Transcriptomics in idiopathic pulmonary fibrosis unveiled: a new perspective from differentially expressed genes to therapeutic targets.

Background: The underlying molecular pathways of idiopathic pulmonary fibrosis (IPF), a progressive lung condition with a high death rate, are still mostly unknown. By using microarray datasets, this study aims to identify new genetic targets for IPF and provide light on the genetic factors that contribute to the development of IPF. Method: We conducted a comprehensive analysis of three independent IPF datasets from the Gene Expression Omnibus (GEO) database, employing R software for data handling and normalization. Our evaluation of the relationships between differentially expressed genes (DEGs) and IPF included differential expression analysis, expression quantitative trait loci (eQTL) analysis, and Mendelian Randomization(MR) analyses. Additionally, we used Gene Set Enrichment Analysis (GSEA) and Gene Ontology (GO)/Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis to explore the functional roles and pathways of these genes. Finally, we validated the results obtained for the target genes. Results: We identified 486 highly expressed genes and 468 lowly expressed genes that play important roles in IPF. MR analysis identified six significantly co-expressed genes associated with IPF, specifically C12orf75, SPP1, ZG16B, LIN7A, PPP1R14A, and TLR2. These genes participate in essential biological processes and pathways, including macrophage activation and neural system regulation. Additionally, CIBERSORT analysis indicated a unique immune cell distribution in IPF, emphasized the significance of immunological processes in the disease. The MR analysis was consistent with the results of the analysis of variance in the validation cohort, which strengthens the reliability of our MR findings. Conclusion: Our findings provide new insights into the molecular basis of IPF and highlight the promise of therapeutic interventions. They emphasize the potential of targeting specific molecular pathways for the treatment of IPF, laying the foundation for further research and clinical work.

A novel long non-coding RNA LINC00524 facilitates invasion and metastasis through interaction with TDP43 in breast cancer.

Breast cancer (BC) remains a significant health concern worldwide, with metastasis being a primary contributor to patient mortality. While advances in understanding the disease's progression continue, the underlying mechanisms, particularly the roles of long non-coding RNAs (lncRNAs), are not fully deciphered. In this study, we examined the influence of the lncRNA LINC00524 on BC invasion and metastasis. Through meticulous analyses of TCGA and GEO data sets, we observed a conspicuous elevation of LINC00524 expression in BC tissues. This increased expression correlated strongly with a poorer prognosis for BC patients. A detailed Gene Ontology analysis suggested that LINC00524 likely exerts its effects through RNA-binding proteins (RBPs) mechanisms. Experimentally, LINC00524 was demonstrated to amplify BC cell migration, invasion and proliferation in vitro. Additionally, in vivo tests showed its potent role in promoting BC cell growth and metastasis. A pivotal discovery was LINC00524's interaction with TDP43, which leads to the stabilization of TDP43 protein expression, an element associated with unfavourable BC outcomes. In essence, our comprehensive study illuminates how LINC00524 accelerates BC invasion and metastasis by binding to TDP43, presenting potential avenues for therapeutic interventions.

GO2Sum: generating human-readable functional summary of proteins from GO terms.

Understanding the biological functions of proteins is of fundamental importance in modern biology. To represent a function of proteins, Gene Ontology (GO), a controlled vocabulary, is frequently used, because it is easy to handle by computer programs avoiding open-ended text interpretation. Particularly, the majority of current protein function prediction methods rely on GO terms. However, the extensive list of GO terms that describe a protein function can pose challenges for biologists when it comes to interpretation. In response to this issue, we developed GO2Sum (Gene Ontology terms Summarizer), a model that takes a set of GO terms as input and generates a human-readable summary using the T5 large language model. GO2Sum was developed by fine-tuning T5 on GO term assignments and free-text function descriptions for UniProt entries, enabling it to recreate function descriptions by concatenating GO term descriptions. Our results demonstrated that GO2Sum significantly outperforms the original T5 model that was trained on the entire web corpus in generating Function, Subunit Structure, and Pathway paragraphs for UniProt entries.

