-
公开(公告)号：WO2023090627A1
公开(公告)日：2023-05-25
申请号：PCT/KR2022/014509
申请日：2022-09-28
Applicant: 주식회사 제이엘케이바이오
Abstract: 본 개시 내용은 화합물 최적화를 위한 및 방법을 제공한다. 상기 방법은, 화합물 데이터에 대한 레이턴트 벡터의 검색 범위를 선택하는 단계; 상기 선택된 검색 범위를 복수개의 격자 범위들로 분할하는 단계; 각각의 격자 범위에 대한 화합물 최적화를 수행하는 단계; 및 각각의 격자 범위에 대하여 산출된 최적화 결과물을 연결하여 최종 화합물 데이터를 제공하는 단계를 포함할 수 있다. 본 개시 내용에 따르면, 다양한 물리-화학적 특성들을 동시에 최적화할 수 있으며 최적화하려는 항목을 상황에 맞게 변화시킬 수 있는 화합물 최적화 모델을 구현할 수 있다.
-
公开(公告)号：WO2023068406A1
公开(公告)日：2023-04-27
申请号：PCT/KR2021/014892
申请日：2021-10-22
Applicant: 경상국립대학교병원
Abstract: 본 발명은 골다공증 발병 예측을 위한 정보제공방법 및 골다공증 발병 예측용 조성물에 관한 것으로, 비타민 D 결합 단백질의 발현 수준을 측정하여 골다공증의 발병 가능성을 정확하고 간단하게 예측할 수 있어 골다공증의 발병을 예방할 수 있다.
-
公开(公告)号：WO2023058576A1
公开(公告)日：2023-04-13
申请号：PCT/JP2022/036775
申请日：2022-09-30
Applicant: ダイキン工業株式会社
Inventor： 太刀川 祥平
IPC: G16C20/30
Abstract: 所望の物性を有する可能性の高い低分子化合物を探索する。コンピュータが実行する方法であって、複数の低分子化合物の化学構造を取得するステップと、回帰モデルを用いて、前記取得された各低分子化合物の化学構造から、前記各低分子化合物の物性値の推定値および前記推定値のばらつきを算出するステップと、前記物性値の推定値および前記推定値のばらつきから、獲得関数を算出するステップと、を含む。
-
公开(公告)号：WO2023030563A1
公开(公告)日：2023-03-09
申请号：PCT/CZ2022/050084
申请日：2022-09-01
Applicant: FYZIKALNI USTAV AV CR, V.V.I.
Inventor： PALATINUS, Lukas , BRAZDA, Petr , KLAR, Paul
IPC: G16C20/30 , G01N23/20058 , G16C20/20
Abstract: The present invention relates to a method for determining the crystal structure of a crystal (4) capable of electron diffraction. The method includes the steps of obtaining a three-dimensional electron diffraction pattern and processing data from the electron diffraction pattern. The essence of the invention is that the method of determination consists in creating virtual diffraction frames containing a list of integrated scattered electron intensities. Subsequently, the dynamical diffraction theory is used in the data processing step. In another embodiment, the invention provides an apparatus capable of performing this method.
-
公开(公告)号：WO2023014007A1
公开(公告)日：2023-02-09
申请号：PCT/KR2022/011269
申请日：2022-08-01
Applicant: 주식회사 제이엘케이바이오
Abstract: 본 개시 내용은 화합물 정보 추출을 위한 장치 및 방법을 제공한다. 상기 방법은, 인코더 계층 및 디코딩 계층으로의 입력을 위해 설정된 차원으로 입력 화합물 데이터를 처리하는 단계; 상기 인코더 계층에서 어텐션 방식으로 상기 입력 화합물 데이터를 학습시키는 단계; 정보 보틀넥 계층에서 상기 학습된 화합물 데이터에 기초하여 레이턴트 차원을 가지는 평균 벡터 및 분산 벡터를 획득하는 단계; 재파라미터화를 통해 상기 평균 벡터 및 상기 분산 벡터에 따른 정규분포로부터 레이턴트 벡터를 추출하는 단계; 화합물 특성 예측 계층에서 상기 평균 벡터에 기초하여 화합물의 물리-화학적 특성을 예측하는 단계; 길이 예측 계층에서 상기 평균 벡터에 기초하여 화합물 시퀀스의 길이를 예측하는 단계; 정보 확장 계층에서 상기 레이턴트 벡터를 상기 디코딩 계층으로의 입력을 위해 설정된 차원을 갖는 인코더-출력 화합물 데이터로 변환하는 단계; 상기 디코더 계층에서 어텐션 방식으로 상기 인코더-출력 화합물 데이터를 이용하여 상기 입력 화합물 데이터를 학습시키는 단계; 및 생성 계층에서 상기 디코더 계층에서 학습된 화합물 데이터로부터 화합물 데이터를 재구성하는 단계를 포함할 수 있다. 본 개시 내용에 따르면, 여러가지 목적의 화합물 예측 모델들에서 공통적으로 사용될 수 있는 화합물 정보들을 추출할 수 있는 화합물 정보 추출 모델을 제공할 수 있다.
