Mercurial > repos > bimib > cobraxy
diff COBRAxy/flux_simulation.xml @ 489:97eea560a10f draft
Uploaded
| author | francesco_lapi |
|---|---|
| date | Mon, 29 Sep 2025 10:33:26 +0000 |
| parents | 0a3ca20848f3 |
| children | 0cb727788cae |
line wrap: on
line diff
--- a/COBRAxy/flux_simulation.xml Tue Sep 23 13:48:24 2025 +0000 +++ b/COBRAxy/flux_simulation.xml Mon Sep 29 10:33:26 2025 +0000 @@ -4,96 +4,153 @@ <import>marea_macros.xml</import> </macros> - <requirements> + <requirements> <requirement type="package" version="1.24.4">numpy</requirement> <requirement type="package" version="2.0.3">pandas</requirement> - <requirement type="package" version="0.29.0">cobra</requirement> + <requirement type="package" version="0.29.0">cobra</requirement> <requirement type="package" version="5.2.2">lxml</requirement> <requirement type="package" version="1.4.2">joblib</requirement> <requirement type="package" version="1.11">scipy</requirement> - </requirements> + </requirements> <command detect_errors="exit_code"> <![CDATA[ python $__tool_directory__/flux_simulation.py --tool_dir $__tool_directory__ - --model_selector $cond_model.model_selector - #if $cond_model.model_selector == 'Custom' - --model $model - --model_name $model.element_identifier + --model_and_bounds $model_and_bounds.model_and_bounds + + #if $model_and_bounds.model_and_bounds == 'True': + --model_upload $model_and_bounds.model_upload + --input "${",".join(map(str, $model_and_bounds.inputs))}" + #set $names = "" + #for $input_temp in $model_and_bounds.inputs: + #set $names = $names + $input_temp.element_identifier + "," + #end for + --name $names + #else: + --input "${",".join(map(str, $model_and_bounds.model_files))}" + #set $names = "" + #for $input_temp in $model_and_bounds.model_files: + #set $names = $names + $input_temp.element_identifier + "," + #end for + --name $names #end if - --input "${",".join(map(str, $inputs))}" - #set $names = "" - #for $input_temp in $inputs: - #set $names = $names + $input_temp.element_identifier + "," - #end for - --name $names - --thinning 0 - #if $algorithm_param.algorithm == 'OPTGP': - --thinning $algorithm_param.thinning + + --sampling_enabled $sampling_params.sampling_enabled + + #if $sampling_params.sampling_enabled == 'true': + --thinning 0 + #if $sampling_params.algorithm_param.algorithm == 'OPTGP': + --thinning $sampling_params.algorithm_param.thinning + #end if + --algorithm $sampling_params.algorithm_param.algorithm + --n_batches $sampling_params.n_batches + --n_samples $sampling_params.n_samples + --seed $sampling_params.seed + --output_type "${",".join(map(str, $sampling_params.output_types))}" + #else: + --thinning 0 + --algorithm 'CBS' + --n_batches 1 + --n_samples 1 + --seed 0 + --output_type 'mean' #end if - --algorithm $algorithm_param.algorithm - --n_batches $n_batches - --n_samples $n_samples - --seed $seed - --output_type "${",".join(map(str, $output_types))}" + --output_type_analysis "${",".join(map(str, $output_types_analysis))}" + + #if 'FVA' in str($output_types_analysis): + --perc_opt $fva_params.optimality_fraction + #end if + --out_log $log ]]> </command> + <inputs> + <conditional name="model_and_bounds"> + <param name="model_and_bounds" argument="--model_and_bounds" type="select" label="Upload mode:" help="Choose whether to upload the model and bounds in separate files or to upload multiple complete model files."> + <option value="True" selected="true">Model + bounds (separate files)</option> + <option value="False">Multiple complete models</option> + </param> - <conditional name="cond_model"> - <expand macro="options_ras_to_bounds_model"/> - <when value="Custom"> - <param name="model" argument="--model" type="data" format="json, xml" label="Custom model" /> + <when value="True"> + <param name="model_upload" argument="--model_upload" type="data" format="csv,tsv,tabular" + label="Model (rules) file:" + help="Upload a CSV/TSV file that contains the model reaction rules. Recommended columns: ReactionID, Reaction (formula), Rule (GPR). Optional columns: name, lower_bound, upper_bound, InMedium. If bounds are present here they may be overridden by separate bound files." /> + + <param name="inputs" argument="--inputs" multiple="true" type="data" format="tabular,csv,tsv" + label="Bound