpasses that of existing methods across three distinct antifungal peptide datasets. This study presents a novel approach to antifungal peptide prediction and offers innovative insights for addressing classification problems with limited sample availability.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108240"},"PeriodicalIF":2.6,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514758","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}