add pathbank download

README.md

@@ -79,10 +79,10 @@ processed_data = (log2_mat - log2_mat.mean(axis=0)) / log2_mat.std(axis=0)
 ```python
 # Pre-loaded pathways
 # Reactome v78
-reactome_pathways  = sspa.process_reactome(organism="Homo sapiens")
+reactome_pathways = sspa.process_reactome(organism="Homo sapiens")
 
 # KEGG v98
-kegg_human_pathways  = sspa.process_kegg(organism="hsa")
+kegg_human_pathways = sspa.process_kegg(organism="hsa")
 ```
 
 Load a custom GMT file (extension .gmt or .csv)
@@ -96,10 +96,14 @@ Download latest version of pathways
 kegg_mouse_latest = sspa.process_kegg("mmu", download_latest=True, filepath=".")
 
 # download Reactome latest
-reactome_mouse_latest = sspa.process_reactome("Mus musculus", download_latest=True, filepath=".")
+reactome_mouse_latest = sspa.process_reactome("Mus musculus", download_latest=True, filepath=".", omicstype='metabolomics')
+
+# download Pathbank latest
+pathbank_human_latest = sspa.process_pathbank("Homo sapiens", download_latest=True, filepath=".", omicstype='metabolomics')
 ```
 
 ## Identifier harmonization 
+Note: KEGG pathways use KEGG compound IDs, Reactome and Pathbank pathways use ChEBI and UniProt (for proteins)
 ```python
 # download the conversion table
 compound_names = processed_data.columns.tolist()
@@ -200,6 +204,9 @@ We are grateful for our contributors who help develop and maintain py-ssPA:
 <details>
 <summary>Read more</summary>
 
+### [v1.0.2] - 4/12/23
+- Enable download of Pathbank pathways (metabolite and protein) via the `process_pathbank()` function
+
 ### [v1.0.0] - 25/08/23
 - Add compatability with SciKitLearn by implementing `fit()`, `transform()` and `fit_transform()` methods for all ssPA methods. This allows integration of ssPA transformation with various machine learning functions in SKLearn such as `Pipeline` and `GridSearchCV`. Specifically for `sspa.sspa_ssClustPA`, `sspa.sspa_SVD`, and `sspa.sspa_KPCA` methods the model can be fit on the training data and the test data is transformed using the fitted model. 
 - Fixed ID conversion bug in `sspa.map_identifiers()` due to MetaboAnalyst API URL change

setup.py

@@ -6,7 +6,7 @@
 
 setup(
     name='sspa',
-    version='1.0.0',
+    version='1.0.2',
     packages=['sspa'],
     package_dir={'':'src'},
     url='https://github.com/cwieder/sspa',

src/sspa/__init__.py

@@ -1,7 +1,7 @@
 from pkg_resources import get_distribution
 __version__ = get_distribution('sspa').version
 
-from .process_pathways import process_reactome, process_kegg, process_gmt
+from .process_pathways import process_reactome, process_kegg, process_gmt, process_pathbank
 from .sspa_cluster import sspa_ssClustPA
 from .sspa_kpca import sspa_KPCA
 from .sspa_zscore import sspa_zscore

src/sspa/download_pathways.py

@@ -238,3 +238,94 @@ def download_metexplore(self):
 
