Computational Biology and Chemistry最新文献

{"title":"Investigations on bioactive compounds of Punica granatum and Beta vulgaris for breast cancer treatment: Network pharmacology predictions, molecular docking, and in-vitro experimental verification of radiation-sensitizing effects","authors":"Nishasri Sukumaran ,&nbsp;C.S. Sureka ,&nbsp;P. Gurusaravanan ,&nbsp;V. Thirunavukkarasu ,&nbsp;R. Alagupandi ,&nbsp;T. Priyadharshini","doi":"10.1016/j.compbiolchem.2025.108512","DOIUrl":"10.1016/j.compbiolchem.2025.108512","url":null,"abstract":"<div><div>Breast cancer represents a significant worldwide health concern for women. Anthocyanin-rich <em>Punica grantum</em> and <em>Beta vulgaris</em> extracts have shown promising anticancer effects. The network pharmacology predictions are used to recognize the bioactive compounds screening of anthocyanins, along with their molecular pathways and targets implicated in breast cancer. The present work includes molecular docking results, the discovery of three potent compounds that can bind strongly to important breast cancer proteins. In vitro experiments were performed in MDA-MB-231 cells to confirm the cytotoxicity and antiproliferative effects of anthocyanin-rich extracts derived from <em>Punica grantum</em> and <em>Beta vulgaris</em>. Also, in-vitro radiation-sensitive studies were done in Low-dose X-rays which paves a new advancement in enhancing Radiotherapy treatment of breast cancer. Current findings indicate that radiation sensitizers are associated with consolidating the pharmacological structure of anthocyanins and specific molecular pathways. Further aspects of natural radiation modifier development for cancer patients undergoing radiation therapy are suggested.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"119 ","pages":"Article 108512"},"PeriodicalIF":2.6,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138221","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":"Combined analysis of somatic mutations and gene expression reveals nuclear speckles-associated enhanced stemness in gingivobuccal carcinoma under DNA damage response","authors":"Sachendra Kumar ,&nbsp;Tamasa De ,&nbsp;Janavi Subramani ,&nbsp;Annapoorni Rangarajan ,&nbsp;Debnath Pal","doi":"10.1016/j.compbiolchem.2025.108513","DOIUrl":"10.1016/j.compbiolchem.2025.108513","url":null,"abstract":"<div><div>Smokeless tobacco chewing habits in India lead to a high prevalence of Gingivobuccal oral squamous cell carcinoma (OSCC-GB). Cancer stem cells (CSCs) are a sub-population of cancer cells within a tumor with stem-like properties and are believed to contribute to tumor initiation, progression, increased resistance to drug therapy, and promote post-therapeutic cancer relapse. An RNA-sequencing data-based combined analysis of somatic mutations and gene expression was performed to explore the role of CSCs in disease progression using the novel Indian-origin OSCC-GB cell line ‘IIOC019’ from a patient with tobacco-chewing habit. The identified DNA damage-related known mutational signature (1 bp T/(A) nucleotide insertions and C&gt;T mutations) indicates the impact of smokeless tobacco-related carcinogens in the IIOC019 cell line. The differentially expressed somatic variants, functional impact predictions, and survival analysis reveal the role of DNA damage response (DDR)-related genes in OSCC-GB, with the SON gene as a significant player. The study suggests that the loss-of-function in a somatic variant of the SON gene is linked to nuclear speckles-associated enhanced stemness and increased risk of disease progression in OSCC-GB under DDR conditions. The newly identified CSC-associated somatic variants appear to promote cancer spread, local recurrence, and resistance to chemotherapy or radiotherapy, contributing to the high mortality rates among Indian OSCC-GB patients.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"119 ","pages":"Article 108513"},"PeriodicalIF":2.6,"publicationDate":"2025-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138220","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":"Alzheimer’s diagnosis by an efficient pipelined gene selection model based on statistical and biological data analysis","authors":"Hamed KA ,&nbsp;Jafar Razmara ,&nbsp;Sepideh Parvizpour ,&nbsp;Morteza Hadizadeh","doi":"10.1016/j.compbiolchem.2025.108511","DOIUrl":"10.1016/j.compbiolchem.2025.108511","url":null,"abstract":"<div><div>Diagnosing Alzheimer’s disease based on gene expression data extracted from microarrays is still an open field of research. Due to the availability of whole-genome data through microarrays technology, diagnosis accuracy is expected