Merge pull request #239 from asherpasha/dev

Refactoring code.

Author: asherpasha

api/resources/gene_information.py

@@ -5,19 +5,14 @@
 """
 
 from flask_restx import Namespace, Resource, fields
-from flask import request, jsonify
+from flask import request
 from markupsafe import escape
 from api.utils.bar_utils import BARUtils
 from marshmallow import Schema, ValidationError, fields as marshmallow_fields
 from api import db
 from api.models.rice_interactions import Interactions as RiceInteractions
 from sqlalchemy import or_
 
-import tempfile
-import os
-import subprocess
-from collections import defaultdict
-
 itrns = Namespace(
     "Interactions",
     description="Interactions (protein-protein, protein-DNA, etc) endpoint",
@@ -41,8 +36,7 @@
     {
         "data": fields.List(
             required=True,
-            example=[["AT5G67420", "AT1G12110"],
-                     ["AT5G67420", "AT1G08090"]],
+            example=[["AT5G67420", "AT1G12110"], ["AT5G67420", "AT1G08090"]],
             cls_or_instance=fields.List(fields.String),
         ),
     },
@@ -55,9 +49,7 @@ class GeneIntrnsSchema(Schema):
 
 
 class MFinderDataSchema(Schema):
-    data = marshmallow_fields.List(
-        marshmallow_fields.List(marshmallow_fields.String())
-    )
+    data = marshmallow_fields.List(marshmallow_fields.List(marshmallow_fields.String()))
 
