diff --git a/_config.yml b/_config.yml index 9c0ec0e3c54870..d405034ed8ed01 100644 --- a/_config.yml +++ b/_config.yml @@ -164,6 +164,7 @@ icon-tag: param-select: fas fa-filter param-text: fas fa-pencil-alt param-toggle: fas fa-toggle-on + point-right: fa fa-hand-o-right pref-info: fas fa-user pref-password: fas fa-unlock-alt pref-identities: far fa-id-card-o diff --git a/topics/genome-annotation/tutorials/crispr-screen/data-library.yaml b/topics/genome-annotation/tutorials/crispr-screen/data-library.yaml index bd605fae98d306..22d3d3dc414b9a 100644 --- a/topics/genome-annotation/tutorials/crispr-screen/data-library.yaml +++ b/topics/genome-annotation/tutorials/crispr-screen/data-library.yaml @@ -13,43 +13,43 @@ items: - name: 'DOI: 10.5281/zenodo.5750854' description: latest items: - - url: https://zenodo.org/api/files/6599878c-f569-41bf-a37a-2c6f3d2e67f9/adapters_list.tsv + - url: https://zenodo.org/records/5750854/files/adapter_list.tsv src: url ext: tsv info: https://zenodo.org/record/5750854 - - url: https://zenodo.org/api/files/6599878c-f569-41bf-a37a-2c6f3d2e67f9/brunello.tsv + - url: https://zenodo.org/records/5750854/files/brunello.tsv src: url ext: tsv info: https://zenodo.org/record/5750854 - - url: https://zenodo.org/api/files/6599878c-f569-41bf-a37a-2c6f3d2e67f9/h.all.v7.4.symbols.gmt + - url: https://zenodo.org/records/5750854/files/h.all.v7.4.symbols.gmt src: url ext: tsv info: https://zenodo.org/record/5750854 - - url: https://zenodo.org/api/files/6599878c-f569-41bf-a37a-2c6f3d2e67f9/kenji_mageck_count_summary.tsv + - url: https://zenodo.org/records/5750854/files/kenji_mageck_count_summary.tsv src: url ext: tsv info: https://zenodo.org/record/5750854 - - url: https://zenodo.org/api/files/6599878c-f569-41bf-a37a-2c6f3d2e67f9/kenji_mageck_count_report.pdf + - url: https://zenodo.org/records/5750854/files/kenji_mageck_count_report.pdf src: url ext: tsv info: https://zenodo.org/record/5750854 - - url: https://zenodo.org/api/files/6599878c-f569-41bf-a37a-2c6f3d2e67f9/kenji_mageck_sgrna_counts.tsv + - url: https://zenodo.org/records/5750854/files/kenji_mageck_sgrna_counts.tsv src: url ext: tsv info: https://zenodo.org/record/5750854 - - url: https://zenodo.org/api/files/6599878c-f569-41bf-a37a-2c6f3d2e67f9/kenji_mageck_mle_design_matrix.tsv + - url: https://zenodo.org/records/5750854/files/kenji_mageck_mle_design_matrix.tsv src: url ext: tsv info: https://zenodo.org/record/5750854 - - url: https://zenodo.org/api/files/6599878c-f569-41bf-a37a-2c6f3d2e67f9/T0-Control.fastq.gz + - url: https://zenodo.org/records/5750854/files/T0-Control.fastq.gz src: url ext: gz info: https://zenodo.org/record/5750854 - - url: https://zenodo.org/api/files/6599878c-f569-41bf-a37a-2c6f3d2e67f9/T8-APR-246.fastq.gz + - url: https://zenodo.org/records/5750854/files/T8-APR-246.fastq.gz src: url ext: gz info: https://zenodo.org/record/5750854 - - url: https://zenodo.org/api/files/6599878c-f569-41bf-a37a-2c6f3d2e67f9/T8-Vehicle.fastq.gz + - url: https://zenodo.org/records/5750854/files/T8-Vehicle.fastq.gz src: url ext: gz info: https://zenodo.org/record/5750854 diff --git a/topics/genome-annotation/tutorials/crispr-screen/tutorial.md b/topics/genome-annotation/tutorials/crispr-screen/tutorial.md index 19c53bfa217220..b6f8a15fa31121 100644 --- a/topics/genome-annotation/tutorials/crispr-screen/tutorial.md +++ b/topics/genome-annotation/tutorials/crispr-screen/tutorial.md @@ -78,9 +78,9 @@ Here we will demonstrate analysing {CRISPR} screen using data from {% cite Fujih > - Copy the following tabular data, paste it into the textbox and press Build > > ``` -> T0-Control https://zenodo.org/record/5750854/files/T0-Control.fastq.gz -> T8-APR-246 https://zenodo.org/record/5750854/files/T8-APR-246.fastq.gz -> T8-Vehicle https://zenodo.org/record/5750854/files/T8-Vehicle.fastq.gz +> T0-Control https://zenodo.org/records/5750854/files/T0-Control.fastq.gz +> T8-APR-246 https://zenodo.org/records/5750854/files/T8-APR-246.fastq.gz +> T8-Vehicle https://zenodo.org/records/5750854/files/T8-Vehicle.fastq.gz > ``` > > ![Rule-based Uploader](../../images/crispr-screen/crispr_rule_uploader.png) @@ -118,7 +118,7 @@ With CRISPR screens we expect adapter sequence to be present, surrounding the gu > > 1. Import the adapters file from [Zenodo]({{ page.zenodo_link }}) or the Shared Data library (if available): > ``` -> https://zenodo.org/record/5750854/files/adapter_list.tsv +> https://zenodo.org/records/5750854/files/adapter_list.tsv > ``` > {% snippet faqs/galaxy/datasets_import_via_link.md %} > @@ -246,7 +246,7 @@ To count how many guides we have for each gene, we need a library file that tell > Count guides per gene > 1. Import the sgRNA library file > ``` -> https://zenodo.org/record/5750854/files/brunello.tsv +> https://zenodo.org/records/5750854/files/brunello.tsv > ``` > > 2. {% tool [MAGeCK count](toolshed.g2.bx.psu.edu/repos/iuc/mageck_count/mageck_count/0.5.9.2.4) %} with the following parameters: @@ -259,9 +259,9 @@ To count how many guides we have for each gene, we need a library file that tell > > 3. We have been using 1% of reads from the samples. Import the MAGeCK count files (sgRNA counts, counts summary and plots pdf) for the full dataset so you can see what results for a real dataset looks like. > ``` -> https://zenodo.org/record/5750854/files/kenji_mageck_sgrna_counts.tsv -> https://zenodo.org/record/5750854/files/kenji_mageck_count_summary.tsv -> https://zenodo.org/record/5750854/files/kenji_mageck_count_report.pdf +> https://zenodo.org/records/5750854/files/kenji_mageck_sgrna_counts.tsv +> https://zenodo.org/records/5750854/files/kenji_mageck_count_summary.tsv +> https://zenodo.org/records/5750854/files/kenji_mageck_count_report.pdf > ``` > {: .hands_on} diff --git a/topics/single-cell/faqs/dimension_reduction.md b/topics/single-cell/faqs/dimension_reduction.md index b4cc520c2b1db4..fbc78327ce4af0 100644 --- a/topics/single-cell/faqs/dimension_reduction.md +++ b/topics/single-cell/faqs/dimension_reduction.md @@ -3,7 +3,7 @@ redirect_from: - /topics/transcriptomics/faqs/dimension_reduction title: Why do we do dimension reduction and then clustering? Why not just cluster on the actual data? -area: gene +area: Analysis box_type: tip layout: faq contributors: [rahmot] diff --git a/topics/single-cell/faqs/gene_profile.md b/topics/single-cell/faqs/gene_profile.md index eeb1792283effa..06c2ea2e077ca3 100644 --- a/topics/single-cell/faqs/gene_profile.md +++ b/topics/single-cell/faqs/gene_profile.md @@ -3,7 +3,7 @@ redirect_from: - /topics/transcriptomics/faqs/gene_profile title: What exactly is a ‘Gene profile’? -area: gene +area: Interpretation box_type: tip layout: faq contributors: [rahmot] diff --git a/topics/single-cell/faqs/notebook_warning.md b/topics/single-cell/faqs/notebook_warning.md new file mode 100644 index 00000000000000..1aac5fb03f0213 --- /dev/null +++ b/topics/single-cell/faqs/notebook_warning.md @@ -0,0 +1,9 @@ +--- +title: Notebook-based tutorials can give different outputs +area: Analysis +box_type: warning +layout: faq +contributors: [hexhowells, nomadscientist] +--- + +The nature of coding pulls the most recent tools to perform tasks. This can - and often does - change the outputs of an analysis. Be prepared, as you are unlikely to get outputs identical to a tutorial if you are running it in a programming environment like a Jupyter Notebook or R-Studio. That's ok! The outputs should still be pretty close. diff --git a/topics/single-cell/faqs/techniques.md b/topics/single-cell/faqs/techniques.md index d9a1638cefac20..299a4c7f8c7977 100644 --- a/topics/single-cell/faqs/techniques.md +++ b/topics/single-cell/faqs/techniques.md @@ -3,7 +3,7 @@ redirect_from: - /topics/transcriptomics/faqs/techniques title: Can RNA-seq techniques be applied to scRNA-seq? -area: Single-Cell RNA +area: Analysis box_type: tip layout: faq contributors: [nomadscientist,mtekman,rahmot] diff --git a/topics/single-cell/faqs/umi.md b/topics/single-cell/faqs/umi.md index f17140e0f0a3e7..6cefe033e314f6 100644 --- a/topics/single-cell/faqs/umi.md +++ b/topics/single-cell/faqs/umi.md @@ -3,7 +3,7 @@ redirect_from: - /topics/transcriptomics/faqs/umi title: Are UMIs not actually unique? -area: Single-Cell RNA +area: Analysis box_type: tip layout: faq contributors: [nomadscientist,mtekman] diff --git a/topics/single-cell/faqs/variable_genes.md b/topics/single-cell/faqs/variable_genes.md index 2276c8f1f075ce..634aa61587223f 100644 --- a/topics/single-cell/faqs/variable_genes.md +++ b/topics/single-cell/faqs/variable_genes.md @@ -3,7 +3,7 @@ redirect_from: - /topics/transcriptomics/faqs/variable_genes title: Why do we only consider highly variable genes? -area: gene +area: Analysis box_type: tip layout: faq contributors: [rahmot] diff --git a/topics/single-cell/index.md b/topics/single-cell/index.md index 7864ea242a988c..e402d143abf77f 100644 --- a/topics/single-cell/index.md +++ b/topics/single-cell/index.md @@ -13,6 +13,6 @@ Check out workflows shared by users like you! If you want to help us behind the scenes, from testing workflows and tutorials to building tools, join our Galaxy Single Cell Community of Practice! - - [Community of Practice](https://galaxyproject.org/projects/singlecell/) - - [Matrix Chat Forum](https://matrix.to/#/#usegalaxy-eu_single-cell-workflows:gitter.im) - - [Mailing List](https://lists.galaxyproject.org/lists/single-cell-cop.lists.galaxyproject.org/) + - {% icon point-right %} [Community of