to be improved. Despite the high potential of the data prepared by the technology, their analysis on different platforms shows that they may differ for different samples concerning biomarker status. This affects the diagnosis accuracy because of the existing bias between two experimental conditions. To address this problem, we propose a pipeline-based approach to diagnose Alzheimer’s disease using statistical analysis of biological data combined with artificial intelligence techniques. At first, the B-statistics and a new score based on a gene interaction network are used to evaluate genes. The B-statistics helps us to find differentially expressed genes. The new score, called the evidence score, measures the compliance level of the differentially expressed genes with past biological evidence. Next, we use artificial intelligence methods to find the subset of genes that define high separability between normal and affected samples. To this end, we employed a genetic algorithm to find the optimal subset. The performance of the pipeline was compared with other state-of-the-art methods. The results indicate that the proposed method can obtain fruitful predictive performance for diagnosing Alzheimer’s disease. All the codes implemented in this study are available online at <span><span>https://github.com/HamedKAAC/AD-gene-selection</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"119 ","pages":"Article 108511"},"PeriodicalIF":2.6,"publicationDate":"2025-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106395","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":"The exploring AI-generated pyrazalone derivatives as antifungal agents: Bringing together molecular docking and quantum chemical approaches","authors":"Muath Suliman ,&nbsp;Aqsa Laraib ,&nbsp;Shamsa Bibi ,&nbsp;Shimmaa Mansour Moustafa Mohamed ,&nbsp;Mohammad Y. Alshahrani ,&nbsp;Shabbir Muhammad","doi":"10.1016/j.compbiolchem.2025.108502","DOIUrl":"10.1016/j.compbiolchem.2025.108502","url":null,"abstract":"<div><div><em>Candida albicans</em>, an opportunistic fungal pathogen, is the most prevalent species among the twenty types of Candida responsible for candidiasis in humans. The condition is characterized by symptoms such as itching, redness, skin rashes, fever, septic shock, and infections of mucous membranes. This study explores the potential of pyrazolones and their AI-generated derivatives as effective treatments for these fungal infections. We conducted molecular docking, quantum molecular simulations, drug-likeness study, spectroscopic analysis, electrostatic potential analysis, and topological analysis to evaluate the potential of these derivatives as effective pharmaceuticals alongside molecular dynamics (MD) simulations. Our results show that several of these derivatives bind strongly to the target protein N-myristoyl transferase (NMT), showing a range of binding energies from −9.2 to −9.8 kcal/mol. Further insights revealed that <strong>D1</strong> interacts with the NMT protein through two hydrogen-bonding residues HIS-227 and LEU-355, while <strong>D2</strong> forms hydrogen bonds with ASP-110 and VAL-108. The ADMET profiling performed using the pkCSM platform identified <strong>D1</strong> as a lead candidate, exhibiting optimal intestinal absorption and a maximum total clearance rate, which aligns with the criteria for drug-likeness and therapeutic viability. Additionally, our results showed that these derivatives had stronger binding affinities as compared to the parent compound. Molecular dynamics simulations of selected complexes (<strong>D1</strong>, <strong>D2</strong>, <strong>D5</strong>, and <strong>D6</strong>) over 120 ns demonstrated their structural stability and dynamic flexibility, as indicated by metrics encompassing root mean square fluctuation (RMSF), root mean square deviation (RMSD), radius of gyration (Rg), and solvent accessible surface area (SASA). The values of RMSD, remaining well within the permissible 4 Å threshold, reflect minimal structural fluctuation, that support the concept of stable complexes during the simulation. Quantum chemical calculations revealed that <strong>D1</strong> and <strong>D4</strong> had enhanced reactivity, which may improve their ability to interact with biological targets. This study also compared experimental and theoretical approaches to analyzing the properties of the parent compound. Our computational findings demonstrate that derivatives D1 and D2 exhibit strong binding to NMT, a validated antifungal target, with interactions critical for disrupting fungal cell viability. ADMET profiling further identifies D1 as a promising lead with favorable pharmacokinetics, suggesting its potential to inhibit <em>Candida albicans</em> growth in vivo. These results position our derivatives as biologically relevant candidates for experimental validation, advancing the development of novel antifungal therapies.