专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2022232615A1 MACHINE LEARNING TECHNIQUES FOR ESTIMATING TUMOR CELL EXPRESSION IN COMPLEX TUMOR TISSUE 审中-公开
公开(公告)号：WO2022232615A1
公开(公告)日：2022-11-03
申请号：PCT/US2022/027088
申请日：2022-04-29
申请人： BOSTONGENE CORPORATION
发明人： ZAITSEV, Aleksandr , BAGAEV, Alexander , CHELUSHKIN, Maksim , BELIAEVA, Valentina , SHPAK, Boris , DYIKANOV, Daniiar , ZOTOVA, Anastasia , GOLDBERG, Michael, F. , TAZEARSLAN, Cagdas
IPC分类号： G16B25/10 , C12Q1/68 , G16B40/20 , C12Q1/6886 , C12Q2600/158 , G16H20/40 , G16H50/20 , G16H70/20
摘要： Techniques for using machine learning to estimate tumor expression levels of genes in tumor cells. The techniques include obtaining expression data for a set of genes comprising a first plurality of genes associated with the tumor cells and a second plurality of genes associated with tumor microenvironment cells; determining the tumor expression levels of the first plurality of genes in the tumor cells using a plurality of machine learning models, the determining comprising: generating a first set of features for the first gene; providing the first set of features as input to the first machine learning model to obtain an output comprising a tumor microenvironment expression level estimate of the first gene in the tumor microenvironment cells; and determining a first tumor expression level for the first gene in the tumor cells using the output of the first machine learning model and a total expression level for the first gene.

2. 发明申请

WO2022165123A1 TECHNIQUES FOR MANAGING DATA IN A DATA PROCESSING SYSTEM USING DATA ENTITIES AND INHERITANCE 审中-公开
公开(公告)号：WO2022165123A1
公开(公告)日：2022-08-04
申请号：PCT/US2022/014232
申请日：2022-01-28
申请人： AB INITIO TECHNOLOGY LLC
发明人： GYLFASON, Halldor, Isak , RADIVOJEVIC, Dusan , PARKS, Robert , WEISS, Adam, Harris
IPC分类号： G06F16/22 , G06F16/21
摘要： Techniques for storing data entities by a data processing system are described herein. The data processing system may store a plurality of data entity instances generated using a plurality of data entities. The plurality of data entity instances may include a first data entity instance generated using a first data entity and a second data entity instance generated using a second data entity. The first data entity instance may include a first attribute that is configured to inherit its value from a second attribute of the second data entity instance. The data processing system may provide the inherited value of the second attribute of the second data entity instance as the value of the first attribute of the first data entity instance.

3. 发明申请

WO2022120256A2 HIERARCHICAL MACHINE LEARNING TECHNIQUES FOR IDENTIFYING MOLECULAR CATEGORIES FROM EXPRESSION DATA 审中-公开
公开(公告)号：WO2022120256A2
公开(公告)日：2022-06-09
申请号：PCT/US2021/061923
申请日：2021-12-04
申请人： BOSTONGENE CORPORATION
发明人： KOTLOV, Nikita , ANTYSHEVA, Zoia , KIRIY, Daria , SIVKOV, Anton , SARACHAKOV, Aleksandr , SVEKOLKIN, Viktor , KOZLOV, Ivan
IPC分类号： G16B25/10 , G16H50/20 , G06N20/10 , G06N20/20 , G06N3/02 , G06N5/003 , G06N7/005 , G16B30/00 , G16B40/00
摘要： Described herein in some embodiments is a method comprising: obtaining expression data previously obtained by processing a biological sample obtained from a subject; processing the expression data using a hierarchy of machine learning classifiers corresponding to a hierarchy of molecular categories to obtain machine learning classifier outputs including a first output and a second output, the hierarchy of molecular categories including a parent molecular category and first and second molecular categories that are children of the parent molecular category in the hierarchy of molecular categories, the hierarchy of machine learning classifiers comprising first and second machine learning classifiers corresponding to the first and second molecular categories; and identifying, using at least some of the machine learning classifier outputs including the first output and the second output, at least one candidate molecular category for the biological sample.

4. 发明申请

WO2022055964A1 GENERATING REALISTIC COUNTERFACTUALS WITH RESIDUAL GENERATIVE ADVERSARIAL NETS 审中-公开
公开(公告)号：WO2022055964A1
公开(公告)日：2022-03-17
申请号：PCT/US2021/049416
申请日：2021-09-08
申请人： HIRED, INC. , H RESTRUCTURING LLC , VETTERY, INC.
发明人： NEMIROVSKY, Daniel, Alexander , THIEBAUT, Nicolas, Kevin
IPC分类号： G06N3/04 , G06N3/08 , G06N20/00
摘要： Techniques for generating counterfactuals in connection with machine learning models. The techniques include applying a trained machine learning model to an input to obtain a first outcome; determining whether the first outcome has a value in a set of one or more target values; when it is determined that the first outcome does not have a value in the set of one or more target values, generating a counterfactual input at least in part by applying a trained neural network model to the input to obtain a corresponding output, the corresponding output indicating changes to be made to one or more values of one or more attributes of the input to obtain the counterfactual input, and generating feedback based on the counterfactual input.