Practice](https://galaxyproject.org/projects/singlecell/) + - {% icon feedback %} [Matrix Chat Forum](https://matrix.to/#/#usegalaxy-eu_single-cell-workflows:gitter.im) + - {% icon email %} [Mailing List](https://lists.galaxyproject.org/lists/single-cell-cop.lists.galaxyproject.org/) diff --git a/topics/single-cell/tutorials/scrna-case-jupyter_basic-pipeline/tutorial.md b/topics/single-cell/tutorials/scrna-case-jupyter_basic-pipeline/tutorial.md index 5ffda81b642575..6474e028120a93 100644 --- a/topics/single-cell/tutorials/scrna-case-jupyter_basic-pipeline/tutorial.md +++ b/topics/single-cell/tutorials/scrna-case-jupyter_basic-pipeline/tutorial.md @@ -50,9 +50,8 @@ notebook: snippet: topics/single-cell/tutorials/scrna-case-jupyter_basic-pipeline/preamble.md --- -> Remember: Notebook-based tutorials can give different outputs! -> The nature of coding pulls the most recent tools to perform tasks. This can - and often does - change the outputs of an analysis. Be prepared, as you are unlikely to get outputs identical to this tutorial. That's ok! The outputs should still be pretty close (the basic interpretation has survived 5 years of analytical updates and counting...). -{: .warning} + +{% snippet topics/single-cell/faqs/notebook_warning.md %} # Install libraries diff --git a/topics/single-cell/tutorials/scrna-case_FilterPlotandExploreRStudio/preamble.md b/topics/single-cell/tutorials/scrna-case_FilterPlotandExploreRStudio/preamble.md index e9b259fd4bdd26..b9d9c8abae0a0e 100644 --- a/topics/single-cell/tutorials/scrna-case_FilterPlotandExploreRStudio/preamble.md +++ b/topics/single-cell/tutorials/scrna-case_FilterPlotandExploreRStudio/preamble.md @@ -55,17 +55,8 @@ This also alleviates the necessity to convert the AnnData object into a Seurat o > {: .hands_on} -# Important tips for easier analysis - -{% snippet faqs/galaxy/tutorial_mode.md %} - -> -> - The Galaxy tool search panel sometimes doesn't find the tools we need from the thousands available. -> - You'll have a much easier time selecting tools from the panel (if you aren't using tutorial mode!) if you are on the [https://humancellatlas.usegalaxy.eu](https://humancellatlas.usegalaxy.eu) -{: .comment} - # Open RStudio in Galaxy -You now should have imported the matrix.mtx, genes.tsv, barcodes.tsv, and exp_design.tsv files into your Galaxy history. For the rest of the workflow, let's move onto RStudio and get coding! +You now should have imported the `matrix.mtx`, `genes.tsv`, `barcodes.tsv`, and `exp_design.tsv` files into your Galaxy history. For the rest of the workflow, let's move onto RStudio and get coding! > Open RStudio in Galaxy > Run {% tool [RStudio](interactive_tool_rstudio)%} {: .hands_on} diff --git a/topics/single-cell/tutorials/scrna-case_FilterPlotandExploreRStudio/tutorial.md b/topics/single-cell/tutorials/scrna-case_FilterPlotandExploreRStudio/tutorial.md index 7e86cee0167a64..a68a251fc28a99 100644 --- a/topics/single-cell/tutorials/scrna-case_FilterPlotandExploreRStudio/tutorial.md +++ b/topics/single-cell/tutorials/scrna-case_FilterPlotandExploreRStudio/tutorial.md @@ -55,6 +55,8 @@ notebook: snippet: topics/single-cell/tutorials/scrna-case_FilterPlotandExploreRStudio/preamble.md --- +{% snippet topics/single-cell/faqs/notebook_warning.md %} + # Setting your environment First thing's first, we need to load the packages we will be using. In order to use any functions of a package, we must first call the library of that package. In your console (likely in the lower left corner of your RStudio window), run the following lines of code to do so: diff --git a/topics/single-cell/tutorials/scrna-case_JUPYTER-trajectories/preamble.md b/topics/single-cell/tutorials/scrna-case_JUPYTER-trajectories/preamble.md index 8e60bdadd86bb8..d08fd95981ae5b 100644 --- a/topics/single-cell/tutorials/scrna-case_JUPYTER-trajectories/preamble.md +++ b/topics/single-cell/tutorials/scrna-case_JUPYTER-trajectories/preamble.md @@ -52,15 +52,6 @@ We've provided you with experimental data to analyse from a mouse dataset of fet > {: .hands_on} -# Important tips for easier analysis - -{% snippet faqs/galaxy/tutorial_mode.md %} - -> -> - The Galaxy tool search panel sometimes doesn't find the tools we need from the thousands available. -> - You'll have a much easier time selecting tools from the panel (if you aren't using tutorial mode!) if you are on the [https://humancellatlas.usegalaxy.eu](https://humancellatlas.usegalaxy.eu) -{: .comment} - ## Filtering for T-cells One problem with our current dataset is that it's not just T-cells: we found in the previous tutorial that it also contains macrophages. This is a problem, because trajectory analysis will generally try to find relationships between all the cells in the sample. We need to remove those cell types to analyse the trajectory. @@ -120,7 +111,7 @@ You have two options for how to proceed with this tutorial - either you download > > 1. Open a Terminal in JupyterLab with File -> New -> Terminal > -> 2. Run +> 2. Run > ``` > wget {{ ipynbpath }} > ``` diff --git a/topics/single-cell/tutorials/scrna-case_JUPYTER-trajectories/tutorial.md b/topics/single-cell/tutorials/scrna-case_JUPYTER-trajectories/tutorial.md index e13b7877bfeda9..4285cee64e1371 100644 --- a/topics/single-cell/tutorials/scrna-case_JUPYTER-trajectories/tutorial.md +++ b/topics/single-cell/tutorials/scrna-case_JUPYTER-trajectories/tutorial.md @@ -52,6 +52,8 @@ notebook: From now on, you can view this tutorial in the Jupyter notebook, which will allow you to read the material and simultaneously execute the code cells! You may have to change certain numbers in the code blocks, so do read carefully. The tutorial is adapted from the [Scanpy Trajectory inference tutorial](https://scanpy-tutorials.readthedocs.io/en/latest/paga-paul15.html). +{% snippet topics/single-cell/faqs/notebook_warning.md %} + ## Install modules & activate them ```python diff --git a/topics/single-cell/tutorials/scrna-case_alevin-combine-datasets/tutorial.md b/topics/single-cell/tutorials/scrna-case_alevin-combine-datasets/tutorial.md index 93a4487a66d1d2..8a06fad5821ebb 100644 --- a/topics/single-cell/tutorials/scrna-case_alevin-combine-datasets/tutorial.md +++ b/topics/single-cell/tutorials/scrna-case_alevin-combine-datasets/tutorial.md @@ -127,8 +127,6 @@ Inspect the {% icon galaxy-eye %} `Experimental Design` text file. This shows yo ## Concatenating objects -{% snippet faqs/galaxy/tutorial_mode.md %} - > Concatenating AnnData objects > > 1. {% tool [Manipulate AnnData](toolshed.g2.bx.psu.edu/repos/iuc/anndata_manipulate/anndata_manipulate/0.7.5+galaxy1) %} with the following parameters: diff --git a/topics/single-cell/tutorials/scrna-case_basic-pipeline/tutorial.md b/topics/single-cell/tutorials/scrna-case_basic-pipeline/tutorial.md index 15e3d93b0a9d71..3ecd8fdf93c4b0 100644 --- a/topics/single-cell/tutorials/scrna-case_basic-pipeline/tutorial.md +++ b/topics/single-cell/tutorials/scrna-case_basic-pipeline/tutorial.md @@ -118,8 +118,6 @@ You can access the data for this tutorial in multiple ways: You have generated an annotated AnnData object from your raw scRNA-seq fastq files. However, you have only completed a 'rough' filter of your dataset - there will still be a number of 'cells' that are actually just background from empty droplets or simply low-quality. There will also be genes that could be sequencing artifacts or that appear with such low frequency that statistical tools will fail to analyse them. This background garbage of both cells and genes not only makes it harder to distinguish real biological information from the noise, but also makes it computationally heavy to analyse. These spurious reads take a lot of computational power to analyse! First on our agenda is to filter this matrix to give us cleaner data to extract meaningful insight from, and to allow faster analysis. -{% snippet faqs/galaxy/tutorial_mode.md %} - > > > 1. What information is stored in your AnnData object? The last tool to generate this object counted the mitochondrial associated genes in your matrix. Where is that data stored? diff --git a/topics/single-cell/tutorials/scrna-case_monocle3-rstudio/tutorial.md b/topics/single-cell/tutorials/scrna-case_monocle3-rstudio/tutorial.md index 35d2a4f5b6a8e5..49f2678ec7193f 100644 --- a/topics/single-cell/tutorials/scrna-case_monocle3-rstudio/tutorial.md +++ b/topics/single-cell/tutorials/scrna-case_monocle3-rstudio/tutorial.md @@ -56,6 +56,8 @@ notebook: snippet: topics/single-cell/tutorials/scrna-case_monocle3-rstudio/preamble.md --- +{% snippet topics/single-cell/faqs/notebook_warning.md %} + ## Setting up the environment and file upload Once the installation is done, we should load the needed packages into our notebook. Navigate back to your `notebook`. If you are using our prepopulated notebook, you can follow the tutorial from there. Otherwise, input the following into your fresh notebook. diff --git a/topics/statistics/tutorials/FNN/tutorial.md b/topics/statistics/tutorials/FNN/tutorial.md index 8d2f99d60308c9..2237d9d36fd8cf 100644 --- a/topics/statistics/tutorials/FNN/tutorial.md +++ b/topics/statistics/tutorials/FNN/tutorial.md @@ -339,7 +339,7 @@ dataset has 723 training examples, and our test dataset has 242 test examples. I > Model config > -> - {% tool [Create a deep learning model architecture](toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/0.5.0) %} +> - {% tool [Create a deep learning model architecture](toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/1.0.10.0) %} > - *"Select keras model type"*: `sequential` > - *"input_shape"*: `(5,)` > - In *"LAYER"*: @@ -366,7 +366,7 @@ layers use ReLU activation function. The model config can be downloaded as a JSO > Model builder (Optimizer, loss function, and fit parameters) > -> - {% tool [Create deep learning model](toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/0.5.0) %} +> - {% tool [Create deep learning model](toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/1.0.10.0) %} > - *"Choose a building mode"*: `Build a training model` > - *"Select the dataset containing model configuration"*: Select the *Keras Model Config* from the previous step. > - *"Do classification or regression?"