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108502"},"PeriodicalIF":2.6,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144089508","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":"In silico study of salicylic acid derivatives as inhibitors of Ebola proteins through molecular docking","authors":"Rezvan Rahimi ,&nbsp;Mohammad Solimannejad ,&nbsp;Mohammad Hossein Abnosi","doi":"10.1016/j.compbiolchem.2025.108504","DOIUrl":"10.1016/j.compbiolchem.2025.108504","url":null,"abstract":"<div><div>The Zaire Ebola virus is a highly virulent RNA virus that causes severe hemorrhagic fever in humans and nonhuman primates, with no effective treatments currently available. This study evaluates the inhibitory potential of six salicylic acid derivatives including aspirin, diflunisal, fendosal, fosfosal, salicylic acid, and salsalate; against three key Ebola virus receptor proteins through in-silico analysis. Molecular docking techniques have employed to model the interactions between these derivatives and the viral proteins VP24, VP35, and VP40. The results revealed that the salicylic acid derivatives demonstrated significantly stronger binding affinities to the VP35 receptor compared to other receptor proteins studied. Among the derivatives screened, those targeting the VP35 protein exhibited superior binding energy, glide energy, glide E_model, glide E_vdw, and glide ligand efficiency, alongside the lowest RMSD values. These findings suggest that salicylic acid derivatives hold promise as potential anti-Ebola therapies and warrant further investigation in clinical trials.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"119 ","pages":"Article 108504"},"PeriodicalIF":2.6,"publicationDate":"2025-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144115152","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":"An integrated bioinformatics and machine learning-based approach to depict key immunological players associated with candidemia during immunodeficiency","authors":"Ali Rejwan Kabir ,&nbsp;Soumita Podder","doi":"10.1016/j.compbiolchem.2025.108505","DOIUrl":"10.1016/j.compbiolchem.2025.108505","url":null,"abstract":"<div><div>It is evident that a robust immune system keeps <em>Candida albicans</em> infection in check, but weakened immunity opens the door for shifting from a benign yeast form to an invasive hyphal form which leads to systemic candidiasis with high mortality rate. However, the crucial players contributing to the increased susceptibility of immune-deficient individuals to Candida infection remain obscure. To uncover the molecular differences between these conditions, blood-associated proteins from the NDEx database and differentially expressed genes from GEO datasets of immunocompetent and immune-deficient individuals infected with <em>C. albicans</em> were analysed. We focused on deregulated proteins exhibiting inverse expression patterns i.e. upregulated in one group and downregulated in the other and identified 539 proteins. Mapping them onto protein-protein interaction network reconstructed with blood- associated proteins, revealed that they exhibit in 45 hubs, 31 network nodes forming 29 intermodular complexes, and 69 clustered into 11 immunologically relevant MCODE modules. Amongst them 13 key host molecules emerging as key player based on their network topological properties. Furthermore, a machine learning model was developed with a precision of 85 %, recall of 92 %, F1-score of 89 %, and accuracy of 81 % which substantiates the robust association of 11 out of 13 proteins with fungal co-infections in immune-deficient individuals. These findings underscore key host proteins maintaining immune balance in healthy individuals while their disruption in immune-deficient conditions may weaken defense mechanisms and promote fungal infections. Identification of crucial proteins promoting T-reg cells proliferation and M2 macrophage polarization in immune-deficient conditions offers promising therapeutic targets following experimental validation.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"119 ","pages":"Article 108505"},"PeriodicalIF":2.6,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106397","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":"Identification of different lung adenocarcinoma subtypes in combination with antidiuretic hormone-related genes and creation of an associated index to predict prognosis and guide immunotherapy","authors":"Yuankai Lv ,&nbsp;Xiaoping Cai ,&nbsp;Hao Zheng ,&nbsp;Hong Dai","doi":"10.1016/j.compbiolchem.2025.108506","DOIUrl":"10.1016/j.compbiolchem.2025.108506","url":null,"abstract":"<div><h3>Background</h3><div>Lung adenocarcinoma (LUAD) is one of the most aggressive and rapidly lethal tumor types. Previous studies have demonstrated the involvement of antidiuretic hormone (ADH)-related genes in cancer. However, the role of ADH-related genes in LUAD remains unclear. Therefore, investigating the characteristics of these genes in LUAD is essential.</div></div><div><h3>Methods</h3><div>Differentially expressed genes (DEGs) associated with ADH in LUAD were identified using the STRING database. Consensus clustering was performed, and a protein-protein interaction network was constructed for the DEGs between subtypes. Genes extracted from the PPI network underwent univariate, LASSO, and multivariate Cox regression analyses to develop a predictive model for LUAD. A nomogram integrating clinical data and risk scores was created, and its prognostic power for overall survival (OS) in LUAD patients was evaluated. Additionally, LUAD patients were analyzed for targeted therapies, immune landscape, functional enrichment, and mutation profiles. Finally, qRT-PCR was used to examine the expression of signature genes in LUAD cells.</div></div><div><h3>Results</h3><div>Based on ADH-related DEGs, LUAD patients were stratified into two clusters (Cluster 1 and Cluster 2) with distinct survival outcomes. A predictive model incorporating nine feature genes was subsequently constructed using DEGs from these two subtypes. The receiver operating characteristic curve demonstrated the model’s prognostic accuracy in predicting OS in LUAD patients. Compared to the high-risk group, patients in the low-risk group exhibited higher immune infiltration levels and immunophenoscore, along with lower tumor immune dysfunction and exclusion scores. Enrichment analysis revealed that immune response pathways and ligand-receptor interactions were the primary functional categories distinguishing the high- and low-risk groups. The low-risk group showed a significantly lower gene mutation burden. Drug sensitivity analysis identified several potential targeted therapies, including Dabrafenib, ARQ-680, Vemurafenib, BGB-283, MLN-2480, and GDC-0994, which might act on hub genes. qRT-PCR validation confirmed that DNAH12 was significantly downregulated in tumor tissues, while DKK1, DLX2, IGFBP1, NTSR1, RPE65, and VGF were markedly upregulated.</div></div><div><h3>Conclusion</h3><div>This study provided potential prognostic biomarkers for LUAD and might facilitate the development of effective immunotherapy strategies for LUAD patients.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"119 ","pages":"Article 108506"},"PeriodicalIF":2.6,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144115165","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 machine learning-based glycolysis and fatty acid metabolism-related prognostic signature is constructed and identified ACSL5 as a novel marker inhibiting the proliferation of breast cancer","authors":"Mei-zhen Liang ,&nbsp;Xian-feng Huang ,&nbsp;Jun-chang Zhu ,&nbsp;Jing-xia Bao ,&nbsp;Cheng-Liang Chen ,&nbsp;Xiao-wu Wang ,&nbsp;Yun-wei Lou ,&nbsp;Ya-ting Pan ,&nbsp;Yin-wei Dai","doi":"10.1016/j.compbiolchem.2025.108507","DOIUrl":"10.1016/j.compbiolchem.2025.108507","url":null,"abstract":"<div><h3>Introduction</h3><div>A new perspective on cancer metabolism suggests that it varies by context and is diverse. Cancer metabolism reprogramming can create a heterogeneous microenvironment that affects immune cell infiltration and function, complicating the selection of treatment methods. However, the specifics of this relationship remain unclear in breast cancer. This research aims to explore how glycolysis and fatty acid metabolism (GF) influence the immune microenvironment and their predictive capabilities for immunotherapy responses and overall survival.</div></div><div><h3>Methods</h3><div>We at first time identified 602 GF-related genes. Utilizing multiple datasets from various centers and employing 10 different machine learning algorithms, we developed a GF-related signature called GFSscore, driven by artificial intelligence.