def compareDistances(actives, decoys):
actives_fps = utilities.getFingerprintList(actives)[0]
decoys_fps = utilities.getFingerprintList(decoys)[0]
distances_min = []
distances_max = []
for decoy in decoys_fps:
dists = utilities.getMolDistFromSet(decoy, actives_fps)
distances_min.append(dists[0])
distances_max.append(dists[1])
return numpy.mean(distances_min), numpy.mean(distances_max)
def playWithResults(results, decoys, actives_test_set):
actives_test_set_fps, keys = utilities.getFingerprintList(actives_test_set)
actives_test_set_pic50 = [-1.0 * numpy.log10(actives_test_set[chmblid]["ic50"] / 10e9) for chmblid in keys]
actives_test_set_fps = numpy.asarray(actives_test_set_fps)
actives_test_set_pic50 = numpy.asarray(actives_test_set_pic50)
# keys = decoys.keys()
# decoys_fingerprint_data = [decoys[cmpnd_id]['fingerprint'] for cmpnd_id in keys]
# decoys_fingerprint_data = numpy.asarray(decoys_fingerprint_data)
# zeros = [10.75 for x in keys]
# best model from cross-validation
best_model_idx = results["scores"].index(max(results["scores"]))
print "Best score: " + str(results["scores"][best_model_idx])
print "Average score: " + str(numpy.mean(results["scores"]))
# predicted_best = results['predicted_values'][best_model_idx]
# true_best = results['true_values'][best_model_idx]
# final model on training set
final_model = results["final_model"]
predicted_train = final_model.predict(results["fingerprint_data"])
print "Score of final model on the molecules from the training set: " + str(
final_model.score(results["fingerprint_data"], results["activity_data"])
)
# predictions_all = final_model.predict(results['fingerprint_data_validation_set'])
# predictions_decoys = final_model.predict(decoys_fingerprint_data)
predictions_test_set = final_model.predict(actives_test_set_fps)
# print "Score of final model on the validation set: " + str(final_model.score(results['fingerprint_data_validation_set'], results['activity_data_validation_set']))
print "Score of final model on the molecules filtered out during clustering: " + str(
final_model.score(actives_test_set_fps, actives_test_set_pic50)
)
span = (min(results["activity_data"]) - 0.25, max(results["activity_data"] + 0.25))
plt.plot((span[0], span[1]), (span[0], span[1]), linestyle="--")
# plt.plot(results['activity_data_validation_set'], predictions_all, marker='o', linestyle='None', label="Validation set performance")
# plt.plot(true_best, predicted_best, marker='+', linestyle='None', label="Performance of the best model in the particular X-validation step")
# plt.plot(zeros, predictions_decoys, marker='o', linestyle='None', label="decoys")
plt.plot(
results["activity_data"], predicted_train, marker="o", linestyle="None", label="Performance on the training set"
)
plt.plot(
actives_test_set_pic50,
predictions_test_set,
marker="o",
linestyle="None",
label="Performance on the molecules filtered out during clustering (validation set)",
)
plt.xlabel("True values")
plt.ylabel("Predicted values")
plt.ylim(span)
plt.xlim(span)
plt.legend()
plt.show()
def predict(classmodel, regressmodel, molfile_path):
print "Starting predictions for: " + molfile_path
suppl = Chem.SDMolSupplier(molfile_path)
mols = dict()
for mol in suppl:
pmol = PropertyMol.PropertyMol(mol)
mols[pmol.GetProp("_Name")] = {"RDKit" : pmol}
fingerprinter.appendMorganFingerprints(mols, dump=None)
actives = pickle.load(open(ACTIVES_DUMP, 'rb'))
found_sth = False
for mol in mols:
prediction = classmodel.predict(mols[mol]['fingerprint'])
fingerprints_actives = utilities.getFingerprintList(actives)[0]
min_distance = utilities.getMolDistFromSet(mols[mol]['fingerprint'], fingerprints_actives)[0]
if min_distance <= APPLICABILITY_DOMAIN_DISTANCE_THRESHOLD and prediction[0]:
print mol + " is active"
print "Predicted pIC50: " + str(regressmodel.predict(mols[mol]['fingerprint'])[0])
found_sth = True
if not found_sth:
print "None of the molecules within the specified set was found to be active."
def estimateDistanceThreshold(mols):
fps = utilities.getFingerprintList(mols)[0]
dists = utilities.generateDistMatrix(fps)[0]
return numpy.median(dists)
