Computational Prediction of Gene Function From High-throughput Data Sources
A large number and variety of genome-wide genomics and proteomics datasets are now available for model organisms. Each dataset on its own presents a distinct but noisy view of cellular state. However, collectively, these datasets embody a more comprehensive view of cell function. This motivates the...
Main Author: | |
---|---|
Other Authors: | |
Language: | en_ca |
Published: |
2011
|
Subjects: | |
Online Access: | http://hdl.handle.net/1807/29820 |
id |
ndltd-LACETR-oai-collectionscanada.gc.ca-OTU.1807-29820 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-LACETR-oai-collectionscanada.gc.ca-OTU.1807-298202013-04-17T04:19:17ZComputational Prediction of Gene Function From High-throughput Data SourcesMostafavi, SaraComputational BiologyMachine LearningPredicting Gene FunctionBiological NetworksCombining High-Throughput Data Sources098408000715A large number and variety of genome-wide genomics and proteomics datasets are now available for model organisms. Each dataset on its own presents a distinct but noisy view of cellular state. However, collectively, these datasets embody a more comprehensive view of cell function. This motivates the prediction of function for uncharacterized genes by combining multiple datasets, in order to exploit the associations between such genes and genes of known function--all in a query-specific fashion. Commonly, heterogeneous datasets are represented as networks in order to facilitate their combination. Here, I show that it is possible to accurately predict gene function in seconds by combining multiple large-scale networks. This facilitates function prediction on-demand, allowing users to take advantage of the persistent improvement and proliferation of genomics and proteomics datasets and continuously make up-to-date predictions for large genomes such as humans. Our algorithm, GeneMANIA, uses constrained linear regression to combine multiple association networks and uses label propagation to make predictions from the combined network. I introduce extensions that result in improved predictions when the number of labeled examples for training is limited, or when an ontological structure describing a hierarchy of gene function categorization scheme is available. Further, motivated by our empirical observations on predicting node labels for general networks, I propose a new label propagation algorithm that exploits common properties of real-world networks to increase both the speed and accuracy of our predictions.Morris, Quaid2011-062011-08-31T17:45:37ZNO_RESTRICTION2011-08-31T17:45:37Z2011-08-31Thesishttp://hdl.handle.net/1807/29820en_ca |
collection |
NDLTD |
language |
en_ca |
sources |
NDLTD |
topic |
Computational Biology Machine Learning Predicting Gene Function Biological Networks Combining High-Throughput Data Sources 0984 0800 0715 |
spellingShingle |
Computational Biology Machine Learning Predicting Gene Function Biological Networks Combining High-Throughput Data Sources 0984 0800 0715 Mostafavi, Sara Computational Prediction of Gene Function From High-throughput Data Sources |
description |
A large number and variety of genome-wide genomics and proteomics datasets are now available for model organisms. Each dataset on its own presents a distinct but noisy view of cellular state. However, collectively, these datasets embody a more comprehensive view of cell function. This motivates the prediction of function for uncharacterized genes by combining multiple datasets, in order to exploit the associations between such genes and genes of known function--all in a query-specific fashion.
Commonly, heterogeneous datasets are represented as networks in order to facilitate their combination. Here, I show that it is possible to accurately predict gene function in seconds by combining multiple large-scale networks. This facilitates function prediction on-demand, allowing users to take advantage of the persistent improvement and proliferation of genomics and proteomics datasets and continuously make up-to-date predictions for large genomes such as humans.
Our algorithm, GeneMANIA, uses constrained linear regression to combine multiple association networks and uses label propagation to make predictions from the combined network. I introduce extensions that result in improved predictions when the number of labeled examples for training is limited, or when an ontological structure describing a hierarchy of gene function categorization scheme is available. Further, motivated by our empirical observations on predicting node labels for general networks, I propose a new label propagation algorithm that exploits common properties of real-world networks to increase both the speed and accuracy of our predictions. |
author2 |
Morris, Quaid |
author_facet |
Morris, Quaid Mostafavi, Sara |
author |
Mostafavi, Sara |
author_sort |
Mostafavi, Sara |
title |
Computational Prediction of Gene Function From High-throughput Data Sources |
title_short |
Computational Prediction of Gene Function From High-throughput Data Sources |
title_full |
Computational Prediction of Gene Function From High-throughput Data Sources |
title_fullStr |
Computational Prediction of Gene Function From High-throughput Data Sources |
title_full_unstemmed |
Computational Prediction of Gene Function From High-throughput Data Sources |
title_sort |
computational prediction of gene function from high-throughput data sources |
publishDate |
2011 |
url |
http://hdl.handle.net/1807/29820 |
work_keys_str_mv |
AT mostafavisara computationalpredictionofgenefunctionfromhighthroughputdatasources |
_version_ |
1716580572233465856 |