-
公开(公告)号：US20200243166A1
公开(公告)日：2020-07-30
申请号：US16850838
申请日：2020-04-16
Applicant: FUJIFILM Corporation
Inventor： Kyosuke TSUMURA , Shino OHIRA , Jun NAKABAYASHI , Mizuki TAKEI
Abstract: Provided are a feature quantity calculating method, a feature quantity calculating program, and a feature quantity calculating device which enable calculation of a feature quantity accurately showing chemical properties of a target structure, a screening method, a screening program, and a screening device which enable efficient screening of a pharmaceutical candidate compound using a feature quantity, and a compound creating method, a compound creating program, and a compound creating device which enable efficient creation of a three-dimensional structure of a pharmaceutical candidate compound using a feature quantity. Since the chemical properties of the target structures are exhibited as the result of an interaction between the target structure and a probe in the periphery thereof, the fact that the degree of accumulation (feature quantity) of probes is similar between target structures indicates that the chemical properties of the target structures are similar. Therefore, the feature quantity accurately showing the chemical properties of the target structure can be calculated using the feature quantity calculating method according to one aspect of the present invention.
-
52.发明授权公开(公告)号：US10726946B2
公开(公告)日：2020-07-28
申请号：US15683678
申请日：2017-08-22
Applicant: Schrödinger, Inc.
Inventor： Lingle Wang , Yuqing Deng , Yujie Wu , Byungchan Kim , Robert L. Abel
Abstract: A method for computing free energy difference between a reference molecule and a target molecule. The target molecule has the common set of atoms PAB and a set of atoms PB. The method includes applying a potential to restrain an interaction of the additional atomic component from the set of atoms PB with the common set of atoms PAB in the initial state. The method includes determining one or more transition states along a transformation path between the initial state and target state. The method includes scaling the restrain potential correspondingly along the transformation path until the potential becomes zero when a corresponding end state is reached, and calculating the free energy difference between the reference molecule and the target molecule using a value obtained along the transformation path from the initial state to the target state.
-
53.发明申请公开(公告)号：US20200234799A1
公开(公告)日：2020-07-23
申请号：US16745970
申请日：2020-01-17
Applicant: Tata Consultancy Services Limited
Inventor： Hemalatha Jayabal , Nitu Verma , Paramveer Sharma , Kishore Gajula , Naga Neehar Dingari , Yogesh Kailas Badhe , Rakesh Gupta , Beena Rai
Abstract: There is a lack of knowledge about bridging the gap between the length and time scales of multiple phenomena related to transport across skin layers and structural changes in skin proteins (collagen, elastin, etc.). The embodiments herein provide a method and system for insilico design and testing of formulations using a physiochemical skin model, which provides a technical solution of integrating expertise in molecular modelling and macroscopic modelling techniques to provide a complete solution for formulation design. The present disclosure integrates phenomena's happening at different length and time scales using molecular, microscopic and macroscopic modelling techniques. The present subject matter incorporates expertise in diverse modelling techniques such as molecular modelling and macroscopic modelling and knowledge about bio-molecular systems and mechanical characterization of materials.
-
公开(公告)号：US20200064334A1
公开(公告)日：2020-02-27
申请号：US16555486
申请日：2019-08-29
Applicant: Purdue Research Foundation
IPC: G01N33/50 , G01N33/574 , A61K31/497 , G16C20/60 , G16C20/50 , G16B15/30
Abstract: An in silico screening method generated compounds that are against laminin receptor 37LR and their anti-cancer functions in prostate cancer cell lines are disclosed herein. A group of derivatives based on the hit compound from the in silico screening are synthesized and tested with improved IC50 value that can have relevant clinical use for prostate cancer or osteoarthritis.
-
55.发明申请公开(公告)号：US20200051661A1
公开(公告)日：2020-02-13
申请号：US16342913
申请日：2017-10-12
Inventor： Haiquan LI , Ikbel ACHOUR , Joanne BERGHOUT , Yves A. LUSSIER
Abstract: Functionally altered biological mechanisms arising from disease-associated polymorphisms remain difficult to characterize when those variants are intergenic, or, fall between genes. The present invention uses computational modelling of single-nucleotide polymorphisms (SNPs) drawn from genome-wide association studies (GWAS) or other databases to identify SNP pairs, including SNP pairs where at least one SNP is outside a protein-coding region of a gene, having convergent biological mechanisms. Additional databases, including genomic databases, biological regulatory databases, and databases related to molecular function, are used to further identify and validate the similarity of the biological mechanisms of the SNP pairs. Prioritized SNP pairs having increased similarity of biological mechanisms are then used to identify disease mechanisms, candidate therapeutic drugs, and candidate therapeutic targets among downstream effectors of intergenic SNPs.
