公开(公告)号：WO2022136180A1

公开(公告)日：2022-06-30

申请号：PCT/EP2021/086591

申请日：2021-12-17

Applicant: FIRMENICH SA

Inventor： GODIN, Guillaume ,  VAN DEURSEN, Ruud ,  NOUCHI, Vincent ,  CAPELA, Fabio André ,  RAMET, Gaétan ,  CALVAYRAC, Thibault ,  CHICHESTER, Christine

IPC: G16C60/00 ,  G16C20/30 ,  G16C20/70 ,  G06N3/04

Abstract: The computer-implemented method (100) for training an autoencoder neural network or generative adversarial network device to generate indeterministic and realistic digital representations of new fragrance or flavor ingredient compositions to be compounded, comprises the steps of: - providing (105) an original set of exemplar fragrance or flavor composition digital identifiers, said exemplar fragrance or flavor composition digital identifiers being representative of materialized fragrance or flavor compositions comprising at least two distinct ingredients and - training (110) an autoencoder device or generative adversarial network device using the original set of exemplar fragrance or flavor composition digital identifiers to generate a fragrance or flavor composition generative model trained to generate new fragrance or flavor ingredient compositions, comprising at least two distinct ingredients, to be compounded. The trained autoencoder device or generative adversarial network device can be used to generate new fragrance or flavor ingredient compositions.

公开(公告)号：WO2022124725A1

公开(公告)日：2022-06-16

申请号：PCT/KR2021/018331

申请日：2021-12-06

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

Inventor： 최진우 CHOI, Jin Woo ,  김이랑 KIM, Yi Rang

IPC: G16C20/70 ,  G16C20/30 ,  G16B30/10 ,  G16B40/00 ,  G06N20/00 ,  G06N3/08

Abstract: 화합물과 단백질의 상호작용 예측 방법, 장치 및 컴퓨터 프로그램이 제공된다. 본 개시의 몇몇 실시예들에 따른 화합물과 단백질의 상호작용 예측 방법은, 학습용 화합물 데이터, 학습용 단백질 데이터 및 상호작용 점수로 구성된 학습데이터를 획득하는 단계, 획득된 학습데이터를 이용하여 딥러닝 모델을 구축하는 단계 및 구축된 딥러닝 모델을 통해 주어진 화합물과 단백질의 상호작용을 예측하는 단계를 포함할 수 있다. 이때, 학습용 단백질의 아미노산 서열에서 상호작용에 부정적인 영향을 미치는 단백질 도메인과 연관된 아미노산 서열을 제외하고 딥러닝 모델을 학습시킴으로써, 생체 내 환경 내에서 주어진 화합물과 단백질의 상호작용이 정확하게 예측될 수 있다.

公开(公告)号：WO2022108012A1

公开(公告)日：2022-05-27

申请号：PCT/KR2021/005661

申请日：2021-05-06

Applicant: 주식회사 에이아이트릭스

Inventor： 류성옥 ,  황도영

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

Abstract: 독성예측 장치 및 독성예측 방법을 제시하며, 일 실시예에 따르면, 독성예측 장치로서, 분석대상 화합물의 독성을 예측하기 위한 프로그램이 저장되는 저장부, 및 상기 프로그램을 실행함으로써 분석대상 화합물의 독성을 예측하는 제어부를 포함하며, 상기 제어부는, 분석대상 화합물의 분자구조를 이루는 원자를 노드, 화학결합을 엣지로 표현하는 그래프로 변형하는 전처리를 수행하고 상기 그래프 및 인공 신경망을 이용하여 상기 분석대상 화합물의 독성을 예측할 수 있다.

公开(公告)号：WO2022083539A1

公开(公告)日：2022-04-28

申请号：PCT/CN2021/124370

申请日：2021-10-18

Applicant: NOVOZYMES A/S ,  AN, Jun

Inventor： CHRISTIANSEN, Liv Spaangner

IPC: G16C60/00 ,  G16C20/30

Abstract: A computer-implemented method for performance evaluation of a detergent composition is disclosed, the method comprising obtaining one or more wash conditions including a first wash condition; obtaining ingredient data comprising first ingredient data and second ingredient data, the first ingredient data associated with one or more first ingredients including a first primary ingredient and the second ingredient data associated with one or more second ingredients including a second primary ingredient; determining a first detergent composition based on the ingredient data; determining a first performance of the first detergent composition; and outputting a first performance representation of the first performance.

公开(公告)号：WO2022076835A1

公开(公告)日：2022-04-14

申请号：PCT/US2021/054195

申请日：2021-10-08

Applicant: DYAX CORP. ,  NGUYEN, Hoa, Q.

Inventor： NGUYEN, Hoa, Q.

IPC: G16B15/30 ,  G16C20/30

Abstract: Aspects of the present application provide for methods and apparatuses for simulating interactions between von Willebrand factors and AD AMTS 13 in endogenous or recombinant form. Some aspects provide for a computer-implemented method for modeling ADAMTS13 and VWF interactions, comprising obtaining a quantitative systems pharmacology (QSP) model representing AD AMTS 13 and VWF interactions including a mechanism by which ADAMTS13 cleaves ultra-large VWF (ULVWF) multimers and inhibition thereof by extracellular hemoglobin; determining disease predictive descriptors, assigning the disease predictive descriptors to a virtual patient population, and processing the virtual patient population using the QSP model to provide processed data, wherein the processed data comprises a concentration of at least one biomarker. The biomarker may include ULVWF multimers, cleaved VWF fragments, lactate dehydrogenase and/or platelet cells. The QSP model may represent AD AMTS 13 interactions with stretched and globular VWF multimers. The QSP model may simulate a conversion of stretched VWF multimers to globular VWF multimers.

