args:
    subject_id: subject
    sample_id: biological_sample
    group_id: group
    missing_method: percentage
    missing_per_group: True
    missing_max: 0.3
    imputation_method: KNN
    columns: clinical_variable
    values: value
    extra: 
        - group
overview: #section
    clinical variables:
        data: clinical variables 
        analyses: []
        plots:
            - basicTable
        args: 
            title: 'List of clinical variables'
    stratification:
        description: '# Principal Component Analysis

                        **Principal component analysis (PCA)** is a statistical procedure that uses an orthogonal transformation to convert a set of observations 
                        of possibly correlated variables (entities each of which takes on various numerical values) into a set of values of linearly uncorrelated 
                        variables called principal components. This transformation is defined in such a way that the first principal component has the largest possible variance 
                        (that is, accounts for as much of the variability in the data as possible), and each succeeding component in turn has the highest variance possible under 
                        the constraint that it is orthogonal to the preceding components. The resulting vectors (each being a linear combination of the variables and containing n observations) 
                        are an uncorrelated orthogonal basis set. PCA is sensitive to the relative scaling of the original variables. [Wikipedia](https://en.wikipedia.org/wiki/Principal_component_analysis)'
        data: processed
        analyses:
            - pca
            #- tsne
            #- umap
        plots:
            - pca
        args:
            hovering_cols: 
                - biological_sample
            x_title: PC1
            y_title: PC2
            drop_cols:
                - subject
                - biological_sample
            components: 2
            perplexity: 40
            n_iter: 1000
            width: 1000
            height: 700
            loadings: 5
            title: 'Sample stratification'
    measurement matrix:
        data: processed
        analyses: []
        plots: 
            - violinplot
            - basicTable
        args:
            drop_cols:
                - subject
                - biological_sample 
            group: group
            x_title: clinical variables
            y_title: value
            title: 'Clinical variables measurements per group'
    regulation:
        data: processed
        analyses: 
            - anova
        plots: 
            - basicTable
        store_analysis: True
        args:
            alpha: 0.05
            fc: 2.0
            is_logged: False
            permutations: 0
            group: group
            subject: subject
            colorscale: Blues
            showscale: False
            marker_size: 10
            x_title: logFC
            y_title: -log(pvalue)
            drop_cols:
                - subject
                - biological_sample
            name: clinical_variable
            title: 'ANOVA analysis'
    correlation:
        data: processed
        analyses:
            - correlation
        plots:
            - network
        store_analysis: True
        args:
            source: node1
            target: node2
            title: 'Clinical Features correlation network'
            format: edgelist
            values: weight
            method: spearman
            dist: False
            node_properties: {}
            maxLinkWidth: 6
            maxRadius: 20
            node_size: 'degree'
            cutoff: 0.0
            subject: subject
            cutoff_abs: True
            color_weight: True
            communities_algorithm: affinity_propagation
            width: 1600
            height: 1600