BMC Bioinformatics最新文献_第2页

MultiOmicsXplorer, a tool to browse, access and analyse multi-omics data. multiomicsxexplorer，一个浏览、访问和分析多组学数据的工具。

IF 3.3 3区生物学

BMC Bioinformatics Pub Date : 2026-04-25 DOI: 10.1186/s12859-026-06460-w

Eleonora Meo, Veronica Lombardi, Veronica Venafra, Valerio Licursi, Francesca Sacco, Livia Perfetto

引用次数: 0

DCI-SiteDTA: drug-target affinity prediction based on binding sites detection and site-aware dual cross-interaction block. DCI-SiteDTA：基于结合位点检测和位点感知双交叉相互作用块的药物靶标亲和力预测。

IF 3.3 3区生物学

BMC Bioinformatics Pub Date : 2026-04-24 DOI: 10.1186/s12859-026-06446-8

Jinyang Zhang, Xingyang Li, Bo Wei, Yuni Zeng

引用次数: 0

FiloAnalyzer: a deep learning approach for cell filopodia segmentation. FiloAnalyzer：用于细胞丝状伪足分割的深度学习方法。

IF 3.3 3区生物学

BMC Bioinformatics Pub Date : 2026-04-24 DOI: 10.1186/s12859-026-06437-9

Vito Paolo Pastore, Riccardo Rorato, Larbi Touijer, Roberto Di Via, Francesca Odone, Lisa M Galli, Laura W Burrus, Simone Bianco

引用次数: 0

Protein and ligand novelty in drug-target interaction prediction: a dual-encoder fusion strategy for more interpretable and generalizable modeling. 蛋白质和配体在药物靶标相互作用预测中的新颖性：一种双编码器融合策略，用于更可解释和可推广的建模。

IF 3.3 3区生物学

BMC Bioinformatics Pub Date : 2026-04-22 DOI: 10.1186/s12859-026-06457-5

Lina Abou-Abbas, Khadidja Henni

{"title":"Protein and ligand novelty in drug-target interaction prediction: a dual-encoder fusion strategy for more interpretable and generalizable modeling.","authors":"Lina Abou-Abbas, Khadidja Henni","doi":"10.1186/s12859-026-06457-5","DOIUrl":"https://doi.org/10.1186/s12859-026-06457-5","url":null,"abstract":"Predicting drug-target interactions (DTIs) is a fundamental task in computational drug discovery, where reliable generalization to novel compounds and protein targets is essential for practical virtual screening and drug repurposing. However, most deep learning models are evaluated using random or single-split settings that fail to reflect the ligand and protein novelty conditions encountered in real-world discovery pipelines. This work proposes a dual-encoder fusion framework for robust and interpretable DTI prediction. The model combines pretrained ESM protein embeddings with two complementary ligand representations: a ChemBERTa-based molecular language encoder and a graph-based structural encoder. Predictions from both branches are integrated through decision-level fusion. To rigorously evaluate generalization, we adopt a novelty-aware protocol that isolates ligand novelty, protein novelty, and their joint occurrence. A ligand-centered, gradientbased interpretability analysis is also employed to examine how molecular substructures contribute to binding predictions. Experiments on the largescale BindingDB dataset show that ligand novelty induces minimal performance degradation, with strong results under warm and cold-drug settings (F1 = 0.84-0.87; AUC = 0.87-0.89). In contrast, protein novelty emerges as the dominant generalization bottleneck, producing the largest performance drops under cold-protein and double-cold conditions. Across all scenarios, the fusion model exhibits the most stable behavior, achieving an AUC of 0.90 in the warm setting. External validation on the Davis and KIBA datasets further demonstrates consistent AUC values (0.60-0.64) and high recall despite substantial biochemical domain shift. These results highlight the importance of novelty-aware evaluation and show that decision-level fusion provides a practical pathway toward reliable and interpretable DTI prediction.","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147761098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reindeer: a protein-ligand feature generator software for machine learning algorithms. 驯鹿：一个蛋白质配体特征生成器软件，用于机器学习算法。

