def test_product_against_rules():
target_smiles = request.form['target_smiles']
smarts = request.form['smarts']
try:
smarts_list = yaml.load(smarts, Loader=yaml.FullLoader)
except:
return jsonify(result={'status': 'fail'})
try:
rxn_list = []
for sma in smarts_list:
rxn_list.append(rdchiralReaction(sma))
except:
return jsonify(result={'status': 'fail'})
try:
network = Network()
if request.form['combine_enantiomers'] == 'true':
network.settings['combine_enantiomers'] = True
else:
network.settings['combine_enantiomers'] = False
network.rxn_obj.rxns = {'test_smarts': rxn_list}
network.rxns = {'test_smarts': rxn_list}
network.generate(target_smiles, 1)
nodes, edges = network.get_visjs_nodes_and_edges()
print(nodes)
result = {'status': 'success', 'nodes': nodes, 'edges': edges}
except:
result = {'status': 'fail'}
return jsonify(result=result)
def create_pathways_for_test(self, target_product):
network = Network()
network.settings.update({
"combine_enantiomers": True,
"remove_simple": True,
"similarity_score_threshold": self.specificity_threshold,
"num_enzymes": 1,
"max_nodes": self.max_nodes,
"prune_steps": 1,
"only_postitive_enzyme_data": self.only_positive_specificity,
'prune_on_substrates': False,
'max_reactions': False,
'include_experimental': False,
'include_two_step': False
})
network.generate(target_product, self.num_steps)
bfs = BFS(network=network,
max_pathways=self.max_pathways,
min_weight=self.min_weight)
bfs.run()
pathways = bfs.get_pathways()
if len(pathways) == self.max_pathways:
self.log(f" ~max pathways reached")
#pathways = group_pathways(pathways)
return pathways
def apply_chemical_steps_molecule():
smiles = request.form['smiles']
smiles = rdkit_smile(smiles)
if smiles is None or smiles == '':
result = {'mol_dict': {}}
return jsonify(result=result)
network = Network(target_smiles=smiles)
network.generate(smiles, 0, calculate_scores=False)
new_substrate_nodes, new_reaction_nodes = network.add_chemical_step(smiles)
list_processed = []
for smi in new_substrate_nodes:
new_smi = re.sub(r"\[(?:[1-9]|[1-9][0-9])\*\]", '*', smi)
list_processed.append(new_smi)
mol_dict = {}
for smi in list_processed:
mol = Chem.MolFromSmiles(smi)
img = get_images.moltosvg(mol, molSize=(200, 200), kekulize=True)
mol_dict[smi] = img
result = {'mol_dict': mol_dict}
return jsonify(result=result)
def _get_retrobiocat_pathways(self,
row,
reaction_names,
combine_enantiomers=True):
product = row['product_1_smiles']
network = Network(print_log=False)
network.settings.update({
"calculate_complexities": True,
"calculate_substrate_specificity": False,
"get_building_blocks": False,
"combine_enantiomers": combine_enantiomers
})
# Only want reactions in list
rxns_to_keep = {}
for rxn_name in network.rxns:
if rxn_name in reaction_names:
rxns_to_keep[rxn_name] = network.rxns[rxn_name]
network.rxns = rxns_to_keep
network.generate(product, 5)
bfs = BFS(network=network, print_log=False, score_pathways=False)
bfs.run()
pathways = bfs.get_pathways()
return pathways
def bfs_with_network_generation():
network = Network()
network.generate('CCCCC=O', 5)
bfs = BFS(network=network, max_pathways=10000)
bfs.run()
pathways = bfs.get_pathways()
return pathways
pathway.other_varients_as_nodes.append(other_pathway.list_nodes)
pathways.append(pathway)
return pathways
def group_pathways(pathways, scores_to_use=None, by_enzyme=True):
if scores_to_use == None:
scores_to_use = default_scores_to_use
end_nodes_dict = _generate_end_nodes_dict(
pathways, scores_to_use) # groups by end_nodes, reactions, scores
grouped_pathways = _get_grouped_pathways(
end_nodes_dict) # converts dict to a list of lists
new_pathways = _collapse_groups(grouped_pathways, by_enzyme)
