Claims for Patent: 6,807,491

Summary for Patent: 6,807,491

Title:	Method and apparatus for combining gene predictions using bayesian networks
Abstract:	Computer based apparatus and method automates gene prediction in a subject genomic sequence. A plurality of expert systems provide preliminary or intermediate gene predictions. A Bayesian network combiner combines the intermediate gene predictions and forms a final gene prediction. The final gene prediction accounts for dependencies between individual expert systems and dependencies between adjacent parts of the subject genomic sequence.
Inventor(s):	Pavlovic; Vladimir (Melrose, MA), Kasif; Simon (Newton, MA), Garg; Ashutosh (Urbana, IL)
Assignee:	Hewlett-Packard Development Company, L.P. (Houston, TX)
Application Number:	09/943,579
Patent Litigation and PTAB cases:	See patent lawsuits and PTAB cases for patent 6,807,491
Patent Claims:	1. A method for automated gene prediction, comprising the steps of: obtaining from a plurality of expert systems a plurality of respective preliminary gene location predictions for a subject gene in a subject genomic sequence; inputting into a digital processor programmed to contain a Bayesian network a plurality of respective datasets representing said gene location predictions; combining said respective datasets in said Bayesian network; and forming from said Bayesian network a data output indicating an improved predicted location for said subject gene in the subject genomic sequence, wherein the Bayesian network includes probabilistic dependencies between individual expert systems and dependencies between adjacent parts of the subject genomic sequence. 2. The method as claimed in claim 1 wherein said Bayesian network combines said plurality of datasets according to the probability equation wherein t is location of a subject gene in the subject genomic sequence and E.sub.1, . . . , E.sub.n are the respective predictions (E for exon or I for intron) made by individual expert systems, n being the number of expert systems in the plurality. 3. The method as claimed in claim 1 wherein the subject genomic sequence is a DNA or RNA sequence. 4. The method as claimed in claim 1 wherein said obtaining and said inputting each comprise predicting an exon location. 5. A method as claimed in claim 4 wherein gene locations further include exon and intron predictions; and the final combined output indicates exons and introns of the predicted genes of the subject genomic sequence. 6. The method of claim 1 wherein said forming comprises creating from said Bayesian network a data output indicating an optimal combined predicted location for each said subject gene in the subject genomic sequence. 7. The method of claim 1 comprising, prior to said combining, providing a training dataset to said processor representing a plurality of known gene locations on a known genomic sequence. 8. The method of claim 7 comprising, constructing a conditional probability function or table from said training dataset. 9. The method of claim 1 comprising selecting a subject gene that is unknown to said expert systems.

Details for Patent 6,807,491

Applicant	Tradename	Biologic Ingredient	Dosage Form	BLA	Approval Date	Patent No.	Expiredate
Merck Sharp & Dohme Corp.	INTRON A	interferon alfa-2b	For Injection	103132	06/04/1986		2039-02-26
Merck Sharp & Dohme Corp.	INTRON A	interferon alfa-2b	For Injection	103132			2039-02-26
Merck Sharp & Dohme Corp.	INTRON A	interferon alfa-2b	Injection	103132			2039-02-26