Partial order relation-based gene ontology embedding improves protein function prediction.

Protein annotation has long been a challenging task in computational biology. Gene Ontology (GO) has become one of the most popular frameworks to describe protein functions and their relationships. Prediction of a protein annotation with proper GO terms demands high-quality GO term representation learning, which aims to learn a low-dimensional dense vector representation with accompanying semantic meaning for each functional label, also known as embedding. However, existing GO term embedding methods, which mainly take into account ancestral co-occurrence information, have yet to capture the full topological information in the GO-directed acyclic graph (DAG). In this study, we propose a novel GO term representation learning method, PO2Vec, to utilize the partial order relationships to improve the GO term representations. Extensive evaluations show that PO2Vec achieves better outcomes than existing embedding methods in a variety of downstream biological tasks. Based on PO2Vec, we further developed a new protein function prediction method PO2GO, which demonstrates superior performance measured in multiple metrics and annotation specificity as well as few-shot prediction capability in the benchmarks. These results suggest that the high-quality representation of GO structure is critical for diverse biological tasks including computational protein annotation.

Construction and analysis of a joint diagnostic model of machine learning for cryptorchidism based on single-cell sequencing.

BACKGROUND: Cryptorchidism is a condition in which one or both of a baby's testicles do not fully descend into the bottom of the scrotum. Newborns with cryptorchidism are at increased risk of developing infertility later in life. The aim of this study was to develop a novel diagnostic model for cryptorchidism and to identify new biomarkers associated with cryptorchidism. METHODS: The study data were obtained from RNA sequencing data of cryptorchid patients from Nantong University Hospital and the Gene Expression Omnibus (GEO) database. Differential expression analysis was used to obtain differentially expressed genes (DEGs) between the control and cryptorchid groups. These DEGs were analyzed for their functions by Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment using GSEA software. Random Forest algorithm was used to screen central genes based on these DEGs. Neuralnet software package was used to develop artificial neural network models. Based on clinical data, receiver operating characteristic (ROC) was used to validate the models. Single-cell sequencing analysis was used for the pathogenesis of cryptorchidism. RESULTS: We obtained a total of 525 important DEGs related to cryptorchidism, which are mainly associated with biological functions such as supramolecular complexes and microtubule cytoskeleton. Random forest approach screening obtained eight hub genes. A neural network based on the hub genes showed a 100% success rate of the model. Finally, single-cell sequencing analysis validated the hub genes. CONCLUSION: We developed a novel diagnostic model for cryptorchidism using artificial neural networks and validated its utility as an effective diagnostic tool.

Comprehensive analysis of cuproptosis-related genes in immune infiltration and development of a novel diagnostic model for acute kidney injury.

BACKGROUND: Acute kidney injury (AKI) represents a diverse range of conditions characterized by high incidence and mortality rates, and it is mainly associated with immune-mediated mechanisms and mitochondrial metabolism dysfunction. Cuproptosis, a recently identified form of programmed cell death dependent on copper, is closely linked to mitochondrial respiration and contributes to various diseases. Our study aimed to investigate the involvement of cuproptosis-related genes (CRGs) in AKI. METHODS: Identification of CRGs was conducted using differential expression analysis, and subsequent Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were conducted using human sequencing profiles. Utilizing CIBERSORT algorithm, receiver operating characteristic (ROC) curve analysis, nomogram development, and decision curve analysis (DCA), the association among immune scores, CRGs, and the diagnostic value of these genes was explored. RESULTS: Notably, six CRGs (FDX1, DLD, DLAT, DBT, PDHA1, and ATP7A) were identified as significant differentiators between AKI and non-AKI groups. The ROC curve, based on these six genes, demonstrated an AUC value of 0.917, which was further validated using an additional dataset with an AUC value of 0.902. Nomogram and DCA further confirmed the accuracy of the model in predicting the risk of AKI. CONCLUSION: This study elucidated the role of cuproptosis in AKI and revealed the association between CRGs and infiltrated immune cells through comprehensive bioinformatic techniques. The six-gene cuproptosis-related signature exhibited remarkable predictive efficiency for AKI.