file(s):" + help="Upload one or more CSV/TSV files containing reaction bounds. Each file must include at least: ReactionID, lower_bound, upper_bound. Files are applied in the order provided; later files override earlier ones for the same ReactionID." /> </when> - </conditional> + + <when value="False"> + <param name="model_files" argument="--model_files" multiple="true" type="data" format="csv,tsv,tabular" + label="Complete model files:" + help="Upload one or more CSV/TSV files, each containing both model rules and reaction bounds for different contexts/cells. Required columns: ReactionID, Reaction, Rule, lower_bound, upper_bound." /> + </when> + </conditional> - <param name="inputs" argument="--inputs" multiple="true" type="data" format="tabular, csv, tsv" label="Bound(s):" /> - - - <conditional name="algorithm_param"> - <param name="algorithm" argument="--algorithm" type="select" label="Choose sampling algorithm:"> - <option value="CBS" selected="true">CBS</option> - <option value="OPTGP">OPTGP</option> - </param> - <when value="OPTGP"> - <param name="thinning" argument="--thinning" type="integer" label="Thinning:" value="100" help="Number of iterations to wait before taking a sample."/> - </when> + <conditional name="sampling_params"> + <param name="sampling_enabled" argument="--sampling_enabled" type="boolean" display="checkboxes" checked="false" label="Enable sampling" help="Enable flux sampling"/> + + <when value="true"> + <conditional name="algorithm_param"> + <param name="algorithm" argument="--algorithm" type="select" label="Choose sampling algorithm:"> + <option value="CBS" selected="true">CBS</option> + <option value="OPTGP">OPTGP</option> + </param> + <when value="OPTGP"> + <param name="thinning" argument="--thinning" type="integer" label="Thinning:" value="100" help="Number of iterations to wait before taking a sample."/> + </when> + </conditional> + + <param name="n_samples" argument="--n_samples" type="integer" label="Samples:" value="1000" min="1" max="1000"/> + <param name="n_batches" argument="--n_batches" type="integer" label="Batches:" value="1" help="This is useful for computational performances."/> + <param name="seed" argument="--seed" type="integer" label="Seed:" value="0" help="Random seed."/> - </conditional> - - - <param name="n_samples" argument="--n_samples" type="integer" label="Samples:" value="1000"/> - - <param name="n_batches" argument="--n_batches" type="integer" label="Batches:" value="1" help="This is useful for computational perfomances."/> + <param type="select" argument="--output_types" multiple="true" name="output_types" label="Choose outputs from sampling"> + <option value="mean" selected="true">Mean</option> + <option value="median" selected="true">Median</option> + <option value="quantiles" selected="true">Quantiles</option> + <option value="fluxes" selected="false">All fluxes</option> + </param> + </when> + + <when value="false"> + <!-- Hidden parameters when sampling is disabled --> + <param name="algorithm" type="hidden" value="CBS"/> + <param name="n_samples" type="hidden" value="1000"/> + <param name="n_batches" type="hidden" value="1"/> + <param name="seed" type="hidden" value="0"/> + <param name="output_types" type="hidden" value="mean"/> + </when> + </conditional> - <param name="seed" argument="--seed" type="integer" label="Seed:" value="0" helph="Random seed."/> - - <param type="select" argument="--output_types" multiple="true" name="output_types" label="Desired outputs from sampling"> - <option value="mean" selected="true">Mean</option> - <option value="median" selected="true">Median</option> - <option value="quantiles" selected="true">Quantiles</option> - <option value="fluxes" selected="false">All fluxes</option> + <param type="select" argument="--output_types_analysis" multiple="true" name="output_types_analysis" label="Choose outputs from optimization"> + <option value="FVA" selected="true">FVA</option> + <option value="pFBA" selected="false">pFBA</option> + <option value="sensitivity" selected="false">Sensitivity reaction knock-out (Biomass)</option> </param> - <param type="select" argument="--output_types_analysis" multiple="true" name="output_types_analysis" label="Desired outputs from flux analysis"> - <option value="pFBA" selected="false">pFBA</option> - <option value="FVA" selected="false">FVA</option> - <option value="sensitivity" selected="false">Sensitivity reaction knock-out (Biomass)</option> - </param> + <conditional name="fva_params"> + <param name="show_fva_options" type="boolean" display="checkboxes" checked="false" label="Configure FVA parameters" help="Show additional FVA configuration options"/> + <when value="true"> + <param name="optimality_fraction" argument="--fva_optimality" type="float" label="FVA Optimality (fraction):" value="0.90" min="0.0" max="1.0" + help="Fraction of optimality for FVA analysis. 