ABSTRACT
Diabetes stands as one of the most prevalent chronic diseases globally. The conventional methods for diagnosing diabetes are frequently overlooked until individuals manifest noticeable symptoms of the condition. This study aimed to address this gap by collecting comprehensive datasets, including 1000 instances of blood routine data from diabetes patients and an equivalent dataset from healthy individuals. To differentiate diabetes patients from their healthy counterparts, a computational framework was established, encompassing eXtreme Gradient Boosting (XGBoost), random forest, support vector machine, and elastic net algorithms. Notably, the XGBoost model emerged as the most effective, exhibiting superior predictive results with an area under the receiver operating characteristic curve (AUC) of 99.90% in the training set and 98.51% in the testing set. Moreover, the model showcased commendable performance during external validation, achieving an overall accuracy of 81.54%. The probability generated by the model serves as a risk score for diabetes susceptibility. Further interpretability was achieved through the utilization of the Shapley additive explanations (SHAP) algorithm, identifying pivotal indicators such as mean corpuscular hemoglobin concentration (MCHC), lymphocyte ratio (LY%), standard deviation of red blood cell distribution width (RDW-SD), and mean corpuscular hemoglobin (MCH). This enhances our understanding of the predictive mechanisms underlying diabetes. To facilitate the application in clinical and real-life settings, a nomogram was created based on the logistic regression algorithm, which can provide a preliminary assessment of the likelihood of an individual having diabetes. Overall, this research contributes valuable insights into the predictive modeling of diabetes, offering potential applications in clinical practice for more effective and timely diagnoses.
Subject(s)
Diabetes Mellitus , Machine Learning , Humans , Diabetes Mellitus/blood , Diabetes Mellitus/diagnosis , Female , Male , Support Vector Machine , Algorithms , ROC Curve , Middle Aged , Erythrocyte Indices , AdultABSTRACT
Pancreatic cancer is a globally recognized highly aggressive malignancy, posing a significant threat to human health and characterized by pronounced heterogeneity. In recent years, researchers have uncovered that the development and progression of cancer are often attributed to the accumulation of somatic mutations within cells. However, cancer somatic mutation data exhibit characteristics such as high dimensionality and sparsity, which pose new challenges in utilizing these data effectively. In this study, we propagated the discrete somatic mutation data of pancreatic cancer through a network propagation model based on protein-protein interaction networks. This resulted in smoothed somatic mutation profile data that incorporate protein network information. Based on this smoothed mutation profile data, we obtained the activity levels of different metabolic pathways in pancreatic cancer patients. Subsequently, using the activity levels of various metabolic pathways in cancer patients, we employed a deep clustering algorithm to establish biologically and clinically relevant metabolic subtypes of pancreatic cancer. Our study holds scientific significance in classifying pancreatic cancer based on somatic mutation data and may provide a crucial theoretical basis for the diagnosis and immunotherapy of pancreatic cancer patients.
Subject(s)
Genomics , Pancreatic Neoplasms , Humans , Prognosis , Genomics/methods , Pancreatic Neoplasms/genetics , Mutation , Cluster AnalysisABSTRACT
BACKGROUND AND OBJECTIVE: Breast cancer is among of the most malignant tumor that occurs in women and is one of the leading causes of death from gynecologic malignancy worldwide. The high degree of heterogeneity that characterizes breast cancer makes it challenging to devise effective therapeutic strategies. Accumulating evidence highlights the crucial role of stratifying breast cancer patients into clinically significant subtypes to achieve better prognoses and treatments. The structural deep clustering network is a graph convolutional network-based clustering algorithm that integrates structural information and has achieved state-of-the-art performance in various applications. METHODS: In this study, we employed structural deep clustering network to integrate somatic mutation profiles for stratifying 2526 breast cancer patients from the Memorial Sloan Kettering Cancer Center into two clinically differentiable subtypes. RESULTS: Breast cancer patients in cluster 1 exhibited better prognosis than breast cancer patients in cluster 2, and the difference between them was statistically significant. The immunogenomic landscape further demonstrated that cluster 1 was associated with remarkable infiltration of the tumor infiltrating lymphocytes. The clustering subtype could be used to evaluate the therapeutic benefit of immunotherapy and chemotherapy in breast cancer patients. Furthermore, our approach effectively classified patients from eight different cancer types, demonstrating its generalizability. CONCLUSIONS: Our study represents a step towards a generic methodology for classifying cancer patients using only somatic mutation data and structural deep clustering network approaches. Employing structural deep clustering network to identify breast cancer subtypes is promising and can inform the development of more accurate and personalized therapies.
