The synergism of spatial metabolomics and morphometry improves machine learning-based renal tumour subtype classification.
Ontology highlight
ABSTRACT:
SUBMITTER: Prade VM
PROVIDER: S-EPMC8858620 | biostudies-literature | 2022 Feb
REPOSITORIES: biostudies-literature
Publications
The synergism of spatial metabolomics and morphometry improves machine learning-based renal tumour subtype classification.
Prade Verena M VM Sun Na N Shen Jian J Feuchtinger Annette A Kunzke Thomas T Buck Achim A Schraml Peter P Moch Holger H Schwamborn Kristina K Autenrieth Michael M Gschwend Jürgen E JE Erlmeier Franziska F Hartmann Arndt A Walch Axel A
Clinical and translational medicine 20220201 2
Similar Datasets
Project description:Metabolomics research has recently gained popularity because it enables the study of biological traits at the biochemical level and, as a result, can directly reveal what occurs in a cell or a tissue based on health or disease status, complementing other omics such as genomics and transcriptomics. Like other high-throughput biological experiments, metabolomics produces vast volumes of complex data. The application of machine learning (ML) to analyze data, recognize patterns, and build models is expanding across multiple fields. In the same way, ML methods are utilized for the classification, regression, or clustering of highly complex metabolomic data. This review discusses how disease modeling and diagnosis can be enhanced via deep and comprehensive metabolomic profiling using ML. We discuss the general layout of a metabolic workflow and the fundamental ML techniques used to analyze metabolomic data, including support vector machines (SVM), decision trees, random forests (RF), neural networks (NN), and deep learning (DL). Finally, we present the advantages and disadvantages of various ML methods and provide suggestions for different metabolic data analysis scenarios.
| S-EPMC9730048 | biostudies-literature
Project description:MotivationMany viruses are organized into taxonomies of subtypes based on their genetic similarities. For human immunodeficiency virus 1 (HIV-1), subtype classification plays a crucial role in infection management. Sequence alignment-based methods for subtype classification are impractical for large datasets because they are costly and time-consuming. Alignment-free methods involve creating numerical representations for genetic sequences and applying statistical or machine learning methods. Despite their high overall accuracy, existing models perform poorly on less common subtypes. Furthermore, there is limited work investigating the impact of sequence vectorization methods, in particular natural language-inspired embedding methods, on HIV-1 subtype classification.ResultsWe present a comprehensive analysis of sequence vectorization methods across machine learning methods. We report a k-mer-based XGBoost model with a balanced accuracy of 0.84, indicating that it has good overall performance for both common and uncommon HIV-1 subtypes. We also report a Word2Vec-based support vector machine that achieves promising results on precision and balanced accuracy. Our study sheds light on the effect of sequence vectorization methods on HIV-1 subtype classification and suggests that natural language-inspired encoding methods show promise. Our results could help to develop improved HIV-1 subtype classification methods, leading to improved individual patient outcomes, and the development of subtype-specific treatments.Availability and implementationSource code is available at https://www.github.com/kwade4/HIV_Subtypes.
| S-EPMC11371153 | biostudies-literature
Project description:Antibody testing in inflammatory bowel disease (IBD) can add to diagnostic accuracy of the main subtypes Crohn's disease (CD) and ulcerative colitis (UC). Whether modern modeling techniques such as supervised and unsupervised machine learning are of value for finer distinction of subtypes such as IBD-unclassified (IBD-U) is not known. We determined the antibody profile of 100 adult IBD patients from the Swiss IBD cohort study with known subtype (50 CD, 50 UC) as well as of 76 IBD-U patients. We included ASCA IgG and IgA, p-ANCA, MPO- and PR3-ANCA, and xANCA measurements for computing different antibody panels as well as machine learning models. The AUC of an optimized antibody panel was 85% (95%CI, 78-92%) to distinguish CD from UC patients. The antibody profile of IBD-U patients was closely related to UC. No specific antibody profile was predictive for IBD-U nor for re-classification. The panel diagnostic was in favor of UC reclassification prediction with a correct assignment rate of 69.2-73.1% depending on the cut-off applied. Supervised machine learning could not distinguish between CD, UC, and IBD-U. More so, unsupervised machine learning suggested only two distinct clusters as a likely number of IBD subtypes. Antibodies in IBD are supportive in confirming clinical determined subtypes CD and UC but have limited capacity to predict IBD-U and reclassification during follow-up. In terms of antibody profiles, IBD-U is not a distinct subtype of IBD.