公开(公告)号：WO2022055944A1

公开(公告)日：2022-03-17

申请号：PCT/US2021/049385

申请日：2021-09-08

Applicant: OMS INVESTMENTS, INC.

Inventor： LEWANDOWSKI, Tera Emilie ,  CASTORANO, Nicholas Joseph ,  D'ANGELO, Daisy Louise ,  RYGIELSKI, Kimberly Ann

IPC: A01B79/02 ,  G16C20/30

Abstract: A method of determining whether a treatment substance is effective for treating a growing media containing persistent herbicides is provided. The method may include determining two or more characteristics of the treatment substance and predicting a mitigation ability of the treatment substance to mitigate phytotoxicity caused by the persistent herbicides present in the growing media based on the two or more characteristics of the treatment substance.

公开(公告)号：WO2022013781A1

公开(公告)日：2022-01-20

申请号：PCT/IB2021/056355

申请日：2021-07-14

Applicant: UNIVERSITY OF SOUTHERN CALIFORNIA

Inventor： BOGDAN, Paul ,  NAZARIAN, Shahin ,  YANG, Zikun

IPC: A61K39/215 ,  A61P31/14 ,  C07K14/005 ,  G16B15/00 ,  G16C20/30 ,  G16B40/20 ,  G16B30/10

Abstract: Computer systems and computer implemented methods are presented for designing and making vaccines to pathogens, particular viral pathogens. Vaccine compositions for COVID-19 are also disclosed, as well as method of using the same.

公开(公告)号：WO2021249329A1

公开(公告)日：2021-12-16

申请号：PCT/CN2021/098570

申请日：2021-06-07

Applicant: 中国石油天然气股份有限公司

Inventor： 王杭州 ,  纪晔 ,  刘一心 ,  孙宝文 ,  石振民

IPC: G16C10/00 ,  G16C20/10 ,  G16C20/20 ,  G16C20/30 ,  G16C20/70 ,  G16C20/90

Abstract: 本发明涉及一种分子级装置的实时优化方法、装置、系统及存储介质。该方法包括：确定石油加工原料的原料分子组成；将原料分子组成输入预先训练的产物预测模型，以得到相应的预测产物的预测分子组成和每种单分子的预测分子含量；获取预先设置的目标产物的预设标准集合；根据预测分子组成和每种单分子的预测分子含量，判断预测产物是否符合预设标准集合中与预测产物对应的目标产物的预设标准；如不符合对应的目标产物的任一预设标准，则调整产物预测模型中的操作参数，以重新获取预测产物预测分子组成和每种单分子预测分子含量，直至符合预设标准。本发明实现了分子级装置从原料到产品加工过程的分子级整体模拟及实时优化，提高了精度和生产效益。

公开(公告)号：WO2021202584A1

公开(公告)日：2021-10-07

申请号：PCT/US2021/024963

申请日：2021-03-30

Applicant: THE REGENTS OF THE UNIVERSITY OF CALIFORNIA

Inventor： KAAZEMPUR-MOFRAD, Mohammad R. ,  SOHEILYPOUR, Mohammad

IPC: G16B5/00 ,  G16B40/20 ,  G16B15/30 ,  G16C20/30 ,  G16C20/70 ,  G06N3/08

Abstract: Methods and systems are provided for simulating metabolic interactions between a microbiome and a chemical compound. In one embodiment, a method includes predicting, with a trained deep neural network, a plurality of enzymes potentially responsible for metabolism of a chemical compound, generating a three-dimensional individual-specific model of a microbiome including one or more microorganisms associated with the plurality of enzymes, and simulating, with the three-dimensional individual-specific model, metabolism of the chemical compound in the microbiome over time. In this way, the individual-specific metabolism of chemical compounds, such as drug compounds, in microbiomes, such as human gut microbiomes, may be reliably predicted in a high-throughput fashion while accounting for three-dimensional compound structure.

公开(公告)号：WO2021141535A1

公开(公告)日：2021-07-15

申请号：PCT/SG2021/050004

申请日：2021-01-07

Applicant: WILMAR INTERNATIONAL LIMITED ,  WILMAR (SHANGHAI) BIOTECHNOLOGY RESEARCH & DEVELOPMENT CENTER CO., LTD.

Inventor： LIM, Junliang Kevin ,  LIANG, Junmei ,  JIANG, Yuanrong

IPC: G01N33/03 ,  G06N3/12 ,  G16C20/30 ,  G16C20/70 ,  A23D7/00 ,  A23D9/00 ,  G06N3/02 ,  G06N20/00

Abstract: According to embodiments of the present invention, a method for optimizing a blending formulation of an edible oil sample is provided. The method includes receiving a dataset of values representing at least one type of index obtained from a plurality of pure oils and/or oil blends; and generating a prediction of the optimized blending formulation from the received dataset of values. The step of generating the prediction of the optimized blending formulation includes using a predictive model configured to generate a plurality of blending formulations based on the received dataset of values, evaluate at least one index value of each blending formulation and compare the evaluated at least one index value with at least one predefined threshold value to determine the optimized blending formulation. According to further embodiments, a system for optimizing a blending formulation is also provided.