         print("Complete!")
         return pathways
+
+
+def download_pathbank(organism, filepath=None, omicstype='metabolomics'):
+    '''
+    Function for PathBank pathway download
+    Args:
+        organism (str): PathBank organism name
+        filepath (str): filepath to save pathway file to, default is None - save to variable
+        omics_type(str): type of omics pathways to download. 
+        Options are 'metabolomics' (ChEBI identifiers), 'proteomics' (UniProt identifiers), or 'multiomics' (ChEBI and UniProt identifiers)
+    '''
+    organisms = ['Homo sapiens', 'Escherichia coli', 'Mus musculus', 'Arabidopsis thaliana',
+    'Saccharomyces cerevisiae', 'Bos taurus', 'Caenorhabditis elegans',
+    'Rattus norvegicus', 'Drosophila melanogaster', 'Pseudomonas aeruginosa']
+    if organism not in organisms:
+        raise ValueError('Organism must be one of '+ ", ".join(organisms))
+
+    version_no = None
+    pathway_names = pd.read_csv('https://pathbank.org/downloads/pathbank_all_pathways.csv.zip', compression='zip', sep=',', header=0)
+    name_dict = dict(zip(pathway_names['SMPDB ID'], pathway_names['Name']))
+
+
+    if omicstype == 'metabolomics':
+        metabolites_url = 'https://pathbank.org/downloads/pathbank_all_metabolites.csv.zip'
+        chebi_pathways = pd.read_csv(metabolites_url, compression='zip', sep=',', header=0, dtype=str)
+        chebi_pathways = chebi_pathways[chebi_pathways['Species'] == organism]
+
+        # reformat to gmt style such that each row contains chebi ID per pathway and each column is a chebi id
+        chebi_pathways = chebi_pathways.groupby(['PathBank ID', 'Pathway Name'])['ChEBI ID'].apply(list).reset_index()
+        chebi_pathways_gmt = pd.DataFrame(chebi_pathways['ChEBI ID'].values.tolist(), index=chebi_pathways['PathBank ID'])
+        chebi_pathways_gmt['Pathway_name'] = chebi_pathways_gmt.index.map(name_dict)
+        chebi_pathways_gmt.insert(0, 'Pathway_name', chebi_pathways_gmt.pop('Pathway_name'))
+
+        if filepath:
+            fpath = filepath + "/Pathbank_" + "_".join(organism.split())+ "_pathways_ChEBI" + ".gmt"
+            chebi_pathways_gmt.to_csv(fpath, sep="\t", header=False)
+            print("Pathbank DB file saved to " + fpath)
+
+        print("Complete!")
+        return chebi_pathways_gmt
+
+    if omicstype == 'proteomics':
+        proteins_url = 'https://pathbank.org/downloads/pathbank_all_proteins.csv.zip'
+        uniprot_pathways = pd.read_csv(proteins_url, compression='zip', sep=',', header=0, dtype=str)
+        uniprot_pathways = uniprot_pathways[uniprot_pathways['Species'] == organism]
+
+        # reformat to gmt style such that each row contains uniprot ID per pathway and each column is a uniprot id
+        uniprot_pathways = uniprot_pathways.groupby(['PathBank ID', 'Pathway Name'])['Uniprot ID'].apply(list).reset_index()
+        uniprot_pathways_gmt = pd.DataFrame(uniprot_pathways['Uniprot ID'].values.tolist(), index=uniprot_pathways['PathBank ID'])
+        uniprot_pathways_gmt['Pathway_name'] = uniprot_pathways_gmt.index.map(name_dict)
+        uniprot_pathways_gmt.insert(0, 'Pathway_name', uniprot_pathways_gmt.pop('Pathway_name'))
+
+        if filepath:
+            fpath = filepath + "/Pathbank_" + "_".join(organism.split())+ "_pathways_UniProt" + ".gmt"
+            uniprot_pathways_gmt.to_csv(fpath, sep="\t", header=False)
+            print("Pathbank DB file saved to " + fpath)
+
+        print("Complete!")
+        return uniprot_pathways_gmt
+
+    if omicstype == 'multiomics':
+        metabolites_url = 'https://pathbank.org/downloads/pathbank_all_metabolites.csv.zip'
+        chebi_pathways = pd.read_csv(metabolites_url, compression='zip', sep=',', header=0, dtype=str)
+        chebi_pathways = chebi_pathways[chebi_pathways['Species'] == organism]
+
+        # reformat to gmt style such that each row contains chebi ID per pathway and each column is a chebi id
+        chebi_pathways = chebi_pathways.groupby(['PathBank ID', 'Pathway Name'])['ChEBI ID'].apply(list).reset_index()
+        chebi_pathways_gmt = pd.DataFrame(chebi_pathways['ChEBI ID'].values.tolist(), index=chebi_pathways['PathBank ID'])
+
+        proteins_url = 'https://pathbank.org/downloads/pathbank_all_proteins.csv.zip'
+        uniprot_pathways = pd.read_csv(proteins_url, compression='zip', sep=',', header=0, dtype=str)
+        uniprot_pathways = uniprot_pathways[uniprot_pathways['Species'] == organism]
+
+        # reformat to gmt style such that each row contains uniprot ID per pathway and each column is a uniprot id
+        uniprot_pathways = uniprot_pathways.groupby(['PathBank ID', 'Pathway Name'])['Uniprot ID'].apply(list).reset_index()
+        uniprot_pathways_gmt = pd.DataFrame(uniprot_pathways['Uniprot ID'].values.tolist(), index=uniprot_pathways['PathBank ID'])
+
+        multiomics_pathways_gmt = pd.concat([chebi_pathways_gmt, uniprot_pathways_gmt], axis=1)
+        multiomics_pathways_gmt['Pathway_name'] = multiomics_pathways_gmt.index.map(name_dict)
+        multiomics_pathways_gmt.insert(0, 'Pathway_name', multiomics_pathways_gmt.pop('Pathway_name'))
+
+        if filepath:
+            fpath = filepath + "/Pathbank_" + "_".join(organism.split())+ "_pathways_multiomics" + ".gmt"
+            multiomics_pathways_gmt.to_csv(fpath, sep="\t", header=False)
+            print("Pathbank DB file saved to " + fpath)
+
+        print("Complete!")
+
+        return multiomics_pathways_gmt
+
+    download_pathbank()

src/sspa/process_pathways.py

@@ -74,6 +74,29 @@ def process_kegg(organism, infile=None, download_latest=False, filepath=None):
         pathways_df = pathways_df.mask(mask, None)
 
         return pathways_df
+
+
+def process_pathbank(organism, infile=None, download_latest=False, filepath=None, omics_type='metabolomics'):
+    '''
+    Function to load PathBank pathways 
+    Args:
+        infile (str): default None, provide a PathBank pathway file to process into the GMT-style dataframe 
+        download_latest (Bool): Downloads the latest version of PathBank metabolic pathways
+        filepath (str): filepath to save pathway file to, default is None - save to variable
+        omics_type(str): If using download_latest, specify type of omics pathways to download. Options are 'metabolomics', 'proteomics', or 'multiomics'
+    Returns: 
+        GMT-like pd.DataFrame containing PathBank pathways
+    '''
+    if download_latest:
+        pathways_df = sspa.download_pathways.download_pathbank(organism, filepath, omics_type)
+        return pathways_df
+
+    else:
+        if infile:
+            pathways_df = pd.read_csv(infile, index_col=0)
+        else: 
+            print('Set download_latest=True to download latest version of PathBank pathways or provide a saved PathBank pathway .csv/.gmt file to load')
+
 
 def process_gmt(infile):
     '''