Exact p-values for global network alignments via combinatorial analysis of shared GO terms : REFANGO: Rigorous Evaluation of Functional Alignments of Networks using Gene Ontology.

Network alignment aims to uncover topologically similar regions in the protein-protein interaction (PPI) networks of two or more species under the assumption that topologically similar regions tend to perform similar functions. Although there exist a plethora of both network alignment algorithms and measures of topological similarity, currently no "gold standard" exists for evaluating how well either is able to uncover functionally similar regions. Here we propose a formal, mathematically and statistically rigorous method for evaluating the statistical significance of shared GO terms in a global, 1-to-1 alignment between two PPI networks. Given an alignment in which k aligned protein pairs share a particular GO term g, we use a combinatorial argument to precisely quantify the p-value of that alignment with respect to g compared to a random alignment. The p-value of the alignment with respect to all GO terms, including their inter-relationships, is approximated using the Empirical Brown's Method. We note that, just as with BLAST's p-values, this method is not designed to guide an alignment algorithm towards a solution; instead, just as with BLAST, an alignment is guided by a scoring matrix or function; the p-values herein are computed after the fact, providing independent feedback to the user on the biological quality of the alignment that was generated by optimizing the scoring function. Importantly, we demonstrate that among all GO-based measures of network alignments, ours is the only one that correlates with the precision of GO annotation predictions, paving the way for network alignment-based protein function prediction.

Feature engineering from meta-data for prediction of differentially expressed genes: An investigation of Mus musculus exposed to space-conditions.

Transcription profiling is a key process that can reveal those biological mechanisms driving the response to various exposure conditions or gene perturbations. In this work, we investigate the prediction of differentially expressed genes (DEGs) when exposed to conditions in space from a set of diverse engineered features. To do this, we collected DEGs and non-differentially expressed genes (NDEGs) of Mus musculus-based experiments on the GeneLab database. We engineered a diverse set of features from factors reported in the literature to affect gene expression. An extreme gradient boosting (XGBoost) model was trained to predict if a given gene would be differentially expressed at various levels of differential expression. The test results on a separate holdout dataset showed an area under the receiver operating characteristics curves (AUCs) of 0.90±0.07, averaged across the five selected percentages of the most and least differentially expressed genes. Subsequently, we investigated the impact of selection of features, both individually with a correlation-based feature-selection procedure and in groups with a combination procedure, on the prediction performance. The feature selection confirmed some known drivers of adaptation to radiation and highlighted some new transcription factors and micro RNAs (miRNAs). Finally, gene ontology (GO) analysis revealed biological processes that tend to have expression patterns most suitable for this approach. This work highlights the potential of detection of differentially expressed genes using a machine learning (ML) approach, and provides some evidence of gene expression changes being captured by a diverse feature set not related to the condition under study.

The scaffold protein AXIN1: gene ontology, signal network, and physiological function.

AXIN1, has been initially identified as a prominent antagonist within the WNT/ß-catenin signaling pathway, and subsequently unveiled its integral involvement across a diverse spectrum of signaling cascades. These encompass the WNT/ß-catenin, Hippo, TGFß, AMPK, mTOR, MAPK, and antioxidant signaling pathways. The versatile engagement of AXIN1 underscores its pivotal role in the modulation of developmental biological signaling, maintenance of metabolic homeostasis, and coordination of cellular stress responses. The multifaceted functionalities of AXIN1 render it as a compelling candidate for targeted intervention in the realms of degenerative pathologies, systemic metabolic disorders, cancer therapeutics, and anti-aging strategies. This review provides an intricate exploration of the mechanisms governing mammalian AXIN1 gene expression and protein turnover since its initial discovery, while also elucidating its significance in the regulation of signaling pathways, tissue development, and carcinogenesis. Furthermore, we have introduced the innovative concept of the AXIN1-Associated Phosphokinase Complex (AAPC), where the scaffold protein AXIN1 assumes a pivotal role in orchestrating site-specific phosphorylation modifications through interactions with various phosphokinases and their respective substrates.