| S-EPMC10417520 | biostudies-literature
Project description:BackgroundRenal papillary cell carcinoma (KIRP) is a relatively rare renal malignancy. Although KIRP subtyping about clinical relevance has been defined, there have been scarce number of studies on the molecular characteristics of KIRP subtypes.MethodIn this study, a independent samples t-test was used to identify differentially expressed (DE) miRNAs between tumor and normal samples of KIRP. Meanwhile, we performed unsupervised clustering using DE miRNA expression data to analyze molecular characteristics of KIRP. The Partitioning Around Medoids clustering approach was used to identify molecular subtypes. The cumulative distribution function (CDF), proportion of ambiguously clustered pairs (PAC), principal component analysis (PCA) and consensus heatmaps were used to assess the optimal subtypes. In the differential molecular subtypes, we performed an integrated analysis of survival, DE genes, biological function and somatic mutations on the cohort of KIRP patients from The Cancer Genome Atlas.ResultsFrom solutions with 2, 3, 4, 5, 6 and 7 clusters we selected three KIRP molecular subtypes after assessing PCA, PAC, CDF and consensus heatmaps. We found that the three subtypes are associated with different overall survival and molecular characteristics. Compared with subtype1 and subtype3, subtype2 had a better prognosis in KIRP patients. After exploring their signaling pathways and biological characteristics, we identified the significantly enriched KEGG pathways and Gene Ontology terms for the three subtypes. The distribution of PARD6B, SETD2, STAG2, CUL3, TNRC18, LRBA, IGSF9B and DUNC1H1 mutations differed between the subtypes.ConclusionWe performed unsupervised clustering using differentially expressed miRNA expression data and described the three KIRP molecular subtypes. The three subtypes differed in overall survival, molecular characteristics and gene mutation frequency.
| S-EPMC6446988 | biostudies-literature
Project description:MotivationTumor sample classification has long been an important task in cancer research. Classifying tumors into different subtypes greatly benefits therapeutic development and facilitates application of precision medicine on patients. In practice, solid tumor tissue samples obtained from clinical settings are always mixtures of cancer and normal cells. Thus, the data obtained from these samples are mixed signals. The 'tumor purity', or the percentage of cancer cells in cancer tissue sample, will bias the clustering results if not properly accounted for.ResultsIn this article, we developed a model-based clustering method and an R function which uses DNA methylation microarray data to infer tumor subtypes with the consideration of tumor purity. Simulation studies and the analyses of The Cancer Genome Atlas data demonstrate improved results compared with existing methods.Availability and implementationInfiniumClust is part of R package InfiniumPurify , which is freely available from CRAN ( https://cran.r-project.org/web/packages/InfiniumPurify/index.html ).Contacthao.wu@emory.edu or xqzheng@shnu.edu.cn.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC6410888 | biostudies-literature
Project description:Triple negative breast cancer (TNBC) lacks well-defined molecular targets and is highly heterogenous, making treatment challenging. Using gene expression analysis, TNBC has been classified into four different subtypes: basal-like immune-activated (BLIA), basal-like immune-suppressed (BLIS), mesenchymal (MES), and luminal androgen receptor (LAR). However, there is currently no standardized method for classifying TNBC subtypes. We attempted to define a gene signature for each subtype, and to develop a classification method based on machine learning (ML) for TNBC subtyping. In these experiments, gene expression microarray data for TNBC patients were downloaded from the Gene Expression Omnibus database. Differentially expressed genes unique to 198 known TNBC cases were identified and selected as a training gene set to train in seven different classification models. We produced a training set consisting of 719 DEGs selected from uniquely expressed genes of all four subtypes. The highest average accuracy of classification of the BLIA, BLIS, MES, and LAR subtypes was achieved by the SVM algorithm (accuracy 95-98.8%; AUC 0.99-1.00). For model validation, we used 334 samples of unknown TNBC subtypes, of which 97 (29.04%), 73 (21.86%), 39 (11.68%) and 59 (17.66%) were predicted to be BLIA, BLIS, MES, and LAR, respectively. However, 66 TNBC samples (19.76%) could not be assigned to any subtype. These samples contained only three upregulated genes (EN1, PROM1, and CCL2). Each TNBC subtype had a unique gene expression pattern, which was confirmed by identification of DEGs and pathway analysis. These results indicated that our training gene set was suitable for development of classification models, and that the SVM algorithm could classify TNBC into four unique subtypes. Accurate and consistent classification of the TNBC subtypes is essential for personalized treatment and prognosis of TNBC.
