Aims: Circular RNAs (circRNAs) act as vital miRNA sponges and participate in the pathogenesis of various complex diseases. Most existing computational methods focus on sequence-level prediction of circRNA-miRNA interactions, while few tools can accurately locate interaction sites at the nucleotide level.

Methods: In this study, we propose CMIFCG, a novel model combining fully convolutional neural networks (FCN) and bidirectional gated recurrent units (BiGRU) for nucleotide-level prediction of circRNA-miRNA interaction sites. We adopted one-hot encoding for sequence preprocessing, utilized stacked convolutional modules to extract high-order features, and integrated BiGRU to capture sequential association features. The decoding module with skip connections restores feature maps to the original sequence size for precise site prediction. We constructed four datasets with different sequence lengths and negative samples to evaluate model performance.

Results: Experimental results show that CMIFCG achieves optimal performance than other baseline models, and excessive module stacking causes performance degradation. Motif analysis confirms that the predicted motifs match well with known miRNA sequences. Partial predicted interactions are further verified via public databases.

Conclusion: In summary, CMIFCG model enables effective fine-grained identification of circRNA-miRNA interaction sites, providing a new tool for exploring circRNA regulatory mechanisms and disease-related molecular pathways.

Polycystic ovary syndrome (PCOS) is a heterogeneous endocrine and metabolic disorder, in which the interaction between insulin resistance (IR) and hyperandrogenism (HA) is a major driver of reproductive and metabolic complications. Accumulating evidence suggests that chromatin remodeling may represent a regulatory layer linking metabolic stress, inflammation, steroidogenic gene expression, and androgen receptor activity. Research indicates that chromatin remodeling may be a key regulatory factor linking metabolic stress, inflammation, steroidogenic gene expression, and androgen receptor activity. This review systematically summarizes current evidence on chromatin remodeling in PCOS-related IR and HA, focusing on histone modifications, DNA methylation, ATP-dependent remodeling complexes, transcription factors, and non-coding RNA-mediated regulation. We distinguish between direct evidence from PCOS tissues and cells and indirect evidence from metabolic, endocrine, and hormone-responsive disease models, proposing a hierarchy of evidence. Available data suggest that chromatin remodeling may influence insulin signaling genes, adipogenesis, ovarian steroidogenic enzymes, and co-transcriptional networks involving Forkhead box protein O1 (FOXO1), Peroxisome Proliferator-Activated Receptor γ (PPARγ), nuclear factor-kappa B (NF-κB), androgen receptor (AR) signaling, and SWI/SNF-related complexes. However, PCOS-specific functional validation remains limited, particularly in theca cells, granulosa cells, adipose tissue, and cell-type-resolved chromatin. Integrating multi-omics, single-cell epigenomics, and CRISPR-based epigenome editing may help identify causal chromatin regulators and clinically relevant PCOS subtypes. We further discuss how computational biomedical approaches, including bioinformatics, Artificial Intelligence (AI), machine learning, and multi-omics integration, can enhance mechanistic inference, biomarker discovery, and PCOS subtype stratification. A chromatin-centric framework may deepen our understanding of the IR-HA cycle and support future biomarker discovery and precision interventions in PCOS.

Aims: Cervical cancer is the second most common cancer globally in women of reproductive age. Current immunotherapies offer only moderate improvement in overall survival for metastatic or refractory disease, highlighting the need for more effective, patient-directed immunotherapies.

Methods: A unified pipelinereprocessed all The Cancer Genome Atlas (TCGA) and genotype tissue expression (GTEx) samples from raw reads using identical alignment and quantification parameters to screen a curated set of 259 high-confidence surface protein genes. This analysis provided the foundation for selecting differentially overexpressed cell surface receptors as potential antibody-drug conjugate (ADCs) targets . Recombinant single chain variable fragment (scFv)-O6-alkylguanine-DNA alkyltransferase (SNAP) fusion proteins were expressed, purified and characterised using immunoblotting. The dose-dependent and selective cytotoxicity of an auristatin F-conjugated (scFv)-SNAP fusion protein was verified in vitro.

Results: Bioinformatic screening revealed 30 potential targets overexpressed in cervical carcinoma (Cervical Squamous Cell Carcinoma and Endocervical Adenocarcinoma (CESC)) vs. healthy tissues. Tissue-of-origin analysis (endocervix vs. ectocervix) further refined priorities. These results, together with supporting evidence from the literature, justified drug production.. The (scFv)-SNAP fusion proteins exhibited strong surface binding across cervical cancer cell lines and, when conjugated to auristatin F, showed dose-dependent cytotoxicity at nanomolar concentrations, confirming the differences observed in transcriptomic analyses of endo- vs. ectocervix profiling.

Conclusion: Bioinformatics and in vitro validation synergize powerfully from initial screening through subtype refinement to iterative target confirmation, enabling a precision medicine approach for cervical cancer-specific immunotherapies. The (scFv)-SNAP-auristatin F (ADC) conjugates reproduced this refinement, showing highly promising potential.

