-
公开(公告)号：US12125260B2
公开(公告)日：2024-10-22
申请号：US18355963
申请日：2023-07-20
申请人： 10X Genomics, Inc.
发明人： Jeffrey Clark Mellen , Jasper Staab , Kevin J. Wu , Neil Ira Weisenfeld , Florian Baumgartner , Brynn Claypoole
IPC分类号： G06V10/762 , G01N1/30 , G06T7/00 , G16B15/00
CPC分类号： G06V10/762 , G01N1/30 , G06T7/0012 , G16B15/00 , G01N2001/302 , G06T2207/30024
摘要： A discrete attribute value dataset is obtained that is associated with a plurality of probe spots each assigned a different probe spot barcode. The dataset comprises spatial projections, each comprising images of a biological sample. Each image includes a corresponding plurality of discrete attribute values for the probe spots. Each such value is associated with a probe spot in the plurality of probes spots based on the probe spot barcodes. The dataset is clustered using the discrete attribute values, or dimension reduction components thereof, for a plurality of loci at each respective probe spot across the images of the projections thereby assigning each probe spot to a cluster in a plurality of clusters. Morphological patterns are identified from the spatial arrangement of the probe spots in the various clusters.
-
公开(公告)号：US20240321389A1
公开(公告)日：2024-09-26
申请号：US18605798
申请日：2024-03-14
申请人： GRAIL, LLC
摘要： A processing system uses a Bayesian inference based model for targeted sequencing or variant calling. In an embodiment, the processing system generates candidate variants of a cell free nucleic acid sample. The processing system determines likelihoods of true alternate frequencies for each of the candidate variants in the cell free nucleic acid sample and in a corresponding genomic nucleic acid sample. The processing system filters or scores the candidate variants by the model using at least the likelihoods of true alternate frequencies. The processing system outputs the filtered candidate variants, which may be used to generate features for a predictive cancer or disease model.
-
公开(公告)号：US12040050B1
公开(公告)日：2024-07-16
申请号：US16812111
申请日：2020-03-06
申请人： Grigory Khimulya , Ethan Alley , Surojit Biswas
发明人： Grigory Khimulya , Ethan Alley , Surojit Biswas
IPC分类号： G06N3/08 , G06N3/0442 , G06N3/045 , G06N3/084 , G06N3/088 , G16B15/00 , G16B20/00 , G16B30/00 , G16B35/00 , G16B25/10 , G16B50/00
CPC分类号： G16B30/00 , G06N3/0442 , G06N3/045 , G06N3/084 , G06N3/088 , G16B15/00 , G16B20/00 , G16B35/00 , G16B25/10 , G16B50/00
摘要： A dataset describing a collection of proteins is loaded, which identifies, for each protein, a respective value of a characteristic of interest. The dataset is provided as one or more inputs to a trained unsupervised representation model to cause the trained unsupervised representation model to generate a representation for each protein in the collection. The representation for each protein is input into a supervised top model to train the supervised top model to obtain a predicted characteristic and the trained supervised top model is used to obtain a predicted characteristic for a particular protein.
-
公开(公告)号：US12002551B2
公开(公告)日：2024-06-04
申请号：US16816306
申请日：2020-03-12
申请人： Nanjing University
发明人： Hongling Liu , Laihao Shi
摘要： The present invention discloses a method of constructing a pharmacophore to determine whether a molecule is a peroxisome proliferator-activated receptor γ full agonist, partial agonist or antagonist in terms of a binding energy or a free energy surface comprising: providing a protein receptor mimicking said peroxisome proliferator-activated receptor γ and a corresponding ligand; docking the corresponding ligand and the protein receptor to form a docked conformation; performing at least two rounds of molecular dynamic simulation to obtain at least one trajectory and at least one free energy surface; inputting the trajectory to construct at least one pharmacophore and obtaining the binding energy of the corresponding ligand; comparing the molecule with the corresponding ligand in terms of the binding energy thereof to the protein receptor in order to determine whether the molecule is the peroxisome proliferator-activated receptor γ full agonist, partial agonist or antagonist.
-
公开(公告)号：US11982679B2
公开(公告)日：2024-05-14
申请号：US16464197
申请日：2017-11-27
发明人： Salvatore Guglielmino , Laura Maria De Plano , Santina Carnazza , Domenico Franco , Alessandra Nicoletti , Mario Zappia , Sabrina Conoci , Salvatore Petralia
CPC分类号： G01N33/6896 , C07K7/08 , C12N15/1037 , G16B15/00 , G16B45/00 , G01N2333/4709 , G01N2800/2821
摘要： The present invention relates to a method for obtaining protein mimotopes occurring in at least two distinct 3D conformations. In a further embodiment, a method for detecting antibodies with diagnostic relevance using said mimotopes is claimed. In a preferred embodiment, said methods are applied to Alzheimer's disease.