1.0 means the flux must be optimal, lower values allow suboptimal solutions."/> + </when> + <when value="false"> + <param name="optimality_fraction" argument="--fva_optimality" type="hidden" value="1.0"/> + </when> + </conditional> + </inputs> - <outputs> <data format="txt" name="log" label="Flux Simulation - Log" /> - <data name="output" format="tabular" label="Flux Simulation - Output"> - <discover_datasets pattern="__name_and_ext__" - directory="flux_simulation" visible="true" /> + <discover_datasets pattern="__name_and_ext__" directory="flux_simulation" visible="true" /> </data> - </outputs> <help> @@ -101,21 +158,21 @@ What it does ------------- -This tool generates flux samples starting from a model in JSON or XML format by using CBS (Corner-based sampling) or OPTGP (Improved Artificial Centering Hit-and-Run sampler) sampling algorithms. +This tool generates flux samples starting from metabolic models using CBS (Corner-based sampling) or OPTGP (Improved Artificial Centering Hit-and-Run sampler) algorithms. -It can return sampled fluxes by appliying summary statistics: +Two upload modes are supported: +1. **Model + bounds**: Upload one base model and multiple bound files (one per context/cell type) +2. **Multiple complete models**: Upload multiple complete model files, each with integrated bounds + +It can return sampled fluxes by applying summary statistics: - mean - median - - quantiles (0.25, 0.50, 0.75). + - quantiles (0.25, 0.50, 0.75) -Flux analysis can be perfomed over the metabolic model: - - parsimoniuos-FBA (optimized by Biomass) - - FVA - - Biomass sensitivity analysis (single reaction knock-out). It is the ratio between the optimal of the Biomass reaction computed by FBA after knocking-out a reaction and the same over the complete model. - -Accepted files: - - A model: JSON, XML, MAT or YAML (.yml) file reporting reactions and rules contained in the model. Supported compressed formats: .zip, .gz and .bz2. Filename must follow the pattern: {model_name}.{extension}.[zip|gz|bz2] - - Context-specific bounds: generated by RAS to Bounds tool. This can be a collection of bounds too (one bounds file per context). +Flux analysis can be performed over the metabolic model by using the objective function already set in the model. The following analyses are supported: + - parsimonious-FBA (optimized by Biomass) + - FVA (with configurable optimality percentage) + - Biomass sensitivity analysis (single reaction knock-out) Output: ------------- @@ -124,11 +181,14 @@ - Samples: reporting the sampled fluxes for each reaction (reaction names on the rows and sample names on the columns). Format: tab-separated. - a log file (.txt). -**TIP**: The Batches parameter is useful to mantain in memory just a batch of samples at time. For example, if you wish to sample 10.000 points, than it is suggested to select n_samples = 1.000 and n_batches=10. -**TIP**: The Thinning parameter of the OPTGP algorithm is useful to converge to a stationary distribution (see cited articles by Galuzzi, Milazzo and Damiani). +**TIP**: Bounds generated by RAStoBound are grouped in a collection. You can select collections by clicking on "Dataset Collection" option in the "Bound file(s):" input parameter. + +**TIP**: The Batches parameter helps maintain memory efficiency. For 10,000 samples, use n_samples=1,000 and n_batches=10. +**TIP**: The Thinning parameter for OPTGP helps converge to stationary distribution. + +**TIP**: FVA optimality percentage allows you to explore suboptimal flux ranges. 100% restricts to optimal solutions, while lower values (e.g., 90%) allow broader flux ranges. ]]> </help> <expand macro="citations_fluxes" /> - </tool> \ No newline at end of file