Subject(s)
Breast Neoplasms , Humans , Female , Breast Neoplasms/genetics , Breast Neoplasms/pathology , Algorithms , Prognosis , Cluster Analysis , MutationABSTRACT
Transcription factors are protein molecules that act as regulators of gene expression. Aberrant protein activity of transcription factors can have a significant impact on tumor progression and metastasis in tumor patients. In this study, 868 immune-related transcription factors were identified from the transcription factor activity profile of 1823 ovarian cancer patients. The prognosis-related transcription factors were identified through univariate Cox analysis and random survival tree analysis, and two distinct clustering subtypes were subsequently derived based on these transcription factors. We assessed the clinical significance and genomics landscape of the two clustering subtypes and found statistically significant differences in prognosis, response to immunotherapy, and chemotherapy among ovarian cancer patients with different subtypes. Multi-scale Embedded Gene Co-expression Network Analysis was used to identify differential gene modules between the two clustering subtypes, which allowed us to conduct further analysis of biological pathways that exhibited significant differences between them. Finally, a ceRNA network was constructed to analyze lncRNA-miRNA-mRNA regulatory pairs with differential expression levels between two clustering subtypes. We expected that our study may provide some useful references for stratifying and treating patients with ovarian cancer.
ABSTRACT
The expression and activity of transcription factors, which directly mediate gene transcription, are strictly regulated to control numerous normal cellular processes. In cancer, transcription factor activity is often dysregulated, resulting in abnormal expression of genes related to tumorigenesis and development. The carcinogenicity of transcription factors can be reduced through targeted therapy. However, most studies on the pathogenic and drug-resistant mechanisms of ovarian cancer have focused on the expression and signaling pathways of individual transcription factors. To improve the prognosis and treatment of patients with ovarian cancer, multiple transcription factors should be evaluated simultaneously to determine the effects of their protein activity on drug therapies. In this study, the transcription factor activity of ovarian cancer samples was inferred from virtual inference of protein activity by enriched regulon algorithm using mRNA expression data. Patients were clustered according to their transcription factor protein activities to investigate the association of transcription factor activities of different subtypes with prognosis and drug sensitivity for filtering subtype-specific drugs. Meanwhile, master regulator analysis was utilized to identify master regulators of differential protein activity between clustering subtypes, thereby identifying transcription factors associated with prognosis and assessing their potential as therapeutic targets. Master regulator risk scores were then constructed for guiding patients' clinical treatment, providing new insights into the treatment of ovarian cancer at the level of transcriptional regulation.
Subject(s)
Gene Expression Regulation , Ovarian Neoplasms , Humans , Female , Prognosis , Ovarian Neoplasms/drug therapy , Ovarian Neoplasms/genetics , Ovarian Neoplasms/pathology , Transcription Factors/genetics , Transcription Factors/metabolism , Genomics , Gene Expression Regulation, NeoplasticABSTRACT
As one of the most common gynecologic malignant tumors, ovarian cancer is usually diagnosed at an advanced and incurable stage because of its early asymptomatic onset. Increasing research into tumor biology has demonstrated that abnormal cellular metabolism precedes tumorigenesis, therefore it has become an area of active research in academia. Cellular metabolism is of great significance in cancer diagnostic and prognostic studies. In this study, we integrated The Cancer Genome Atlas dataset with multiple Gene Expression Omnibus ovarian cancer datasets, identified 17 metabolic pathways with prognostic values using the random forest algorithm, constructed a metabolic risk scoring model based on metabolic pathway enrichment scores, and classified patients with ovarian cancer into two subtypes. Then, we systematically investigated the differences between different subtypes in terms of prognosis, differential gene expression, immune signature enrichment, Hallmark signature enrichment, and somatic mutations. As well, we successfully predicted differences in sensitivity to immunotherapy and chemotherapy drugs in patients with different metabolic risk subtypes. Moreover, we identified 5 drug targets associated with high metabolic risk and low metabolic risk ovarian cancer phenotypes through the weighted correlation network analysis and investigated their roles in the genesis of ovarian cancer. Finally, we developed an XGBoost classifier for predicting metabolic risk types in patients with ovarian cancer, producing a good predictive effect. In light of the above study, the research findings will provide valuable information for prognostic prediction and personalized medical treatment of patients with ovarian cancer.
