Computational Biology and Chemistry最新文献

{"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}

{"title":"Machine learning and explainable artificial intelligence reveals the MicroRNAs associated with survival of head and neck squamous cell carcinoma patients","authors":"Nabeela Kausar","doi":"10.1016/j.compbiolchem.2025.108503","DOIUrl":"10.1016/j.compbiolchem.2025.108503","url":null,"abstract":"<div><div>Dysregulated microRNAs (miRNAs) play a significant role in cancer development and metastasis. In literature, miRNAs have been used for the survival prediction of different types of cancers using AI. Although AI is useful for diagnosis and prognosis prediction of cancer, however, a major criticism of incorporating it into medical fields is that it is essentially a mechanistically uninterpretable opaque “black box”, and hence it may not have the required level of accountability, transparency, and reliability in decisions of cancer diagnosis and prognosis for their adoption in clinical settings. Therefore, there is need to develop intelligent models which may explain their prediction so that they may be reliably used by the clinicians. As dysregulated miRNAs are reported to cause cancer metastasis hence, they can play role in survival of patient. Therefore, there is needed to develop ML based techniques which may automatically indicate specific miRNAs involved in survival of patients. In this research, Machine Learning and Explainable AI (XAI) based models have been developed for survival prediction of Head and Neck Squamous Cell Carcinoma (HNSC) patients using miRNA sequences and clinical datasets. miRNAs dataset contains the data of 485 HNSC patients and clinical dataset contains data of 528 patients. The proposed XAI based model explains its prediction by showing the specific miRNA sequences involved in survival of the patients to demonstrate its reliability to be used by clinicians for therapeutic decisions. In this study, it has been shown that explainable ML can provide explicit knowledge of how models make their predictions, which is necessary for increasing the trust and adoption of innovative ML techniques in oncology and healthcare.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108503"},"PeriodicalIF":2.6,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143947603","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":"Towards automated and reliable lung cancer detection in histopathological images using DY-FSPAN: A feature-summarized pyramidal attention network for explainable AI","authors":"Tathagat Banerjee","doi":"10.1016/j.compbiolchem.2025.108500","DOIUrl":"10.1016/j.compbiolchem.2025.108500","url":null,"abstract":"<div><div>Medical image classification is critical for accurate disease diagnosis, necessitating models that balance performance and interpretability. This study presents Dilated Y-Block-based Feature Summarized Pyramidal Attention Network (DY-FSPAN), a deep learning framework designed for robust feature extraction and classification. The architecture incorporates Y-blocks and attention mechanisms to enhance spatial feature representation while maintaining receptive field coherence. The proposed model achieves a classification accuracy of 98.5 %, surpassing existing approaches such as convolutional block attention networks, adversarial learning models, and multi-output 3D CNNs. To validate the efficacy of DY-FSPAN, we conduct an extensive experiment, including comparative benchmarking against state-of-the-art methods, robustness assessments, and ablation studies. The model’s structural improvements are tested through various configurations to assess the impact of key components, confirming the contribution of attention mechanisms to performance enhancement. Grad-CAM analysis was employed to visualize learned feature maps, highlighting the model’s focus on diagnostically relevant regions, thereby improving trust in AI-driven medical decision-making. From an explainable AI perspective, the proposed framework achieves superior classification accuracy and enhances interpretability, addressing a crucial requirement in medical imaging applications. The qualitative and quantitative analyses demonstrate that DY-FSPAN effectively localizes disease-specific features, making it a suitable tool for clinical use. The findings suggest that integrating attention-based architectures with optimized feature selection can significantly advance automated medical diagnosis. The model’s ability to improve diagnostic reliability while maintaining transparency underscores its potential for real-world deployment in healthcare settings.