Merge pull request #568 from zargham-ahmad/ms2deepscore

Added ms2deepscore tool suite

tools/ms2deepscore/.shed.yml

@@ -0,0 +1,16 @@
+name: ms2deepscore
+owner: recetox
+remote_repository_url: "https://github.com/RECETOX/galaxytools/tree/master/tools/ms2deepscore"
+homepage_url: "https://github.com/matchms/ms2deepscore"
+categories:
+  - Metabolomics
+description: "Mass spectra similarity scoring using a trained ms2deepscore model."
+long_description: "ms2deepscore provides a Siamese neural network that is trained to predict molecular structural similarities (Tanimoto scores) from pairs of mass spectrometry spectra."
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "{{ tool_name }} tool from the ms2deepscore package."
+suite:
+  name: suite_ms2deepscore
+  description: tools from the ms2deepscore suite are used for training a siamese model, and computing the similarities between pairs of spectra.
+  type: repository_suite_definition
+

tools/ms2deepscore/macros.xml

@@ -0,0 +1,150 @@
+<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="[email protected]"
+                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>

tools/ms2deepscore/ms2deepscore_config_generator.xml

@@ -0,0 +1,89 @@
+<tool id="ms2deepscore_config_generator" name="MS2DeepScore Configuration Generator" version="@TOOL_VERSION@+galaxy0">
+    <description>Generates model parameters for MS2DeepScore in JSON format</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="creator"/>
+    <expand macro="edam" />
+
+    <requirements>
+        <requirement type="package" version="@TOOL_VERSION@">ms2deepscore</requirement>
+    </requirements>
+
+    <command detect_errors="exit_code"><![CDATA[
+        python3 ${python_wrapper}
+    ]]></command>
+    <configfiles>
+    <configfile name="python_wrapper">
+import numpy as np
+from typing import Optional
+from ms2deepscore.SettingsMS2Deepscore import SettingsMS2Deepscore
+
+random_seed: Optional[int] = $training_settings.random_seed
+
+#set dims = tuple([int($layer.dims) for $i, $layer in enumerate($model_structure.layers)])
+
+params = {
+    "base_dims": $dims,
+    "embedding_dim": $model_structure.embedding_dim,
+    "ionisation_mode": "$model_structure.ionisation_mode",
+    "dropout_rate": $training_settings.dropout_rate,
+    "learning_rate": $training_settings.learning_rate,
+    "epochs": $training_settings.epochs,
+    "patience": $training_settings.patience,
+    "loss_function": "$training_settings.loss_function",
+    "weighting_factor": $training_settings.weighting_factor,
+    "min_mz": $tensorization_settings.min_mz,
+    "max_mz": $tensorization_settings.max_mz,
+    "mz_bin_width": $tensorization_settings.mz_bin_width,
+    "intensity_scaling": $tensorization_settings.intensity_scaling,
+    "batch_size": $training_settings.batch_size,
+    "average_pairs_per_bin": $training_settings.average_pairs_per_bin,
+    "same_prob_bins": np.array([(0, 0.2), (0.2, 1.0)]),
+    "random_seed": random_seed,
+    "fingerprint_type": "$tensorization_settings.fingerprint_type",
+    "fingerprint_nbits": $tensorization_settings.fingerprint_nbits
+}
+
+settings = SettingsMS2Deepscore(**params)
+settings.save_to_file("$output_file")
+</configfile>
+</configfiles>
+
+    <inputs>
+        <expand macro="config_generator" />
+    </inputs>
+
+    <outputs>
+        <data name="output_file" format="json" label="Model Parameter JSON" />
+    </outputs>
+
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="layers_0|dims" value="20"/>
+            <param name="layers_1|dims" value="20"/>
+            <param name="embedding_dim" value="15" />
+            <param name="ionisation_mode" value="negative" />
+            <param name="epochs" value="2" />
+            <param name="batch_size" value="2" />
+            <param name="average_pairs_per_bin" value="2" />
+            <param name="random_seed" value="42"/>
+            <output name="output_file" value="Model_Parameter_JSON.json" ftype="json" compare="diff" lines_diff="2"/>
+        </test>
+    </tests>
+
+    <help>
+<![CDATA[
+Info
+====
+This tool generates a configuration file needed to train a MS2DeepScore model using the 'MS2DeepScore Training' tool.
+The generated JSON file contains all the parameters necessary for model training - this includes the model architecture as well as information regarding how to discretize the input tensors.
+If you trained a model offline, you can also upload the JSON file configuration of that trained model into Galaxy and use it for the 'MS2DeepScore' similarity or training module.
+
+About
+=====
+@HELP@
+]]>
+    </help>
+    <expand macro="citations"/>
+</tool>