Subject(s)
Ovarian Neoplasms , Random Forest , Female , Humans , Ovarian Neoplasms/drug therapy , Ovarian Neoplasms/genetics , Carcinogenesis , Drug Delivery Systems , ImmunotherapyABSTRACT
Transcription factors directly bind to DNA and regulate the expression of the gene, causing epigenetic modification of the DNA. They often mediate epigenetic parameters of transcriptional and posttranscriptional mechanisms, and their expression activities can be used to characterize genomic aberrations in cancer cell. In this study, the activity profile of transcription factors inferred by VIPER algorithm. The autoencoder model was applied for compressing the transcription factor activity profile for obtaining more useful transformed features for stratifying patients into two different breast cancer subtypes. The deep learning-based subtypes exhibited superior prognostic value and yielded better risk-stratification than the transcription factor activity-based method. Importantly, according to transformed features, a deep neural network was constructed to predict the subtypes, and achieved the accuracy of 94.98% and area under the ROC curve of 0.9663, respectively. The proposed subtypes were found to be significantly associated with immune infiltration, tumor immunogenicity and so on. Furthermore, the ceRNA network was constructed for the breast cancer subtypes. Besides, 11 master regulators were found to be associated with patients in cluster 1. Given the robustness performance of our deep learning model over multiple breast cancer cohorts, we expected this model may be useful in the area of prognosis prediction and lead some possibility for personalized medicine in breast cancer patients.
Subject(s)
Breast Neoplasms , Deep Learning , Algorithms , Breast Neoplasms/metabolism , Female , Genomics , Humans , Transcription Factors/geneticsABSTRACT
Triple-negative breast cancer (TNBC) is the breast cancer subtype with the highest fatality rate, and it seriously threatens women's health. Recent studies found that the level of immune cell infiltration in TNBC was associated with tumor progression and prognosis. However, due to practical constraints, most of these TNBC immune infiltration studies only used a small number of patient samples and a few immune cell types. Therefore, it is necessary to integrate more TNBC patient samples and immune cell types to comprehensively study immune infiltration in TNBC to contribute to the prognosis and treatment of patients. In this study, 12 TNBC datasets were integrated and an extensive collection of 182 gene sets with immune-related signatures were included to comprehensively investigate tumor immune microenvironment of TNBC. A single sample gene set enrichment analysis was performed to calculate the infiltration score of each immune-related signature in each patient, and an immune-related risk scoring model for TNBC was constructed to accurately assess patient prognosis. Significant differences were found in immunogenomic landscape between different immune risk subtypes. In addition, the immunotherapy response and chemotherapy drug sensitivity of patients with different immune risk subtypes were also analyzed. The results showed that there were significant differences in these characteristics. Finally, a prediction model for immune risk subtypes of TNBC patients was constructed to accurately predict patients with unknown subtypes. Based on the aforementioned findings, we believed that the immune-related risk score constructed in this study can assist in providing personalized medicine to TNBC patients.
