annotate macros.xml @ 0:58c95171a0d3 draft default tip

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/ms2deepscore commit 4bd610e0cbbcbed51a6bfb880179777fc8034fd6

<macros>
    <token name="@TOOL_VERSION@">2.0.0</token>
    <token name="@ONNX_VERSION@">1.16.2</token>

    <xml name="creator">
        <creator>
            <person
                givenName="Zargham"
                familyName="Ahmad"
                url="https://github.com/zargham-ahmad"
                identifier="0000-0002-6096-224X" />
            <organization
                url="https://www.recetox.muni.cz/"
                email="[e-mail]"
                name="RECETOX MUNI" />
        </creator>
    </xml>

    <xml name="edam">
        <xrefs>
            <xref type="bio.tools">ms2deepscore</xref>
        </xrefs>
    </xml>

    <xml name="input_param">
        <conditional name="scores">
            <param name="use_scores" label="Use Scores Object" type="select">
                <option value="False" selected="true">FALSE</option>
                <option value="True">TRUE</option>
            </param>
            <when value="True">
                <param label="Scores object" name="scores_in" type="data" format="json"
                    help="Scores objects calculated previously using one of the matchms similarity tools." />
            </when>
            <when value="False">
                <param label="Queries spectra" name="queries" type="data" format="msp"
                    help="Query mass spectra to match against references."/>
                <param label="Reference spectra" name="references" type="data" format="msp"
                    help="Reference mass spectra to match against as library."/>
            </when>
        </conditional>
        <param name="model" type="data" format="onnx" label="Model" 
            help="Select the trained MS2DeepScore model file (onnx format) in the ONNX format as created by the 'MS2DeepScore Training' tool."/>
        <param name="model_param" type="data" format="json" label="Configuration"
            help="Select the MS2DeepScore model configurations  in JSON format. Can be created using the 'MS2DeepScore Config Generator' tool."/>
    </xml>

    <xml name="training_param">
        <param label="Training Dataset" name="spectra" type="data" format="msp,mgf"
            help="Spectra file that should be used for training. (it will be split in training, validation and test sets)."/>
        <param name="model_param" type="data" format="json" label="Model Settings" help="json file with the MS2Deepscore model settings."/>
        <param name="validation_split_fraction" type="integer" min="0" max="100" value="20" label="Validation split fraction [%]" 
            help="The fraction of the inchikeys that will be used for validation and test"/>
    </xml>

    <xml name="config_generator">
        <section name="model_structure" title="Model Structure" expanded="true">
            <repeat name="layers" title="Layer" min="1" default="1" >
                <param name="dims" type="integer" label="Dimensions" min = "0" value="2000" help="Size of the in-between layer to add." />
            </repeat>
            <param name="embedding_dim" type="integer" label="Embedding Dimension" value="400" help="The dimension of the final embedding layer." />
            <param name="ionisation_mode" type="select" label="Ionisation Mode">
                <option value="positive" selected="true">Positive</option>
                <option value="negative">Negative</option>
                <option value="both">Both</option>
            </param>
        </section>
        
        <section name="tensorization_settings" title="Tensorization Settings" expanded="true">
            <param name="min_mz" type="integer" label="Min m/z" value="10" />
            <param name="max_mz" type="integer" label="Max m/z" value="1000" />
            <param name="mz_bin_width" type="float" label="m/z Bin Width" value="0.1" />
            <param name="intensity_scaling" type="float" label="Intensity Scaling" value="0.5" />
            <param name="fingerprint_type" type="text" value="daylight" label="Fingerprint Type" help="The fingerprint type that should be used for tanimoto score calculations." />
            <param name="fingerprint_nbits" type="integer" label="Fingerprint Number of Bits" value="2048" help="The number of bits to use for the fingerprint." />
        </section>
                

        <section name="training_settings" title="Training Settings" expanded="false">
            <param name="dropout_rate" type="float" label="Dropout Rate" value="0.0" />
            <param name="learning_rate" type="float" label="Learning Rate" value="0.00025" />
            <param name="epochs" type="integer" label="Epochs" value="250" />
            <param name="patience" type="integer" label="Patience" value="20" help="How long the model should keep training if validation does not improve" />
            <param name="loss_function" type="select" label="Loss Function">
                <option value="mse" selected="true">Mean Squared Error (mse)</option>
                <option value="mae">Mean Absolute Error (mae)</option>
                <option value="rmse">Root Mean Squared Error (rmse)</option>
                <option value="risk_mae">Risk Aware MAE (risk_aware_mae)</option>
                <option value="risk_mse">Risk Aware MSE (risk_aware_mse)</option>
            </param>
            <param name="weighting_factor" type="integer" label="Weighting Factor" value="0" />
            <param name="batch_size" type="integer" value="32" label="Batch Size" help="Number of pairs per batch" />
            <param name="average_pairs_per_bin" type="integer" value="20" label="Average pairs per bin" help="The aimed average number of pairs of spectra per spectrum in each bin." />
            <param name="random_seed" type="text" label="Random seed" value="None" help="Specify random seed for reproducible random number generation." />
        </section>
    </xml>

    <xml name="citations">
        <citations>
            <citation type="doi">https://doi.org/10.1186/s13321-021-00558-4</citation>
            <citation type="doi">https://doi.org/10.1101/2024.03.25.586580</citation>
        </citations>
    </xml>


<token name="@HELP@">
    ms2deepscore provides a Siamese neural network that is trained to predict molecular structural similarities (Tanimoto scores) from pairs of mass spectrometry spectra.
    The library provides an intuitive classes to prepare data, train a siamese model, and compute similarities between pairs of spectra.
    In addition to the prediction of a structural similarity, MS2DeepScore can also make use of Monte-Carlo dropout to assess the model uncertainty.
    MS2DeepScore is able to identify highly-reliable structural matches and to predict Tanimoto scores for pairs of molecules based on their fragment spectra with a root mean squared error of about 0.15.
    Furthermore, the prediction uncertainty estimate can be used to select a subset of predictions with a root mean squared error of about 0.1.
    MS2DeepScore can also be used to create chemically meaningful mass spectral embeddings that could be used to cluster large numbers of spectra.
</token>


<token name="@init_scores@">
from matchms.importing import load_from_msp, scores_from_json
from matchms import Scores
#if $scores.use_scores == "True"
scores = scores_from_json("${scores_in}")
#else
scores = Scores(references=list(load_from_msp("$references")), queries=list(load_from_msp("$queries")), is_symmetric=False)
#end if
</token>
        
<token name="@init_logger@">
from matchms import set_matchms_logger_level
set_matchms_logger_level("WARNING")
</token>

<token name="@json_load@">
import numpy as np
import json

with open("$model_param", 'r') as json_file:
    model_params = json.load(json_file)

# Conditionally convert specific keys if they are present
if 'base_dims' in model_params:
    model_params['base_dims'] = tuple(model_params['base_dims'])

if 'same_prob_bins' in model_params:
    model_params['same_prob_bins'] = np.array(model_params['same_prob_bins'])

if 'additional_metadata' in model_params:
    model_params['additional_metadata'] = [
        (entry[0], entry[1]) for entry in model_params['additional_metadata']
    ]
</token>
</macros>