*: `KerasGRegressor` @@ -391,7 +391,7 @@ batch_size decides the size of this subset (which we set to 50). The model build > Training the model > -> - {% tool [Deep learning training and evaluation](toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.8.3) %} +> - {% tool [Deep learning training and evaluation](toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.10.0) %} > - *"Select a scheme"*: `Train and Validate` > - *"Choose the dataset containing pipeline/estimator object"*: Select the *Keras Model Builder* from the previous step. > - *"Select input type:"*: `tabular data` @@ -406,14 +406,13 @@ batch_size decides the size of this subset (which we set to 50). The model build > {: .hands_on} -The training step generates 3 datasets. 1) accuracy of the trained model, 2) the trained model, downloadable as a zip file, and 3) the trained -model weights, downloadable as an hdf5 file. These files are needed for prediction in the next step. +The training step generates 2 datasets. 1) accuracy of the trained model, 2) the trained model, in h5mlm format. These files are needed for prediction in the next step. ## Model Prediction > Testing the model > -> - {% tool [Model Prediction](toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.8.3) %} +> - {% tool [Model Prediction](toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.10.0) %} > - *"Choose the dataset containing pipeline/estimator object"* : Select the trained model from the previous step. > - *"Choose the dataset containing weights for the estimator above"* : Select the trained model weights from the previous step. > - *"Select invocation method"*: `predict` diff --git a/topics/statistics/tutorials/FNN/workflows/Intro_To_FNN.ga b/topics/statistics/tutorials/FNN/workflows/Intro_To_FNN.ga deleted file mode 100644 index f6a349d346bcd5..00000000000000 --- a/topics/statistics/tutorials/FNN/workflows/Intro_To_FNN.ga +++ /dev/null @@ -1,508 +0,0 @@ -{ - "a_galaxy_workflow": "true", - "annotation": "Introduction to feedforward neural networks (FNN)", - "format-version": "0.1", - "name": "Intro_To_FNN", - "steps": { - "0": { - "annotation": "", - "content_id": null, - "errors": null, - "id": 0, - "input_connections": {}, - "inputs": [ - { - "description": "", - "name": "X_train" - } - ], - "label": "X_train", - "name": "Input dataset", - "outputs": [], - "position": { - "bottom": 254.70170211791992, - "height": 61.73295211791992, - "left": 392.9829406738281, - "right": 592.9829406738281, - "top": 192.96875, - "width": 200, - "x": 392.9829406738281, - "y": 192.96875 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null}", - "tool_version": null, - "type": "data_input", - "uuid": "478ba9f7-22f6-4615-aec6-ddad97da39d9", - "workflow_outputs": [ - { - "label": null, - "output_name": "output", - "uuid": "f01fb19d-e816-48dc-b4e3-509f159fe0d6" - } - ] - }, - "1": { - "annotation": "", - "content_id": null, - "errors": null, - "id": 1, - "input_connections": {}, - "inputs": [ - { - "description": "", - "name": "y_train" - } - ], - "label": "y_train", - "name": "Input dataset", - "outputs": [], - "position": { - "bottom": 374.7301139831543, - "height": 61.73295211791992, - "left": 392.9829406738281, - "right": 592.9829406738281, - "top": 312.9971618652344, - "width": 200, - "x": 392.9829406738281, - "y": 312.9971618652344 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null}", - "tool_version": null, - "type": "data_input", - "uuid": "1168c128-8c62-4ee1-8c19-3c8ac839cf93", - "workflow_outputs": [ - { - "label": null, - "output_name": "output", - "uuid": "209b92da-d490-4e4d-a881-ce3b755fce35" - } - ] - }, - "2": { - "annotation": "", - "content_id": null, - "errors": null, - "id": 2, - "input_connections": {}, - "inputs": [ - { - "description": "", - "name": "X_test" - } - ], - "label": "X_test", - "name": "Input dataset", - "outputs": [], - "position": { - "bottom": 494.71589279174805, - "height": 61.73295211791992, - "left": 392.9829406738281, - "right": 592.9829406738281, - "top": 432.9829406738281, - "width": 200, - "x": 392.9829406738281, - "y": 432.9829406738281 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null}", - "tool_version": null, - "type": "data_input", - "uuid": "d89f919d-330a-4c88-959e-4e39d1d86373", - "workflow_outputs": [ - { - "label": null, - "output_name": "output", - "uuid": "92fa6af3-d4b1-41e6-bad3-b498abf14e8d" - } - ] - }, - "3": { - "annotation": "", - "content_id": null, - "errors": null, - "id": 3, - "input_connections": {}, - "inputs": [ - { - "description": "", - "name": "y_test" - } - ], - "label": "y_test", - "name": "Input dataset", - "outputs": [], - "position": { - "bottom": 614.7300834655762, - "height": 61.73295211791992, - "left": 392.9829406738281, - "right": 592.9829406738281, - "top": 552.9971313476562, - "width": 200, - "x": 392.9829406738281, - "y": 552.9971313476562 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null}", - "tool_version": null, - "type": "data_input", - "uuid": "1e3f710b-8098-4847-aed0-f21eceb7029d", - "workflow_outputs": [ - { - "label": null, - "output_name": "output", - "uuid": "65dae08e-33a0-4576-af09-2507dcd35ccc" - } - ] - }, - "4": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/0.5.0", - "errors": null, - "id": 4, - "input_connections": {}, - "inputs": [], - "label": null, - "name": "Create a deep learning model architecture", - "outputs": [ - { - "name": "outfile", - "type": "json" - } - ], - "position": { - "bottom": 775.4971313476562, - "height": 102.5, - "left": 392.9829406738281, - "right": 592.9829406738281, - "top": 672.9971313476562, - "width": 200, - "x": 392.9829406738281, - "y": 672.9971313476562 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/0.5.0", - "tool_shed_repository": { - "changeset_revision": "0c933465d70e", - "name": "keras_model_config", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"model_selection\": {\"model_type\": \"sequential\", \"__current_case__\": 0, \"input_shape\": \"(5, )\", \"layers\": [{\"__index__\": 0, \"layer_selection\": {\"layer_type\": \"Dense\", \"__current_case__\": 0, \"units\": \"12\", \"activation\": \"relu\", \"kwargs\": \"\"}}, {\"__index__\": 1, \"layer_selection\": {\"layer_type\": \"Dense\", \"__current_case__\": 0, \"units\": \"8\", \"activation\": \"relu\", \"kwargs\": \"\"}}, {\"__index__\": 2, \"layer_selection\": {\"layer_type\": \"Dense\", \"__current_case__\": 0, \"units\": \"1\", \"activation\": \"linear\", \"kwargs\": \"\"}}]}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "0.5.0", - "type": "tool", - "uuid": "d354a1dd-3096-4d93-880f-4e38852bcf9c", - "workflow_outputs": [ - { - "label": null, - "output_name": "outfile", - "uuid": "9588723b-7ab1-4360-87c1-5ccab374d34c" - } - ] - }, - "5": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/0.5.0", - "errors": null, - "id": 5, - "input_connections": { - "mode_selection|infile_json": { - "id": 4, - "output_name": "outfile" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Create deep learning model", - "name": "mode_selection" - } - ], - "label": null, - "name": "Create deep learning model", - "outputs": [ - { - "name": "outfile", - "type": "zip" - } - ], - "position": { - "bottom": 367.61363220214844, - "height": 174.64488220214844, - "left": 612.9971313476562, - "right": 812.9971313476562, - "top": 192.96875, - "width": 200, - "x": 612.9971313476562, - "y": 192.96875 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/0.5.0", - "tool_shed_repository": { - "changeset_revision": "9b6faa256f15", - "name": "keras_model_builder", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"mode_selection\": {\"mode_type\": \"train_model\", \"__current_case__\": 0, \"infile_json\": {\"__class__\": \"RuntimeValue\"}, \"learning_type\": \"KerasGRegressor\", \"compile_params\": {\"loss\": \"mean_squared_error\", \"optimizer_selection\": {\"optimizer_type\": \"Adam\", \"__current_case__\": 4, \"optimizer_options\": {\"lr\": \"0.001\", \"decay\": \"0.0\", \"beta_1\": \"0.9\", \"beta_2\": \"0.999\", \"amsgrad\": \"false\"}}, \"metrics\": [\"mse\", \"mae\"]}, \"fit_params\": {\"epochs\": \"150\", \"batch_size\": \"50\", \"steps_per_epoch\": null, \"validation_steps\": null, \"callbacks\": [{\"__index__\": 0, \"callback_selection\": {\"callback_type\": \"None\", \"__current_case__\": 0}}]}, \"random_seed\": null, \"get_params\": \"false\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "0.5.0", - "type": "tool", - "uuid": "86e097fa-a489-4d9d-b115-a0f02d15ab70", - "workflow_outputs": [ - { - "label": null, - "output_name": "outfile", - "uuid": "2a670da1-9019-4162-a2ac-174051641213" - } - ] - }, - "6": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.8.3", - "errors": null, - "id": 6, - "input_connections": { - "experiment_schemes|infile_estimator": { - "id": 