-
公开(公告)号：US20240145040A1
公开(公告)日：2024-05-02
申请号：US18496650
申请日：2023-10-27
申请人： Hyperspectral Corp.
发明人： Euan F. Mowat , Matthew Theurer , Zachary Shaffer
摘要： An example method comprising: receiving a first set of intensity values based on a first set of intensity measurements for a set of wavelengths, the set of intensity measurements obtained by an apparatus configured to generate light and another light, detect the light that has passed through a portion of a sample, and measure intensity of the light by optical sensor, an angle separating the optical sensor and apparatus; applying a trained model to obtain a result; based on the result, determining a subset of wavelengths; receiving another set of intensity values, another set of intensity values being based on another set of intensity measurements for the set of wavelengths, the other set of intensity measurements obtained by the other light, detect the other light that has passed through another portion of the sample, and measure intensity by the optical sensor, another angle separating the optical sensor and the apparatus, the angles being different, applying another trained model to obtain another result, trained models being different from each other; applying the results to a trained multi-model to determine a positive or a negative pathogen detection for the pathogen in the sample, generating a notification and providing the notification.
-
公开(公告)号：US11961589B2
公开(公告)日：2024-04-16
申请号：US16201912
申请日：2018-11-27
申请人： GRAIL, Inc.
CPC分类号： G16B20/20 , C12Q1/6869 , G06F17/10 , G16B5/20 , G16B15/00 , G16B30/10 , G16B40/00 , C12Q1/6869 , C12Q2537/165
摘要： A processing system uses a Bayesian inference based model for targeted sequencing or variant calling. In an embodiment, the processing system generates candidate variants of a cell free nucleic acid sample. The processing system determines likelihoods of true alternate frequencies for each of the candidate variants in the cell free nucleic acid sample and in a corresponding genomic nucleic acid sample. The processing system filters or scores the candidate variants by the model using at least the likelihoods of true alternate frequencies. The processing system outputs the filtered candidate variants, which may be used to generate features for a predictive cancer or disease model.
-
公开(公告)号：US11929152B1
公开(公告)日：2024-03-12
申请号：US16896877
申请日：2020-06-09
发明人： Alexander Sewall Ford , Zachary Wu , Layne Christopher Price , Franziska Seeger , Yen Ling Adelene Sim
摘要： Techniques for predicting a pair of an enzyme primary sequence and a substrate, and interaction probability for the pair are described. An exemplary method includes receiving a request to predict a pair of an enzyme primary sequence and a substrate, and interaction probability for the pair; combining an enzyme vector, a substrate vector, and an interaction indication for the enzyme and substrate to form a machine learning model input; applying a machine learning model to the machine learning model input to predict the pair of an enzyme primary sequence and a substrate, and interaction probability for the pair; and outputting a result of the application of the machine learning model including the predicted pair of an enzyme primary sequence and a substrate, and interaction probability for the pair.
-
公开(公告)号：US20240071563A1
公开(公告)日：2024-02-29
申请号：US18471597
申请日：2023-09-21
发明人： Renqiang Min , Hans Peter Graf , Ziqi Chen
摘要： A method for generating binding peptides presented by any given Major Histocompatibility Complex (MHC) protein is presented. The method includes, given a peptide and an MHC protein pair, enabling a Reinforcement Learning (RL) agent to interact with and exploit a peptide mutation environment by repeatedly mutating the peptide and observing an observation score of the peptide, learning to form a mutation policy, via a mutation policy network, to iteratively mutate amino acids of the peptide to obtain desired presentation scores, and generating, based on the desired presentation scores, qualified peptides and binding motifs of MHC Class I proteins.
-
公开(公告)号：US11767555B2
公开(公告)日：2023-09-26
申请号：US17512581
申请日：2021-10-27
发明人： Amirali Talasaz , Helmy Eltoukhy
IPC分类号： C12Q1/68 , C12Q1/6869 , C12Q1/6886 , G16B15/00
CPC分类号： C12Q1/6869 , C12Q1/6886 , C12Q2535/122 , C12Q2600/158 , G16B15/00
摘要： Disclosed herein in are methods and systems for determining genetic variants (e.g., copy number variation) in a polynucleotide sample. A method for determining copy number variations includes tagging double-stranded polynucleotides with duplex tags, sequencing polynucleotides from the sample and estimating total number of polynucleotides mapping to selected genetic loci. The estimate of total number of polynucleotides can involve estimating the number of double-stranded polynucleotides in the original sample for which no sequence reads are generated. This number can be generated using the number of polynucleotides for which reads for both complementary strands are detected and reads for which only one of the two complementary strands is detected.
-
-
-
-
-
-
-
-
-
搜索结果
434 条记录 (耗时 0.025 秒)