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108500"},"PeriodicalIF":2.6,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070896","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":"Machine learning-driven discovery of antimicrobial peptides targeting the GAPDH-TPI protein-protein interaction in Schistosoma mansoni for novel antischistosomal therapeutics","authors":"Mustafa Alhaji Isa,&nbsp;Abidemi Paul Kappo","doi":"10.1016/j.compbiolchem.2025.108501","DOIUrl":"10.1016/j.compbiolchem.2025.108501","url":null,"abstract":"<div><div>Schistosomiasis, caused by <em>Schistosoma mansoni</em>, remains a significant public health burden, particularly in endemic regions with limited access to effective treatment. The emergence of resistance to praziquantel necessitates the urgent discovery of novel therapeutic targets. This study explores the potential of antimicrobial peptides (AMPs) as inhibitors of the glyceraldehyde-3-phosphate dehydrogenase (GAPDH) and triose phosphate isomerase (TPI) protein-protein interaction (PPI) in <em>S. mansoni</em>, a crucial glycolytic pathway component essential for parasite survival. A machine learning-driven approach was employed to filter 3306 AMPs from the Antimicrobial Peptide Database (APD) based on physicochemical properties and predicted binding affinities. Eighteen peptides were selected based on desirable physicochemical attributes and further subjected to molecular docking using HADDOCK 2.4. The results identified AP02590 (-103.5 ± 2.7 kcal/mol) and AP02754 (-87.8 ± 1.0 kcal/mol) as the most promising inhibitors, exhibiting strong binding affinities and stable complex formation compared to the native GAPDH-TPI complex (-77.8 ± 17.2 kcal/mol). Molecular dynamics (MD) simulations confirmed the stability of these complexes, with lower root mean square deviation (RMSD) values (AP02590: ∼2.5 Å, AP02754: ∼3.0 Å) and reduced root mean square fluctuation (RMSF) of key interacting residues. Radius of gyration (Rg) analysis further indicated compact structural stability. MMGBSA analysis validated these findings, showing favourable binding free energies for AP02590 (-50.80 ± 0.90 kcal/mol) and AP02754 (-46.31 ± 0.83 kcal/mol), reinforcing their potential as lead compounds for antischistosomal drug development. These findings provide a foundation for further experimental validation of peptide-based inhibitors targeting metabolic pathways in <em>S. mansoni</em>.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108501"},"PeriodicalIF":2.6,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943557","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":"NABP-LSTM-Att: Nanobody–Antigen binding prediction using bidirectional LSTM and soft attention mechanism","authors":"Fatma S. Ahmed ,&nbsp;Saleh Aly ,&nbsp;Mohamed A.M. El-Tabakh ,&nbsp;Xiangrong Liu","doi":"10.1016/j.compbiolchem.2025.108490","DOIUrl":"10.1016/j.compbiolchem.2025.108490","url":null,"abstract":"<div><div>In vertebrates, antibody-mediated immunity is a vital component of the immune system, and antibodies have become a rapidly expanding class of therapeutic agents. Nanobodies, a distinct type of antibody, have recently emerged as a stable and cost-effective alternative to traditional antibodies. Their small size, high target specificity, notable solubility, and stability make nanobodies promising candidates for developing high-quality drugs. However, the lack of available nanobodies for most antigens remains a key challenge. Advancing the development of nanobodies requires a better understanding of their interactions with antigens to enhance binding affinity and specificity. Experimental methods for identifying these interactions are essential but often costly and time-consuming, posing challenges for developing nanobody therapies. Although several computational approaches have been designed to screen potential nanobodies, their dependency on 3D structures limits their broad application. This research introduces NABP-LSTM-Att, a deep learning model designed to predict nanobody–antigen binding solely from sequence information. NABP-LSTM-Att leverages bidirectional long short-term memory (biLSTM) to capture both long- and short-term dependencies within nanobody and antigen sequences, combined with a soft attention mechanism to focus on key features. When evaluated on nanobody–antigen sequence pairs from the SAbDab-nano database, NABP-LSTM-Att achieved an AUROC of 0.926 and an AUPR of 0.952. Considering the significance of nanobody-based treatments and their prospective uses in immunotherapy and diagnostics, we believe that the proposed model will serve as an effective tool for predicting nanobody–antigen binding.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108490"},"PeriodicalIF":2.6,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929207","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 anti-oxidant and anti-inflammatory study of diverse honey types of Kashmir valley through In Vitro, analytical chemistry and computational approach","authors":"Ruqqaya Javid ,&nbsp;Shahnawaz Ahmad Dar ,&nbsp;Suma Mohan ,&nbsp;Zahoor Ahmad Baba ,&nbsp;Faheem Jeelani Wani ,&nbsp;Munazah Yaqoob ,&nbsp;P.M.Osman Javid ,&nbsp;Shahid Ahmad Padder ,&nbsp;Shabir Ahmad Ganai","doi":"10.1016/j.compbiolchem.2025.108499","DOIUrl":"10.1016/j.compbiolchem.2025.108499","url":null,"abstract":"<div><div>Diverse factors including geographical and floral origin have marked impact on honey parameters. These factors in the long run influence the different activities exerted by honey. Herein, we performed the novel comparative study of five different honey types of Kashmir valley differing in floral origin apart from latitude, longitude and altitude. Following the rigorous comparison of their antioxidant and anti-inflammatory activity through <em>In vitro</em> study, the most promising honey was screened for various molecules using high-resolution liquid chromatography mass spectrometry (HR-LCMS) approach. Moreover, the identified molecules were docked against the inflammation implicated molecular targets namely histone deacetylase (HDAC)-3 and cyclooxygenase-2 (COX-2). Eventually, the binding free energy assessment was performed using conventional and thermal molecular mechanics with generalized Born surface area (MM-GBSA). The maximum binding affinity demonstrating molecule was evaluated for stability and compatibility with COX-2 by making the use of extended molecular dynamics simulation method. This study proved <em>Robinia pseudoacacia</em> honey has the maximum potential for alleviating the free radicals and inflammation. Further, the luteolin and genistein confirmed through HR-LCMS evinced the highest propensity of binding towards COX-2 and HDAC3 respectively.