Insights into the inner workings of transformer models for protein function prediction.

MOTIVATION: We explored how explainable artificial intelligence (XAI) can help to shed light into the inner workings of neural networks for protein function prediction, by extending the widely used XAI method of integrated gradients such that latent representations inside of transformer models, which were finetuned to Gene Ontology term and Enzyme Commission number prediction, can be inspected too. RESULTS: The approach enabled us to identify amino acids in the sequences that the transformers pay particular attention to, and to show that these relevant sequence parts reflect expectations from biology and chemistry, both in the embedding layer and inside of the model, where we identified transformer heads with a statistically significant correspondence of attribution maps with ground truth sequence annotations (e.g. transmembrane regions, active sites) across many proteins. AVAILABILITY AND IMPLEMENTATION: Source code can be accessed at https://github.com/markuswenzel/xai-proteins.

A new experimental evidence-weighted signaling pathway resource in FlyBase.

Research in model organisms is central to the characterization of signaling pathways in multicellular organisms. Here, we present the comprehensive and systematic curation of 17 Drosophila signaling pathways using the Gene Ontology framework to establish a dynamic resource that has been incorporated into FlyBase, providing visualization and data integration tools to aid research projects. By restricting to experimental evidence reported in the research literature and quantifying the amount of such evidence for each gene in a pathway, we captured the landscape of empirical knowledge of signaling pathways in Drosophila.

IDSL.GOA: gene ontology analysis for interpreting metabolomic datasets.

Biological interpretation of metabolomic datasets often ends at a pathway analysis step to find the over-represented metabolic pathways in the list of statistically significant metabolites. However, definitions of biochemical pathways and metabolite coverage vary among different curated databases, leading to missed interpretations. For the lists of genes, transcripts and proteins, Gene Ontology (GO) terms over-presentation analysis has become a standardized approach for biological interpretation. But, GO analysis has not been achieved for metabolomic datasets. We present a new knowledgebase (KB) and the online tool, Gene Ontology Analysis by the Integrated Data Science Laboratory for Metabolomics and Exposomics (IDSL.GOA) to conduct GO over-representation analysis for a metabolite list. The IDSL.GOA KB covers 2393 metabolic GO terms and associated 3144 genes, 1,492 EC annotations, and 2621 metabolites. IDSL.GOA analysis of a case study of older versus young female brain cortex metabolome highlighted 82 GO terms being significantly overrepresented (FDR < 0.05). We showed how IDSL.GOA identified key and relevant GO metabolic processes that were not yet covered in other pathway databases. Overall, we suggest that interpretation of metabolite lists should not be limited to only pathway maps and can also leverage GO terms as well. IDSL.GOA provides a useful tool for this purpose, allowing for a more comprehensive and accurate analysis of metabolite pathway data. IDSL.GOA tool can be accessed at https://goa.idsl.me/ .

Unravelling the transcriptome response of Enterobacter sp. S-33 under varying temperature.

Enterobacter genus includes the bacteria occupying every aspect of environment, however, their adaptability at varying temperature is not clear. In the present study, we analyzed the transcriptome response of Enterobacter sp. S-33 and their functional genes under various temperatures (30-45 ℃) that were expressed and accumulated in cells under temperature-stress. During a temperature shift from 37 to 45 ℃, 165 genes showed differential expression including 112 up-regulated and 53 down-regulated. In particular, heat-shock genes such as CspA, 16 kDa heat shock protein A/B and transcriptional regulators such as LysR, TetR, and LuxR were differentially expressed, indicating the role of complex molecular mechanism of Enterobacter adapting to temperature stress. Similarly, genes associated to signal transduction, ABC transporters, iron homeostasis, and quorum sensing were also induced. The Gene ontology enrichment analysis of differentially expressed genes (DEGs) were categorized into "transmembrane transport", "tRNA binding", "hydrogen sulfide biosynthetic process" and "sulfate assimilation" terms. In addition, Kyoto Encyclopedia of Genes and Genomes pathways showed that ABC transporter as well as quorum sensing pathways were significantly enriched. Overall, current study has contributed to explore the adaptive molecular mechanisms of Enterobacter spp. upon temperature change, which further opens new avenues for future in-depth functional studies.

Gender specific SNP markers in Coscinium fenestratum (Gaertn.) Colebr. for resource augmentation.

BACKGROUND: Unregulated extraction of highly traded medicinal plant species results in drastic decline of the natural resources and alters viable sex ratio of populations. Conservation and long-term survival of such species, require gender specific restoration programs to ensure reproductive success. However, it is often difficult to differentiate sex of individuals before reaching reproductive maturity. C. fenestratum is one of the medicinally important and overexploited dioecious woody liana, with a reproductive maturity of 15 years. Currently, no information is available to identify sex of C. fenestratum in seedling stage while augmenting the resources. Thus, the current study envisages to utilize transcriptomics approach for gender differentiation which is imperative for undertaking viable resource augmentation programmes. METHODS AND RESULTS: Gender specific SNPs with probable role in sexual reproduction/sex determination was located using comparative transcriptomics approach (sampling male and female individuals), alongside gene ontology and annotation. Nine sets of primers were synthesized from 7 transcripts (involved in sexual reproduction/other biological process) containing multiple SNP variants. Out of the nine primer pairs, only one SNP locus with no available information of its role in reproduction, showed consistent and accurate results (males-heterozygous and females-homozygous), in the analyzed 40 matured individuals of known sexes. Thus validated the efficiency of this SNP marker in differentiating male and female individuals. CONCLUSIONS: The study could identify SNPs linked to the loci with apparent role in gender differentiation. This SNP marker can be used for early sexing of seedlings for in-situ conservation and resource augmentation of C. fenestratum in Kerala, India.

Unraveling the link between atopic dermatitis and autoimmune diseases in children: Insights from a large-scale cohort study with 15-year follow-up and shared gene ontology analysis.

BACKGROUND: Atopic dermatitis and autoimmune diseases are highly heritable conditions that may co-occur from an early age. METHODS: The primary study is a national administrative cohort study involving 499,428 children born in 2002, tracked until 2017. Atopic dermatitis was defined as five or more principal diagnoses of atopic dermatitis and two or more topical steroid prescriptions. We estimated the risks for the occurrence of 41 autoimmune diseases, controlling for risk factors. In addition, we sourced a gene library from the National Library of Medicine to conduct a comprehensive gene ontology. We used Gene Weaver to identify gene set similarity and clustering, and used GeneMania to generate a network for shared genes. RESULTS: Exposed and unexposed groups included 39,832 and 159,328 children, respectively. During a mean follow-up of 12 years, the exposed group had an increased risk of autoimmune disease (hazard ratio, 1.27 [95 % confidence interval, 1.23-1.32]) compared to the unexposed group. The hazard ratios of autoimmune illnesses consistently increased with two- and five years lag times and alternative atopic dermatitis definitions. Shared genes between atopic dermatitis and autoimmune diseases were associated with comorbidities such as asthma, bronchiolitis, and specific infections. Genetic interactions of these shared genes revealed clustering in Th1, Th2, Th17, and non-classifiable pathways. CONCLUSIONS: Atopic dermatitis was significantly associated with an increased risk of subsequent autoimmune disease. we identified the genetically associated disease in atopic dermatitis patients comorbid with autoimmune disease and demonstrated a genetic network between atopic dermatitis and autoimmune diseases.

