Merge pull request lukekoch#1 from lukekoch/unstable

Merge Unstable

Author: lukekoch

flask-backend/Dockerfile

@@ -11,4 +11,4 @@ RUN source ./venv/bin/activate
 RUN pip install -r ./requirements.txt
 RUN apt-get -y update && apt install -y curl && apt-get install -y wget unzip genometools samtools tabix
 
-CMD python3 src/worker.py & python3 src/worker.py & python3 src/main.py
+CMD python3 -u src/worker.py & python3 -u src/worker.py & python3 -u src/main.py

flask-backend/src/Routes/__init__.py

@@ -15,6 +15,7 @@ def create_app():
     from .combined_imports import imports_bp
     from .files import files_bp
     from .tasks import tasks_bp
+    from .taxaminer_data import taxaminer_bp
 
     app.register_blueprint(taxa_bp, url_prefix="/")
     app.register_blueprint(users_bp, url_prefix="/")
@@ -26,6 +27,7 @@ def create_app():
     app.register_blueprint(imports_bp, url_prefix="/")
     app.register_blueprint(files_bp, url_prefix="/")
     app.register_blueprint(tasks_bp, url_prefix="/")
+    app.register_blueprint(taxaminer_bp, url_prefix="/taxaminer/")
 
     CORS(app)
     return app

flask-backend/src/Routes/annotations.py

@@ -13,6 +13,7 @@
     fetchFeatures,
     import_annotation,
     updateAnnotationLabel,
+    grepFeature
 )
 
 # setup blueprint name
@@ -173,6 +174,31 @@ def annotations_bp_fetchFeatures():
         return REQUESTMETHODERROR
 
 
+# FETCH ALL ASSEMBLIES
+@annotations_bp.route("/grepFeatures", methods=["POST"])
+def annotations_bp_grepFeatures():
+    if request.method == "POST":
+        req = request.get_json(force=True)
+        userID = req.get("userID", None)
+        token = req.get("token", None)
+
+        # token still active
+        valid_token, error = validateActiveToken(userID, token, ACCESS_LVL_1)
+        if not valid_token:
+            response = jsonify({"payload": {}, "notification": error})
+            response.headers.add("Access-Control-Allow-Origin", "*")
+            return response
+        
+        # grep input
+        search = req.get("search", None)
+        annotation_id = req.get("annotationID", None)
+
+        coords = grepFeature(search, annotation_id)
+        return jsonify({"coords": coords})
+    else:
+        return REQUESTMETHODERROR
+
+
 # FETCH ALL UNIQUE FEATURE TYPES
 @annotations_bp.route("/fetchFeatureSeqIDs", methods=["POST"])
 def annotations_bp_fetchFeatureSeqIDs():