5. 发明申请

WO2021183917A8 SYSTEMS AND METHODS FOR DECONVOLUTION OF EXPRESSION DATA 审中-公开
公开(公告)号：WO2021183917A8
公开(公告)日：2021-09-16
申请号：PCT/US2021/022155
申请日：2021-03-12
申请人： BOSTONGENE CORPORATION , ZAITSEV, Alexander , CHELUSHKIN, Maksim , NUZHDINA, Ekaterina , ZYRIN, Vladimir , DYYKANOV, Daniyar , BAGAEV, Alexander , ATAULLAKHANOV, Ravshan , CHEREMUSHKIN, Ilya , SHPAK, Boris , OOO BOSTONDZHIN
发明人： ZAITSEV, Aleksandr , CHELUSHKIN, Maksim , NUZHDINA, Ekaterina , ZYRIN, Vladimir , DYIKANOV, Daniiar , BAGAEV, Alexander , ATAULLAKHANOV, Ravshan , CHEREMUSHKIN, Ilya , SHPAK, Boris
IPC分类号： G16B40/20 , G16B25/10 , G06F17/18
摘要： Techniques for determining one or more cell composition percentages from expression data. The techniques include obtaining expression data for a biological sample, the biological sample previously obtained from a subject, the expression data including first expression data associated with a first set of genes associated with a first cell type; determining a first cell composition percentage for the first cell type using the expression data and one or more non-linear regression models including a first non-linear regression model, wherein the first cell composition percentage indicates an estimated percentage of cells of the first cell type in the biological sample, wherein determining the first cell composition percentage for the first cell type comprises: processing the first expression data with the first non-linear regression model to determine the first cell composition percentage for the first cell type; and outputting the first cell composition percentage.

6. 发明申请

WO2020146356A1 MACHINE LEARNING TECHNIQUES FOR DETERMINING THERAPEUTIC AGENT DOSAGES 审中-公开
公开(公告)号：WO2020146356A1
公开(公告)日：2020-07-16
申请号：PCT/US2020/012543
申请日：2020-01-07
申请人： PRESIDENT AND FELLOWS OF HARVARD COLLEGE
发明人： ENGELHARDT, Dalit
IPC分类号： A61B34/10 , A61K9/20 , G01N15/06 , G06F17/18 , G06N3/08 , G06N5/04 , G16H50/50
摘要： Techniques for determining a dosage plan for administering at least one therapeutic agent to a subject. The techniques include using at least one computer hardware processor to perform: accessing information specifying a plurality of cell population concentrations for a respective plurality of cell populations in a biological sample from a subject; and determining the dosage plan using a trained statistical model and the plurality of cell population concentrations, the dosage plan including one or more concentrations of the at least one therapeutic agent to be administered to the subject at one or more respective different times. The trained statistical model may be trained using an actor-critic reinforcement learning technique and a model of cell evolution. The trained statistical model may include a deep neural network.

7. 发明申请

WO2020005853A1 SYSTEMS AND METHODS FOR SECURING COMMUNICATIONS 审中-公开
公开(公告)号：WO2020005853A1
公开(公告)日：2020-01-02
申请号：PCT/US2019/038769
申请日：2019-06-24
申请人： VIRTUAL SOFTWARE SYSTEMS, INC. , TROIANI, Mario
发明人： TROIANI, Mario , KAMAN, Charles, H. , WELCH, Nathaniel , FIORENTINO, Richard, D.
IPC分类号： G06F21/60 , H04K1/04 , H04L9/06 , H04L9/18
摘要： Techniques for securing communication. The techniques include using at least one device to perform: selecting a first operation from a plurality of operations, each of the plurality of operations associated with a respective type of data to be encrypted; generating first data to be encrypted at least in part by performing the first operation; encrypting both information identifying the first operation and the first data to obtain corresponding first ciphertext; and outputting the first ciphertext.