return new_pathways
if __name__ == '__main__':
from retrobiocat_web.retro.generation.network_generation.network import Network
from retrobiocat_web.retro.generation.pathway_generation.best_first_search import BFS
network = Network(max_nodes=300)
network.generate('[C@H]1(C2=CC=CC=C2)NCCCC1', 5)
bfs = BFS(network=network, max_pathways=200)
bfs.run()
pathways = bfs.get_pathways()
pathways = group_pathways(pathways)
pathways = pathways[0:10]
def task_make_network(form_data):
job = get_current_job()
job.meta['progress'] = 'started'
job.save_meta()
network = Network(include_experimental=bool(form_data['include_experimental']),
include_two_step=bool(form_data['include_two_step']),
include_requires_absence_of_water=bool(form_data['include_requires_absence_of_water']),
print_log=not current_app.config['PRODUCTION'])
network.update_settings({"allow_backwards_steps": bool(form_data['allow_backwards']),
"remove_simple": bool(form_data['remove_small']),
"similarity_score_threshold": float(form_data['sub_thres']),
"combine_enantiomers" : bool(form_data['combine_enantiomers']),
"num_enzymes": 1,
"calculate_complexities": bool(form_data['calc_complexity']),
"calculate_substrate_specificity": bool(form_data['sub_sim']),
"max_nodes": int(form_data['max_initial_nodes'],),
"colour_reactions" : form_data['colour_reactions'],
"colour_arrows": form_data['colour_edges'],
"show_negative_enzymes" : form_data['show_neg_enz'],
"only_postitive_enzyme_data" : not form_data['show_neg_enz'],
"max_reactions": form_data["max_reactions"],
'only_reviewed_activity_data': bool(form_data["only_reviewed"])})
if form_data["specificity_scoring_mode"] == 'Product + substrates (slower)':
network.update_settings({'specificity_score_substrates' : True})
#print(f"include_experimental = {network.settings['include_experimental']}")
#print(f"include_two_step = {network.settings['include_two_step']}")
network.generate(form_data['target_smiles'], form_data['number_steps'], calculate_scores=False)
job.meta['progress'] = 'network_generated'
job.save_meta()
network.calculate_scores()
job.meta['progress'] = 'scores_calculated'
job.save_meta()
nodes, edges = network.get_visjs_nodes_and_edges()
#options = {'interaction': {'multiselect': 'true',}}
options = {}
default_network_name = 'Network for ' + str(network.target_smiles)
result = {'save_id':str(uuid.uuid4()),
'save_links' : [],
'save_name' : default_network_name,
'nodes':nodes,
'edges':edges,
'options':json.dumps(options),
'graph_dict':json.dumps(nx.to_dict_of_lists(network.graph)),
'target_smiles':str(network.target_smiles),
'network_options':json.dumps(network.settings),
'attr_dict':json.dumps(network.attributes_dict()),
'max_reactions' : int(network.settings['max_reactions'])}
current_app.redis.mset({job.id: json.dumps(result)})
time_to_expire = 15*60 #15 mins * 60 seconds
current_app.redis.expire(job.id, time_to_expire)
return result
def select_best_enzyme(self, network):
if network.settings['calculate_substrate_specificity'] == True:
for node in network.reaction_nodes:
current_enz = network.graph.nodes[node]['attributes'][
'selected_enzyme']
current_score = network.graph.nodes[node]['attributes'][
'specificity_scores'][current_enz]
current_score_neg = True
possible_enzymes = network.graph.nodes[node]['attributes'][
'possible_enzymes']
for enz in possible_enzymes:
score = network.graph.nodes[node]['attributes'][
'specificity_scores'][enz]
if (score > current_score
and score != 0) or (abs(score) > current_score
and current_score_neg == True):
network.graph.nodes[node]['attributes'][
'selected_enzyme'] = enz
current_score = abs(score)
if score < 0:
current_score_neg = True
