Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_d6a6f422b091ba12ea61d4adbf1b0e8e |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-084 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16C20-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16C20-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16C20-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16C20-30 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16C20-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16C20-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16C20-30 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16C20-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
filingDate |
2021-06-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f0e484e353d800b64753a6618d564583 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2417657a07ff1037c1ad627c4f7faade http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_1fffe38da4b6c87b9afb56ba38bad52c http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6833a5c1b543347ac73283261ed29e88 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_1ed76ea124ce388691ff51d69b7400bd http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2bcc05fa222a7cc921e72d562fcb06d7 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6fd8c837cb9feabb756af12995009ed2 |
publicationDate |
2021-09-07-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-113362905-A |
titleOfInvention |
A deep learning-based method for predicting enantioselectivity of asymmetric catalytic reactions |
abstract |
The invention discloses a method for predicting the enantioselectivity of asymmetric catalytic reaction based on deep learning. The method first acquires and organizes the data of asymmetric catalytic reactions involving isocyanoacetate, and designs a model training set and an out-of-sample test set; calculates and processes the molecular descriptors of the compounds involved in the reaction, and summarizes them together with the reaction conditions into one Group feature vector input model; build deep neural network and convolutional neural network regression models based on the training set and optimize their hyperparameters, and then obtain a model that can accurately predict the enantioselectivity of the training set response; use the best neural network model to predict samples The enantioselectivity of the external reaction was tested to test the transferability of the model. The results show that the model can accurately predict the enantioselectivity of out-of-sample reactions, which further verifies the robustness and transferability of the model. |
isCitedBy |
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116189804-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-116230109-A |
priorityDate |
2021-06-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |