Vladimir N Jojic

US Patent:

20060095241, May 4, 2006

Filed:

Oct 29, 2004

Appl. No.:

10/977415

Inventors:

Nebojsa Jojic - Redmond WA, US
Vladimir Jojic - Bellevue WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06G 7/48
G06G 7/58

US Classification:

703011000

Abstract:

The subject invention provides systems and methods that facilitate AIDS vaccine cocktail assembly which optimize an optimization criterion, via machine learning algorithms, e.g., a greedy algorithm, an expectation-maximization (EM) algorithm, etc. Such assembly can be utilized to generate vaccine cocktails for species of pathogens that evolve quickly under immune pressure of the host. For example, the systems and methods of the subject invention can be utilized to facilitate design of T cell vaccines for pathogens such HIV. In addition, the systems and methods of the subject invention can be utilized in connection with other applications, such as, for example, sequence alignment, motif discovery, classification, and recombination hot spot detection. The novel techniques described herein can provide for improvements over traditional approaches to designing vaccines by constructing vaccine cocktails with higher epitope coverage, for example, in comparison with cocktails of consensi, tree nodes and random strains from data.

US Patent:

20060160070, Jul 20, 2006

Filed:

Dec 30, 2005

Appl. No.:

11/324467

Inventors:

Simon Mallal - East Perth, AU
David Heckerman - Bellevue WA, US
Nebojsa Jojic - Redmond WA, US
Vladimir Jojic - Bellevue WA, US
Christopher Meek - Kirkland WA, US
Corey Moore - North Lake, AU
Carl Kadie - Bellevue WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

C12Q 1/70
G06F 19/00

US Classification:

435005000, 702019000

Abstract:

Systems that facilitate immunogen design are described herein. An optimization component is provided to determine an immunogen according to at least one criterion. The immunogen comprises a set of overlapping sequences comprising sequences that are known to be and/or are likely to be immunogenic. At least one of the sequences that are likely to be immunogenic can be determined by analyzing associations between a host and a pathogen at a population level. Methods of determining an epitome are described herein. A plurality of sequences are received. At least one of the sequences is predicted to be an epitope based on a relationship between a diverse trait of a population and a mutation of a pathogen. A collection of the plurality of sequences is optimized according to one or more criteria to determine the epitome. Epitomes and immunogens determined by the systems and methods described herein are also contemplated.

US Patent:

20060178861, Aug 10, 2006

Filed:

Dec 30, 2005

Appl. No.:

11/324506

Inventors:

Nebojsa Jojic - Redmond WA, US
Vladimir Jojic - Bellevue WA, US
David Heckerman - Bellevue WA, US
Brendan Frey - Mississauga, CA
Christopher Meek - Kirkland WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06G 7/48
G06G 7/58

US Classification:

703011000

Abstract:

The subject invention provides systems and methods that facilitate AIDS vaccine cocktail assembly via machine learning algorithms such as a cost function, a greedy algorithm, an expectation-maximization (EM) algorithm, etc. Such assembly can be utilized to generate vaccine cocktails for species of pathogens that evolve quickly under immune pressure of the host. For example, the systems and methods of the subject invention can be utilized to facilitate design of T cell vaccines for pathogens such HIV. In addition, the systems and methods of the subject invention can be utilized in connection with other applications, such as, for example, sequence alignment, motif discovery, classification, and recombination hot spot detection. The novel techniques described herein can provide for improvements over traditional approaches to designing vaccines by constructing vaccine cocktails with higher epitope coverage, for example, in comparison with cocktails of consensi, tree nodes and random strains from data.

US Patent:

20060190226, Aug 24, 2006

Filed:

Dec 30, 2005

Appl. No.:

11/324691

Inventors:

Nebojsa Jojic - Redmond WA, US
Vladimir Jojic - Bellevue WA, US
David Heckerman - Bellevue WA, US
Brendan Frey - Mississauga, CA
Christopher Meek - Kirkland WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06G 7/48
A61K 39/21

US Classification:

703011000, 424208100

Abstract:

The subject invention provides systems and methods that facilitate AIDS vaccine cocktail assembly via machine learning algorithms such as a cost function, a greedy algorithm, an expectation-maximization (EM) algorithm, etc. Such assembly can be utilized to generate vaccine cocktails for species of pathogens that evolve quickly under immune pressure of the host. For example, the systems and methods of the subject invention can be utilized to facilitate design of T cell vaccines for pathogens such HIV. In addition, the systems and methods of the subject invention can be utilized in connection with other applications, such as, for example, sequence alignment, motif discovery, classification, and recombination hot spot detection. The novel techniques described herein can provide for improvements over traditional approaches to designing vaccines by constructing vaccine cocktails with higher epitope coverage, for example, in comparison with cocktails of consensi, tree nodes and random strains from data.

US Patent:

20090171640, Jul 2, 2009

Filed:

Dec 28, 2007

Appl. No.:

11/966446

Inventors:

Nebojsa Jojic - Redmond WA, US
Vladimir Jojic - Bellevue WA, US
Tomer Hertz - Seattle WA, US

Assignee:

MICROSOFT CORPORATION - Redmond WA

International Classification:

G06G 7/48

US Classification:

703 11

Abstract:

The claimed subject matter provides systems and/or methods that facilitate generating population sequences of strain variants included in a sample. Sequencing can be based on high throughput of short reads. Further, site variants exhibited in the short reads can be linked to reconstruct multiple full strains of a targeted gene, including low concentration variants in the sample. Cues in the short read data can be utilized to perform multi-strain assembly. For example, the cues can include different strain concentrations that lead to more frequently seen strains being responsible for more frequent reads and quilting of overlapping reads to infer mutation linkage over long stretches of DNA.