Koninklijke Philips Corporation N.v.

Intertrust Technologies Corporation

Alexander Ryan Mankovich

Nevenka Dimitrova

Raymond J Krasinski

Vartika Agrawal

Yong Mao

Jarl A Nilsson

Nilanjana Banerjee

Jin Qu

William Knox Carey

Yee Him Cheung

Bart Grantham

Robbert Christiaan Van Ommering

Johanna Maria De Bont

Fubiao Xia

Jozef Hieronymus Maria Raijmakers

Weijian Qin

Samuel Frank Pilato

Woei-Jye Yee

Qingxin Wu

A method for assessing quality of genomic regions studied for inclusion in standardized clinical formats includes receiving data sets to be applied to a plurality of gene panels. The method also includes applying, by a processor executing instructions, standardized quality control metrics to the data sets to be applied to the plurality of gene panels; filtering, by the processor executing the instructions, each of the data sets to be applied to the plurality of gene panels to sets of variants and formatting the sets of variants in a clinical format, and outputting the sets of variants resulting from the filtering to a downstream application.

Assessing quality of genomic regions studied for inclusion in standardized clinical formats

In patient cohort identification, clustering () of patients is performed using a patient comparison metric dependent on a set of features (). Information is displayed on sample patients who are similar or dissimilar to a query patient according to the clustering. User inputted comparison values are received comparing the sample patients with the query patient. The set of features and/or feature weights are adjusted to generate an adjusted patient comparison metric having improved agreement with the user inputted comparison values. The clustering is repeated using the adjusted patient comparison metric. A patient cohort is identified from a cluster () containing the query patient produced by the last clustering repetition. The information on the sample patients may be shown by simultaneously displaying two or more graphical modality representations () each plotting the sample patients and the query patient against two or more features of the modality.

Relevance feedback to improve the performance of clustering model that clusters patients with similar profiles together

A method () for standardizing gene nomenclature, comprising: (i) receiving () a source; (ii) tokenizing () the source; (iii) comparing () a first token to a prefix tree structure with a root node, edges, and leaf nodes; (iv) determining () which edge extending from the root node to associated first leaf nodes the first token matches; (v) updating () an identification pointer with the location of the first leaf node; (vi) determining () which of one or more edges that a second token matches; (vii) updating () the identification pointer with the location of the second leaf node; (viii) repeating () the determining () and updating () steps with subsequent tokens until a subsequent token fails to match an edge extending from a leaf node or there is no edge extending from the leaf node; and (ix) providing () an identification of a canonical gene name.

Method and system for normalization of gene names in medical text

A method for assessing risk associated with a request from an inquirer for allele frequency from a database of genetic data, comprising: (i) generating an allele database comprising allele frequency information and request frequency information for each of a plurality of alleles; (ii) generating an inquirer database comprising allele request information about a plurality of inquirers; (iii) receiving a request for genetic data from an inquirer, comprising a request for allele frequency for one or more alleles and an identifier of the inquirer; (iv) updating the request frequency information based on the received request; (v) updating the allele request information for the requesting inquirer; (vi) calculating an allele risk score; (vii) calculating an inquirer risk score; and (viii) assessing, based on the allele risk score and the inquirer risk score, a risk associated with the received request.

Proactive resistance to re-identification of genomic data

Methods and apparatus for a secure framework for storing and analyzing genomic data. Embodiments of the present invention apply persistent governance to sensitive information and to the analytics that operate upon it, managing the interaction between the two.

Genomic informatics service

Growing community of inventors

Boston, MA, United States of America

Alexander Ryan Mankovich