Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020115580 - SYSTEM AND METHOD FOR PROMOTER PREDICTION IN HUMAN GENOME

Publication Number WO/2020/115580
Publication Date 11.06.2020
International Application No. PCT/IB2019/059139
International Filing Date 24.10.2019
IPC
G16B 20/30 2019.01
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
BBIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
20ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
30Detection of binding sites or motifs
G16B 40/20 2019.01
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
BBIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
40ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
20Supervised data analysis
G06N 3/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
CPC
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G16B 20/30
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
BBIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
20ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
30Detection of binding sites or motifs
G16B 40/20
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
BBIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
40ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
20Supervised data analysis
Applicants
  • KING ABDULLAH UNIVERSITY OF SCIENCE AND TECHNOLOGY [SA]/[SA]
Inventors
  • GAO, Xin
  • UMAROV, Ramzan
Priority Data
62/774,49403.12.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SYSTEM AND METHOD FOR PROMOTER PREDICTION IN HUMAN GENOME
(FR) SYSTÈME ET PROCÉDÉ DE PRÉDICTION DE PROMOTEUR DANS LE GÉNOME HUMAIN
Abstract
(EN)
A method for training a deep neural network model (100) based on a known genome sequence (500) includes receiving (1100) the known genome sequence (500); training (1102) the deep neural network model (100) with a current negative set (502) obtained from the known genome sequence (500); applying (1104) the deep neural network model (100) to the known genome sequence (500) and recording false positive sets; selecting (1106) a subset of the new false positive sets (508); updating (1108) the current negative set (502) with the new false positive sets (508); and repeating (1110) the steps of training, applying, selecting and updating until a number of the new false positive sets is smaller than a given threshold.
(FR)
La présente invention concerne un procédé d'apprentissage d'un modèle de réseau neuronal profond (100) sur la base d'une séquence génomique connue (500), ledit procédé consistant à recevoir (1100) la séquence génomique connue (500) ; à former (1102) le modèle de réseau neuronal profond (100) avec un ensemble négatif actuel (502) obtenu à partir de la séquence génomique connue (500) ; à appliquer (1104) le modèle de réseau neuronal profond (100) à la séquence génomique connue (500) et à enregistrer de faux ensembles positifs ; à sélectionner (1106) un sous-ensemble des nouveaux ensembles faux positifs (508) ; à mettre à jour (1108) l'ensemble négatif actuel (502) avec les nouveaux ensembles faux positifs (508) ; et à répéter (1110) les étapes d'apprentissage, d'application, de sélection et de mise à jour jusqu'à ce qu'un nombre de nouveaux ensembles faux positifs soit inférieur à un seuil donné.
Latest bibliographic data on file with the International Bureau