 
 @itrns.route("/<species>/<query_gene>")
@@ -164,200 +156,3 @@ def post(self):
             return BARUtils.success_exit(res)
         else:
             return BARUtils.error_exit("No data for the given species/genes"), 400
-
-
-@itrns.route("/mfinder")
-class MFinder(Resource):
-    @itrns.expect(post_int_data)
-    def post(self):
-        """This endpoint was originally written by Vincent Lau to return mFinder
-        results to AGENT in his express node.JS app. However Tianhui Zhao refactored
-        to the BAR_API
-        """
-        data = request.get_json()
-        # Validate json
-        try:
-            data = MFinderDataSchema().load(data)
-        except ValidationError as err:
-            return BARUtils.error_exit(err.messages), 400
-
-        filtered_valid_arr = self.input_validation(data['data'])
-        if isinstance(filtered_valid_arr, str):
-            return BARUtils.error_exit(filtered_valid_arr), 400
-        settings = self.settings_validation(data.get('options', {}))
-        ret_json = self.create_files_and_mfinder(filtered_valid_arr, settings)
-        return jsonify(self.beautify_results(ret_json))
-
-    # Eliminates same pairs
-    def uniq_with(self, arr, comp_func):
-        unique_arr = []
-        for item in arr:
-            if not any(comp_func(item, unique_item) for unique_item in unique_arr):
-                unique_arr.append(item)
-        return unique_arr
-
-    def is_equal(self, a, b):
-        return a == b
-
-    def find_key(self, d, value):
-        return next(key for key, val in d.items() if val == value)
-
-    # Check if JSON body data obj is an array of arrays (2d arr)
-    # ex [ [ "AT1G010100", "AT5G01010" ], ["AT3G10000", "AT2G03240"]]
-    # {Array<Array<string>>} input: the above arr
-    def input_validation(self, input):
-        if not isinstance(input, list):
-            return "invalid JSON, not an arr"
-
-        if len(input) == 0:
-            return "arr length 0!"
-
-        if any(len(i) != 2 for i in input):
-            return "inner arr length is not of length 2!"
-
-        if not all(isinstance(i, list) for i in input):
-            return "invalid JSON, check arr members are arrs!"
-
-        if not all(isinstance(j, str) for i in input for j in i):
-            return "invalid JSON, check if inside arr members are strings!"
-
-        if not all(BARUtils.is_arabidopsis_gene_valid(j) for i in input for j in i):
-            return "Invalid gene ID contained!"
-
-        # filter self-edges and duplicate edges (mFinder does not accept)
-        return self.uniq_with([i for i in input if i[0] != i[1]], self.is_equal)
-
-    # Some mFinders params allowed within reasonable server load. Namely mFinder takes 3 basic params: nd (non-directed network),
-    # r (# of rand networks to gen), s (motif size), u (unique min), z (z-score min). The defaults are directed, 100, 3, 4, & 2
-    # respectively. HOWEVER choose r of 30 for speed
-    # Do a validation check on each value too!
-    # opts: the JSON settings object, can be empty in which we provide the default
-    def settings_validation(self, opts):
-        opts = opts or {}
-        self.injection_check(opts)
-        settings_obj = opts.copy()
-        if 'nd' not in opts:
-            settings_obj['nd'] = False
-        elif not isinstance(opts['nd'], bool):
-            return "incorrect nd setting - is it boolean?", 400
-
-        if 'r' not in opts:
-            settings_obj['r'] = 50
-        elif not isinstance(opts['r'], int) or opts['r'] > 150:
-            return "incorrect r setting - is it a number under 151?", 400
-
-        if 's' not in opts:
-            settings_obj['s'] = 3
-        elif not isinstance(opts['s'], int) or opts['s'] < 2 or opts['s'] > 4:
-            return "incorrect s setting - is it a number between 2 and 4?", 400
-
-        if 'u' not in opts:
-            settings_obj['u'] = 4
-        elif not isinstance(opts['u'], int) or opts['u'] > 999:
-            return "incorrect u setting - is it a number or below 1000?", 400
-
-        if 'z' not in opts:
-            settings_obj['z'] = 2
-        elif not isinstance(opts['z'], int) or opts['z'] > 99:
-            return "incorrect z setting - is it a number or below 100?", 400
-
-        return settings_obj
-
-    # Check for injection, throw if suspiciously long command is found.
-    # object: to validate for injection
-    def injection_check(self, obj):
-        for key, value in obj.items():
-            if len(str(value)) > 10:
-                return f"{key} settings param is too long", 400
-
-    # Take in the filtered array of gene-id pairs (edges) and perform
-    # mFinder analysis on them (create temp text files to do so)
-    # Performed SYNCHRONOUSLY !!!
-    def create_files_and_mfinder(self, input, opts_obj):
-
-        # give read/write permissions to user but nada to anybody else
-        tmpfile = tempfile.NamedTemporaryFile(mode='w+', suffix='.txt', delete=False)
-        os.chmod(tmpfile.name, 0o600)
-
-        # get a hash of IDs -> numbers for later lookup and writable string
-        hash_of_ids, return_str = self.get_gene_id_hash_map(input)
-
-        # write to temp file which mFinder will run/read on
-        tmpfile.write(return_str)
-        tmpfile.flush()
-
-        command = (
-            f"/bartmp/mfinder {tmpfile.name} "
-            f"-s {opts_obj['s']} "
-            f"-r {opts_obj['r']} "
-            f"-u {opts_obj['u']} "
-            f"-z {opts_obj['z']} "
-            f"{'-nd ' if opts_obj.get('nd') else ''}"
-            "-omem"
-        )
-        subprocess.run(command, shell=True, check=True)
-
-        with open(tmpfile.name[:-4] + "_OUT.txt", 'r') as stats_file:
-            mfinder_stats = stats_file.read()
-
-        with open(tmpfile.name[:-4] + "_MEMBERS.txt", 'r') as members_file:
-            mfinder_members = members_file.read()
-
-        tmpfile.close()
-        os.remove(tmpfile.name)
-
-        return {'hashOfIds': hash_of_ids, 'mFinderStats': mfinder_stats, 'mFinderMembers': mfinder_members}
-
-    # Take an input of array of array of strings which represent edges and transform those gene IDs (unique!) to a hash table and
-    # coinciding edges i.e. [["PHE", "PAT"], ["PAT, "PAN"]] to "232 210 1 \n 210 100 1\n"
-    def get_gene_id_hash_map(self, input):
-        hash_of_ids = defaultdict(lambda: None)
-        iter = 1
-        return_str = ""
-        for item in input:
-            if item[0] not in hash_of_ids.values():
-                hash_of_ids[iter] = item[0]
-                iter += 1
-            if item[1] not in hash_of_ids.values():
-                hash_of_ids[iter] = item[1]
-                iter += 1
-            return_str += f"{self.find_key(hash_of_ids, item[0])} {self.find_key(hash_of_ids, item[1])} 1\n"
-
-        return hash_of_ids, return_str
-
-    # Beautify the output file string and members file string
-    def beautify_results(self, mfinder_res_obj):
-        stats = mfinder_res_obj['mFinderStats']
-        mems = mfinder_res_obj['mFinderMembers']
-        id_map = mfinder_res_obj['hashOfIds']
-        ret_obj = {'sigMotifs': {}, 'motifList': {}}
-
-        try:
-            sig_motifs_str = stats.split('[MILI]\t\n\n')[1].split('Full')[0].split('\n\n')
-        # In case stats has less than 2 parts after split('[MILI]\t\n\n')[1]
-        except IndexError:
-            raise ValueError("Expected delimiter '[MILI]\t\n\n' or 'Full' not found in the stats string.")
-        sig_motifs_str = sig_motifs_str[:len(sig_motifs_str) - 2:2]
-        for item in sig_motifs_str:
-            split_stats_for_motif_id = item.split('\t')
-            ret_obj['sigMotifs'][split_stats_for_motif_id[0]] = {
-                'numAppearances': split_stats_for_motif_id[1],
-                'numAppearancesRand': split_stats_for_motif_id[2],
-                'appearancesZScore': split_stats_for_motif_id[3],
-                'pValue': split_stats_for_motif_id[4],
-                'uniq': split_stats_for_motif_id[5],
-                'conc': split_stats_for_motif_id[6],
-            }
-
-        subgraphs_list_str = mems.split('subgraph id = ')[1:]
-        for subgraph_str in subgraphs_list_str:
-            member_list_split = subgraph_str.split('\n')
-            motif_mem_list = [i.rstrip('\t') for i in member_list_split[5:-2]]
-            motif_mem_results = []
-            for i in motif_mem_list:
-                three_genes = i.split('\t')
-                formatted_str = f"{id_map[int(three_genes[0])]}\t{id_map[int(three_genes[1])]}\t{id_map[int(three_genes[2])]}"  # i.e. PAT\tPAN\tEGFR
-                motif_mem_results.append(formatted_str)
-            ret_obj['motifList'][member_list_split[0]] = motif_mem_results
-
-        return BARUtils.success_exit(ret_obj)