CircSKA3 is Associated With the Risk of Extracranial Artery Stenosis and Plaque Instability Among Ischemic Stroke Patients.

Circular RNA circSKA3 (spindle and kinetochore-related complex subunit 3) has been identified as a prognostic factor in ischemic stroke. The objective of this study was to investigate the association of circSKA3 with the risk of extracranial artery stenosis (ECAS) and plaque instability in patients with ischemic stroke. We constructed a competing endogenous RNA (ceRNA) network regulated by circSKA3 based on differentially expressed circRNAs and mRNAs between five patients and five controls. Gene Ontology (GO) analysis was performed on the 65 mRNAs within the network, revealing their primary involvement in inflammatory biological processes. A total of 284 ischemic stroke patients who underwent various imaging examinations were included for further analyses. Each 1 standard deviation increase in the log-transformed blood circSKA3 level was associated with a 56.3% increased risk of ECAS (P = 0.005) and a 142.1% increased risk of plaque instability (P = 0.005). Patients in the top tertile of circSKA3 had a 2.418-fold (P < 0.05) risk of ECAS compared to the reference group (P for trend = 0.02). CircSKA3 demonstrated a significant but limited ability to discriminate the presence of ECAS (AUC = 0.594, P = 0.015) and unstable carotid plaques (AUC = 0.647, P = 0.034). CircSKA3 improved the reclassification power for ECAS (NRI: 9.86%, P = 0.012; IDI: 2.97%, P = 0.007) and plaque instability (NRI: 36.73%, P = 0.008; IDI: 7.05%, P = 0.04) beyond conventional risk factors. CircSKA3 played an important role in the pathogenesis of ischemic stroke by influencing inflammatory biological processes. Increased circSKA3 was positively associated with the risk of ECAS and plaque instability among ischemic stroke patients.

DisProt in 2024: improving function annotation of intrinsically disordered proteins.

DisProt (URL: https://disprot.org) is the gold standard database for intrinsically disordered proteins and regions, providing valuable information about their functions. The latest version of DisProt brings significant advancements, including a broader representation of functions and an enhanced curation process. These improvements aim to increase both the quality of annotations and their coverage at the sequence level. Higher coverage has been achieved by adopting additional evidence codes. Quality of annotations has been improved by systematically applying Minimum Information About Disorder Experiments (MIADE) principles and reporting all the details of the experimental setup that could potentially influence the structural state of a protein. The DisProt database now includes new thematic datasets and has expanded the adoption of Gene Ontology terms, resulting in an extensive functional repertoire which is automatically propagated to UniProtKB. Finally, we show that DisProt's curated annotations strongly correlate with disorder predictions inferred from AlphaFold2 pLDDT (predicted Local Distance Difference Test) confidence scores. This comparison highlights the utility of DisProt in explaining apparent uncertainty of certain well-defined predicted structures, which often correspond to folding-upon-binding fragments. Overall, DisProt serves as a comprehensive resource, combining experimental evidence of disorder information to enhance our understanding of intrinsically disordered proteins and their functional implications.

Circular RNA mapping reveals CircCWC22 as a MiR-3059-x sponge in yak fat deposition by regulating HMGCL.