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108499"},"PeriodicalIF":2.6,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929208","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":"iEnhancer-DS: Attention-based improved densenet for identifying enhancers and their strength","authors":"Yongxian Fan,&nbsp;Chen Wang,&nbsp;Guicong Sun","doi":"10.1016/j.compbiolchem.2025.108484","DOIUrl":"10.1016/j.compbiolchem.2025.108484","url":null,"abstract":"<div><div>Enhancers are short DNA fragments that enhance gene expression by binding to transcription factors. Accurately identifying enhancers and their strength is crucial for understanding gene regulation mechanisms. However, traditional enhancer sequencing techniques are costly and time-consuming. Therefore, it is necessary to develop computational methods to quickly and accurately identify enhancers and their strength. Given the limitations of existing computational methods, such as low performance and complex encoding, this study proposes a deep learning-based multi-task framework, iEnhancer-DS, for enhancer identification and their strength classification. First, feature embeddings characterizing DNA sequences are obtained using one-hot encoding and nucleotide chemical properties (NCP). Next, an improved DenseNet module is applied to learn implicit high-order features from the concatenated feature embeddings. Subsequently, the self-attention mechanism is used to dynamically assess the importance of features and assign weights to them, and then the features are passed to the multilayer perceptron (MLP) to calculate the prediction probabilities. Experimental results show that iEnhancer-DS achieves state-of-the-art performance in both enhancer identification and strength prediction. In the enhancer identification task, iEnhancer-DS improves ACC and MCC by 4.03% and 8.47% respectively over the current state-of-the-art methods. Similarly, in the enhancer strength prediction task, the ACC and MCC values of iEnhancer-DS increased by 1.40% and 3.81%, respectively. In addition, we used the t-SNE method to perform an interpretable analysis of the mechanism of action of iEnhancer-DS. The detailed code and raw data of iEnhancer-DS can be obtained from <span><span>https://github.com/zha12ja/iEnhancer-DS</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108484"},"PeriodicalIF":2.6,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929210","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":"Asymmetric drug interaction prediction via multi-scale fusion of directed topological relationships and drug features","authors":"Kaibiao Lin ,&nbsp;Fengxin Huang ,&nbsp;Shuangta Zhuo ,&nbsp;Qiqi Zhou ,&nbsp;Dawei Pan ,&nbsp;Shenbao Yu ,&nbsp;Fan Yang","doi":"10.1016/j.compbiolchem.2025.108491","DOIUrl":"10.1016/j.compbiolchem.2025.108491","url":null,"abstract":"<div><div>Drug-drug interactions (DDIs), particularly asymmetric DDIs, pose a critical challenge to patient safety, potentially leading to severe side effects or reduced therapeutic efficacy in combination therapies. However, existing models largely overlook the directionality of interactions and fail to capture the multi-scale topological relationships among drugs, which are crucial in reflecting both local and global interaction patterns within directed drug-drug interaction (DDI) networks. To address these gaps, we propose ADI-MSF, a novel asymmetric DDI prediction model. ADI-MSF integrates directed topological information and drug self-features through a dual-channel multi-scale encoder. The topological encoder utilizes a multi-layer graph attention network to extract first- and second-order directed neighborhood embeddings, whereas the feature encoder employs an autoencoder to generate multi-scale drug representations. These representations were fused using summation and the Hadamard product to form comprehensive drug pair embeddings for downstream predictions. Experiments on two real-world datasets, covering asymmetric DDI prediction (Task 1) and direction prediction (Task 2), demonstrated the superior performance of ADI-MSF, achieving over 95% accuracy and F1 scores for Task 1 and over 92% F1 for Task 2. Ablation studies confirmed the significance of each module, whereas case studies validated the effectiveness of modeling asymmetric DDIs. The source code and data are available at <span><span>https://github.com/FengxinHuang/ADI-MSF</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108491"},"PeriodicalIF":2.6,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143903788","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}