5, - "output_name": "outfile" - }, - "input_options|infile1": { - "id": 0, - "output_name": "output" - }, - "input_options|infile2": { - "id": 1, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Deep learning training and evaluation", - "name": "experiment_schemes" - }, - { - "description": "runtime parameter for tool Deep learning training and evaluation", - "name": "input_options" - }, - { - "description": "runtime parameter for tool Deep learning training and evaluation", - "name": "input_options" - } - ], - "label": null, - "name": "Deep learning training and evaluation", - "outputs": [ - { - "name": "outfile_result", - "type": "tabular" - }, - { - "name": "outfile_object", - "type": "zip" - }, - { - "name": "outfile_weights", - "type": "h5" - } - ], - "position": { - "bottom": 641.8323669433594, - "height": 448.8636169433594, - "left": 832.9971313476562, - "right": 1032.9971313476562, - "top": 192.96875, - "width": 200, - "x": 832.9971313476562, - "y": 192.96875 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.8.3", - "tool_shed_repository": { - "changeset_revision": "ead8f1822587", - "name": "keras_train_and_eval", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__job_resource\": {\"__job_resource__select\": \"no\", \"__current_case__\": 0}, \"experiment_schemes\": {\"selected_exp_scheme\": \"train_val\", \"__current_case__\": 0, \"infile_estimator\": {\"__class__\": \"RuntimeValue\"}, \"hyperparams_swapping\": {\"infile_params\": {\"__class__\": \"RuntimeValue\"}, \"param_set\": [{\"__index__\": 0, \"sp_name\": null, \"sp_value\": \"\"}]}, \"test_split\": {\"split_algos\": {\"shuffle\": \"simple\", \"__current_case__\": 1, \"test_size\": \"0.2\", \"random_state\": null}}, \"metrics\": {\"scoring\": {\"primary_scoring\": \"default\", \"__current_case__\": 0}}}, \"input_options\": {\"selected_input\": \"tabular\", \"__current_case__\": 0, \"infile1\": {\"__class__\": \"RuntimeValue\"}, \"header1\": \"true\", \"column_selector_options_1\": {\"selected_column_selector_option\": \"all_columns\", \"__current_case__\": 4}, \"infile2\": {\"__class__\": \"RuntimeValue\"}, \"header2\": \"true\", \"column_selector_options_2\": {\"selected_column_selector_option2\": \"all_columns\", \"__current_case__\": 4}}, \"save\": [\"save_estimator\"], \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.0.8.3", - "type": "tool", - "uuid": "60e71355-fd81-4f60-8ef7-0cc5603cb374", - "workflow_outputs": [ - { - "label": null, - "output_name": "outfile_result", - "uuid": "78aea1bd-8450-4556-b29a-137896af643a" - }, - { - "label": null, - "output_name": "outfile_object", - "uuid": "5d22057f-dc14-460f-974a-cb43cfc1a201" - }, - { - "label": null, - "output_name": "outfile_weights", - "uuid": "6cd64871-ef5c-4613-b567-2cbccfb01c95" - } - ] - }, - "7": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.8.3", - "errors": null, - "id": 7, - "input_connections": { - "infile_estimator": { - "id": 6, - "output_name": "outfile_object" - }, - "infile_weights": { - "id": 6, - "output_name": "outfile_weights" - }, - "input_options|infile1": { - "id": 2, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Model Prediction", - "name": "infile_estimator" - }, - { - "description": "runtime parameter for tool Model Prediction", - "name": "infile_weights" - }, - { - "description": "runtime parameter for tool Model Prediction", - "name": "input_options" - } - ], - "label": null, - "name": "Model Prediction", - "outputs": [ - { - "name": "outfile_predict", - "type": "tabular" - } - ], - "position": { - "bottom": 428.38067626953125, - "height": 235.41192626953125, - "left": 1052.98291015625, - "right": 1252.98291015625, - "top": 192.96875, - "width": 200, - "x": 1052.98291015625, - "y": 192.96875 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.8.3", - "tool_shed_repository": { - "changeset_revision": "60c726f5cc5e", - "name": "model_prediction", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__job_resource\": {\"__job_resource__select\": \"no\", \"__current_case__\": 0}, \"infile_estimator\": {\"__class__\": \"RuntimeValue\"}, \"infile_weights\": {\"__class__\": \"RuntimeValue\"}, \"input_options\": {\"selected_input\": \"tabular\", \"__current_case__\": 0, \"infile1\": {\"__class__\": \"RuntimeValue\"}, \"header1\": \"true\", \"column_selector_options_1\": {\"selected_column_selector_option\": \"all_columns\", \"__current_case__\": 4}}, \"method\": \"predict\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.0.8.3", - "type": "tool", - "uuid": "8d6663a6-5d7f-47ea-b223-518bc9972806", - "workflow_outputs": [ - { - "label": null, - "output_name": "outfile_predict", - "uuid": "0d958d00-aed8-488a-99af-fc2d0e5c8097" - } - ] - }, - "8": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/plotly_regression_performance_plots/plotly_regression_performance_plots/0.1", - "errors": null, - "id": 8, - "input_connections": { - "infile_input": { - "id": 3, - "output_name": "output" - }, - "infile_output": { - "id": 7, - "output_name": "outfile_predict" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Plot actual vs predicted curves and residual plots", - "name": "infile_input" - }, - { - "description": "runtime parameter for tool Plot actual vs predicted curves and residual plots", - "name": "infile_output" - } - ], - "label": null, - "name": "Plot actual vs predicted curves and residual plots", - "outputs": [ - { - "name": "output_actual_vs_pred", - "type": "html" - }, - { - "name": "output_scatter_plot", - "type": "html" - }, - { - "name": "output_residual_plot", - "type": "html" - } - ], - "position": { - "bottom": 560.6817932128906, - "height": 367.7130432128906, - "left": 1272.9970703125, - "right": 1472.9970703125, - "top": 192.96875, - "width": 200, - "x": 1272.9970703125, - "y": 192.96875 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/plotly_regression_performance_plots/plotly_regression_performance_plots/0.1", - "tool_shed_repository": { - "changeset_revision": "389227fa1864", - "name": "plotly_regression_performance_plots", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"infile_input\": {\"__class__\": \"RuntimeValue\"}, \"infile_output\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "0.1", - "type": "tool", - "uuid": "4ba08ee0-dbdd-4b6a-8fc2-5eea1af0e567", - "workflow_outputs": [ - { - "label": null, - "output_name": "output_actual_vs_pred", - "uuid": "74eae0e4-6b80-4091-b46a-16c58d2ce36b" - }, - { - "label": null, - "output_name": "output_scatter_plot", - "uuid": "5f42df99-c504-47b0-bb0a-9b6033141413" - }, - { - "label": null, - "output_name": "output_residual_plot", - "uuid": "2c6b76a6-0869-4ab6-84bc-11d555ab1b2f" - } - ] - } - }, - "tags": [ - "statistics", - "ml", - "fnn" - ], - "uuid": "85038aae-2c0f-42c6-9be7-686906fd1b00", - "version": 1 -} diff --git a/topics/statistics/tutorials/FNN/workflows/Intro_To_FNN_v1_0_10_0-test.yml b/topics/statistics/tutorials/FNN/workflows/Intro_To_FNN_v1_0_10_0-test.yml new file mode 100644 index 00000000000000..3bea4dc4366658 --- /dev/null +++ b/topics/statistics/tutorials/FNN/workflows/Intro_To_FNN_v1_0_10_0-test.yml @@ -0,0 +1,23 @@ +- doc: Test outline for Intro_To_FNN_v1_0_10_0 + job: + X_test: + class: File + path: https://zenodo.org/records/4660497/files/X_test.tsv + filetype: tabular + X_train: + class: File + path: https://zenodo.org/records/4660497/files/X_train.tsv + filetype: tabular + y_test: + class: File + path: https://zenodo.org/records/4660497/files/y_test.tsv + filetype: tabular + y_train: + class: File + path: https://zenodo.org/records/4660497/files/y_train.tsv + filetype: tabular + outputs: + output_actual_vs_pred: + asserts: + has_text: + text: 'True vs predicted values' diff --git a/topics/statistics/tutorials/FNN/workflows/Intro_To_FNN_v1_0_10_0.ga b/topics/statistics/tutorials/FNN/workflows/Intro_To_FNN_v1_0_10_0.ga new file mode 100644 index 00000000000000..1be121c4c57563 --- /dev/null +++ b/topics/statistics/tutorials/FNN/workflows/Intro_To_FNN_v1_0_10_0.ga @@ -0,0 +1,343 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "", + "creator": [{"class": "Person", "identifier":"0000-0001-6585-3619", "name": "Kaivan Kamali"}], + "format-version": "0.1", + "license": "CC-BY-4.0", + "name": "Intro_To_FNN_v1_0_10_0", + "steps": { + "0": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "X_test" + } + ], + "label": "X_test", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 10, + "top": 10 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "d9e33ebf-398b-41f5-83d4-aecd6f42817d", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "X_train" + } + ], + "label": "X_train", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 10, + "top": 130 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "ad5497f9-1638-4f14-835e-4ba48ccccfad", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "y_test" + } + ], + "label": "y_test", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 10, + "top": 250 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "e9939b7b-c469-4823-9339-799a0b47397e", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 3, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "y_train" + } + ], + "label": "y_train", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 10, + "top": 370 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "978203ee-a2bc-4cf7-ad01-0793b7e27431", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/1.0.10.0", + "errors": null, + "id": 4, + "input_connections": {}, + "inputs": [], + "label": null, + "name": "Create