tools/ms2deepscore/ms2deepscore_similarity.xml

@@ -0,0 +1,104 @@
+<tool id="ms2deepscore_similarity" name="MS2DeepScore Similarity" version="@TOOL_VERSION@+galaxy0">
+    <description>Compute similarity scores using a pre-trained MS2DeepScore model</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="creator"/>
+    <expand macro="edam" />
+
+    <requirements>
+        <requirement type="package" version="@TOOL_VERSION@">ms2deepscore</requirement>
+        <requirement type="package" version="@ONNX_VERSION@">onnx</requirement>
+    </requirements>
+
+    <command detect_errors="exit_code"><![CDATA[
+        python3 ${python_wrapper}
+    ]]></command>
+<configfiles>
+<configfile name="python_wrapper">
+@init_logger@
+
+import onnx
+import torch
+from ms2deepscore import MS2DeepScore
+from matchms import calculate_scores
+from matchms.importing import load_from_msp, scores_from_json
+from ms2deepscore.models.SiameseSpectralModel import SiameseSpectralModel
+from ms2deepscore.SettingsMS2Deepscore import SettingsMS2Deepscore
+
+onnx_model = onnx.load("$model")
+
+# Extract the initializers (weights and biases)
+initializers = {init.name: onnx.numpy_helper.to_array(init) for init in onnx_model.graph.initializer}
+
+# Convert NumPy arrays to PyTorch tensors
+state_dict = {name: torch.tensor(np_array) for name, np_array in initializers.items()}
+
+@json_load@
+
+model = SiameseSpectralModel(settings=SettingsMS2Deepscore(**model_params))
+model.load_state_dict(state_dict)
+model.eval()
+
+#if $scores.use_scores == "True"
+scores_in = scores_from_json("${scores_in}")
+references=scores_in.references
+queries=scores_in.queries
+#else
+references=list(load_from_msp("$references"))
+queries=list(load_from_msp("$queries"))
+#end if
+
+similarity = MS2DeepScore(model)
+scores = calculate_scores(references, queries, similarity)
+
+#if $scores.use_scores == "True"
+scores_in._scores.add_dense_matrix(scores.to_array(), "MS2DeepScore")
+scores_in.to_json("$similarity_scores")
+#else
+scores.to_json("$similarity_scores")
+#end if
+</configfile>
+</configfiles>
+
+    <inputs>
+        <expand macro="input_param" />
+    </inputs>
+
+    <outputs>
+        <data label="ms2deepscore scores of ${on_string}" name="similarity_scores" format="json"/>
+    </outputs>
+
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="use_scores" value="False"/>
+            <param name="references" value="inp_filtered_library.msp" ftype="msp"/>
+            <param name="queries" value="inp_filtered_spectra.msp" ftype="msp"/>
+            <param name="model" value="Trained_model.onnx" ftype="onnx"/>
+            <param name="model_param" value="Model_Parameter_JSON.json" ftype="json"/>
+            <output name="similarity_scores" value="msp_json_score_out.json" ftype="json" compare="sim_size" />
+        </test>
+        <test expect_num_outputs="1">
+            <param name="use_scores" value="True"/>
+            <param name="scores_in" value="ri_match_60.json" ftype="json"/>
+            <param name="model" value="Trained_model.onnx" ftype="onnx"/>
+            <param name="model_param" value="Model_Parameter_JSON.json" ftype="json"/>
+            <output name="similarity_scores" value="usescore_json_score_out.json" ftype="json" compare="sim_size" />
+        </test>
+    </tests>
+
+    <help>
+<![CDATA[
+Info
+====
+Use a MS2DeepScore model for spectral similarity calculation.
+For security reasons, only ONNX models are supported to be used.
+If you want to use your own model, you can convert it to ONNX using the code contained in the 'MS2DeepScore Model Training' tool.
+
+About
+=====
+@HELP@
+]]>
+    </help>   
+    <expand macro="citations"/>
+</tool>