Computational and structural biotechnology journal最新文献

{"title":"The role of microglia and complement C5/C5a in the pathogenesis of rhegmatogenous retinal detachment with choroidal detachment.","authors":"Huiyan Xu, Qiuhong Wang, Xuan Chen, Qingyu Huang, Shasha Xu, Zhifeng Wu","doi":"10.1016/j.csbj.2025.08.019","DOIUrl":"10.1016/j.csbj.2025.08.019","url":null,"abstract":"<p><strong>Background: </strong>Rhegmatogenous retinal detachment with choroidal detachment (RRDCD) is an uncommon and sight-threatening disorder marked by fast development and significant inflammation. This study aimed to identify cellular and molecular signatures distinguishing RRDCD from typical rhegmatogenous retinal detachment (RRD) and to investigate the roles of microglia and the complement C5/C5a pathway in disease pathogenesis.</p><p><strong>Methods: </strong>Single-cell RNA sequencing (scRNA-seq) was employed to analyze vitreous samples from patients with RRD and RRDCD to characterize the cellular composition and molecular pathways. In vitro co-culture experiments were performed to investigate the functional impact of complement C5 on primary retinal microglia, and their subsequent effects on RF/6 A endothelial cells and ARPE-19 epithelial cells.</p><p><strong>Results: </strong>Our findings revealed a distinct cellular landscape in RRDCD, characterized by enhanced connectivity between microglia and dendritic cells, alongside a significant upregulation of the complement C5-C5AR1 interaction. In vitro experiments indicated that treatment with complement C5 enhanced microglial metabolic activity and activation, induced apoptosis in RF/6 A endothelial cells, and led to disruption of tight junction protein ZO-1 localization in ARPE-19 epithelial cells, suggesting a role in blood-retina barrier dysfunction.</p><p><strong>Conclusion: </strong>The findings substantiate the inflammatory hypothesis regarding the pathogenesis of RRDCD, emphasizing the critical functions of microglia and the complement C5/C5a pathway in intensifying retinal inflammation and undermining vascular integrity.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"3804-3813"},"PeriodicalIF":4.1,"publicationDate":"2025-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12454608/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145136639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A quartet-based approach for inferring phylogenetically informative features from genomic and phenomic data.","authors":"Vivian B Brandenburg, Ben Luis Hack, Axel Mosig","doi":"10.1016/j.csbj.2025.08.015","DOIUrl":"10.1016/j.csbj.2025.08.015","url":null,"abstract":"<p><p>Neural networks are widely used in bioinformatics to extract features from morphological, structural, and sequence data of different taxa. A key question is whether such features are compatible with a known phylogenetic tree describing the evolutionary relationships among the taxa. We address this question with a machine learning approach that takes taxon-specific data and a reference tree as input, and trains a neural network to produce a latent feature space whose pairwise distances are consistent with the tree topology. Our approach builds on the established role of quartets in distance-based phylogeny, leading to a quartet-based loss function for neural network training. In a proof-of-concept study using bacterial ribosomal RNA sequences, we show that the learned feature distances closely match the reference phylogeny. This framework can be applied to diverse biological data types, providing a principled way to incorporate phylogenetic constraints into neural network-based feature extraction.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"3710-3718"},"PeriodicalIF":4.1,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12398925/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144945781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Context-informed few-shot molecular property prediction via heterogeneous meta-learning.","authors":"Junhao Xue, Jun Liu, Kai Chen","doi":"10.1016/j.csbj.2025.08.016","DOIUrl":"10.1016/j.csbj.2025.08.016","url":null,"abstract":"<p><p>Molecular property prediction is essential in diversified applications, as it helps identify molecules with the desired characteristics. However, the task often suffers from limited data, making the few-shot learning challenging. We introduce a Context-informed Few-shot Molecular Property Prediction via a Heterogeneous Meta-Learning approach, which employs graph neural networks combined with self-attention encoders to effectively extract and integrate both property-specific and property-shared molecular features, respectively. Based on the property-shared molecular features, we further infer molecular relations by using an adaptive relational learning module. The final molecular embedding is improved by aligning with the property label in the property-specific classifier. Furthermore, we employ a heterogeneous meta-learning strategy that updates parameters of the property-specific features within individual tasks in the inner loop and jointly updates all parameters in the outer loop. This enhances the model's ability to effectively capture both general and contextual information, leading to a substantial improvement in predictive accuracy. The model's performance was rigorously evaluated across various real molecular datasets, showcasing its superiority over current methods, especially in challenging few-shot learning scenarios.