Subject(s)
Triple Negative Breast Neoplasms , Female , Humans , Prognosis , Triple Negative Breast Neoplasms/drug therapy , Triple Negative Breast Neoplasms/genetics , Tumor Microenvironment/geneticsABSTRACT
ABCB1 is an important gene that closely related to analgesic tolerance to opioids, and plays an important role in their postoperative treatment. Recent studies have demonstrated that ABCB1 genotype is significantly associated with the chemico-resistance and chemical sensitivity in breast cancer patients. So, it is become very important to investigate the important role of ABCB1 for predicting drug response in breast cancer patients. In this study, by conducting the Cox proportional hazards regression analysis in breast cancer patients, significant differences were found in prognosis between the ABCB1 high- and low-expression subtypes. Meanwhile, by using immune infiltration profiles as well as transcriptomics datasets, the ABCB1 high subtype was found to be significantly enriched in many immune-related KEGG pathways and biological processes, and was characterized by the high infiltration levels of immune cell types. Furthermore, bioinformatics inference revealed that the ABCB1 subtypes were associated with the therapeutic effect of immunotherapy, which would be important for patient prognosis. In conclusion, these findings may provide useful help for recognizing the diversity between ABCB1 subtypes in tumor immune microenvironment, and may unravel prognosis outcomes and immunotherapy utility for ABCB1 in breast cancer.
Subject(s)
Biological Phenomena , Breast Neoplasms , ATP Binding Cassette Transporter, Subfamily B/genetics , ATP Binding Cassette Transporter, Subfamily B/therapeutic use , Breast Neoplasms/drug therapy , Breast Neoplasms/genetics , Breast Neoplasms/pathology , Female , Humans , Prognosis , Tumor Microenvironment/geneticsABSTRACT
Breast cancer is a kind of malignant tumor that occurs in breast tissue, which is the most common cancer in women. Cellular metabolism is a critical determinant of the viability and function of cancer cells in tumor microenvironment. In this study, based on the gene expression profile of metabolism-related genes, the prognostic value of 20 metabolic pathways in patients with breast cancer was identified. A universal risk stratification signature that relies on 20 metabolic pathways was established and validated in training cohort, two testing cohorts and The Cancer Genome Atlas pan cancer cohort. Then, the relationship between metabolic risk score subtype, prognosis, immune infiltration level, cancer genotypes and their impact on therapeutic benefit were characterized. Results demonstrated that the patients with the low metabolic risk score subtype displayed good prognosis, high level of immune infiltration and exhibited a favorable response to neoadjuvant chemotherapy and immunotherapy. Taken together, the work presented in this study may deepen the understanding of metabolic hallmarks of breast cancer, and may provide some valuable information for personalized therapies in patients with breast cancer.
Subject(s)
Breast Neoplasms , Biomarkers, Tumor/genetics , Breast Neoplasms/genetics , Female , Gene Expression Profiling , Gene Expression Regulation, Neoplastic , Humans , Prognosis , Risk Factors , Tumor Microenvironment/geneticsABSTRACT
Breast cancer is one of the most common types of cancers and the leading cause of death from malignancy among women worldwide. Tumor-infiltrating lymphocytes are a source of important prognostic biomarkers for breast cancer patients. In this study, based on the tumor-infiltrating lymphocytes in the tumor immune microenvironment, a risk score prognostic model was developed in the training cohort for risk stratification and prognosis prediction in breast cancer patients. The prognostic value of this risk score prognostic model was also verified in the two testing cohorts and the TCGA pan cancer cohort. Nomograms were also established in the training and testing cohorts to validate the clinical use of this model. Relationships between the risk score, intrinsic molecular subtypes, immune checkpoints, tumor-infiltrating immune cell abundances and the response to chemotherapy and immunotherapy were also evaluated. Based on these results, we can conclude that this risk score model could serve as a robust prognostic biomarker, provide therapeutic benefits for the development of novel chemotherapy and immunotherapy, and may be helpful for clinical decision making in breast cancer patients.