flask-backend/src/Routes/file_io.py

@@ -0,0 +1,141 @@
+# TODO remove this once testing has finished
+
+import csv
+import json
+
+from flask import jsonify
+
+def load_datasets():
+    with open('./datasets/datasets.json', 'r') as f:
+        data = json.load(f)
+    return data
+
+def convert_csv_to_json(path):
+    """Load the main scatterplot datafile and convert it to JSON"""
+    with open(path, encoding='utf-8') as csvf:
+        # load csv file data using csv library's dictionary reader
+        csv_reader = csv.DictReader(csvf)
+        labeled_dict = dict()
+
+        for row in csv_reader:
+            if row['plot_label'] in labeled_dict.keys():
+                labeled_dict[row['plot_label']].append(row)
+            else:
+                labeled_dict[row['plot_label']] = [row]
+
+    traces_list = []
+    for key in labeled_dict.keys():
+        traces_list.append(labeled_dict[key])
+
+    return traces_list
+
+
+def fast_fasta_loader(path, fasta_id):
+    """Load fasta sequence data"""
+    seq = ""
+    start_index = -1
+
+    with open(path, "r") as f:
+        lines = f.readlines()
+        for i, line in enumerate(lines):
+            lines[i] = line.rstrip()
+
+    for i, line in enumerate(lines):
+        if line.startswith(">" + fasta_id):
+            start_index = i
+            break
+
+    if start_index == -1:
+        return ""
+
+    for i in range(start_index + 1, len(lines)):
+        if not lines[i].startswith(">"):
+            seq += lines[i]
+        else:
+            break
+
+    return seq
+
+
+def diamond_to_json_str(path):
+    """Convert diamond table rows to JSON strings"""
+    rows = []
+    # format as defined here:
+    # https://github.com/fdarthen/taXaminer/blob/988f408afed4830e23a1b8b837b24bab3e8fc5b9/taxonomic_assignment.py#L718
+    fields = ['qseqid', 'sseqid', 'pident', 'length', 'mismatch', 'gapopen', 'qstart', 'qend', 'sstart', 'send',
+              'evalue', 'bitscore', 'taxid', 'taxname']
+    with open(path, encoding='utf-8') as csvf:
+        # load csv file data using csv library's dictionary reader
+        csv_reader = csv.DictReader(csvf, delimiter='\t', fieldnames=fields)
+        for i, row in enumerate(csv_reader):
+            json_string = json.dumps(row)
+            rows.append(json_string)
+    
+    return rows
+
+def taxonomic_hits_loader(fasta_id, path):
+    """Load all taxonomic hits"""
+    fields = ['qseqid', 'sseqid', 'pident', 'length', 'mismatch', 'gapopen', 'qstart', 'qend', 'sstart', 'send',
+              'evalue', 'bitscore', 'staxids', 'ssciname']
+    match_rows = []
+    start_index = -1
+    with open(path, encoding='utf-8') as csvf:
+        # load csv file data using csv library's dictionary reader
+        csv_reader = csv.DictReader(csvf, delimiter='\t', fieldnames=fields)
+        for i, row in enumerate(csv_reader):
+            if row['qseqid'] == fasta_id:
+                match_rows.append(row)
+
+    for row in match_rows:
+        if len(row['ssciname']) > 20:
+            row['ssciname'] = row['ssciname'][0:20] + "..."
+    return match_rows
+
+def load_user_config(path):
+    """Load a user config"""
+    with open(f"{path}user_config.json", "r") as file:
+        lines = file.readlines()
+    
+    return "".join(lines)
+
+def parse_user_config(path):
+    """Parse user config to JSON"""
+    with open(f'{path}user_config.json', 'r') as f:
+        data = json.load(f)
+    return data
+
+def write_user_config(json_data, path):
+    """Write user config to disk"""
+    with open(f'{path}user_config.json', 'w') as json_file:
+        json.dump(json_data, json_file)
+
+def load_pca_coords(dataset_id):
+    """3D plot of variable contribution"""
+    with open(f"/flask-backend/data/storage/taxa/Burkholderia_multivorans/Burkholderia_multivorans_id1/analyses/taxaminer/Burkholderia_multivorans_id1_taxaminer_id1/pca_loadings.csv", 'r') as file:
+        lines = file.readlines()
+    
+    final_lines = []
+    for line in lines[1:-1]:
+        fields = line.split(",")
+        new_dict = dict()
+        new_dict['label'] = fields[0]
+        new_dict['x'] = [fields[1]]
+        new_dict['y'] = [fields[2]]
+        new_dict['z'] = [fields[3]]
+        final_lines.append(new_dict)
+    
+    return final_lines
+
+def indexed_data(path):
+    """Load the main scatterplot datafile and convert it to JSON"""
+    with open(path, encoding='utf-8') as csvf:
+        # load csv file data using csv library's dictionary reader
+        csv_reader = csv.DictReader(csvf)
+        labeled_dict = dict()
+
+        for row in csv_reader:
+            labeled_dict[row['g_name']] = row
+
+
+    return labeled_dict
+