a deep learning model architecture", + "outputs": [ + { + "name": "outfile", + "type": "json" + } + ], + "position": { + "left": 10, + "top": 490 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/1.0.10.0", + "tool_shed_repository": { + "changeset_revision": "f22a9297440f", + "name": "keras_model_config", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/cvmfs/data.galaxyproject.org/managed/len/ucsc/?.len\", \"model_selection\": {\"model_type\": \"sequential\", \"__current_case__\": 0, \"input_shape\": \"(5, )\", \"layers\": [{\"__index__\": 0, \"layer_selection\": {\"layer_type\": \"Dense\", \"__current_case__\": 0, \"units\": \"12\", \"activation\": \"relu\", \"kwargs\": \"\"}}, {\"__index__\": 1, \"layer_selection\": {\"layer_type\": \"Dense\", \"__current_case__\": 0, \"units\": \"8\", \"activation\": \"relu\", \"kwargs\": \"\"}}, {\"__index__\": 2, \"layer_selection\": {\"layer_type\": \"Dense\", \"__current_case__\": 0, \"units\": \"1\", \"activation\": \"linear\", \"kwargs\": \"\"}}]}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": null, + "type": "tool", + "uuid": "0221dde4-c749-4494-97ff-7deb5a90f655", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/1.0.10.0", + "errors": null, + "id": 5, + "input_connections": { + "mode_selection|infile_json": { + "id": 4, + "output_name": "outfile" + } + }, + "inputs": [], + "label": null, + "name": "Create deep learning model", + "outputs": [ + { + "name": "outfile", + "type": "h5mlm" + } + ], + "position": { + "left": 230, + "top": 10 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/1.0.10.0", + "tool_shed_repository": { + "changeset_revision": "66d7efc06000", + "name": "keras_model_builder", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/cvmfs/data.galaxyproject.org/managed/len/ucsc/?.len\", \"mode_selection\": {\"mode_type\": \"train_model\", \"__current_case__\": 0, \"infile_json\": null, \"learning_type\": \"KerasGRegressor\", \"compile_params\": {\"loss\": \"mean_squared_error\", \"optimizer_selection\": {\"optimizer_type\": \"Adam\", \"__current_case__\": 4, \"optimizer_options\": {\"learning_rate\": \"0.001\", \"beta_1\": \"0.9\", \"beta_2\": \"0.999\", \"epsilon\": \"1e-07\", \"amsgrad\": false}}, \"metrics\": [\"mse\"]}, \"fit_params\": {\"epochs\": \"150\", \"batch_size\": \"50\", \"steps_per_epoch\": null, \"validation_split\": \"0.1\", \"validation_steps\": null, \"callbacks\": [{\"__index__\": 0, \"callback_selection\": {\"callback_type\": \"None\", \"__current_case__\": 0}}], \"verbose\": \"1\"}, \"random_seed\": null}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": null, + "type": "tool", + "uuid": "8e860dd7-b1fc-48c3-840b-071580f3189f", + "when": null, + "workflow_outputs": [] + }, + "6": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.10.0", + "errors": null, + "id": 6, + "input_connections": { + "experiment_schemes|infile_estimator": { + "id": 5, + "output_name": "outfile" + }, + "input_options|infile1": { + "id": 1, + "output_name": "output" + }, + "input_options|infile2": { + "id": 3, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Deep learning training and evaluation", + "outputs": [ + { + "name": "outfile_result", + "type": "tabular" + }, + { + "name": "outfile_object", + "type": "h5mlm" + } + ], + "position": { + "left": 450, + "top": 10 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.10.0", + "tool_shed_repository": { + "changeset_revision": "818f9b69d8a0", + "name": "keras_train_and_eval", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/cvmfs/data.galaxyproject.org/managed/len/ucsc/?.len\", \"experiment_schemes\": {\"selected_exp_scheme\": \"train_val\", \"__current_case__\": 0, \"infile_estimator\": null, \"hyperparams_swapping\": {\"param_set\": [{\"__index__\": 0, \"sp_name\": null, \"sp_value\": \"\"}]}, \"test_split\": {\"split_algos\": {\"shuffle\": \"simple\", \"__current_case__\": 1, \"test_size\": \"0.2\", \"random_state\": null}}, \"metrics\": {\"scoring\": {\"primary_scoring\": \"neg_mean_squared_error\", \"__current_case__\": 23, \"secondary_scoring\": null}}}, \"input_options\": {\"selected_input\": \"tabular\", \"__current_case__\": 0, \"infile1\": null, \"header1\": true, \"column_selector_options_1\": {\"selected_column_selector_option\": \"all_columns\", \"__current_case__\": 4}, \"infile2\": null, \"header2\": true, \"column_selector_options_2\": {\"selected_column_selector_option2\": \"all_columns\", \"__current_case__\": 4}}, \"save\": \"save_estimator\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": null, + "type": "tool", + "uuid": "6c3c43bd-8197-4f75-b6f8-d3262713291e", + "when": null, + "workflow_outputs": [] + }, + "7": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.10.0", + "errors": null, + "id": 7, + "input_connections": { + "infile_estimator": { + "id": 6, + "output_name": "outfile_object" + }, + "input_options|infile1": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Model Prediction", + "outputs": [ + { + "name": "outfile_predict", + "type": "tabular" + } + ], + "position": { + "left": 670, + "top": 10 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.10.0", + "tool_shed_repository": { + "changeset_revision": "9991c4ddde14", + "name": "model_prediction", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/cvmfs/data.galaxyproject.org/managed/len/ucsc/?.len\", \"infile_estimator\": null, \"input_options\": {\"selected_input\": \"tabular\", \"__current_case__\": 0, \"infile1\": null, \"header1\": true, \"column_selector_options_1\": {\"selected_column_selector_option\": \"all_columns\", \"__current_case__\": 4}}, \"method\": \"predict\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": null, + "type": "tool", + "uuid": "b600be41-d100-4ed9-b39d-eff85a09eb49", + "when": null, + "workflow_outputs": [] + }, + "8": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/plotly_regression_performance_plots/plotly_regression_performance_plots/0.1", + "errors": null, + "id": 8, + "input_connections": { + "infile_input": { + "id": 2, + "output_name": "output" + }, + "infile_output": { + "id": 7, + "output_name": "outfile_predict" + } + }, + "inputs": [], + "label": null, + "name": "Plot actual vs predicted curves and residual plots", + "outputs": [ + { + "name": "output_actual_vs_pred", + "type": "html" + }, + { + "name": "output_scatter_plot", + "type": "html" + }, + { + "name": "output_residual_plot", + "type": "html" + } + ], + "position": { + "left": 890, + "top": 10 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/plotly_regression_performance_plots/plotly_regression_performance_plots/0.1", + "tool_shed_repository": { + "changeset_revision": "389227fa1864", + "name": "plotly_regression_performance_plots", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"tabular\", \"chromInfo\": \"/cvmfs/data.galaxyproject.org/managed/len/ucsc/?.len\", \"infile_input\": null, \"infile_output\": null, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": null, + "type": "tool", + "uuid": "15be4f9a-762b-495a-a7b2-f8f5b3f0f042", + "when": null, + "workflow_outputs": [] + } + }, + "tags": [ + "statistics", + "ml", + "fnn" + ], + "uuid": "bd1e9e38-997b-41e0-9556-ccf13490fa08", + "version": 1 +} diff --git a/topics/statistics/tutorials/RNN/tutorial.md b/topics/statistics/tutorials/RNN/tutorial.md index ece79a8dd04f39..796ddc94d63384 100644 --- a/topics/statistics/tutorials/RNN/tutorial.md +++ b/topics/statistics/tutorials/RNN/tutorial.md @@ -255,11 +255,11 @@ In the section, we define a RNN and train it using IMDB movie reviews training d words in a review we can predict whether the review was positive or negative. We then evaluate the trained RNN on the test dataset and plot the confusion matrix. -### **Create a deep learning model architecture** +## Create a deep learning model architecture > Model config > -> - {% tool [Create a deep learning model architecture](toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/0.5.0) %} +> - {% tool [Create a deep learning model architecture](toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/1.0.10.0) %} > - *"Select keras model type"*: `sequential` > - *"input_shape"*: `(500,)` > - In *"LAYER"*: @@ -284,11 +284,11 @@ an embedding layer, that transforms each review words into a 32 dimensional vect *sigmoid* activation function, that generates an output between 0 and 1. Any output greater than 0.5 is considered a predicted positive review, and anything less than 0.5 a negative one. The model config can be downloaded as a JSON file. -### **Create a deep learning model** +## Create a deep learning model > Model builder (Optimizer, loss function, and fit parameters) > -> - {% tool [Create deep learning model](toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/0.5.0) %} +> - {% tool [Create deep learning model](toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/1.0.10.0) %} > - *"Choose a building mode"*: `Build a training model` > - *"Select the dataset containing model configuration"*: Select the *Keras Model Config* from the previous step. > - *"Do classification or regression?"