-
公开(公告)号：US12087407B2
公开(公告)日：2024-09-10
申请号：US16811844
申请日：2020-03-06
IPC分类号： G16C20/10 , G06F3/0482 , G06F18/2113 , G06N3/08 , G06N5/01 , G06N20/00 , G16C20/70 , G16C20/80
CPC分类号： G16C20/10 , G06F3/0482 , G06F18/2113 , G06N3/08 , G06N5/01 , G06N20/00 , G16C20/70 , G16C20/80
摘要： A chemical product formulation system automatically generates seed formulae from historic experiments data for the synthesis of a chemical product. Independent and dependent features are identified from the historic experiments data and feature importance scores are calculated using a supervised machine learning (ML) model. The feature importance scores are used to build data structures from which analytical rules are extracted. The analytical rules are further processed to derive the seed formulae which are user-editable. The intermediate formulae generated via user edits of the seed formulae are further validated and approved in order to be used as the final formulae which are employed for the synthesis of the chemical product.
-
公开(公告)号：US20240290436A1
公开(公告)日：2024-08-29
申请号：US18589248
申请日：2024-02-27
摘要： Embodiments determine behavior of reactive flow systems. One such embodiment defines a plurality of models of the reactive flow system, wherein each defined model represents the reactive flow system at a respective scale. A velocity field for the reactive flow system is determined using a first model, at a first respective scale, of the defined plurality of models and a diffusivity for the reactive flow system is determined using a second model, at a second respective scale, of the defined plurality of models. In turn, a plurality of reaction parameters for the reactive flow system are defined. Then, behavior of the reactive flow system is automatically determined by using the determined velocity field, the determined diffusivity, and the defined plurality of reaction parameters as inputs to a reactive transport solver.
-
公开(公告)号：US12057199B2
公开(公告)日：2024-08-06
申请号：US17761322
申请日：2021-02-07
发明人： Hongji Qi , Long Zhang , Duanyang Chen
IPC分类号： C30B11/02 , G06N3/0464 , G06N3/08 , G16C20/10 , G16C20/70
CPC分类号： G16C20/10 , C30B11/02 , G06N3/0464 , G06N3/08 , G16C20/70
摘要： A preparation method of conductive gallium oxide based on deep learning and vertical Bridgman growth method. The prediction method includes: obtaining a preparation data of the conductive gallium oxide single crystal, the preparation data includes a seed crystal data, an environmental data, a control data and a raw material data, and the raw material data includes a doping type data and a conductive doping concentration; preprocessing the preparation data to obtain a preprocessed preparation data; inputting the preprocessed preparation data into a trained neural network model, and obtaining a predicted property data corresponding to the conductive gallium oxide single crystal through the trained neural network model, the predicted property data includes a predicted carrier concentration.
-
公开(公告)号：US20240257921A1
公开(公告)日：2024-08-01
申请号：US18635717
申请日：2024-04-15
申请人： SRI International
摘要： Retrosynthetic methods are described for determining one or more optimal synthetic routes to generate a target compound.
-
公开(公告)号：US20240242784A1
公开(公告)日：2024-07-18
申请号：US18619052
申请日：2024-03-27
摘要： This application discloses a molecular energy prediction method performed by a computer device. The method includes: obtaining first prediction energy of a target molecule and a quantum operator of the target molecule by using a first calculation method, the quantum operator of the target molecule being configured for describing a wave function of the target molecule; predicting energy information of the target molecule through a molecular energy prediction model and according to the quantum operator of the target molecule; and determining final prediction energy of the target molecule according to the first prediction energy and the energy information. The first prediction energy of the target molecule and the quantum operator of the target molecule obtained through the first calculation method are used to predict the final prediction energy of the target molecule according to the molecular energy prediction model.
-
公开(公告)号：US12027240B2
公开(公告)日：2024-07-02
申请号：US17522702
申请日：2021-11-09
发明人： Yaodong Yang , Hongyao Tang , Guangyong Chen , Shengyu Zhang , Changyu Hsieh , Jianye Hao
摘要： Embodiments of this application relate to a retrosynthesis processing method and apparatus, an electronic device, and a computer-readable storage medium. A retrosynthesis processing method is performed by a computer device. The method includes determining molecular representation information of a target molecule. The method includes inputting the molecular representation information into a target neural network. The method includes performing, via the target neural network, retrosynthesis processing on the target molecule based on the molecular representation information of the target molecule, to obtain a respective retrosynthesis reaction of the target molecule for each step of the retrosynthesis processing. The target neural network is obtained by training a predetermined neural network according to a sample cost dictionary that is generated by concurrently performing retrosynthesis reaction training on each of a plurality of sample molecules, and the respective retrosynthesis reaction is performed according to a preset retrosynthesis reaction architecture.