Aims: Translating pre-clinical findings into clinical evidence is essential for cancer research. Although succinyl-CoA ligase ADP-forming subunit beta (SUCLA2) has been implicated in metastasis through stress granule assembly in pre-clinical models, direct clinical evidence linking SUCLA2, alone or in interaction with stress granule components such as ubiquitin-specific peptidase 10 (USP10), to distant metastasis-free survival (DMFS) remains limited. This study aimed to evaluate whether the SUCLA2-USP10 interaction correlates with breast cancer DMFS and whether treatment modifies this association.

Methods: We analyzed four independent breast cancer cohorts with DMFS data (GSE17705, GSE45255, GSE7390, and GSE11121). Patients were stratified into four subgroups based on median SUCLA2 and USP10 expression levels: low-SUCLA2/low-USP10 (LL), low-SUCLA2/high-USP10 (LH), high-SUCLA2/low-USP10 (HL), and high-SUCLA2/high-USP10 (HH). Stratified Cox regression was applied, with cohort as the stratification factor, to examine whether the prognostic impact of these subgroups differed between treated and untreated patients.

Results: A significant interaction was observed between treatment status and SUCLA2-USP10 subgroup membership, specifically for the LH subgroup (p = 0.00038). In untreated patients, the LH subgroup exhibited a significantly higher risk for DMFS (HR = 2.45), whereas in treated patients, this elevated risk was completely abrogated (HR = 0.71). Neither SUCLA2 nor USP10 alone showed a consistent association with DMFS across the four cohorts.

Conclusion: These findings provide clinical evidence that the SUCLA2-USP10 interaction, rather than either factor alone, correlates with breast cancer DMFS. The treatment-modulated risk reversal observed in the LH subgroup supports the development of anti-metastatic strategies targeting this interaction.

Antibody polyreactivity refers to the ability of a monoclonal antibody to non-specifically bind to a diverse range of antigens. While this property may be an intrinsic mechanism of the immune response, it poses significant challenges in therapeutic antibody development, often leading to off-target effects, poor pharmacokinetics, and potential toxicity. This review compiles the data resources related to polyreactive antibodies and places a particular emphasis on computational models for predicting antibody polyreactivity. The latter includes empirical models based on physicochemical properties, traditional machine learning models, deep learning networks, and protein language models. Through delineating the complexity of antibody polyreactivity, this review emphasizes the critical role and growing potential of computational prediction tools in selecting and engineering antibody drug candidates at early stages, thereby reducing development risks and accelerating the development of safer and better therapeutic antibodies.

Aims: Circular RNAs (circRNAs) have been shown to be closely associated with the occurrence and progression of various diseases. However, most existing circRNA-disease association prediction methods are limited to homogeneous networks and are unable to effectively capture deep semantic associations through high-order meta-paths. This study aims to develop an efficient computational method for accurately predicting potential circRNA-disease associations.

Methods: We propose a meta-relation-aware heterogeneous graph learning framework for circRNA-disease association prediction. Specifically, known circRNA-disease associations are first used to compute Gaussian interaction profile kernel similarity and extract node attribute features, based on which a heterogeneous graph network is constructed. A graph neural network is then employed to perform multi-layer message passing on the heterogeneous graph, aggregating neighborhood information to achieve deep fusion of multi-source features and generate node embeddings that encode both local and global structural information. Finally, the learned embeddings are fed into a gradient boosting decision tree classifier, and an ensemble strategy is adopted to improve prediction accuracy. Five-fold cross-validation is used for performance evaluation.

Results: Experimental results on three benchmark datasets, CircR2Disease V2.0, circAtlas 3.0, and circRNADisease V2.0, show that the proposed model achieves area under the receiver operating characteristic curve (AUC) values of 92.17%, 91.83%, and 91.73%, respectively. The model outperforms traditional methods in terms of accuracy, precision, and recall. Furthermore, ablation studies validate the effectiveness of the meta-relation-aware strategy.

Conclusions: Overall, this work provides an efficient and reliable computational framework for molecular association prediction and biomarker discovery in the biomedical domain.

Aims: Alternative splicing serves as a primary mechanism for diversifying the proteome, making the prediction of distinct isoform functions critical for understanding complex disease mechanisms. However, determining the specific functional roles of isoforms remains hindered by high sequence homology among variants and the sparsity of isoform-level annotations.

Methods: In this study, we propose SpliceEM, a deep learning framework for isoform function prediction at single-cell resolution. SpliceEM utilizes a splicing event-aware encoder with cross-modal attention to separate functional signals from global protein sequences. A Heterogeneous Graph Transformer captures the dependencies among isoforms, genes, and Gene Ontology terms. To bridge the annotation gap, we incorporate a self-distillation framework guided by an Exponential Moving Average teacher model and Multi-Instance Learning, optimized by an Asymmetric Loss and hierarchical constraints.

Results: Benchmarking on human datasets demonstrates that SpliceEM outperforms existing methods in isoform function prediction, particularly in identifying rare functional terms under data-sparse conditions. Furthermore, splicing-function analysis reveals that specific splicing events, such as skipped exons and alternative first exons, act as prominent drivers in oncogenic signaling cascades and context-specific functional switching.

Conclusion: SpliceEM provides a computational foundation for exploring transcriptomic functional diversity. By shifting the focus from global sequences to localized splicing events and utilizing hierarchical biological priors, it offers high-resolution insights into cell-type-specific molecular mechanisms and potential therapeutic targets.