if __name__ == '__main__':
from retrobiocat_web.retro.generation.network_generation.network import Network
network = Network()
network.generate('CCCCC=O',
4) # evaluator calculate scores called during generate
class BFS():
def __init__(self,
network=None,
target=None,
max_pathways=50000,
max_pathway_length=5,
min_weight=1,
use_random=False,
print_log=False,
score_pathways=True,
allow_longer_pathways=False):
"""
Best First Search object, for generating pathways from a network
After initialising, run search using the .run() method
Args:
network: a network object which has been generated
min_weight: the minimum weight to assign to zero complexity change (and Stop)
max_pathways: the maximum number of pathways to generate before stopping
use_random: set the bfs to use weighted random selection rather than always picking the best
"""
self.score_pathways = score_pathways
self.print_log = print_log
self.min_weight = min_weight
self.choices = {}
self.max_pathways = max_pathways
self.max_pathway_length = max_pathway_length
self.allow_longer_pathways = allow_longer_pathways
self.pathways = []
self.use_random = use_random
self.network = network
self.generate_network = False
if self.network == None:
self.target = node_analysis.rdkit_smile(target, warning=True)
self.generate_network = True
self.network = Network(target_smiles=self.target,
number_steps=self.max_pathway_length,
print_log=False)
self.network.generate(self.target, 0)
self.log('BFS - will generate network')
else:
self.target = self.network.target_smiles
def log(self, msg):
if self.print_log == True:
print(msg)
def _get_context(self, nodes):
""" Returns the pathway context, which is a string of node numbers"""
list_node_numbers = []
context = ''
for node in nodes:
list_node_numbers.append(
self.network.graph.nodes[node]['attributes']['node_num'])
sorted_node_numbers = sorted(list_node_numbers)
for node_num in sorted_node_numbers:
context += str(node_num)
context += '-'
return context
def _expand_network(self, smi):
nodes_added = []
new_substrates, new_reactions = self.network.add_step(smi)
nodes_added.extend(new_substrates)
nodes_added.extend(new_reactions)
return nodes_added
def _get_choices(self, end_nodes):
""" Returns a list of reaction nodes (and Stop) which are choices for the next step"""
def get_choice_scores(choices):
scores = [0]
for node in choices[1:]:
scores.append(self.network.graph.nodes[node]['attributes']
['change_in_complexity'])
return scores
def get_weighted_scores(scores):
# invert changes so decreases in complexity are favoured
inverted_reaction_complexity_changes = [x * -1 for x in scores]
min_change = min(inverted_reaction_complexity_changes)
if min_change < 0:
min_change = -min_change
else:
min_change = 0
non_neg_changes = [
x + self.min_weight + min_change
for x in inverted_reaction_complexity_changes
]
return non_neg_changes
def get_choices(end_nodes, graph):
successor_reactions = ['Stop']
for node in end_nodes:
successor_reactions.extend(list(graph.successors(node)))
return successor_reactions
def make_choice_dict(choices, scores):
choice_dict = {}
for i, choice in enumerate(choices):
choice_dict[choice] = scores[i]
return choice_dict
choices = get_choices(end_nodes, self.network.graph)
scores = get_choice_scores(choices)
weighted_scores = get_weighted_scores(scores)
choice_dict = make_choice_dict(choices, weighted_scores)
return choice_dict
def _pick_choice(self, context):
""" Given a context, picks an option to extend (or stop) that pathway """
def pick_best(choices, scores):
sorted_options = node_analysis.sort_by_score(choices,
scores,
reverse=False)
return sorted_options[0]
def pick_weighted_random(choices, scores):
