Microsoft Technology Licensing, LLC

Amazon Technologies, Inc.

Flow Pharma, Inc.

Other

David Earl Heckerman

David Maxwell Chickering

Christopher A Meek

Robert L Rounthwaite

Bo Thiesson

Carl Myers Kadie

Joshua T Goodman

Nebojsa Jojic

Eric I Horvitz

John S Breese

D Maxwell Chickering

Gregory L Shaw

John Carlton Platt

Alexei V Bocharov

Zhaohui Tang

David O Hovel

Scott Conrad Oveson

Samuel D Hobson

Bryan T Starbuck

Nathan D Howell

Adrian C Klein

Daniel Rosen

Dan Geiger

Jacobus A Rommelse

Craig J Mundie

Adrian Napoles

Geoffrey John Hulten

Eric Barber Vigesaa

Allan Folting

Fileno A Alleva

Mei-Yuh Hwang

Christopher Raymond Grajewski

Randy Hinrichs

Jennifer Listgarten

Andreas Caduff

Leo Benedict Baldwin

Reid M Rubsamen

Ying Li

Susan Theresa Dumais

Li Erran Li

Eric S Chung

John Grant Bennett

Eliot Carleton Gillum

Tarek Najm

Paul S Bradley

John D Mehr

Daniel Lo

Steven J White

Yoram Yaacovi

John L Manferdelli

Ravindra Pandya

Brian Burdick

Kalin Ovtcharov

Rajeev Prasad

Raxit A Kagalwala

Michael Vogelsong

Layne Christopher Price

Murali Vajjiravel

Dean Alan Slawson

Micah C Rupersburg

Sachin Dhawan

James Robert Hamilton

John R Douceur

Amir Netz

George G Robertson

Chris Demetrios Karkanias

Darko Kirovski

Vladimir Sadovsky

Chao Wang

Ilia Vitsnudel

Brian Scott Ruble

Nuria M Oliver

Oren Rosenbloom

Usama M Fayyad

Jason David Carlson

Jesper B Lind

Jack W Stokes

Pyungchul Kim

Behrooz Chitsaz

Viktor Rozgic

Jeffrey Bernhardt

James Randall Flynn

Brendan John Frey

Christian Seifert

Christian Bernd Schormann

Keiji Kanazawa

Jakob Peter Nielsen

Karen Jensen

Sean Boon

Ashis Kumar Roy

Sasi Parthasarathy

Pablo Argon

Thierry D'Hers

Robert I Davidson

Roman Snytsar

Ariel Katz

Patrick Chow

Yifat Sagiv

Joshua W Lee

Vladimir Jojic

Disclosed herein is a method for determining tumor margins relative to non-tumorous tissue using a deep-learning platform. Also disclosed herein are methods for removing a tumor from a tumor biopsy.

Enrichment of surgical specimens for tumor tissue

Data about concentration of one or more types of molecules present within a human body are determined noninvasively using radio frequency signals. These signals at several different frequencies are generated at very low power levels are emitted and acquired using an antenna mounted to a wearable device. Information about changes to the signals, such as phase variances of the signals at different frequencies is indicative of the concentration of one or more types molecules within the user. The antenna includes concentric elements with one or more being used to emit the signal(s) while one or more are used to acquire the signal(s). Concentrations at different depths may be measured by selectively using particular concentric elements. A maximum depth may approximately equal the spacing between the elements being used at a given time. Other sensors may be emplaced or operate through windows located between one or more of the concentric elements.

Radio frequency antenna for wearable device

A wearable device may compress the skin of a user when worn, which may affect values determined using sensors of the device. To determine the effect of skin compression on the values, a time-of-flight signal, images, or frames of video data that depict a portion of the body having indentations from wearing the device may be acquired. Characteristics of the images, such as shadows associated with the indentations, may be processed using a machine learning algorithm or mathematical function to determine a depth of various portions of the indentations. Depth data from the time of flight signal may be used to refine or modify these determined depths. The amount of skin compression associated with the indentations may be used to modify signals acquired using sensors, or output a recommendation for a band or other method for securing the device.

Systems for determining elevations of skin features

Data about concentration of one or more types of molecules present within a human body are determined noninvasively using radio frequency (RF) signals. Signals at several different frequencies at very low power levels are emitted using an antenna mounted to a wearable device. Operating values, such as changes to the impedance of the antenna resulting from interaction between the RF signals and the user, are associated with the concentration of one or more types of molecules within the user. These changes in impedance may be relatively small. Circuitry in the device determines internal impedance of the circuitry, compensating for internal impedances and improving overall accuracy of the measured impedance resulting from interaction with the user.

Radio frequency biosensor with integrated compensation

Techniques are described and relate to anisotropic pooling for contextual embedding of a protein sequence. In an example, a system receives a first biological sequence and determines a sequence arrangement that comprises a component of the first biological sequence and a second biological sequence of components. By using an artificial intelligence (AI) model, the system determines a third sequence that comprises a contextual embedding vector corresponding to the component of the first biological sequence. The AI model generates the third sequence based at least in part on the sequence arrangement and by at least using a convolution and anisotropic pooling.

Anisotropic pooling for contextual embedding of a compound sequence

Data about concentration of one or more types of molecules present within a human body are determined noninvasively using radio frequency signals. Signals at several different frequencies at very low power levels are emitted using an antenna mounted to a wearable device. The antenna includes nested elements of different sizes. Operating values, such as changes to the impedance of the antenna, are associated with the concentration of one or more types molecules within the user. Concentrations at different depths may be measured by using different sets of the nested elements at different times. Operating values at those times are measured and used to determine information indicative of concentration of the molecules. During use, a long axis of the antenna may be aligned with a long axis of a user's arm.

Described is a system and method that determines character sequences from speech, without determining the words of the speech, and processes the character sequences to determine sentiment data indicative of emotional state of a user that output the speech. The emotional state may then be presented or provided as an output to the user.

Character-level emotion detection

Systems, devices, and methods are provided for detecting and correcting eating behavior. A device may receive audio data, determine that the audio data is indicative of consumption of a product by a user. The device may determine, based on the product, a measureable attribute associated with the user. The device may receive first data associated with the measureable attribute. The device may determine that the first data exceeds a threshold. The device may generate a message for presentation.

Methods and devices for detection of eating behavior

Techniques for generating multiple-resolutions of time series data are described. An input irregular time series having a plurality of data points is obtained, each data point of the plurality of data points including a timestamp and a feature vector. Based on the input irregular time series, multiple variant time series are generated. A data point in one of the variant time series is based in part on a combination of at least two data points of the input irregular time series. The multiple variant time series can then be used for machine learning tasks such as training a machine learning model or using a machine learning model to infer an output.

Temporal-clustering invariance in irregular time series data

An automated life science laboratory or a storage facility for biological specimens may be located together with or in close proximity to a data center. The location of the data center, the automated life science laboratory, and the storage facility may be a location in which land and/or electricity are less expensive than locations where the biological specimens are collected. The automated life science laboratory may have a high-capacity data connection to the data center. The life science laboratory, storage facility, and the data center may share a connection to the electrical grid, an HVAC system, and/or a security perimeter. A biological specimen may be removed from storage at the storage facility, process by one or more biotechnology protocols at the automated life science laboratory, and data from the processing may be stored in the data center.

Remote life science laboratories and storage facilities

Comparisons between two nucleotide sequences can be performed by customized integrated circuitry that can implement a Smith Waterman analysis in series, as opposed to the parallel implementations known in the art. Series performance enables such customized integrated circuitry to take advantage of optimizations, including enveloping thresholds that demarcate between cells of a two-dimensional matrix for which nucleotide comparisons are to be performed, and cells of the two-dimensional matrix for which no such comparison need be performed, and, instead, a value of zero can simply be entered. Additionally, such customized integrated circuitry facilitates the combination of multiple control units, each directing the comparison of a unique pair of nucleotides, with a single calculation engine that can generate values for individual cells of the two-dimensional matrices by which such pairs of nucleotides are compared.

Customized integrated circuit for serial comparison of nucleotide sequences

Comparisons between two nucleotide sequences can be performed by customized integrated circuitry that can implement a Smith Waterman analysis in a reduced memory footprint, storing and referencing only individual portions, or subsections, of a two-dimensional matrix that is representative of the comparison between the two nucleotide sequences. As the backtracking proceeds, backtracking metadata corresponding to a cell from a subsection that is not currently retained in memory can be required. Such a subsection can be regenerated from previously generated scores associated with checkpoint cells of the two-dimensional matrix that comprise two edges of the subsection being regenerated. Moreover, to further reduce memory consumption, the backtracking metadata stored for each cell can comprise four binary digits: two indicative of a directional assignment, one indicative of whether the corresponding cell is part of a deletion stretching across multiple contiguous cells, and one analogously indicative of insertions stretching across multiple contiguous cells.

Reduced memory nucleotide sequence comparison

A composition as disclosed is comprised of a plurality of groups of particles. The particles are comprised of a biocompatible polymer which may be a co-polymer such as PLGA combined with a peptide of a sequence of interest, e.g. a sequence which corresponds to a sequence presented on a surface of a cell infected with a virus. A plurality of different groups of particles are provided in the formulation wherein the particles within any single group include peptides of identical amino acid sequence. The particles are sized such that they are sufficiently large so as to prevent more than the contents of a single particle from being presented to a single immune system cell.

Peptide particle formulation

Distribution displays for categories are provided which illuminate the distribution of continuous attributes over all cases in a category, and which provide a histogram of the population of the different states of categorical attributes. An array of such displays by attribute (in one dimension) and category (in another dimension) may be provided. Category diagram displays are also provided for visualizing the different categories, and their distributions, populations, and similarities. These are displayed through different shading of nodes and edges representing categories and the relationship between two categories, and through proximity of nodes.

System and method for visualization of categories

A composition as disclosed is comprised of a plurality of groups of particles. The particles are comprised of a biocompatible polymer which maybe a co-polymer such as PLGA combined with a peptide of a sequence of interest, e.g. a sequence which corresponds to a sequence presented on a surface of a cell infected with a virus. A plurality of different groups of particles are provided in the formulation wherein the particles within any single group include peptides of identical amino acid sequence. The particles are sized such that they are sufficiently large so as to prevent more than the contents of a single particle from being presented to a single immune system cell.

Growing community of inventors

Bellevue, WA, United States of America

David Earl Heckerman