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"4173-4182"},"PeriodicalIF":4.1,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12510055/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145279218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Non-invasive maturity assessment of iPSC-CMs based on optical maturity characteristics using interpretable AI.","authors":"Fabian Scheurer, Alexander Hammer, Mario Schubert, Robert-Patrick Steiner, Oliver Gamm, Kaomei Guan, Frank Sonntag, Hagen Malberg, Martin Schmidt","doi":"10.1016/j.csbj.2025.08.024","DOIUrl":"10.1016/j.csbj.2025.08.024","url":null,"abstract":"<p><p>Human induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs) are an important resource for identifying novel therapeutic targets and cardioprotective drugs. However, a key limitation of iPSC-CMs is their immature, fetal-like phenotype. Cultivation of iPSC-CMs in lipid-supplemented maturation media (MM) enhances the structural, metabolic and electrophysiological properties of iPSC-CMs. Nevertheless, they face substantial limitations as there are labor-intensive, time consuming and go in line with cell damage or loss of the sample. To address this issue, we have developed a non-invasive approach for automated classification of iPSC-CM maturity through interpretable artificial intelligence (AI)-based analysis of beat characteristics derived from video-based motion analysis. In a prospective study, we evaluated 230 video recordings of early-state, immature iPSC-CMs on day 21 after differentiation (d21) and more mature iPSC-CMs cultured in MM (d42, MM). For each recording, 10 features were extracted using Maia motion analysis software and entered into a support vector machine (SVM). The hyperparameters of the SVM were optimized in a grid search on 80 % of the data using 5-fold cross-validation. The optimized model achieved an accuracy of 99.5 ± 1.1 % on a hold-out test set. Shapley Additive Explanations (SHAP) identified displacement, relaxation-rise time and beating duration as the most relevant features for assessing iPSC-CM maturity. Our results suggest the use of non-invasive, optical motion analysis combined with AI-based methods as a tool to assess iPSC-CMs maturity and could be applied before performing functional readouts or drug testing. This may potentially reduce the variability and improve the reproducibility of experimental studies.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"3719-3728"},"PeriodicalIF":4.1,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12409467/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145014051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital cousins: Simultaneous optimization of one model for BMP signaling in distant relatives reveals essential core.","authors":"Linlin Li, Thembi Mdluli, Gregery Buzzard, David Umulis","doi":"10.1016/j.csbj.2025.08.021","DOIUrl":"10.1016/j.csbj.2025.08.021","url":null,"abstract":"<p><p>Spatially distributed, nonuniform morphogen gradients play a crucial role in tissue organization during development across the animal kingdom. The Bone Morphogenetic Protein (BMP) pathway, a well-studied morphogen involved in dorsal-ventral (D-V) axis patterning, has been extensively studied in zebrafish, <i>Drosophila</i>, and other organisms. Given that this pathway is highly conserved in both form and function, we sought to determine whether a core mathematical model that constrained topology and biophysical parameters could fully reproduce the observed dynamics of gradient formation in both <i>Drosophila</i> and zebrafish through changes in expression only. We used multi-objective optimization to simultaneously fit a single core model to <i>Drosophila</i> and zebrafish data and conditions. By exploring a single model with varied parameters, we identified both the homology and diversification of the BMP pathway. We find that variation in a small subset of parameters-particularly diffusion-related rates-can reconcile the experimentally measured BMP gradients in both species under wild-type conditions, whereas fitting both WT and mutant conditions requires additional species-specific regulatory extensions beyond the core model. This approach, involving simulation and multispecies optimization, provides a systematic method to explore the minimal parametric variations needed to account for interspecies differences in a developmental pathway. Rather than making predictive claims, our finding offers a framework for improving the interpretability and translational relevance of cross-species models.