return random.choices(choices, scores, k=1)[0]
def get_lists_choices_scores(choices_dict):
list_choices = []
list_scores = []
for choice in choices_dict:
list_choices.append(choice)
list_scores.append(choices_dict[choice])
return list_choices, list_scores
choices, scores = get_lists_choices_scores(self.choices[context])
if self.use_random == False:
option = pick_best(choices, scores)
else:
option = pick_weighted_random(choices, scores)
return option
def _add_reaction(self, reaction_choice):
new_end_nodes = list(self.network.graph.successors(reaction_choice))
added_nodes = [reaction_choice] + new_end_nodes
return added_nodes, new_end_nodes
def _check_pathway_has_end(self, nodes):
pathway_subgraph = self.network.graph.subgraph(nodes)
end_nodes = node_analysis.get_nodes_with_no_successors(
pathway_subgraph)
if len(end_nodes) == 0:
return False
return True
def _make_pathway(self, nodes):
""" Create pathway object from list of nodes"""
return Pathway(nodes, self.network, calc_scores=self.score_pathways)
def _check_if_should_expand_network(self, end_nodes, pathway_nodes):
if self.generate_network == True:
if self._num_reactions(pathway_nodes) < self.max_pathway_length:
for node in end_nodes:
if len(list(self.network.graph.successors(node))) == 0:
self._expand_network(node)
def _is_node_already_in_pathway(self, current_nodes, new_nodes):
for node in new_nodes:
if node in current_nodes:
return True
return False
def _num_reactions(self, nodes):
count = 0
for node in nodes:
if self.network.graph.nodes[node]['attributes'][
'node_type'] == 'reaction':
count += 1
return count
def run(self):
"""
Generate pathways using best first search
Returns: list of pathways
"""
self.log('Run BFS')
self.pathways = []
self.choices = {}
nodes = [self.target]
context = self._get_context(nodes)
self._check_if_should_expand_network(nodes, nodes)
self.choices[context] = self._get_choices(nodes)
start_context = copy.deepcopy(context)
while (len(self.pathways) < self.max_pathways) and (len(
self.choices[start_context]) > 0):
nodes = [self.network.target_smiles]
context = self._get_context(nodes)
steps = 0
while len(self.choices[context]) > 0:
if steps > self.max_pathway_length:
self.choices[context] = []
if self._check_pathway_has_end(nodes) == True:
self.pathways.append(nodes)
break
best_choice = self._pick_choice(context)
if best_choice == 'Stop':
if self._check_pathway_has_end(nodes) == True:
self.pathways.append(nodes)
self.choices[context].pop('Stop')
steps = 0
break
else:
steps += 1
added_nodes, new_end_nodes = self._add_reaction(
best_choice)
if self._is_node_already_in_pathway(nodes,
added_nodes) == True:
self.choices[context].pop(best_choice)
break
else:
new_context = self._get_context(nodes + added_nodes)
if new_context not in self.choices:
self._check_if_should_expand_network(
new_end_nodes, nodes + added_nodes)
self.choices[new_context] = self._get_choices(
new_end_nodes)
if len(self.choices[new_context]) == 0:
self.choices[context].pop(best_choice)
else:
nodes = nodes + added_nodes
context = new_context
self.log('BFS complete')
if len(self.pathways) >= self.max_pathways:
self.log('Max pathways reached')
return self.pathways
def get_pathways(self):
pathway_objects = []
for list_nodes in self.pathways:
pathway = self._make_pathway(list_nodes)
if self.allow_longer_pathways == True:
pathway_objects.append(pathway)
elif len(pathway.reactions) <= self.max_pathway_length:
pathway_objects.append(pathway)
return pathway_objects
def task_get_pathways(form_data):
job = get_current_job()
job.meta['progress'] = 'started'
job.save_meta()
network = Network(print_log=not current_app.config['PRODUCTION'],
