公开(公告)号：WO2022163996A1

公开(公告)日：2022-08-04

申请号：PCT/KR2021/017765

申请日：2021-11-29

Applicant: 광주과학기술원

Inventor： 남호정 ,  이인구

IPC: G16C20/30 ,  G16C20/70 ,  G16C20/50 ,  G16B35/00 ,  G16C20/60 ,  G06N20/00 ,  G06N3/08

Abstract: 본 발명은 딥 러닝을 이용한 약물-표적 단백질 상호작용 예측에 관한 것으로 본 발명에 따른 약물-표적 상호작용 예측 장치 및 방법은 약물과 단백질 사이의 상호작용 여부 뿐 아니라 약물과 단백질의 바인딩 영역을 함께 이용하여 트랜스포머 네트워크를 학습하고 어텐션 스코어를 사용하는 트랜스포머 네트워크를 이용하여 DTI와 바인딩 영역을 예측함으로써 DTI 예측 성능을 높일 수 있는 효과가 있다.

公开(公告)号：WO2022152478A1

公开(公告)日：2022-07-21

申请号：PCT/EP2021/085326

申请日：2021-12-10

Applicant: ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL) ,  IMPERIAL COLLEGE INNOVATIONS LIMITED

Inventor： BRONSTEIN, Michael ,  SVERRISSON, Freyr ,  PIERRE FEYDY, Jean, Bao ,  GAINZA, Pablo ,  FERREIRA DE SOUSA CORREIA, Bruno, Emanuel

IPC: G16B15/30 ,  G16B40/20 ,  G16C10/00 ,  G16C20/30 ,  G16C20/70

Abstract: The present invention concerns a computer-system-implemented method for predicting properties of a protein molecule, comprising the steps of: receiving an input representation of the protein molecule; applying a surface generator to produce a molecular surface; applying at least one layer of geometric convolution on the molecular surface to produce a set of surface features; and using the set of features to predict the properties of the molecule.

公开(公告)号：WO2022148847A1

公开(公告)日：2022-07-14

申请号：PCT/EP2022/050287

申请日：2022-01-07

Applicant: DEEPMIND TECHNOLOGIES LIMITED

Inventor： KIRKPATRICK, James ,  MCMORROW, Brendan Charles ,  TURBAN, David Herbert Phillip ,  GAUNT, Alexander Lloyd ,  SPENCER, James ,  MATTHEWS, Alexander Graeme de Garis ,  COHEN, Aron Jonathan

IPC: G16C20/30

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for predicting an exchange-correlation energy of an atomic system. The system obtains respective electron-orbital features of the atomic system at each of a plurality of grid points; generates, for each of the plurality of grid points, a respective input feature vector for the electron-orbital features at the grid point; and processes the respective input feature vectors for the plurality of grid points using a neural network to generate a predicted exchange-correlation energy of the atomic system.

公开(公告)号：WO2022136654A1

公开(公告)日：2022-06-30

申请号：PCT/EP2021/087521

申请日：2021-12-23

Applicant: BASF SE ,  BASF ADVANCED CHEMICALS CO., LTD.

Inventor： YANG, Zhe Xiong ,  ZHANG, Jian ,  JIANG, Zhi Ting ,  BARTH, Johannes

IPC: G16C20/10 ,  G16C20/30 ,  G16C60/00

Abstract: A computer implemented method for generating synthesis specifications comprising the steps of providing to a computer processor via a communication interface a proposed target application property of the new synthesis specification;providing to the computer processor via the communication interface a data driven model, parametrized based on historical synthesis specifications comprising historical list of components, historical amounts for each of the components and historical target criteria,determining via the computer processor a target synthesis specification based on the data driven model and the target application property providing to an output unit via the communication interface the target synthesis specification, comprising a list of target components and the amount of each of the components.

公开(公告)号：WO2022124724A1

公开(公告)日：2022-06-16

申请号：PCT/KR2021/018330

申请日：2021-12-06

Applicant: 주식회사 온코크로스 ONCOCROSS CO., LTD. [KR]/[KR]

Inventor： 김이랑 KIM, Yi Rang ,  이용흔 LEE, Young Heun ,  심우광 SIM, Woo Gwang ,  구창대 GU, Chang Dai ,  조준희 JO, Jun Hee

IPC: G16C20/70 ,  G16C20/30 ,  G16H50/50 ,  G16H50/70 ,  G16B40/20 ,  G16B10/00 ,  G06N20/00 ,  G06N3/08

Abstract: 기계 학습 기반의 예후 예측 방법 및 그 장치가 제공된다. 본 개시의 몇몇 실시예들에 따른 예후 예측 방법은, 복수의 환자의 유전자발현데이터와 생존기간데이터를 포함하는 원본데이터를 획득하는 단계, 획득된 원본데이터를 전처리하여 학습데이터를 구성하는 단계, 구성된 학습데이터를 이용하여 예후예측모델을 구축하는 단계 및 예후예측모델을 이용하여 피검자의 예후를 예측하는 단계를 포함할 수 있다.