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"3729-3741"},"PeriodicalIF":4.1,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12445611/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145111448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A semi-mechanistic mathematical framework for simulating multi-hormone dynamics in reproductive endocrinology.","authors":"Alexandre Vallée, Anis Feki, Gaby Moawad, Jean-Marc Ayoubi","doi":"10.1016/j.csbj.2025.08.013","DOIUrl":"10.1016/j.csbj.2025.08.013","url":null,"abstract":"<p><strong>Background: </strong>The dynamic interplay of ovarian hormones is central to reproductive physiology, yet the complexity of their cyclic variations poses challenges for analysis, simulation, and teaching. This study presents a framework for generating physiologically constrained, multi-hormone synthetic time series that capture intra- and inter-individual variability across phenotypes.</p><p><strong>Methods: </strong>We developed a semi-mechanistic mathematical framework to generate synthetic multi-hormone profiles (estradiol, FSH, LH, AMH, testosterone, GnRH) using parametric equations embedding known physiological feedbacks (e.g., estradiol-LH delay, estradiol suppression of FSH). Stochastic components were calibrated to reported physiological ranges. Eumenorrheic and PCOS-like phenotypes were defined through parameter adjustments. Data were analysed using Principal Component Analysis (PCA) for phenotype separation, and evaluated in a supervised setting using logistic regression with stratified train/test splitting, reporting accuracy, sensitivity, specificity, and ROC AUC.</p><p><strong>Results: </strong>Eumenorrheic profiles displayed classical mid-cycle estradiol and LH peaks, biphasic FSH, and stable AMH and testosterone levels. In contrast, PCOS profiles showed elevated LH and testosterone, high AMH, blunted estradiol, and dysregulated GnRH pulsatility. PCA revealed clear separation between phenotypes (PC1 +PC2 = 82 % variance), and k-means clustering (k = 2) accurately grouped individuals without label information. PCA showed clear separation between phenotypes, consistent with known endocrine patterns. Logistic regression achieved 100 % accuracy, sensitivity, and specificity, with an AUC of 1.00, confirming robust, phenotype-discriminative features in the synthetic dataset.</p><p><strong>Conclusion: </strong>This simulation framework reproduces physiologically accurate hormone dynamics and discriminates ovulatory from anovulatory cycles, offering applications in AI training, phenotype discovery, and medical education.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"3654-3662"},"PeriodicalIF":4.1,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12395073/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144945754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evolutionary trajectory estimation via replication simulation of coronavirus spike gene based on random mutation and similarity-based selection.","authors":"Min Chan Kim, Hye Ji Jung, Seong Sik Jang, Van Thi Lo, Hye Kwon Kim","doi":"10.1016/j.csbj.2025.08.012","DOIUrl":"10.1016/j.csbj.2025.08.012","url":null,"abstract":"<p><p>Viruses exhibit rapid evolutionary dynamics through random mutations and selection, driving their adaptation and cross-species transmission. To investigate these mechanisms, we designed a simulation framework with a graphical user interface (GUI), implementing random mutation and similarity-based selection. This system models the evolution of a user-supplied viral sequence toward a designated target by recursively selecting the top-N amino acid sequences with the greatest similarity in each replication cycle. Simulations tracking the evolution of SARS-CoV-2 Wuhan-Hu-1 toward the Omicron variant (BA.1) displayed plateau-like similarity trajectories, where increased substitution rates resulted in a more rapid attainment of the plateau stage. The model-generated intermediate spike sequences exhibited similarities to real-world evolutionary patterns, including B, B.1.2, B.1.160, B.1.398, B.1.1.529, and BA.1 lineages. Additionally, the approach replicated the divergent evolutionary outcomes of PEDV subjected to distinct selection regimes (with and without trypsin treatment). While the model is simplified, it provides a means to explore plausible viral evolutionary paths and may contribute to identifying potential intermediates relevant to zoonotic spillover. Integrating features such as recombination, population-level effects, and further biological constraints could substantially enhance its predictive power in future iterations.