-
Patent Agency Ranking
公开(公告)号：US20250045843A1
公开(公告)日：2025-02-06
申请号：US18718463
申请日：2022-12-16
Applicant: BASF SE
Inventor： Oliver SALA , Rebecca SURE , Miriam MATHEA
Abstract: In order to provide a more reliable process for target temporal odour producing fragrance products, a computer-implemented method (100) is provided for generating a recipe profile of a fragrance product having a target temporal odour profile, wherein the fragrance product comprises a fragrance composition with one or a plurality of fragrance ingredient(s), the computer-implemente d method comprising the steps of: a) providing (110) the target temporal odour profile, wherein the target temporal odour profile comprises a time-dependent fractural amount of a plurality of odour families over a predetermined period of time, which is indicative of a desired evaporation behaviour of each odour family in the fragrance composition; b) providing (120), for each odour family, one or more fragrance ingredients having olfactive contributions matching the respective odour family; c) selecting (130) at least one ingredient from each odour family to form one or more recipes of the fragrance product, wherein each recipe comprises fragrance composition data associated with the fragrance ingredients of the recipe; d) determining (140) a temporal odour profile for each recipe; e) determining (150) a distance of each determined temporal odour profile of the one or more recipes to the target temporal odour profile of the fragrance product; f) selecting (160) at least one recipe from the one or more recipes that has a distance satisfying a predefined criterion; and g) providing (170) a recipe profile of the at least one selected recipe preferably usable for production of the fragrance product.
-
57.发明申请公开(公告)号：US20250037805A1
公开(公告)日：2025-01-30
申请号：US18752455
申请日：2024-06-24
Applicant: Tata Consultancy Services Limited
Inventor： SOWMYA RAMASWAMY KRISHNAN , ARIJIT ROY , NAVNEET BUNG , RAJGOPAL SRINIVASAN
IPC: G16C20/50
Abstract: Deep learning-based generative models have improved the exploration of chemical space in small molecule drug discovery. Although thousands of novel small molecules can be generated with such models, synthesizing them still remains a challenging task. In literature, several methods have been proposed to predict the synthetic route of a target molecule by working backwards to find the most suitable starting reactants (retrosynthesis). While retrosynthesis is shown to be successful, for novel molecules it is often difficult to find the synthesis path. System and method of the present disclosure generate molecules along with its synthesis route and also provide an insight into the interactions in the active site of target protein, using graph convolution networks (GCNs) and Monte Carlo tree search (MCTS). A target-specific bioactivity prediction model is used as the scoring function to navigate the MCTS search space efficiently.
-
公开(公告)号：US20250037791A1
公开(公告)日：2025-01-30
申请号：US18751664
申请日：2024-06-24
Applicant: Kumarpal A. SHAH
Inventor： Kumarpal A. SHAH
Abstract: Solutions for prophylaxis, immune therapy and vaccine strategies for triple negative breast cancer. The immune pathogenesis of cancer and its tumor micro environment (TME) is defined in terms of SNS concept that contributes to cancer drug resistance and metastasis. In one embodiment a method for identifying candidate drug compounds for treating cancer is provided by training an artificial intelligence engine for simulating Self-Non Self (SNS) modeling of normal subjects. An analysis module of an artificial intelligence engine is generated which directs the simulated SNS modeling to specific cancer to redefine cancer immune pathogenesis. SNS mimicking compounds are identified with the analysis module to target immune pathogenesis of cancer. The analysis module is applied to screen candidate cancer drugs that can be combined strategically with SNS mimicking compound for cancer therapy.
-
公开(公告)号：US20250014688A1
公开(公告)日：2025-01-09
申请号：US18890687
申请日：2024-09-19
Applicant: Good Chemistry Inc.
Inventor： Kevin RYCZKO , Amit KADAN , Takeshi YAMAZAKI
Abstract: A method for machine learning aided modeling of two interacting structures may include: (a) receiving an input structure comprising an interaction region; (b) generating a plurality of candidate structures using a first differentiable machine learning model; (c) docking one or more candidate structures of the plurality of candidate structures at the interaction region of the input structure using a second differentiable machine learning model to predict a docking geometry; (d) ranking the one or more candidate structures of the plurality of candidate structures docked in (c) using a third differentiable machine learning model to predict a score; and (e) backpropagating the score to (i) the first differentiable machine learning model to update the plurality of candidate structures or (ii) the second differentiable machine learning model to update the docking geometry.
-
公开(公告)号：US20240395367A1
公开(公告)日：2024-11-28
申请号：US18694101
申请日：2022-09-20
Applicant: Lemon Inc.
Inventor： Yuwei YANG , Siqi OUYANG , Hao ZHOU , Lei LI , Hang LI
Abstract: According to the embodiments of the disclosure, a method, apparatus, device, storage media, and program products for designing ligand molecules is provided. The methods described herein include: editing a first molecular structure with an editing model to determine a second molecular structure, the editing at least comprising deleting a fragment from the first molecular structure or adding a fragment to the first molecular structure; in response to determining that an evaluation of the second molecular structure is better than the first molecular structure, training the editing model based on the editing, the evaluation at least indicating binding capacity between the second molecular structure and a target molecule; and determining a target structure of the ligand molecule for the target molecule with the trained editing model and based on the second molecular structure.
-
-
-
-
-
-
-
-
-
Search Results
328
records
(took 0.014 seconds)
