comparison flexynesis_utils.xml @ 2:e5ecfffcfe45 draft

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/flexynesis commit 1afbaf45449e25238935e222f983da62392c067a

1:8fa64b6a9544

            ln -s '$utils_conditional.labels' 'inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext' &&
        cat '$flexynesis_utils_config' &&
        python '$flexynesis_utils_config'
        #end if
        #if $utils_conditional.util == "split_data":
            ln -s '$utils_conditional.clin' inputs/clin.csv &&
            #set $omics_names = []
            #for $omics_file in $utils_conditional.omics:
                ln -s '$omics_file' 'inputs/${omics_file.element_identifier}.${omics_file.ext}' &&
                #silent $omics_names.append('inputs/' + str($omics_file.element_identifier) + '.' + str($omics_file.ext))
            #end for

            python '$__tool_directory__/flexynesis_utils.py'
                --util split
                --clin inputs/clin.csv
                --omics '$(",".join($omics_names))'
                --split $utils_conditional.split
                --out output
        #end if
        #if $utils_conditional.util == "binarize":

                                #end if
                                X=X)
cluster_df = pd.DataFrame(data=cluster_labels, index=X.index, columns=['louvain_cluster'])
label_data = label_data.merge(cluster_df[['louvain_cluster']], left_index=True, right_index=True, how='left')

output_path = f"output/clustered_labels.csv"
label_data.to_csv(output_path, index=True)

#else if $utils_conditional.util == "get_optimal_clusters":
label_data = load_omics('inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext')
X = load_omics('inputs/$utils_conditional.X.element_identifier.$utils_conditional.X.ext')

print(f"Silhouette scores: \n{silhouette_scores}")

cluster_df = pd.DataFrame(data=kmeans_cluster_labels, index=X.index, columns=['optimal_kmeans_cluster'])
label_data = label_data.merge(cluster_df[['optimal_kmeans_cluster']], left_index=True, right_index=True, how='left')

output_path = f"output/optimal_clusters_labels.csv"
label_data.to_csv(output_path, index=True)

#else if $utils_conditional.util == "k_means_clustering":
label_data = load_omics('inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext')
X = load_omics('inputs/$utils_conditional.X.element_identifier.$utils_conditional.X.ext')

print(f"{kmeans}")
cluster_df = pd.DataFrame(data=cluster_labels, index=X.index, columns=['kmeans_cluster'])
label_data = label_data.merge(cluster_df[['kmeans_cluster']], left_index=True, right_index=True, how='left')

output_path = f"output/kmeans_labels.csv"
label_data.to_csv(output_path, index=True)

#else if $utils_conditional.util == "compute_ami_ari":
label_data = load_omics('inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext')

true_label = label_data.columns[$utils_conditional.true_label-2]