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"3663-3672"},"PeriodicalIF":4.1,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12395072/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144945684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel decoding strategy for ProteinMPNN to design with less visibility to cytotoxic T-lymphocytes.","authors":"Hans-Christof Gasser, Ajitha Rajan, Javier A Alfaro","doi":"10.1016/j.csbj.2025.07.055","DOIUrl":"10.1016/j.csbj.2025.07.055","url":null,"abstract":"<p><p>Due to their versatility and diverse production methods, proteins have attracted a lot of interest for industrial as well as therapeutic applications. Designing new therapeutics requires careful consideration of immune responses, particularly the cytotoxic T-lymphocyte (CTL) reaction to intra-cellular proteins. In this study, we introduce CAPE-Beam, a novel decoding strategy for the established ProteinMPNN protein design model. Our approach minimizes CTL immunogenicity risk by limiting designs to only consist of kmers that are either predicted not to be presented to CTLs or are subject to central tolerance that prevents CTLs from attacking self-peptides. We compare CAPE-Beam to the standard way of sampling from ProteinMPNN and the state of the art (SOTA) technique CAPE-MPNN. We find that our novel decoding strategy can produce structurally similar proteins while incorporating more human like kmers. This significantly lowers CTL immunogenicity risk in precision medicine, and represents a key step towards reducing this risk in protein therapeutics targeting a wider patient population. Source: https://github.com/hcgasser/CAPE_Beam.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"3693-3703"},"PeriodicalIF":4.1,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12396444/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144945736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"scAGG: Sample-level embedding and classification of Alzheimer's disease from single-nucleus data.","authors":"T Verlaan, G A Bouland, A Mahfouz, M J T Reinders","doi":"10.1016/j.csbj.2025.08.009","DOIUrl":"10.1016/j.csbj.2025.08.009","url":null,"abstract":"<p><p>Identifying key cell types and genes in Alzheimer's Disease (AD) is crucial for understanding its pathogenesis and discovering therapeutic targets. Single-cell RNA sequencing technology (scRNAseq) has provided unprecedented opportunities to study the molecular mechanisms that underlie AD at the cellular level. In this study, we address the problem of sample-level classification of AD using scRNAseq data, where we predict the disease status of entire samples from the gene expression profiles of their cells, which are not necessarily all affected by the disease. We introduce scAGG (single-cell AGGregation), a sample-level classification model that uses a sample-level pooling mechanism to aggregate single-cell embeddings, and show that it can accurately classify AD individuals and healthy controls. We then investigate the latent space learnt by the model and find that the model learns an ordering of the cells corresponding to disease severity. Genes associated with this ordering are enriched in AD-linked pathways, including cytokine signalling, apoptosis, and metal ion response. We also evaluate two attention-based models that perform on par with scAGG, but entropy analysis of their attention scores reveals limited interpretability value. As scRNAseq is increasingly applied to large cohorts and cell-level disease association annotations do not exist, our approach provides a way to classify phenotypes from single-cell measurements. The yielded cell- and sample-level severity scores may enable identification of AD-associated cell subtypes, paving the way for targeted drug development and personalized treatment strategies in AD. Code is available at: https://github.com/timoverlaan/scAGG.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"3753-3761"},"PeriodicalIF":4.1,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12448040/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145111698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"pyCAST, a Python package for the detection of cavities on surface proteins.","authors":"Giorgio Luciano, Ulderico Fugacci, Silvia Biasotti","doi":"10.1016/j.csbj.2025.07.054","DOIUrl":"10.1016/j.csbj.2025.07.054","url":null,"abstract":"<p><p>Identifying enzymatic activity sites, signal transduction pathways, and binding sites is crucial in biochemical research, prompting various methodologies. This study introduces pyCAST, a Python package designed to detect cavities on protein surfaces using the CAST methodology, a widely recognized approach for cavity identification. The paper describes the principle of the CAST methods and presents our implementation, including the results achieved over benchmark data sets. Furthermore, it discusses the limitations of the technique and potential future improvements. pyCAST is user-friendly, modular, adaptable to diverse applications, and openly available under the MIT license.</p>","PeriodicalId":10715,"journal":{"name":"Computational and structural biotechnology journal","volume":"27 ","pages":"3589-3597"},"PeriodicalIF":4.1,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12357058/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144871836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}