公开(公告)号：WO2022113945A1

公开(公告)日：2022-06-02

申请号：PCT/JP2021/042833

申请日：2021-11-22

Applicant: 昭和電工マテリアルズ株式会社

Inventor： 花岡　恭平

IPC: G16C20/30

Abstract: 一実施形態に係る情報処理システムは、少なくとも一つのプロセッサを備える。少なくとも一つのプロセッサは、複数の成分オブジェクトのそれぞれについての数値表現および複合比を取得し、複数の数値表現に基づいて機械学習を実行して、複数の成分オブジェクトに対応する複数の回帰パラメータを算出し、複数の回帰パラメータによって定義される回帰モデルに複数の複合比を適用して、複数の成分オブジェクトを複合させることで得られる複合オブジェクトの特性を示す予測値を算出する。

公开(公告)号：WO2022094468A1

公开(公告)日：2022-05-05

申请号：PCT/US2021/057731

申请日：2021-11-02

Applicant: REGENERON PHARMACEUTICALS, INC.

Inventor： ARORA, Jayant ,  TANG, Xiaolin ,  SHAMEEM, Mohammed ,  TAFAZZOL, Alireza

IPC: G16B15/00 ,  G16B15/30 ,  G16B40/20 ,  G16C20/00 ,  G16C20/10 ,  G16C20/30 ,  G16C20/50 ,  G16C20/60 ,  G16C20/70

Abstract: Disclosed are methods comprising determining experimental data associated with one or more monoclonal antibodies (mAbs), determining computationally-derived data associated with the one or more mAbs, wherein the computationally-derived data comprises one or more computational parameters weighted based on accessible surfaces (ASAs) of one or more residues of the one or more mAbs, determining, based on the experimental data and the computationally-derived data, a plurality of candidate predictive models, determining an optimal predictive model from the plurality of candidate predictive models, and outputting the optimal predictive model.

公开(公告)号：WO2022084495A1

公开(公告)日：2022-04-28

申请号：PCT/EP2021/079323

申请日：2021-10-22

Applicant: BASF SE

Inventor： BHATTACHARYA, Sandip ,  HLOUCHA, Matthias ,  PRINZ, Daniela ,  EISFELD, Wolf

IPC: G16C60/00 ,  G16C20/30

Abstract: A system (110) for predicting sensory attributes or physico-chemical properties of an oil or a mixture of oils for personal care is proposed. The system (110) comprises at least one communication interface (112) for providing data and at least one processing device (114). The processing device (114) is configured for: - obtaining via the communication interface (112) of at least one physico-chemical property of the oil or the mixture of oils or of at least one sensory attribute and of at least one model relating one or more physico-chemical properties to one or more sensory attributes; - determining at least one sensory attribute of the oil or the mixture of oils based on the obtained physico-chemical properties and the model or determining at least one physico-chemical property of the oil or the mixture of oils based on the obtained sensory attributes and the model; - providing via the communication interface (112) the determined sensory attribute or the determined physico-chemical property.

公开(公告)号：WO2022026211A1

公开(公告)日：2022-02-03

申请号：PCT/US2021/041973

申请日：2021-07-16

Applicant: AMGEN INC.

Inventor： NOGUERAS, Hector ,  COUFAL, Myra ,  SOTO-ORTEGA, Deborah

IPC: G16C20/30 ,  G16C60/00

Abstract: A method of selecting raw materials for use in a column chromatography purification process in which, for each of one or more candidate resins, a respective set of resin attribute values is received, including at least one analytical measurement of the candidate resin. The method also includes, for each candidate resin, predicting a respective value of a performance indicator for the column chromatography purification process by applying the respective set of resin attribute values, and possibly other parameter values (e.g., harvest filtrate and/or purification process parameters) as inputs to a multivariate statistical model. The method further includes selecting a resin of the one or more candidate resins based at least in part on the predicted respective value(s) of the performance indicator, and performing the column chromatography purification process using the selected resin as a stationary phase.

公开(公告)号：WO2021262955A1

公开(公告)日：2021-12-30

申请号：PCT/US2021/038856

申请日：2021-06-24

Applicant: EDGEWELL PERSONAL CARE BRANDS, LLC

Inventor： BLATTER, Alan ,  CHASEN, James ,  SWEENEY, Gregory ,  GRIFFIN, Avery

IPC: G16C20/30 ,  B26B21/00 ,  G06N20/00 ,  G16H40/60

Abstract: Systems, devices, and methods for applying machine learning to provide feedback related to a personal care device are described. Embodiments of the systems, devices, and methods may identify data from a device such as a razor comprising a plurality of sensors on a razor, predict one or more features such as shaving features based on the data using a machine learning model trained using data from the plurality of sensors, and provide shaving feedback based on the one or more features such as shaving features. Embodiments of the systems, devices, and methods may train a machine learning model, execute a trained machine learning model, capture and/or process data for the machine learning model, provide feedback based on the output of the trained machine learning model, or combinations thereof.