*: `KerasGClassifier` @@ -309,11 +309,11 @@ feed to the network, the training will be very slow (as we have 25000 training e only a subset of the training examples to the network, after which we update the weights/biases. *batch_size* decides the size of this subset. The model builder can be downloaded as a zip file. -### **Deep learning training and evaluation** +## Deep learning training and evaluation > Training the model > -> - {% tool [Deep learning training and evaluation](toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.8.3) %} +> - {% tool [Deep learning training and evaluation](toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.10.0) %} > - *"Select a scheme"*: `Train and Validate` > - *"Choose the dataset containing pipeline/estimator object"*: Select the *Keras Model Builder* from the previous step. > - *"Select input type:"*: `tabular data` @@ -326,14 +326,13 @@ The model builder can be downloaded as a zip file. > {: .hands_on} -The training step generates 3 datasets. 1) accuracy of the trained model, 2) the trained model, downloadable as a zip file, and 3) the trained -model weights, downloadable as an hdf5 file. These files are needed for prediction in the next step. +The training step generates 2 datasets. 1) accuracy of the trained model, 2) the trained model, in h5mlm format. These files are needed for prediction in the next step. -### **Model Prediction** +## Model Prediction > Testing the model > -> - {% tool [Model Prediction](toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.8.3) %} +> - {% tool [Model Prediction](toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.10.0) %} > - *"Choose the dataset containing pipeline/estimator object"* : Select the trained model from the previous step. > - *"Choose the dataset containing weights for the estimator above"* : Select the trained model weights from the previous step. > - *"Select invocation method"*: `predict` @@ -347,11 +346,11 @@ model weights, downloadable as an hdf5 file. These files are needed for predicti The prediction step generates 1 dataset. It's a file that has predictions (1 or 0 for positive or negative movie reviews) for every review in the test dataset. -### **Machine Learning Visualization Extension** +## Machine Learning Visualization Extension > Creating the confusion matrix > -> - {% tool [Machine Learning Visualization Extension](toolshed.g2.bx.psu.edu/repos/bgruening/ml_visualization_ex/ml_visualization_ex/1.0.8.3) %} +> - {% tool [Machine Learning Visualization Extension](toolshed.g2.bx.psu.edu/repos/bgruening/ml_visualization_ex/ml_visualization_ex/1.0.10.0) %} > - *"Select a plotting type"*: `Confusion matrix for classes` > - *"Select dataset containing the true labels"*": `y_test` > - *"Choose how to select data by column:"*: `All columns` diff --git a/topics/statistics/tutorials/RNN/workflows/Intro_To_RNN.ga b/topics/statistics/tutorials/RNN/workflows/Intro_To_RNN.ga deleted file mode 100644 index 76b51f2c3ab263..00000000000000 --- a/topics/statistics/tutorials/RNN/workflows/Intro_To_RNN.ga +++ /dev/null @@ -1,466 +0,0 @@ -{ - "a_galaxy_workflow": "true", - "annotation": "Introduction to RNNs", - "format-version": "0.1", - "name": "Intro_To_RNN", - "steps": { - "0": { - "annotation": "", - "content_id": null, - "errors": null, - "id": 0, - "input_connections": {}, - "inputs": [ - { - "description": "", - "name": "X_test" - } - ], - "label": "X_test", - "name": "Input dataset", - "outputs": [], - "position": { - "bottom": 342.6988639831543, - "height": 61.73295211791992, - "left": 680.9801025390625, - "right": 880.9801025390625, - "top": 280.9659118652344, - "width": 200, - "x": 680.9801025390625, - "y": 280.9659118652344 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null}", - "tool_version": null, - "type": "data_input", - "uuid": "a5e70504-f58c-4e47-898e-e19862e263c8", - "workflow_outputs": [] - }, - "1": { - "annotation": "", - "content_id": null, - "errors": null, - "id": 1, - "input_connections": {}, - "inputs": [ - { - "description": "", - "name": "X_train" - } - ], - "label": "X_train", - "name": "Input dataset", - "outputs": [], - "position": { - "bottom": 462.72724533081055, - "height": 61.73295211791992, - "left": 680.9801025390625, - "right": 880.9801025390625, - "top": 400.9942932128906, - "width": 200, - "x": 680.9801025390625, - "y": 400.9942932128906 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null}", - "tool_version": null, - "type": "data_input", - "uuid": "8628fa07-9b42-43c3-9dfd-bb2a0a4b37e6", - "workflow_outputs": [] - }, - "2": { - "annotation": "", - "content_id": null, - "errors": null, - "id": 2, - "input_connections": {}, - "inputs": [ - { - "description": "", - "name": "y_test" - } - ], - "label": "y_test", - "name": "Input dataset", - "outputs": [], - "position": { - "bottom": 582.7130546569824, - "height": 61.73295211791992, - "left": 680.9801025390625, - "right": 880.9801025390625, - "top": 520.9801025390625, - "width": 200, - "x": 680.9801025390625, - "y": 520.9801025390625 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null}", - "tool_version": null, - "type": "data_input", - "uuid": "b832ca33-c953-482f-a600-45bdbdfdbf61", - "workflow_outputs": [] - }, - "3": { - "annotation": "", - "content_id": null, - "errors": null, - "id": 3, - "input_connections": {}, - "inputs": [ - { - "description": "", - "name": "y_train" - } - ], - "label": "y_train", - "name": "Input dataset", - "outputs": [], - "position": { - "bottom": 702.7272758483887, - "height": 61.73295211791992, - "left": 680.9801025390625, - "right": 880.9801025390625, - "top": 640.9943237304688, - "width": 200, - "x": 680.9801025390625, - "y": 640.9943237304688 - }, - "tool_id": null, - "tool_state": "{\"optional\": false, \"tag\": null}", - "tool_version": null, - "type": "data_input", - "uuid": "108d6cd4-1eb9-4782-9f62-206274dae3d0", - "workflow_outputs": [] - }, - "4": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/0.5.0", - "errors": null, - "id": 4, - "input_connections": {}, - "inputs": [], - "label": null, - "name": "Create a deep learning model architecture", - "outputs": [ - { - "name": "outfile", - "type": "json" - } - ], - "position": { - "bottom": 863.4801025390625, - "height": 102.5, - "left": 680.9801025390625, - "right": 880.9801025390625, - "top": 760.9801025390625, - "width": 200, - "x": 680.9801025390625, - "y": 760.9801025390625 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/0.5.0", - "tool_shed_repository": { - "changeset_revision": "0c933465d70e", - "name": "keras_model_config", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"model_selection\": {\"model_type\": \"sequential\", \"__current_case__\": 0, \"input_shape\": \"(500, )\", \"layers\": [{\"__index__\": 0, \"layer_selection\": {\"layer_type\": \"Embedding\", \"__current_case__\": 53, \"input_dim\": \"10000\", \"output_dim\": \"32\", \"kwargs\": \"\"}}, {\"__index__\": 1, \"layer_selection\": {\"layer_type\": \"LSTM\", \"__current_case__\": 45, \"units\": \"100\", \"kwargs\": \"\"}}, {\"__index__\": 2, \"layer_selection\": {\"layer_type\": \"Dense\", \"__current_case__\": 0, \"units\": \"1\", \"activation\": \"sigmoid\", \"kwargs\": \"\"}}]}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "0.5.0", - "type": "tool", - "uuid": "9f0aab1e-dbf8-4ebd-8374-2ed20a2aa3d2", - "workflow_outputs": [ - { - "label": null, - "output_name": "outfile", - "uuid": "117abab4-f1f1-4d86-910f-93b0e80a285c" - } - ] - }, - "5": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/0.5.0", - "errors": null, - "id": 5, - "input_connections": { - "mode_selection|infile_json": { - "id": 4, - "output_name": "outfile" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Create deep learning model", - "name": "mode_selection" - } - ], - "label": null, - "name": "Create deep learning model", - "outputs": [ - { - "name": "outfile", - "type": "zip" - } - ], - "position": { - "bottom": 455.6107940673828, - "height": 174.64488220214844, - "left": 900.9801025390625, - "right": 1100.9801025390625, - "top": 280.9659118652344, - "width": 200, - "x": 900.9801025390625, - "y": 280.9659118652344 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/0.5.0", - "tool_shed_repository": { - "changeset_revision": "9b6faa256f15", - "name": "keras_model_builder", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"mode_selection\": {\"mode_type\": \"train_model\", \"__current_case__\": 0, \"infile_json\": {\"__class__\": \"RuntimeValue\"}, \"learning_type\": \"KerasGClassifier\", \"compile_params\": {\"loss\": \"binary_crossentropy\", \"optimizer_selection\": {\"optimizer_type\": \"Adam\", \"__current_case__\": 4, \"optimizer_options\": {\"lr\": \"0.001\", \"decay\": \"0.0\", \"beta_1\": \"0.9\", \"beta_2\": \"0.999\", \"amsgrad\": \"false\"}}, \"metrics\": [\"acc\"]}, \"fit_params\": {\"epochs\": \"2\", \"batch_size\": \"128\", \"steps_per_epoch\": null, \"validation_steps\": null, \"callbacks\": [{\"__index__\": 0, \"callback_selection\": {\"callback_type\": \"None\", \"__current_case__\": 0}}]}, \"random_seed\": null, \"get_params\": \"false\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "0.5.0", - "type": "tool", - "uuid": "47786457-2fd4-432d-90c3-b1c22f39a358", - "workflow_outputs": [ - { - "label": null, - "output_name": "outfile", - "uuid": "746d4df4-57d9-4c2f-afe9-f507d657ed26" - } - ] - }, - "6": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.8.3", - "errors": null, - "id": 6, - "input_connections": { - "experiment_schemes|infile_estimator": { - "id": 5, - "output_name": "outfile" - }, - "input_options|infile1": { - "id": 1, - "output_name": "output" - }, - "input_options|infile2": { - "id": 3, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Deep learning training and evaluation", - "name": "experiment_schemes" - }, - { - "description": "runtime parameter for tool Deep learning training