The regulatory mechanisms and functions of circular RNAs (circRNAs) in yak intramuscular fat (IMF) deposition remain unclear. This study aimed to investigate yak circRNAs with high and low IMF content using high-throughput sequencing. A total of 270 differentially expressed circRNAs were identified, of which 129 were upregulated and 141 were downregulated. Among these circRNAs, circCWC22, derived from the yak CWC22 gene, was further studied to understand its functions and regulatory mechanisms. Sequencing and RNase R processing confirmed the circular nature of circCWC22. By constructing a circRNA-miRNA-mRNA co-expression network, the potential regulatory pathway of circCWC22/miR-3059-x/HMGCL was identified. To investigate the roles of circCWC22, miR-3059-x, and HMGCL in the deposition of yak intramuscular preadipocytes (YIMAs), CCK-8, EdU, BODIPY, triglyceride content, and qRT-PCR analyses were performed. The results demonstrated that circCWC22, miR-3059-x, and HMGCL promoted the differentiation and inhibited the proliferation of YIMAs. Using the dual-luciferase reporter system and qRT-PCR, we confirmed that circCWC22 adsorbed miR-3059-x, and HMGCL was identified as a target gene of miR-3059-x. In conclusion, this study uncovered a large number of potential circRNAs involved in IMF deposition and highlighted the significant role of circCWC22 in yak IMF deposition via the circCWC22/miR-3059-x/HMGCL axis.

Artificial neural network-based gene screening and immune cell infiltration analysis of osteosarcoma feature.

BACKGROUND: The present study aimed to construct an artificial neural network (ANN) model that leverages characteristic genes associated with osteosarcoma (OS) to enable accurate prognostication for OS patients. METHODS: Our research revealed 467 differentially expressed genes (DEGs) via gene expression contrast analysis, consisting of 345 downregulated genes and 122 upregulated genes. Gene Ontology (GO) enrichment analysis illuminated functions primarily encompassing T-cell activation, secretory granule lumen and antioxidant activity, among others. Through Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis, we discovered significant correlations between the DEGs and certain pathways, including phagosome, Staphylococcus aureus infection and human T-cell leukemia virus 1 infection. We then screened out 30 characteristic DEGs (CDEGs) based on random forest analysis and constructed the ANN model using the gene score matrix. To verify the credibility and accuracy of the ANN model, we performed internal and external validation processes, which affirmed our model's predictive capabilities. RESULTS: The study further delved into the analysis of immune cell infiltration and its correlation with the target CDEGs, revealing disparities in the infiltration of 22 types of immune cells across different groups and their interrelationships. Moreover, we probed the expression of the two foremost CDEGs (YES1 and MFNG) in OS and normal tissues. We noted a positive relationship between the expression of YES1 and MFNG in OS tissues and the clinicopathological characteristics of OS patients. CONCLUSIONS: Collectively, the findings of the present study validate the effectiveness of the CDEGs-based ANN model in predicting OS patients, which might facilitate early diagnosis and treatment of OS.

Implementing link prediction in protein networks via feature fusion models based on graph neural networks.

MOTIVATION: Protein-protein interactions serve as the cornerstone for various biochemical processes within biological organisms. Existing research methodologies predominantly employ link prediction techniques to analyze these interaction networks. However, traditional approaches often fall short in delivering satisfactory predictive performance when applied to multi-species datasets. Current computational methods largely focus on analyzing the network topology, resulting in a somewhat monolithic feature set. The integration of diverse features in the model could potentially yield superior performance and broader applicability. To this end, we propose an autoencoder model built on graph neural networks, designed to enhance both predictive performance and generalizability by leveraging the integration of gene ontology. RESULTS: In this research, we developed AGraphSAGE, a model specifically designed for analyzing protein-protein interaction network data. By seamlessly integrating gene ontology into the graph structure, we employed a dual-channel graph sampling and aggregation network that capitalizes on topological information to process high-dimensional features. Feature fusion is achieved through the implementation of graph attention mechanisms, and we adopted a link prediction framework as the experimental training model. Performance was evaluated on real-world datasets using key metrics, such as Area Under the Curve (AUC). A hyperparameter search space was established, and a Bayesian optimization strategy was applied to iteratively fine-tune the model, assessing the impact of various parameters on predictive efficacy. The experimental results validate that our proposed model is capable of effectively predicting protein-protein interactions across diverse biological species.