IF 3.3 3区生物学

BMC Bioinformatics Pub Date : 2026-04-22 DOI: 10.1186/s12859-026-06452-w

Milad Rayka, S Shahab Naghavi

引用次数: 0

TransBindpMHCI: a transformer-based model for pan-specific MHC-I peptide binding prediction. TransBindpMHCI：基于转换器的泛特异性MHC-I肽结合预测模型。

IF 3.3 3区生物学

BMC Bioinformatics Pub Date : 2026-04-20 DOI: 10.1186/s12859-026-06423-1

Hu Xu, Yuanli Ni, Zixuan Chai, Xuan Cui, Xia Lei, Limei Liu, Juanjuan Shan, Cheng Qian

引用次数: 0

Enhancing genomic prediction accuracy in Huaxi cattle through integration of transcriptomic data and a self-attention-based SNP selection strategy. 通过整合转录组学数据和基于自我注意的SNP选择策略提高华西牛基因组预测的准确性。

IF 3.3 3区生物学

BMC Bioinformatics Pub Date : 2026-04-18 DOI: 10.1186/s12859-026-06443-x

Li Qian, Lili Du, Mang Liang, Keanning Li, Jinbu Wang, Shiyuan Qiu, Meng Mao, Lupei Zhang, Xue Gao, Lingyang Xu, Caihong Zheng, Bo Zhu, Yan Chen, Zezhao Wang, Junya Li, Huijiang Gao

引用次数: 0

Genomica: linear mixed model based, multiple hypothesis testing corrected, ortholog functional enrichment analysis. 基因组：基于线性混合模型，修正多个假设检验，同源功能富集分析。

IF 3.3 3区生物学

BMC Bioinformatics Pub Date : 2026-04-18 DOI: 10.1186/s12859-026-06450-y

Salvatore Galgano

{"title":"Genomica: linear mixed model based, multiple hypothesis testing corrected, ortholog functional enrichment analysis.","authors":"Salvatore Galgano","doi":"10.1186/s12859-026-06450-y","DOIUrl":"https://doi.org/10.1186/s12859-026-06450-y","url":null,"abstract":"Background: The analysis of ortholog genes derived from metagenomic experiments provides an invaluable opportunity to assess the functional role of microbial communities towards, for example, antimicrobial resistance or biochemical pathways under different experimental conditions. Nevertheless, the integration of the statistical analysis of these complex data sets and the enrichment of the derived significantly differential abundant orthologs is not currently facilitated by existing software. Genomica is an R package that, with minimal input from the user, allows to perform a double-step analysis of functional orthologs from the KEGG Orthology. The pipeline is carried out via combining false discovery rate corrected linear mixed models to functional enrichment analysis through integrating established R pipelines (i.e., lme4 and MicrobiomeProfiler).Results: Only two data frames are needed as input to run Genomica, which contain data and metadata, respectively. The fast pipeline integrated within the function Genomica allows to analyze 4000 orthologs in circa 3 min. The outputs are collected in a single directory, containing publication-ready results from the linear mixed model and from the enrichment analysis. The Benjamini & Hochberg correction is applied to the results from the linear mixed model, therefore only P adjusted significant comparisons are further included in the enrichment analysis.Conclusions: Genomica is a simple-to-use R package to analyze complex datasets, integrating a well-founded statistical analysis, accounting for the calculation of the type I error under repeated testing, with the enrichment analysis of the significantly differential abundant orthologs across experimental conditions, all with minimal input from the user.","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":" ","pages":""},"PeriodicalIF":3.3,"publicationDate":"2026-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147715758","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reciprocal best matching: a new pipeline for scoring models with unknown stoichiometry in CASP experiments. 互惠最佳匹配：CASP实验中未知化学计量的评分模型的新管道。

IF 3.3 3区生物学

BMC Bioinformatics Pub Date : 2026-04-17 DOI: 10.1186/s12859-026-06439-7

Rongqing Yuan, Jing Zhang, Qian Cong

引用次数: 0

A novel IVN-entropy based distance-driven MARCOS framework for evaluating and ranking global green hydrogen-producing countries. 一种基于ivn -熵的距离驱动MARCOS框架，用于全球绿色产氢国的评价和排名。

IF 3.3 3区生物学

BMC Bioinformatics Pub Date : 2026-04-16 DOI: 10.1186/s12859-026-06425-z

Venkata Prasanna Nagari, Vinoth Subbiah

引用次数: 0