| S-EPMC8472680 | biostudies-literature
Project description:Conservation is a strong predictor for the pathogenicity of single-nucleotide variants (SNVs). However, some positions that present complex conservation patterns across vertebrates stray from this paradigm. Here, we analyzed the association between complex conservation patterns and the pathogenicity of SNVs in the 115 disease-genes that had sufficient variant data. We show that conservation is not a one-rule-fits-all solution since its accuracy highly depends on the analyzed set of species and genes. For example, pairwise comparisons between the human and 99 vertebrate species showed that species differ in their ability to predict the clinical outcomes of variants among different genes using conservation. Furthermore, certain genes were less amenable for conservation-based variant prediction, while others demonstrated species that optimize prediction. These insights led to developing EvoDiagnostics, which uses the conservation against each species as a feature within a random-forest machine-learning classification algorithm. EvoDiagnostics outperformed traditional conservation algorithms, deep-learning based methods and most ensemble tools in every prediction-task, highlighting the strength of optimizing conservation analysis per-species and per-gene. Overall, we suggest a new and a more biologically relevant approach for analyzing conservation, which improves prediction of variant pathogenicity.
| S-EPMC8988715 | biostudies-literature
Project description:Metabolomic data often present challenges due to high dimensionality, collinearity, and variability in metabolite concentrations. Machine learning (ML) application in metabolomic analyses is enabling the extraction of meaningful information from complex data. Bringing together domain-specific knowledge from metabolomics with explainable ML methods can refine the predictive performance and interpretability of models used in atherosclerosis research. In this work, we aimed to identify the most impactful metabolites associated with the presence of atherosclerotic cardiovascular disease (ASCVD) in cross-sectional case-control studies using explainable ML methods integrated with metabolomics domain knowledge. For this, a subset from the FLEMENGHO cohort with metabolomic data available was used as the training cohort, including 63 patients with a history of ASCVD and 52 non-smoking controls matched by age, sex, and body mass index from the same population. First, Partial Least Squares Discriminant Analysis (PLS-DA) was applied for dimensionality reduction. The selected metabolites' correlations were analyzed by considering their chemical categorization. Then, eXtreme Gradient Boosting (XGBoost) was used to identify metabolites that characterize ASCVD. Next, the selected metabolites were evaluated in an external cohort to determine their effectiveness in distinguishing between cases and controls. A total of 56 metabolites were selected for ASCVD discrimination using PLS-DA. The primary identified metabolites' superclasses included lipids, organic acids, and organic oxygen compounds. Upon integrating these metabolites with the XGBoost model, the classification yielded a test area under the curve (AUC) of 0.75. SHAP analyses ranked cholesterol, 3-methylhistidine, and glucuronic acid among the most impactful features and showed the diversity of metabolites considered for building the ASCVD discriminator. Also using XGBoost, the selected metabolites achieved an AUC of 0.93 in an independent external validation cohort. In conclusion, the combination of different metabolites has the potential to build classifiers for ASCVD. Integrating metabolite categorization within the SHAP analysis further enhanced the interpretability of the model, offering insights into metabolite-specific contributions to ASCVD risk.
| S-EPMC11641503 | biostudies-literature
Project description:BackgroundRNA methylation modifications, such as N1-methyladenosine/N6-methyladenosine /N5-methylcytosine (m1A/m6A/m5C), are the most common RNA modifications and are crucial for a number of biological processes. Nonetheless, the role of RNA methylation modifications of m1A/m6A/m5C in the pathogenesis of renal interstitial fibrosis (RIF) remains incompletely understood.MethodsFirstly, we downloaded 2 expression datasets from the GEO database, namely GSE22459 and GSE76882. In a differential analysis of these datasets between patients with and without RIF, we selected 33 methylation-related genes (MRGs). We then applied a PPI network, LASSO analysis, SVM-RFE algorithm, and RF algorithm to identify key MRGs.ResultsWe eventually obtained five candidate MRGs (WTAP, ALKBH5, YTHDF2, RBMX, and ELAVL1) to forecast the risk of RIF. We created a nomogram model derived from five key MRGs, which revealed that the nomogram model may be advantageous to patients. Based on the selected five significant MRGs, patients with RIF were classified into two MRG patterns using consensus clustering, and the correlation between the five MRGs, the two MRG patterns, and the genetic pattern with immune cell infiltration was shown. Moreover, we conducted GO and KEGG analyses on 768 DEGs between MRG clusters A and B to look into their different involvement in RIF. To measure the MRG patterns, a PCA algorithm was developed to determine MRG scores for each sample. The MRG scores of the patients in cluster B were higher than those in cluster A.ConclusionsUltimately, we concluded that cluster A in the two MRG patterns identified on these five key m1A/m6A/m5C regulators may be associated with RIF.
| S-EPMC10373342 | biostudies-literature
Project description:Bladder tumours used to construct a tumour stage classifier Keywords = bladder cancer, disease stages, classification Keywords: other
2002-12-08 | GSE89 | GEO