-
Patent Agency Ranking
公开(公告)号：WO2023274850A1
公开(公告)日：2023-01-05
申请号：PCT/EP2022/067251
申请日：2022-06-23
Applicant: BASF SE
Inventor： SALA, Oliver , GARLICHS, Florian , MATHEA, Miriam , SURE, Rebecca
Abstract: The present invention relates to a computer-implemented for quality assessment of aroma molecules using single-molecule olfactory predictions comprising (i) receiving input data, preferably via an input unit (10), of at least one set of odorant descriptions (A) obtained by olfactory prediction of an aroma molecule and a second set of odorant descriptions (B) obtained by human olfactory evaluation (ii) comparing the received set of odorant descriptions (A) obtained by olfactory prediction of the aroma molecule to the second set of odorant descriptions (B) obtained by olfactory prediction of the same aroma molecule (iii) determining quality of aroma molecule based on the discrepancy between the at least one set of odorant descriptions (A) obtained by olfactory prediction of the aroma molecule and the second set of odorant descriptions (B) obtained by human olfactory evaluation via a processing unit (20) (iv) providing, preferably via an output unit (30), quality assessment results of the aroma molecule.
-
7.发明申请
公开(公告)号：WO2022259185A1
公开(公告)日：2022-12-15
申请号：PCT/IB2022/055350
申请日：2022-06-08
Applicant: INSILICO MEDICINE IP LIMITED
Inventor： KUZNETSOV, Maksim , RYABOV, Fedor , POLYKOVSKIY, Daniil , KADURIN, Artur , ZAVORONKOVS, Aleksandrs
IPC: G16C20/30
Abstract: A computer-implemented method for a generative adversarial approach for conformational space modeling of molecules is provided. The method can include obtaining molecule graph data for a molecule and inputting the molecule graph data into a machine learning platform. The machine learning platform can include architecture of a molecular graph generator, conformation discriminator, stochastic encoder, and latent variables discriminator. The method can include generating a plurality of conformations for the molecule with the machine learning platform. The plurality of conformations are specific to the molecule. Each conformation can have internal coordinates defining positions of atoms of the molecule. At least one conformation for the molecule can be selected based on at least one parameter related to molecular conformations. A report can be prepared that includes the selected at least one conformation for the molecule.
-
8.发明申请
公开(公告)号：WO2022245543A1
公开(公告)日：2022-11-24
申请号：PCT/US2022/027629
申请日：2022-05-04
Applicant: GOOGLE LLC
Inventor： WILTSCHKO, Alexander
Abstract: Electronic chemical sensors can output raw electrical signal data in response to sensing a chemical compound, but the raw electrical signal data can be difficult to interpret. Processing the electrical signal data with a machine-learned model to generate an embedding output in an embedding space can provide a better understanding of the electrical signal data. Moreover, leveraging preexisting chemical property prediction models to generate other embeddings in the embedding space can allow for more accurate and efficient classification tasks of the electrical signal data.
-
公开(公告)号：WO2022224245A1
公开(公告)日：2022-10-27
申请号：PCT/IL2022/050393
申请日：2022-04-14
Applicant: TALIAZ LTD.
Inventor： TALIAZ, Dekel
Abstract: There is provided herein a method for early detection of a psychotherapeutic treatment response for a subject in need thereof, the method including obtaining data associated with a level of severity of a mental health of the subject four weeks or less after initiation of the psychotherapeutic treatment, calculating a post-initiation score associated with the subject's mental health based on the obtained data, and classifying the subject as responsive or non-responsive to the specified psychotherapeutic treatment based, at least in part, on a comparison of the post-initiation score to a score associated with the mental health of comparable subjects that have received the specified psychotherapeutic treatment.
-
公开(公告)号：WO2022164688A1
公开(公告)日：2022-08-04
申请号：PCT/US2022/012888
申请日：2022-01-19
Applicant: CITRINE INFORMATICS, INC.
Inventor： SEVGEN, Selami, Emre , FOLIE, Brendan, David , LING, Julia, Black
Abstract: A device receives an ingredient list having a sequence of ingredients ordered by relative amount, and generates formulation vectors by sampling the ingredients list. The device inputs the plurality of formulation vectors into a machine-learned model, the machine-learned model generating an encoded version of each of the plurality of formulation vectors using an encoder, and then outputting a plurality of reconstructed formulation vectors as derived using a decoder. The device identifies reconstructed formulation vectors that have an order that matches the sequence, defines a latent space using the encoded version of the matching reconstructed formulation vectors. The device iteratively samples the latent space until a threshold number of samples are derived that match an ordering constraint that corresponds to the sequence, performs a statistical aggregation of the samples, and outputs an indication of an absolute amount of each ingredient in the ingredients list.
-
-
-
-
-
-
-
-
-
Search Results
203
records
(took 0.021 seconds)