include_experimental=form_data['include_experimental'],
include_two_step=form_data['include_two_step'],
include_requires_absence_of_water=bool(
form_data['include_requires_absence_of_water']))
network.update_settings({
"remove_simple":
bool(form_data['remove_small']),
"combine_enantiomers":
bool(form_data['combine_enantiomers']),
'max_nodes':
int(form_data['max_nodes']),
'similarity_score_threshold':
float(form_data['sub_thres']),
'colour_reactions':
form_data['colour_reactions'],
"colour_arrows":
form_data['colour_edges'],
"show_negative_enzymes":
form_data['show_neg_enz'],
"only_postitive_enzyme_data":
not form_data['show_neg_enz'],
'only_reviewed_activity_data':
bool(form_data["only_reviewed"])
})
if form_data[
"specificity_scoring_mode"] == 'Product + substrates (slower)':
network.update_settings({'specificity_score_substrates': True})
network.generate(form_data['target_smiles'],
form_data['number_steps'],
calculate_scores=False)
job.meta['progress'] = 'network_generated'
job.save_meta()
network.calculate_scores()
job.meta['progress'] = 'network_scored'
job.save_meta()
network_data = {
'graph_dict': json.dumps(nx.to_dict_of_lists(network.graph)),
'target_smiles': str(network.target_smiles),
'network_options': json.dumps(network.settings),
'attr_dict': json.dumps(network.attributes_dict())
}
current_app.redis.mset({f"{job.id}__network": json.dumps(network_data)})
current_app.redis.expire(f"{job.id}__network", 60 * 60)
bfs = BFS(network=network,
max_pathways=form_data['max_pathways'],
max_pathway_length=form_data['number_steps'],
min_weight=float(form_data['min_weight']),
print_log=not current_app.config['PRODUCTION'])
bfs.run()
pathways = bfs.get_pathways()
job.meta['progress'] = 'pathways_generated'
job.save_meta()
package_all_pathways(job.id, pathways)
pathway_evaluator = evaluate_pathways(pathways, [
form_data['weight_num_enzymes'], form_data['weight_complexity'],
form_data['weight_starting'], form_data['weight_known_enzymes'],
form_data['weight_diversity']
])
package_evaluated_pathways(pathway_evaluator.df, job.id)
package_visjs_pathways(job.id)
job.meta['progress'] = 'pathways_scored'
job.save_meta()
options = {}
if form_data['hierarchical'] == True:
options.update({
"layout": {
"improvedLayout": 'true',
'hierarchical': {
'direction': 'DU',
"sortMethod": "hubsize",
"nodeSpacing": 200,
"treeSpacing": 400
}
}
})
pathway_settings = {
'weight_num_enzymes': form_data['weight_num_enzymes'],
'weight_complexity': form_data['weight_complexity'],
'weight_starting': form_data['weight_starting'],
'weight_known_enzymes': form_data['weight_known_enzymes'],
'weight_diversity': form_data['weight_diversity'],
'options': options
}
current_app.redis.mset(
{f"{job.id}__pathway_settings": json.dumps(pathway_settings)})
current_app.redis.expire(job.id, 60 * 60)
smiles = node_analysis.rdkit_smile(smiles)
listSmiles, listReactions = self.retrosynthesisEngine.single_step(
smiles, self.retrorules_rxns, self.network.graph)
self.network.get_node_types()
if calculate_scores == True:
self.network.evaluator.calculate_scores(self.network)
return listSmiles, listReactions
if __name__ == '__main__':
from retrobiocat_web.retro.generation.network_generation.network import Network
target = 'CCCCCO'
network = Network()
network.generate(target, 2)
network.retrorules.diameters = [2]
network.retrorules.load()
network.retrorules.add_step('CCCCCC(C)=O')
"""
file = str(Path(__file__).parents[3]) + '/data/reaction_rules/retrorules/retrorules_all.pkl'
rxns = pickle.load(open(file, "rb"))
for d in rxns:
print(d)
file_name = 'rules' + str(d) + '.pkl'
with open(file_name, 'wb') as handle:
pickle.dump(rxns[d], handle, protocol=pickle.HIGHEST_PROTOCOL)
"""