and evaluation", - "name": "input_options" - }, - { - "description": "runtime parameter for tool Deep learning training and evaluation", - "name": "input_options" - } - ], - "label": null, - "name": "Deep learning training and evaluation", - "outputs": [ - { - "name": "outfile_result", - "type": "tabular" - }, - { - "name": "outfile_object", - "type": "zip" - }, - { - "name": "outfile_weights", - "type": "h5" - } - ], - "position": { - "bottom": 729.8295288085938, - "height": 448.8636169433594, - "left": 1120.9801025390625, - "right": 1320.9801025390625, - "top": 280.9659118652344, - "width": 200, - "x": 1120.9801025390625, - "y": 280.9659118652344 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.8.3", - "tool_shed_repository": { - "changeset_revision": "ead8f1822587", - "name": "keras_train_and_eval", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__job_resource\": {\"__job_resource__select\": \"no\", \"__current_case__\": 0}, \"experiment_schemes\": {\"selected_exp_scheme\": \"train_val\", \"__current_case__\": 0, \"infile_estimator\": {\"__class__\": \"RuntimeValue\"}, \"hyperparams_swapping\": {\"infile_params\": {\"__class__\": \"RuntimeValue\"}, \"param_set\": [{\"__index__\": 0, \"sp_name\": null, \"sp_value\": \"\"}]}, \"test_split\": {\"split_algos\": {\"shuffle\": \"simple\", \"__current_case__\": 1, \"test_size\": \"0.2\", \"random_state\": null}}, \"metrics\": {\"scoring\": {\"primary_scoring\": \"default\", \"__current_case__\": 0}}}, \"input_options\": {\"selected_input\": \"tabular\", \"__current_case__\": 0, \"infile1\": {\"__class__\": \"RuntimeValue\"}, \"header1\": \"false\", \"column_selector_options_1\": {\"selected_column_selector_option\": \"all_columns\", \"__current_case__\": 4}, \"infile2\": {\"__class__\": \"RuntimeValue\"}, \"header2\": \"false\", \"column_selector_options_2\": {\"selected_column_selector_option2\": \"all_columns\", \"__current_case__\": 4}}, \"save\": [\"save_estimator\"], \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.0.8.3", - "type": "tool", - "uuid": "d0a5583e-26b4-4ebf-bb83-d33f7c047202", - "workflow_outputs": [ - { - "label": null, - "output_name": "outfile_object", - "uuid": "5e19e3b7-adb1-430d-9fc1-39537141bc20" - }, - { - "label": null, - "output_name": "outfile_weights", - "uuid": "ae0da295-1b03-4f74-9a3a-6df41ac9324f" - }, - { - "label": null, - "output_name": "outfile_result", - "uuid": "caae2dbf-5955-4685-b174-0dc9d48f496f" - } - ] - }, - "7": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.8.3", - "errors": null, - "id": 7, - "input_connections": { - "infile_estimator": { - "id": 6, - "output_name": "outfile_object" - }, - "infile_weights": { - "id": 6, - "output_name": "outfile_weights" - }, - "input_options|infile1": { - "id": 0, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Model Prediction", - "name": "infile_estimator" - }, - { - "description": "runtime parameter for tool Model Prediction", - "name": "infile_weights" - }, - { - "description": "runtime parameter for tool Model Prediction", - "name": "input_options" - } - ], - "label": null, - "name": "Model Prediction", - "outputs": [ - { - "name": "outfile_predict", - "type": "tabular" - } - ], - "position": { - "bottom": 516.3778381347656, - "height": 235.41192626953125, - "left": 1340.9801025390625, - "right": 1540.9801025390625, - "top": 280.9659118652344, - "width": 200, - "x": 1340.9801025390625, - "y": 280.9659118652344 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.8.3", - "tool_shed_repository": { - "changeset_revision": "60c726f5cc5e", - "name": "model_prediction", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"__job_resource\": {\"__job_resource__select\": \"no\", \"__current_case__\": 0}, \"infile_estimator\": {\"__class__\": \"RuntimeValue\"}, \"infile_weights\": {\"__class__\": \"RuntimeValue\"}, \"input_options\": {\"selected_input\": \"tabular\", \"__current_case__\": 0, \"infile1\": {\"__class__\": \"RuntimeValue\"}, \"header1\": \"false\", \"column_selector_options_1\": {\"selected_column_selector_option\": \"all_columns\", \"__current_case__\": 4}}, \"method\": \"predict\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.0.8.3", - "type": "tool", - "uuid": "de5c73e5-e389-4835-a277-424744cd7158", - "workflow_outputs": [ - { - "label": null, - "output_name": "outfile_predict", - "uuid": "ce123116-5aa1-44f9-a1dc-4d163e6fb9f1" - } - ] - }, - "8": { - "annotation": "", - "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/ml_visualization_ex/ml_visualization_ex/1.0.8.3", - "errors": null, - "id": 8, - "input_connections": { - "plotting_selection|infile_predicted": { - "id": 7, - "output_name": "outfile_predict" - }, - "plotting_selection|infile_true": { - "id": 2, - "output_name": "output" - } - }, - "inputs": [ - { - "description": "runtime parameter for tool Machine Learning Visualization Extension", - "name": "plotting_selection" - }, - { - "description": "runtime parameter for tool Machine Learning Visualization Extension", - "name": "plotting_selection" - } - ], - "label": null, - "name": "Machine Learning Visualization Extension", - "outputs": [ - { - "name": "output", - "type": "html" - } - ], - "position": { - "bottom": 526.7613525390625, - "height": 245.79544067382812, - "left": 1560.9801025390625, - "right": 1760.9801025390625, - "top": 280.9659118652344, - "width": 200, - "x": 1560.9801025390625, - "y": 280.9659118652344 - }, - "post_job_actions": {}, - "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/ml_visualization_ex/ml_visualization_ex/1.0.8.3", - "tool_shed_repository": { - "changeset_revision": "4a229a7ad638", - "name": "ml_visualization_ex", - "owner": "bgruening", - "tool_shed": "toolshed.g2.bx.psu.edu" - }, - "tool_state": "{\"plotting_selection\": {\"plot_type\": \"classification_confusion_matrix\", \"__current_case__\": 6, \"infile_true\": {\"__class__\": \"RuntimeValue\"}, \"header_true\": \"false\", \"column_selector_options_true\": {\"selected_column_selector_option\": \"all_columns\", \"__current_case__\": 4}, \"infile_predicted\": {\"__class__\": \"RuntimeValue\"}, \"header_predicted\": \"true\", \"title\": \"Confusion matrix between true and predicted labels\", \"plot_format\": \"png\", \"plot_color\": \"Greens\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", - "tool_version": "1.0.8.3", - "type": "tool", - "uuid": "67283ffa-dc68-412c-8f82-a61570bf3d0c", - "workflow_outputs": [ - { - "label": null, - "output_name": "output", - "uuid": "342d1766-9ee5-45f3-9cab-05cbb5331f71" - } - ] - } - }, - "tags": [ - "statistics", - "rnn", - "ml" - ], - "uuid": "5637dc89-39fc-43c1-98a9-7a06dad9dbdc", - "version": 4 -} diff --git a/topics/statistics/tutorials/RNN/workflows/Intro_To_RNN_v1_0_10_0-test.yml b/topics/statistics/tutorials/RNN/workflows/Intro_To_RNN_v1_0_10_0-test.yml new file mode 100644 index 00000000000000..4144cab4a2de94 --- /dev/null +++ b/topics/statistics/tutorials/RNN/workflows/Intro_To_RNN_v1_0_10_0-test.yml @@ -0,0 +1,23 @@ +- doc: Test outline for Intro_To_RNN_v1_0_10_0 + job: + X_test: + class: File + path: https://zenodo.org/records/4477881/files/X_test.tsv + filetype: tabular + X_train: + class: File + path: https://zenodo.org/records/4477881/files/X_train.tsv + filetype: tabular + y_test: + class: File + path: https://zenodo.org/records/4477881/files/y_test.tsv + filetype: tabular + y_train: + class: File + path: https://zenodo.org/records/4477881/files/y_train.tsv + filetype: tabular + outputs: + output: + asserts: + has_text: + text: 'PNG' diff --git a/topics/statistics/tutorials/RNN/workflows/Intro_To_RNN_v1_0_10_0.ga b/topics/statistics/tutorials/RNN/workflows/Intro_To_RNN_v1_0_10_0.ga new file mode 100644 index 00000000000000..3d7ecca77e7af4 --- /dev/null +++ b/topics/statistics/tutorials/RNN/workflows/Intro_To_RNN_v1_0_10_0.ga @@ -0,0 +1,370 @@ +{ + "a_galaxy_workflow": "true", + "annotation": "", + "creator": [{"class": "Person", "identifier":"0000-0001-6585-3619", "name": "Kaivan Kamali"}], + "format-version": "0.1", + "license": "CC-BY-4.0", + "name": "Intro_To_RNN_v1_0_10_0", + "steps": { + "0": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 0, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "X_test" + } + ], + "label": "X_test", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 10, + "top": 10 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "c84eb1e9-61dc-4d37-b13e-999665b31337", + "when": null, + "workflow_outputs": [] + }, + "1": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 1, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "X_train" + } + ], + "label": "X_train", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 10, + "top": 130 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "0e7e1ec8-f422-4349-889a-4e3e66670c2f", + "when": null, + "workflow_outputs": [] + }, + "2": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 2, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "y_test" + } + ], + "label": "y_test", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 10, + "top": 250 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "ec09b380-de33-44e1-bce4-c203c10c47d6", + "when": null, + "workflow_outputs": [] + }, + "3": { + "annotation": "", + "content_id": null, + "errors": null, + "id": 3, + "input_connections": {}, + "inputs": [ + { + "description": "", + "name": "y_train" + } + ], + "label": "y_train", + "name": "Input dataset", + "outputs": [], + "position": { + "left": 10, + "top": 370 + }, + "tool_id": null, + "tool_state": "{\"optional\": false, \"tag\": null}", + "tool_version": null, + "type": "data_input", + "uuid": "e0784c26-64c5-4135-ad67-03c62a362b7b", + "when": null, + "workflow_outputs": [] + }, + "4": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/1.0.10.0", + "errors": null, + "id": 4, + "input_connections": {}, + "inputs": [], + "label": null, + "name": "Create a deep learning model architecture", + "outputs": [ + { + "name": "outfile", + "type": "json" + } + ], + "position": { + "left": 10, + "top": 490 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_config/keras_model_config/1.0.10.0", + "tool_shed_repository": { + "changeset_revision": "f22a9297440f", + "name": "keras_model_config", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/cvmfs/data.galaxyproject.org/managed/len/ucsc/?.len\", \"model_selection\": {\"model_type\": \"sequential\", \"__current_case__\": 0, \"input_shape\": \"(500, )\", \"layers\": [{\"__index__\": 0, \"layer_selection\": {\"layer_type\": \"Embedding\", \"__current_case__\": 53, \"input_dim\": \"10000\", \"output_dim\": \"32\", \"kwargs\": \"\"}}, {\"__index__\": 1, \"layer_selection\": {\"layer_type\": \"LSTM\", \"__current_case__\": 45, \"units\": \"100\", \"kwargs\": \"\"}}, {\"__index__\": 2, \"layer_selection\": {\"layer_type\": \"Dense\", \"__current_case__\": 0, \"units\": \"1\", \"activation\": \"sigmoid\", \"kwargs\": \"\"}}]}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": null, + "type": "tool", + "uuid": "f61aba17-35c3-4990-acb9-0e96b0979e7c", + "when": null, + "workflow_outputs": [] + }, + "5": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/ml_visualization_ex/ml_visualization_ex/1.0.8.3", + "errors": null, + "id": 5, + "input_connections": { + "plotting_selection|infile_true": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Machine Learning Visualization Extension", + "outputs": [ + { + "name": "output", + "type": "html" + } + ], + "position": { + "left": 230, + "top": 10 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/ml_visualization_ex/ml_visualization_ex/1.0.8.3", + "tool_shed_repository": { + "changeset_revision": "947c2eacccb8", + "name": "ml_visualization_ex", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"__workflow_invocation_uuid__\": \"75b2007ed24c11edba82005056ba2773\", \"chromInfo\": \"/cvmfs/data.galaxyproject.org/managed/len/ucsc/?.len\", \"plotting_selection\": {\"plot_type\": \"classification_confusion_matrix\", \"__current_case__\": 6, \"infile_true\": null, \"header_true\": false, \"column_selector_options_true\": {\"selected_column_selector_option\": \"all_columns\", \"__current_case__\": 4}, \"infile_predicted\": null, \"header_predicted\": true, \"title\": \"Confusion matrix between true and predicted labels\", \"plot_format\": \"png\", \"plot_color\": \"Greens\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": null, + "type": "tool", + "uuid": "62893cf8-21d5-4f12-b164-bf16d145843d", + "when": null, + "workflow_outputs": [] + }, + "6": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/1.0.10.0", + "errors": null, + "id": 6, + "input_connections": { + "mode_selection|infile_json": { + "id": 4, + "output_name": "outfile" + } + }, + "inputs": [], + "label": null, + "name": "Create deep learning model", + "outputs": [ + { + "name": "outfile", + "type": "h5mlm" + } + ], + "position": { + "left": 230, + "top": 130 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_model_builder/keras_model_builder/1.0.10.0", + "tool_shed_repository": { + "changeset_revision": "66d7efc06000", + "name": "keras_model_builder", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/cvmfs/data.galaxyproject.org/managed/len/ucsc/?.len\", \"mode_selection\": {\"mode_type\": \"train_model\", \"__current_case__\": 0, \"infile_json\": null, \"learning_type\": \"KerasGClassifier\", \"compile_params\": {\"loss\": \"binary_crossentropy\", \"optimizer_selection\": {\"optimizer_type\": \"Adam\", \"__current_case__\": 4, \"optimizer_options\": {\"learning_rate\": \"0.001\", \"beta_1\": \"0.9\", \"beta_2\": \"0.999\", \"epsilon\": \"1e-07\", \"amsgrad\": false}}, \"metrics\": [\"acc\"]}, \"fit_params\": {\"epochs\": \"2\", \"batch_size\": \"128\", \"steps_per_epoch\": null, \"validation_split\": \"0.1\", \"validation_steps\": null, \"callbacks\": [{\"__index__\": 0, \"callback_selection\": {\"callback_type\": \"None\", \"__current_case__\": 0}}], \"verbose\": \"1\"}, \"random_seed\": null}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": null, + "type": "tool", + "uuid": "5d389aed-7cba-45bb-b635-526b6b6c12cb", + "when": null, + "workflow_outputs": [] + }, + "7": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.10.0", + "errors": null, + "id": 7, + "input_connections": { + "experiment_schemes|infile_estimator": { + "id": 6, + "output_name": "outfile" + }, + "input_options|infile1": { + "id": 1, + "output_name": "output" + }, + "input_options|infile2": { + "id": 3, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Deep learning training and evaluation", + "outputs": [ + { + "name": "outfile_result", + "type": "tabular" + }, + { + "name": "outfile_object", + "type": "h5mlm" + } + ], + "position": { + "left": 450, + "top": 10 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/keras_train_and_eval/keras_train_and_eval/1.0.10.0", + "tool_shed_repository": { + "changeset_revision": "818f9b69d8a0", + "name": "keras_train_and_eval", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/cvmfs/data.galaxyproject.org/managed/len/ucsc/?.len\", \"experiment_schemes\": {\"selected_exp_scheme\": \"train_val\", \"__current_case__\": 0, \"infile_estimator\": null, \"hyperparams_swapping\": {\"param_set\": [{\"__index__\": 0, \"sp_name\": null, \"sp_value\": \"\"}]}, \"test_split\": {\"split_algos\": {\"shuffle\": \"simple\", \"__current_case__\": 1, \"test_size\": \"0.2\", \"random_state\": null}}, \"metrics\": {\"scoring\": {\"primary_scoring\": \"f1\", \"__current_case__\": 4, \"secondary_scoring\": null}}}, \"input_options\": {\"selected_input\": \"tabular\", \"__current_case__\": 0, \"infile1\": null, \"header1\": false, \"column_selector_options_1\": {\"selected_column_selector_option\": \"all_columns\", \"__current_case__\": 4}, \"infile2\": null, \"header2\": false, \"column_selector_options_2\": {\"selected_column_selector_option2\": \"all_columns\", \"__current_case__\": 4}}, \"save\": [\"save_estimator\"], \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": null, + "type": "tool", + "uuid": "ef36b0d2-4e0e-4247-8763-5b59eb2b859d", + "when": null, + "workflow_outputs": [] + }, + "8": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.10.0", + "errors": null, + "id": 8, + "input_connections": { + "infile_estimator": { + "id": 7, + "output_name": "outfile_object" + }, + "input_options|infile1": { + "id": 0, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Model Prediction", + "outputs": [ + { + "name": "outfile_predict", + "type": "tabular" + } + ], + "position": { + "left": 670, + "top": 10 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/model_prediction/model_prediction/1.0.10.0", + "tool_shed_repository": { + "changeset_revision": "9991c4ddde14", + "name": "model_prediction", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/cvmfs/data.galaxyproject.org/managed/len/ucsc/?.len\", \"infile_estimator\": null, \"input_options\": {\"selected_input\": \"tabular\", \"__current_case__\": 0, \"infile1\": null, \"header1\": false, \"column_selector_options_1\": {\"selected_column_selector_option\": \"all_columns\", \"__current_case__\": 4}}, \"method\": \"predict\", \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": null, + "type": "tool", + "uuid": "84e00c86-0370-4232-b20d-1d54f8c00d6e", + "when": null, + "workflow_outputs": [] + }, + "9": { + "annotation": "", + "content_id": "toolshed.g2.bx.psu.edu/repos/bgruening/ml_visualization_ex/ml_visualization_ex/1.0.10.0", + "errors": null, + "id": 9, + "input_connections": { + "plotting_selection|infile_predicted": { + "id": 8, + "output_name": "outfile_predict" + }, + "plotting_selection|infile_true": { + "id": 2, + "output_name": "output" + } + }, + "inputs": [], + "label": null, + "name": "Machine Learning Visualization Extension", + "outputs": [ + { + "name": "output", + "type": "html" + } + ], + "position": { + "left": 890, + "top": 10 + }, + "post_job_actions": {}, + "tool_id": "toolshed.g2.bx.psu.edu/repos/bgruening/ml_visualization_ex/ml_visualization_ex/1.0.10.0", + "tool_shed_repository": { + "changeset_revision": "1588f9076e32", + "name": "ml_visualization_ex", + "owner": "bgruening", + "tool_shed": "toolshed.g2.bx.psu.edu" + }, + "tool_state": "{\"__input_ext\": \"input\", \"chromInfo\": \"/cvmfs/data.galaxyproject.org/managed/len/ucsc/?.len\", \"plotting_selection\": {\"plot_type\": \"classification_confusion_matrix\", \"__current_case__\": 6, \"infile_true\": null, \"header_true\": false, \"column_selector_options_true\": {\"selected_column_selector_option\": \"all_columns\", \"__current_case__\": 4}, \"infile_predicted\": null, \"header_predicted\": true, \"title\": \"Confusion matrix between true and predicted labels\", \"plot_format\": \"png\", \"plot_color\": \"Greens\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}", + "tool_version": null, + "type": "tool", + "uuid": "46cc48a1-b1c9-49fe-9c3c-5996ed4cc592", + "when": null, + "workflow_outputs": [] + } + }, + "tags": [], + "uuid": "c995f5c8-de9c-4bc5-9a15-1060eb569d40", + "version": 1 +}