-
7.发明公开公开(公告)号：US20240136025A1
公开(公告)日：2024-04-25
申请号：US18278411
申请日：2021-04-24
发明人： Zhengwei XIE , Jie ZHU , Jingxiang WANG , Mingjing GAO , Zhurui LIU
摘要： The present disclosure provides a compound function prediction method based on a neural network and a connectivity map (CMAP) algorithm. The compound function prediction method is used to predict an efficacy of a compound, and the compound function prediction method includes the following steps: constructing a compound molecule—encoding vector neural network; constructing and training an encoding vector—marker gene expression variation deep neural network; constructing and training a marker gene expression level or gene expression variation—whole genome gene expression level or gene expression variation neural network; constructing upregulated and downregulated gene sets of a disease or a phenotype; and evaluating a correlation between the compound and the disease or the phenotype.
-
公开(公告)号：US20240055080A1
公开(公告)日：2024-02-15
申请号：US18267603
申请日：2021-12-17
发明人： Zhe Xiong Yang , Huan Huan Gao , Hai Long Lv , Ke Wang , Ye Fan Wu , Ke Shi , Johannes Barth , Andreas Kuehner , Xuyuan Peng-Poehler , Yi Zhou Zheng
摘要： A computer implemented method of predicting a phase stability parameter for a polymer material comprising the steps of providing to a computer processor via a communication interface a digital representation of the polymer material; providing to the processor via the communication interface a data driven model parametrized on a digital representation of historical polymer material, and historical phase stability parameters; determining with the computer processor a phase stability parameter for the polymer material based on the provided data driven model, and the digital representation of the polymer material; providing via the communication interface the determined phase stability parameter.
-
公开(公告)号：US20230420085A1
公开(公告)日：2023-12-28
申请号：US17850763
申请日：2022-06-27
发明人： Sudipto MUKHERJEE , Liang DU , Ke JIANG , Robin ABRAHAM
CPC分类号： G16C20/70 , G16C20/10 , G16C20/20 , G06N3/0445 , G06N3/063
摘要： This disclosure describes a machine learning system that includes a contrastive learning based two-tower model for retrieval of relevant chemical reaction procedures given a query chemical reaction. The two-tower model uses attention-based transformers and neural networks to convert tokenized representations of chemical reactions and chemical reaction procedures to embeddings in a shared embedding space. Each tower can include a transformer network, a pooling layer, a normalization layer, and a neural network. The model is trained with labeled data pairs that include a chemical reaction and the text of a chemical reaction procedure for that chemical reaction. New queries can locate chemical reaction procedures for performing a given chemical reaction as well as procedures for similar chemical reactions. The architecture and training of the model make it possible to perform semantic matching based on chemical structures. The model is highly accurate providing an average recall at K=5 of 95.9%.
-
公开(公告)号：US11854670B2
公开(公告)日：2023-12-26
申请号：US16995858
申请日：2020-08-18
发明人： Leonidas Georgopoulos , Aleksandros Sobczyk , Alain Claude Vaucher , Philippe Schwaller , Vishnu Harikrishnan Nair , Joppe Geluykens , Teodoro Laino
CPC分类号： G16C20/10 , B01J19/0033 , B01J19/0046 , G16C20/90 , B01J2219/00038 , B01J2219/00195 , B01J2219/00695
摘要： A method for executing multiple chemical experiments in parallel may be provided. The method comprises receiving a list of actions to be performed for synthesizing a chemical product. Thereby, the actions correspond to at least two chemical partial reactions and the list comprises a delimiter symbol separating two chemical partial reactions, determining identical chemical partial reactions, and building a reaction commonality tree (RCT) of the chemical reactions. Furthermore, the method comprises executing a plurality of the identical chemical partial reactions independent of a sequence of chemical partial reactions of the reaction commonality tree only once. Each of the identical chemical partial reactions is executed in a different chemical reactor and each resulting intermediate product has a quantity of the sum of the related identical chemical partial reactions. The method also comprises, storing the intermediate chemical products in a separate container, and executing remaining chemical partial reactions according to the RCT.
-
-
-
-
-
-
-
-
-
搜索结果
218 条记录 (耗时 0.03 秒)