                <option value="compute_ami_ari">Compute AMI and ARI</option>
                <option value="split_data">Split data to train and test</option>
                <option value="binarize">Binarize mutation data</option>
            </param>
            <when value="louvain_clustering">
                <param argument="--X" type="data" format="tabular,csv" label="Matrix" help="Input matrix, (samples, features)"/>
                <expand macro="plots_common_input"/>
                <param argument="--threshold" type="float" min="0" optional="true" label="Distance threshold to create an edge between two nodes"/>
                <param argument="--k" type="integer" min="0" optional="true" label="Number of nearest neighbors to connect for each node"/>
            </when>
            <when value="get_optimal_clusters">
                <param argument="--X" type="data" format="tabular,csv" label="Matrix" help="Input matrix, (samples, features)"/>
                <expand macro="plots_common_input"/>
                <param argument="--min_k" type="integer" min="0" value="2" optional="false" label="Minimum number of clusters to try"/>
                <param argument="--max_k" type="integer" min="0" value="10" optional="false" label="Maximum number of clusters to try"/>
            </when>
            <when value="k_means_clustering">
                <param argument="--X" type="data" format="tabular,csv" label="Matrix" help="Input matrix, (samples, features)"/>
                <expand macro="plots_common_input"/>
                <param argument="--k" type="integer" min="0" optional="true" label="The number of clusters to form"/>
            </when>
            <when value="compute_ami_ari">
                <expand macro="plots_common_input"/>
                    <param name="true_label" type="data_column" data_ref="labels" label="Column name in the labels file to use for the true labels"/>
                    <param name="predicted_label" type="data_column" data_ref="labels" label="Column name in the labels file to use for the predicted labels"/>
            </when>
            <when value="split_data">
                <param argument="--clin" type="data" format="csv" optional="false" label="Clinical data" help="Samples in rows"/>
                <param argument="--omics" type="data" format="tabular,csv" optional="false" multiple="true" label="Omics data" help="samples in columns"/>
                <param argument="--split" type="float" min="0" max="1" value="0.7" label="Training/Test split ratio" help="Proportion of data to use for training (e.g., 0.7 means 70% train, 30% test)"/>
            </when>
            <when value="binarize">
                <param argument="--mutation" type="data" format="tabular,csv" label="Mutation data" help="Mutation data with both genes and samples in rows"/>
                <param argument="--gene_idx" type="data_column" data_ref="mutation" label="Column in the mutation file with genes"/>
                <param argument="--sample_idx" type="data_column" data_ref="mutation" label="Column in the mutation file with samples"/>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="util_out" auto_format="true" from_work_dir="output/*" label="${tool.name} on ${on_string}: ${utils_conditional.util}">
            <filter>utils_conditional['util'] != "split_data"</filter>
        </data>
        <collection name="train_out" type="list" label="${tool.name} on ${on_string}: train datasets">
            <discover_datasets pattern="__name_and_ext__" format="csv" directory="output/train"/>
            <filter>utils_conditional['util'] == "split_data"</filter>
        </collection>
        <collection name="test_out" type="list" label="${tool.name} on ${on_string}: test datasets">
            <discover_datasets pattern="__name_and_ext__" format="csv" directory="output/test"/>
            <filter>utils_conditional['util'] == "split_data"</filter>
        </collection>
    </outputs>
    <tests>
        <!-- test 1: Louvain clustering -->
        <test expect_num_outputs="1">
            <param name="non_commercial_use" value="True"/>
            <conditional name="utils_conditional">
                <param name="util" value="louvain_clustering"/>
                <param name="X" value="embeddings.csv"/>
                <param name="labels" value="labels_pr.csv"/>
                <param name="k" value="15"/>
            </conditional>
            <output name="util_out">
                <assert_contents>
                    <has_text text="sample_id,variable,class_label,probability,known_label,predicted_label,split,louvain_cluster"/>
                    <has_text text="MB-4818,CLAUDIN_SUBTYPE,LumA,0.8582904,LumB,LumA,test,3.0"/>
                </assert_contents>
            </output>
        </test>
        <!-- test 2: Get optimal clusters -->
        <test expect_num_outputs="1">
            <param name="non_commercial_use" value="True"/>
            <conditional name="utils_conditional">
                <param name="util" value="get_optimal_clusters"/>
                <param name="X" value="embeddings.csv"/>
                <param name="labels" value="labels_pr.csv"/>
                <param name="min_k" value="2"/>
                <param name="max_k" value="10"/>
            </conditional>
            <assert_stdout>
                <has_text text="Optimal number of clusters: 2"/>
                <has_text text="Silhouette scores: "/>
            </assert_stdout>
            <output name="util_out">
                <assert_contents>
                    <has_text text="sample_id,variable,class_label,probability,known_label,predicted_label,split,optimal_kmeans_cluster"/>
                    <has_text text="MB-4818,CLAUDIN_SUBTYPE,LumA,0.8582904,LumB,LumA,test,0.0"/>
                </assert_contents>
            </output>
        </test>
        <!-- test 3: K-Means clustering -->
        <test expect_num_outputs="1">
            <param name="non_commercial_use" value="True"/>
            <conditional name="utils_conditional">
                <param name="util" value="k_means_clustering"/>
                <param name="X" value="embeddings.csv"/>
                <param name="labels" value="labels_pr.csv"/>
                <param name="k" value="2"/>
            </conditional>
            <assert_stdout>
                <has_text text="KMeans(n_clusters=2, random_state=42)"/>
            </assert_stdout>
            <output name="util_out">
                <assert_contents>
                    <has_text text="sample_id,variable,class_label,probability,known_label,predicted_label,split,kmeans_cluster"/>
                    <has_text text="MB-4818,CLAUDIN_SUBTYPE,LumA,0.8582904,LumB,LumA,test,0.0"/>
                </assert_contents>
            </output>
        </test>
        <!-- test 4: Compute AMI and ARI -->
        <test expect_num_outputs="1">
            <param name="non_commercial_use" value="True"/>
            <conditional name="utils_conditional">
                <param name="util" value="compute_ami_ari"/>
                <param name="labels" value="labels.csv"/>
                <param name="true_label" value="5"/>
                <param name="predicted_label" value="6"/>
            </conditional>
            <assert_stdout>
                <has_text_matching expression="AMI: 0.5108[0-9]+"/>

            </conditional>
            <output name="util_out">
                <assert_contents>
                    <has_n_lines n="1611"/>
                    <has_text text="Hugo_Symbol"/>
                    <has_text text="AADACL2,0.0,0.0"/>
                    <has_text text="ABCB1,0.0,0.0,0.0,1.0"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

2:e5ecfffcfe45

            ln -s '$utils_conditional.labels' 'inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext' &&
        cat '$flexynesis_utils_config' &&
        python '$flexynesis_utils_config'
        #end if
        #if $utils_conditional.util == "split_data":
            ln -s '$utils_conditional.clin' inputs/clin.tabular &&
            #set $omics_names = []
            #for $omics_file in $utils_conditional.omics:
                ln -s '$omics_file' 'inputs/${omics_file.element_identifier}.${omics_file.ext}' &&
                #silent $omics_names.append('inputs/' + str($omics_file.element_identifier) + '.' + str($omics_file.ext))
            #end for

            python '$__tool_directory__/flexynesis_utils.py'
                --util split
                --clin inputs/clin.tabular
                --omics '$(",".join($omics_names))'
                --split $utils_conditional.split
                --out output
        #end if
        #if $utils_conditional.util == "binarize":

                                #end if
                                X=X)
cluster_df = pd.DataFrame(data=cluster_labels, index=X.index, columns=['louvain_cluster'])
label_data = label_data.merge(cluster_df[['louvain_cluster']], left_index=True, right_index=True, how='left')

output_path = f"output/clustered_labels.tabular"
label_data.to_csv(output_path, sep="\t", index=True)

#else if $utils_conditional.util == "get_optimal_clusters":
label_data = load_omics('inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext')
X = load_omics('inputs/$utils_conditional.X.element_identifier.$utils_conditional.X.ext')

print(f"Silhouette scores: \n{silhouette_scores}")

cluster_df = pd.DataFrame(data=kmeans_cluster_labels, index=X.index, columns=['optimal_kmeans_cluster'])
label_data = label_data.merge(cluster_df[['optimal_kmeans_cluster']], left_index=True, right_index=True, how='left')

output_path = f"output/optimal_clusters_labels.tabular"
label_data.to_csv(output_path, sep="\t", index=True)

#else if $utils_conditional.util == "k_means_clustering":
label_data = load_omics('inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext')
X = load_omics('inputs/$utils_conditional.X.element_identifier.$utils_conditional.X.ext')

print(f"{kmeans}")
cluster_df = pd.DataFrame(data=cluster_labels, index=X.index, columns=['kmeans_cluster'])
label_data = label_data.merge(cluster_df[['kmeans_cluster']], left_index=True, right_index=True, how='left')

output_path = f"output/kmeans_labels.tabular"
label_data.to_csv(output_path, sep="\t", index=True)

#else if $utils_conditional.util == "compute_ami_ari":
label_data = load_omics('inputs/$utils_conditional.labels.element_identifier.$utils_conditional.labels.ext')

true_label = label_data.columns[$utils_conditional.true_label-2]

                <option value="compute_ami_ari">Compute AMI and ARI</option>
                <option value="split_data">Split data to train and test</option>
                <option value="binarize">Binarize mutation data</option>
            </param>
            <when value="louvain_clustering">
                <param argument="--X" type="data" format="tabular" label="Matrix" help="Input matrix, (samples, features)"/>
                <expand macro="plots_common_input"/>
                <param argument="--threshold" type="float" min="0" optional="true" label="Distance threshold to create an edge between two nodes"/>
                <param argument="--k" type="integer" min="0" optional="true" label="Number of nearest neighbors to connect for each node"/>
            </when>
            <when value="get_optimal_clusters">
                <param argument="--X" type="data" format="tabular" label="Matrix" help="Input matrix, (samples, features)"/>
                <expand macro="plots_common_input"/>
                <param argument="--min_k" type="integer" min="0" value="2" optional="false" label="Minimum number of clusters to try"/>
                <param argument="--max_k" type="integer" min="0" value="10" optional="false" label="Maximum number of clusters to try"/>
            </when>
            <when value="k_means_clustering">
                <param argument="--X" type="data" format="tabular" label="Matrix" help="Input matrix, (samples, features)"/>
                <expand macro="plots_common_input"/>
                <param argument="--k" type="integer" min="0" optional="true" label="The number of clusters to form"/>
            </when>
            <when value="compute_ami_ari">
                <expand macro="plots_common_input"/>
                    <param name="true_label" type="data_column" data_ref="labels" label="Column name in the labels file to use for the true labels"/>
                    <param name="predicted_label" type="data_column" data_ref="labels" label="Column name in the labels file to use for the predicted labels"/>
            </when>
            <when value="split_data">
                <param argument="--clin" type="data" format="tabular" optional="false" label="Clinical data" help="Samples in rows"/>
                <param argument="--omics" type="data" format="tabular" optional="false" multiple="true" label="Omics data" help="samples in columns"/>
                <param argument="--split" type="float" min="0" max="1" value="0.7" label="Training/Test split ratio" help="Proportion of data to use for training (e.g., 0.7 means 70% train, 30% test)"/>
            </when>
            <when value="binarize">
                <param argument="--mutation" type="data" format="tabular" label="Mutation data" help="Mutation data with both genes and samples in rows"/>
                <param argument="--gene_idx" type="data_column" data_ref="mutation" label="Column in the mutation file with genes"/>
                <param argument="--sample_idx" type="data_column" data_ref="mutation" label="Column in the mutation file with samples"/>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="util_out" auto_format="true" from_work_dir="output/*" label="${tool.name} on ${on_string}: ${utils_conditional.util}">
            <filter>utils_conditional['util'] != "split_data"</filter>
        </data>
        <collection name="train_out" type="list" label="${tool.name} on ${on_string}: train datasets">
            <discover_datasets pattern="__name_and_ext__" format="tabular" directory="output/train"/>
            <filter>utils_conditional['util'] == "split_data"</filter>
        </collection>
        <collection name="test_out" type="list" label="${tool.name} on ${on_string}: test datasets">
            <discover_datasets pattern="__name_and_ext__" format="tabular" directory="output/test"/>
            <filter>utils_conditional['util'] == "split_data"</filter>
        </collection>
    </outputs>
    <tests>
        <!-- test 1: Louvain clustering -->
        <test expect_num_outputs="1">
            <param name="non_commercial_use" value="True"/>
            <conditional name="utils_conditional">
                <param name="util" value="louvain_clustering"/>
                <param name="X" value="embeddings.tabular"/>
                <param name="labels" value="labels_pr.tabular"/>
                <param name="k" value="15"/>
            </conditional>
            <output name="util_out">
                <assert_contents>
                    <has_text_matching expression="sample_id\tvariable\tclass_label\tprobability\tknown_label\tpredicted_label\tsplit\tlouvain_cluster"/>
                    <has_text_matching expression="MB-4818\tCLAUDIN_SUBTYPE\tLumA\t0.8582904\tLumB\tLumA\ttest\t3.0"/>
                </assert_contents>
            </output>
        </test>
        <!-- test 2: Get optimal clusters -->
        <test expect_num_outputs="1">
            <param name="non_commercial_use" value="True"/>
            <conditional name="utils_conditional">
                <param name="util" value="get_optimal_clusters"/>
                <param name="X" value="embeddings.tabular"/>
                <param name="labels" value="labels_pr.tabular"/>
                <param name="min_k" value="2"/>
                <param name="max_k" value="10"/>
            </conditional>
            <assert_stdout>
                <has_text text="Optimal number of clusters: 2"/>
                <has_text text="Silhouette scores: "/>
            </assert_stdout>
            <output name="util_out">
                <assert_contents>
                    <has_text_matching expression="sample_id\tvariable\tclass_label\tprobability\tknown_label\tpredicted_label\tsplit\toptimal_kmeans_cluster"/>
                    <has_text_matching expression="MB-4818\tCLAUDIN_SUBTYPE\tLumA\t0.8582904\tLumB\tLumA\ttest\t0.0"/>
                </assert_contents>
            </output>
        </test>
        <!-- test 3: K-Means clustering -->
        <test expect_num_outputs="1">
            <param name="non_commercial_use" value="True"/>
            <conditional name="utils_conditional">
                <param name="util" value="k_means_clustering"/>
                <param name="X" value="embeddings.tabular"/>
                <param name="labels" value="labels_pr.tabular"/>
                <param name="k" value="2"/>
            </conditional>
            <assert_stdout>
                <has_text text="KMeans(n_clusters=2, random_state=42)"/>
            </assert_stdout>
            <output name="util_out">
                <assert_contents>
                    <has_text_matching expression="sample_id\tvariable\tclass_label\tprobability\tknown_label\tpredicted_label\tsplit\tkmeans_cluster"/>
                    <has_text_matching expression="MB-4818\tCLAUDIN_SUBTYPE\tLumA\t0.8582904\tLumB\tLumA\ttest\t0.0"/>
                </assert_contents>
            </output>
        </test>
        <!-- test 4: Compute AMI and ARI -->
        <test expect_num_outputs="1">
            <param name="non_commercial_use" value="True"/>
            <conditional name="utils_conditional">
                <param name="util" value="compute_ami_ari"/>
                <param name="labels" value="labels.tabular"/>
                <param name="true_label" value="5"/>
                <param name="predicted_label" value="6"/>
            </conditional>
            <assert_stdout>
                <has_text_matching expression="AMI: 0.5108[0-9]+"/>

            </conditional>
            <output name="util_out">
                <assert_contents>
                    <has_n_lines n="1611"/>
                    <has_text text="Hugo_Symbol"/>
                    <has_text_matching expression="AADACL2\t0.0\t0.0"/>
                    <has_text_matching expression="ABCB1\t0.0\t0.0\t0.0\t1.0"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[