Subject(s)
Biomarkers, Tumor , Breast Neoplasms , Gene Expression Profiling , Gene Expression Regulation, Neoplastic , Models, Immunological , Tumor Microenvironment , Biomarkers, Tumor/genetics , Biomarkers, Tumor/immunology , Breast Neoplasms/diagnosis , Breast Neoplasms/genetics , Breast Neoplasms/immunology , Breast Neoplasms/therapy , Female , Humans , Lymphocytes, Tumor-Infiltrating/immunology , Predictive Value of Tests , Prognosis , Tumor Microenvironment/genetics , Tumor Microenvironment/immunologyABSTRACT
AIMS: Because of the high affinity of these animal neurotoxin proteins for some special target site, they were usually used as pharmacological tools and therapeutic agents in medicine to gain deep insights into the function of the nervous system. BACKGROUND AND OBJECTIVE: The animal neurotoxin proteins are one of the most common functional groups among the animal toxin proteins. Thus, it was very important to characterize and predict the animal neurotoxin proteins. METHODS: In this study, the differences between the animal neurotoxin proteins and non-toxin proteins were analyzed. RESULT: Significant differences were found between them. In addition, the support vector machine was proposed to predict the animal neurotoxin proteins. The predictive results of our classifier achieved the overall accuracy of 96.46%. Furthermore, the random forest and k-nearest neighbors were applied to predict the animal neurotoxin proteins. CONCLUSION: The compared results indicated that the predictive performances of our classifier were better than other two algorithms.
Subject(s)
Amino Acids/analysis , Machine Learning , Neurotoxins/chemistry , Animals , Neurotoxins/classification , Proteins/chemistry , Proteins/classificationABSTRACT
Breast cancer is the most common cancer and the leading cause of cancer death among women in the world. Tumour-infiltrating lymphocytes were defined as the white blood cells left in the vasculature and localized in tumours. Recently, tumour-infiltrating lymphocytes were found to be associated with good prognosis and response to immunotherapy in tumours. In this study, to examine the influence of FLI1 in immune system in breast cancer, we interrogated the relationship between the FLI1 expression levels with infiltration levels of 28 immune cell types. By splitting the breast cancer samples into high and low expression FLI1 subtypes, we found that the high expression FLI1 subtype was enriched in many immune cell types, and the up-regulated differentially expressed genes between them were enriched in immune system processes, immune-related KEGG pathways and biological processes. In addition, many important immune-related features were found to be positively correlated with the FLI1 expression level. Furthermore, we found that the FLI1 was correlated with the immune-related genes. Our findings may provide useful help for recognizing the relationship between tumour immune microenvironment and FLI1, and may unravel clinical outcomes and immunotherapy utility for FLI1 in breast cancer.
Subject(s)
Breast Neoplasms/etiology , Breast Neoplasms/pathology , Lymphocytes, Tumor-Infiltrating/immunology , Lymphocytes, Tumor-Infiltrating/metabolism , Proto-Oncogene Protein c-fli-1/genetics , Tumor Microenvironment , Biomarkers, Tumor , Female , Gene Expression Profiling , Gene Expression Regulation, Neoplastic , Gene Regulatory Networks , Genes, BRCA1 , Genes, BRCA2 , Humans , Prognosis , Proto-Oncogene Protein c-fli-1/metabolism , TranscriptomeABSTRACT
Prostate cancer is one of the leading causes of death in men worldwide, revealing a substantial heterogeneity in terms of molecular and clinical behaviors. Tumor infiltrating immune cell is associated with prognosis and response to immunotherapy in several cancer types. However, until now, the immune infiltrate profile of distinct subtypes for prostate cancer remains poorly characterized. In this study, using immune infiltration profiles as well as transcriptomic datasets, we characterized this subtype of prostate tumors. We observed that the FLI1 subtype of prostate tumors was highly enriched in immune system processes, immune related KEGG pathways and biological processes. We also expanded this approach to explore the immune infiltration profile of the high FLI1 expression subtype for skin cutaneous melanoma, similar results were found. Investigation of the association of immune infiltration features with the FLI1 expression demonstrated that many important features were associated with the FLI1 expression.