</div></div><div><h3>Results</h3><div>The GFSscore served as an independent prognostic indicator and demonstrated greater robustness than other models. Its validity was validated through multiple databases. Our study found that breast cancer patients with a high GFSscore, indicative of a greater tendency towards glycolytic activity, experienced poorer prognosis due to immunosuppression from distinct immune evasion mechanisms. Conversely, those with a low GFSscore, more inclined towards fatty acid metabolism, had better outcomes. Additionally, the GFSscore has the potential to forecast how well a patient might respond to immunotherapy and their susceptibility to chemotherapy medications. Moreover, we found that the overexpressed ACSL5 gene inhibits the proliferation of BRCA through experiments.</div></div><div><h3>Conclusions</h3><div>The GFSscore may offer patients personalized therapy by identifying new therapeutic targets for tumors. By understanding the relationship between cancer metabolism and the immune microenvironment, we can better tailor treatments to individual patients.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"119 ","pages":"Article 108507"},"PeriodicalIF":2.6,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106398","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":"Coevolutionary dynamics of 53BP1 and its impact on TP53 interaction for DNA damage repair","authors":"Komal Kumari ,&nbsp;Gyan Prakash Rai ,&nbsp;Srishti Shriya ,&nbsp;Nooruddin Khan ,&nbsp;Mohammad Shamsul Ola ,&nbsp;Asheesh Shanker ,&nbsp;Rizwanul Haque","doi":"10.1016/j.compbiolchem.2025.108508","DOIUrl":"10.1016/j.compbiolchem.2025.108508","url":null,"abstract":"<div><div>The p53-binding protein 1 (53BP1) is essential for DNA damage repair via non-homologous end joining (NHEJ) and plays a crucial role in maintaining genomic stability by interacting with the tumor suppressor protein p53, a key regulator of the DNA damage response (DDR). This study investigates the role of coevolution within 53BP1 and its impact on structural integrity and binding affinity with p53. Through multiple sequence alignment and phylogenetic analysis, we identified 72 coevolving groups of amino acid residues, five of which were mapped to the BRCT domain of 53BP1. Mutational effects on these residues were assessed using point mutation mapping and stability analysis via DynaMut, with a detailed evaluation of groups 12 and 16. Docking studies revealed that coevolution-induced modifications enhanced 53BP1-p53 interactions, with group 12 exhibiting the highest binding affinity (-9.9 kcal/mol), followed by group 16 (-9 kcal/mol), both outperforming the wild-type (-8.9 kcal/mol). These modifications resulted in novel interactions that contributed to overall structural stability. Our findings highlight the significance of coevolution in shaping protein-protein interactions and maintaining the structural and functional integrity of 53BP1 protein.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108508"},"PeriodicalIF":2.6,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070949","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":"UB-Former: A fine-grained classification method for images of insects using biomorphic features","authors":"Shilu Kang,&nbsp;Hua Huo,&nbsp;Aokun Mei,&nbsp;Jiaxin Xu","doi":"10.1016/j.compbiolchem.2025.108496","DOIUrl":"10.1016/j.compbiolchem.2025.108496","url":null,"abstract":"<div><div>Insect fine-grained image classification is a detailed classification of animal images of the same class of insects. It requires precise identification of insect targets and an understanding of species-specific traits across various life stages. In this work, we propose a novel fine-grained insect image classification model using biomorphic information to address challenges, namely using biomorphic features former(UB-Former). The model consists of three components: it first introduces a segmentation module to isolate the insect targets and minimize background noise. Then, the using biomorphic features module (UBM) extracts dual-channel features from both the segmented image and the contour texture image. Finally, a multi-image feature comparison method (MIFC) is used for cross-domain learning, capturing shared features among individuals of different life stages to enhance classification performance. UB-Former achieved state-of-the-art results with 61.1% and 53.2% accuracy on the Insecta and IP102 datasets. The accuracy of 92.0%, 95.0%, and 92.2% is achieved on the image fine-grained classification datasets CUB200-2011, Stanford Cars, and Stanford Dogs of other species, respectively, demonstrating its effectiveness in both insect and other fine-grained image classification tasks.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108496"},"PeriodicalIF":2.6,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943558","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}