8. 发明申请

WO2019212849A1 DEVICE AUTHENTICATION BASED ON ANALOG CHARACTERISTICS WITHOUT ERROR CORRECTION 审中-公开
公开(公告)号：WO2019212849A1
公开(公告)日：2019-11-07
申请号：PCT/US2019/029077
申请日：2019-04-25
申请人： ANALOG DEVICES, INC.
发明人： ADAMS, Robert, W. , WALLRABENSTEIN, John, Ross , KARAKOYUNLU, Deniz
IPC分类号： H04L9/32 , G06F21/44 , G09C1/00 , H04L9/08
摘要： This application describes systems and methods for using a physical unclonable function (PUF) to authenticate a device, which may include circuitry for generating PUF values that may uniquely identify the device. According to one aspect, the device may provide enrollment PUF values to an authentication device. The device may later be authenticated if PUF values generated by the device are within a threshold distance of the enrollment PUF values. Since the PUF values are compared using a distance, it may not necessary to apply an error correcting code to the PUF values. The enrollment values and/or the calculated distance may be adjusted to compensate for time variations in the PUF values due to circuit aging. Systems and methods are also described herein for authenticating the device without revealing new PUF values to any second party, for example using a cryptographic technique known as a garbled circuit.

9. 发明申请

WO2018089633A1 SYSTEMS AND METHODS FOR DETERMINING RELATIONSHIPS AMONG DATA ELEMENTS 审中-公开
标题翻译：确定数据元素之间关系的系统和方法
公开(公告)号：WO2018089633A1
公开(公告)日：2018-05-17
申请号：PCT/US2017/060860
申请日：2017-11-09
申请人： AB INITIO TECHNOLOGY LLC
发明人： GOULD, Joel , RADIVOJEVIC, Dusan
IPC分类号： G06F17/30
摘要： A data processing system configured to perform: obtaining a first data lineage representing relationships among physical data elements, the first data lineage being generated at least in part by performing at least one of: (a) analyzing source code of at least one computer program configured to access the physical data elements; and (b) analyzing information obtained during runtime of the at least one computer program; obtaining, based on user input, a second data lineage representing relationships among business data elements; obtaining an association between at least some of the physical data elements of the first data lineage and at least some of the business data elements of the second data lineage; and generating, based on the association between the physical data elements and the business data elements, an indication of agreement or discrepancy between the first data lineage and the second data lineage.
摘要翻译：数据处理系统，被配置为执行：获得表示物理数据元素之间的关系的第一数据沿袭，所述第一数据沿袭至少部分通过执行以下中的至少一个来生成：（a）分析源至少一个计算机程序的代码，其被配置为访问所述物理数据元素; 和（b）分析在所述至少一个计算机程序的运行时期间获得的信息; 基于用户输入获得表示业务数据元素之间的关系的第二数据沿袭; 获得第一数据沿袭的至少一些物理数据元素与第二数据沿袭的至少一些商业数据元素之间的关联; 以及基于物理数据元素与商业数据元素之间的关联，生成第一数据系列与第二数据系列之间的一致或差异的指示。

10. 发明申请

WO2018064254A1 SYSTEMS AND METHODS FOR PLANNING PRINTING OF THREE-DIMENSIONAL OBJECTS 审中-公开
标题翻译：用于规划三维物体印刷的系统和方法
公开(公告)号：WO2018064254A1
公开(公告)日：2018-04-05
申请号：PCT/US2017/053879
申请日：2017-09-28
申请人： SHAPEWAYS, INC.
发明人： YAW, Hunter , RINK, Stefan , CAPO, Robert , SONK, Jacob , HORTIATIS, Paul , DELGADO-GAMBINI, Martin , SCHEPERS, Barry , COSTA SAO JOSE, Tiago, André , DILLON, Zachary, Hansen , VAN DIJK, Maarten
IPC分类号： B05C19/00 , B22F3/00 , B22F3/105 , B22F7/02 , B23K26/08 , B23K26/34 , B29C35/04 , B29C41/12 , B29C41/46
摘要： A system for planning printing of three-dimensional (3D) objects. The system comprises at least one computer hardware processor, and at least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by the at least one computer hardware processor, cause the at least one computer hardware processor to perform acts of: accessing information specifying a plurality of 3D objects to be printed using at least one 3D printer, the at least one 3D printer including a first 3D printer; determining a priority for each of at least some of the plurality 3D objects to obtain determined 3D object priorities; assigning, based on the determined 3D object priorities, a subset of the plurality of 3D objects to a first printer tray adapted for use with the first 3D printer; and obtaining a packing plan indicating an arrangement of the subset of the 3D objects within the first printer tray.
摘要翻译：
一种计划打印三维（3D）对象的系统。该系统包括至少一个计算机硬件处理器和存储处理器可执行指令的至少一个非暂时性计算机可读存储介质，所述处理器可执行指令在由所述至少一个计算机硬件处理器执行时使所述至少一个计算机硬件处理器执行以下行为：使用至少一个3D打印机访问指定要打印的多个3D对象的信息，所述至少一个3D打印机包括第一3D打印机; 确定所述多个3D对象中的至少一些中的每一个的优先级以获得确定的3D对象优先级; 基于确定的3D对象优先级，将多个3D对象的子集分配给适用于第一3D打印机的第一打印机托盘; 并且获得指示第一打印机托盘内的3D对象的子集的布置的打包计划。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式