Subject(s)
Adenocarcinoma/genetics , Melanoma/genetics , Prostatic Neoplasms/genetics , Skin Neoplasms/genetics , Transcriptome , Tumor Microenvironment/immunology , Adenocarcinoma/immunology , Humans , Lymphocytes, Tumor-Infiltrating/metabolism , Male , Melanoma/immunology , Prostatic Neoplasms/immunology , Proto-Oncogene Protein c-fli-1/genetics , Proto-Oncogene Protein c-fli-1/metabolism , Skin Neoplasms/immunologyABSTRACT
Knowing the protein localization can provide valuable information resource for elucidating protein function. In recent years, with the advances of human genomics and proteomics, it is possible to characterize human proteins that are located in different subcellular localizations. In this study, we used the topological properties and biological properties to characterize human proteins with six subcellular localizations. Almost all of these properties were found to be significantly different among six protein categories. Network topology analysis indicated that several significant topological properties, including the degree and k-core, were higher for the mitochondrial proteins. Biological property analysis showed that the nuclear proteins appeared to be correlated with important biological function. We hope these findings may provide some important help for comprehensive understanding the biological function of proteins, and prediction of protein subcellular localizations in human.
Subject(s)
Nuclear Proteins , Proteomics , Humans , Mitochondrial Proteins/genetics , Mitochondrial Proteins/metabolism , Nuclear Proteins/genetics , Nuclear Proteins/metabolismABSTRACT
Knowing the comprehensive knowledge about the protein subcellular localization is an important step to understand the function of the proteins. Recent advances in system biology have allowed us to develop more accurate methods for characterizing the proteins at subcellular localization level. In this study, the analysis method was developed to characterize the topological properties and biological properties of the cytoplasmic proteins, inner membrane proteins, outer membrane proteins and periplasmic proteins in Escherichia coli (E. coli). Statistical significant differences were found in all topological properties and biological properties among proteins in different subcellular localizations. In addition, investigation was carried out to analyze the differences in 20 amino acid compositions for four protein categories. We also found that there were significant differences in all of the 20 amino acid compositions. These findings may be helpful for understanding the comprehensive relationship between protein subcellular localization and biological function.
Subject(s)
Bacterial Outer Membrane Proteins/metabolism , Escherichia coli Proteins/metabolism , Amino Acid Motifs , Bacterial Outer Membrane Proteins/chemistry , Cell Membrane/metabolism , Cytoplasm/metabolism , Escherichia coli/metabolism , Escherichia coli Proteins/chemistryABSTRACT
The animal toxin proteins are one of the disulfide rich small peptides that detected in venomous species. They are used as pharmacological tools and therapeutic agents in medicine for the high specificity of their targets. The successful analysis and prediction of toxin proteins may have important signification for the pharmacological and therapeutic researches of toxins. In this study, significant differences were found between the toxins and the non-toxins in amino acid compositions and several important biological properties. The random forest was firstly proposed to predict the animal toxin proteins by selecting 400 pseudo amino acid compositions and the dipeptide compositions of reduced amino acid alphabet as the input parameters. Based on dipeptide composition of reduced amino acid alphabet with 13 reduced amino acids, the best overall accuracy of 85.71% was obtained. These results indicated that our algorithm was an efficient tool for the animal toxin prediction.
Subject(s)
Amino Acids/analysis , Toxins, Biological/toxicity , Algorithms , Animals , Dipeptides/analysis , Reproducibility of Results , Toxins, Biological/chemistryABSTRACT
To tackle the issue of poor cycling stability for metal oxide nanoparticles as supercapacitor electrode, porous ZnO/Co3O4 composites were fabricated via solid-state thermolysis of [CoZn(BTC)(NO3)](2H2O)(0.5DMF) under air atmosphere. The results demonstrate that the products are mesoporous polyhedron structure with the diameter of about 10 µm, which are constructed by many interconnected nanocrystals with the sizes of around 20 nm. ZnO/Co3O4 composites as supercapacitor electrode exhibited excellent cyclic stability capacity, showing a maximum specific capacitance of 106.7 F g-1 and a capacity retention of 102.7 F · g-1 after 1000 cycles at 0.5 A · g-1. The superior electrochemical performance was contributed to ZnO/Co3O4 composites with porous structures and small size, which shortened the route of electronic transmission as well as ions insertion and desertion processes. Additionally, the synergetic effect of bimetallic oxides improved the electrochemical stability.