api/resources/interactions.py

@@ -26,22 +26,21 @@ def get(self, gene_id=""):
         gene_id = escape(gene_id.upper())
 
         if BARUtils.is_arabidopsis_gene_valid(gene_id):
-            rows = (
-                db.session.execute(db.select(Summaries).where(Summaries.gene_id == gene_id))
-                .first()
-            )
+            rows = db.session.execute(db.select(Summaries).where(Summaries.gene_id == gene_id)).first()
 
-            if len(rows) == 0:
+            if rows and len(rows) > 0:
+                res = {
+                    "summary": rows[0].summary,
+                    "gene_id": rows[0].gene_id,
+                    "bert_score": rows[0].bert_score,
+                }
+
+                return BARUtils.success_exit(res)
+            else:
                 return (
                     BARUtils.error_exit("There are no data found for the given gene"),
                     400,
                 )
-            else:
-                res = {
-                            "summary": rows[0].summary,
-                            "gene_id": rows[0].gene_id,
-                            "bert_score": rows[0].bert_score,
-                    }
-                return BARUtils.success_exit(res)
+
         else:
             return BARUtils.error_exit("Invalid gene id"), 400

api/resources/llama3.py

@@ -4,22 +4,22 @@ attrs==24.2.0
 black==24.8.0
 blinker==1.8.2
 cachelib==0.9.0
-certifi==2024.7.4
+certifi==2024.8.30
 charset-normalizer==3.3.2
 click==8.1.7
 coverage==7.6.1
 Deprecated==1.2.14
 flake8==7.1.1
 Flask==3.0.3
 Flask-Caching==2.3.0
-Flask-Cors==4.0.1
+Flask-Cors==5.0.0
 Flask-Limiter==3.8.0
 flask-marshmallow==1.2.1
 flask-restx==1.3.0
 Flask-SQLAlchemy==3.1.1
-greenlet==3.0.3
-idna==3.7
-importlib_resources==6.4.3
+greenlet==3.1.1
+idna==3.10
+importlib_resources==6.4.5
 iniconfig==2.0.0
 itsdangerous==2.2.0
 Jinja2==3.1.4
@@ -36,25 +36,25 @@ mysqlclient==2.2.4
 ordered-set==4.1.0
 packaging==24.1
 pathspec==0.12.1
-platformdirs==4.2.2
+platformdirs==4.3.6
 pluggy==1.5.0
 pycodestyle==2.12.1
 pyflakes==3.2.0
 Pygments==2.18.0
 pyrsistent==0.20.0
-pytest==8.3.2
+pytest==8.3.3
 python-dateutil==2.9.0.post0
-pytz==2024.1
-redis==5.0.8
+pytz==2024.2
+redis==5.1.0
 referencing==0.35.1
 requests==2.32.3
-rich==13.7.1
+rich==13.8.1
 rpds-py==0.20.0
-setuptools==73.0.1
+setuptools==75.1.0
 six==1.16.0
-SQLAlchemy==2.0.32
+SQLAlchemy==2.0.35
 typing_extensions==4.12.2
-urllib3==2.2.2
-Werkzeug==3.0.3
+urllib3==2.2.3
+Werkzeug==3.0.4
 wheel==0.44.0
 wrapt==1.16.0