Construction of graph-based network longitudinal algorithms.
Research type
Research Study
Full title
Construction of graph-based network longitudinal algorithms to identify screening and prognostic biomarkers and therapeutic targets.
IRAS ID
277108
Contact name
Usha Menon
Contact email
Sponsor organisation
University College London
Clinicaltrials.gov Identifier
Z636406 2019 12 82, UCL Data Protection Registration
Duration of Study in the UK
3 years, 0 months, 0 days
Research summary
There is a growing need for a personalised approach to medicine and the analysis of Big Data with network tools, particularly in diagnosis and choice of treatment. Typical Big Data (e.g. results of next generation sequencing, or high-throughput proteomic and epigenetic analyses) contains high-dimensional data including many parameters which can be continuous or categorical. Additionally, this data can be from serial (longitudinal) measurements taken over time from the same patients. One difficulty in interpreting this data for defining clinically useful information is that multiple different changes may be responsible for the onset of a disease, as exemplified by the efforts of The Cancer Genome Atlas project. Hence, there is a need to develop methodology able to analyse different changes in high-dimensional data containing categorical and longitudinal continuous data in order to identify prognostic, diagnostic and therapeutic targets, e.g., to solve the task of classification of diseased/healthy patients, particularly for early diagnosis.
The main aim of this application is to develop a methodology for representation of serial data containing categorical and continuous parameters in the form of networks, the longitudinal analysis of network dynamics, and hence, the construction of longitudinal network biomarkers, generating diagnostic, prognostic and drugable targets. Data networks have been successfully applied to the problem of detecting key genes and metabolites in different diseases. The research planned will include the combination of data network analysis with our previously developed algorithms for serial data analysis.
Lay Summary of results:
There is a growing need for a personalised approach to medicine and the analysis of Big Data with network tools, particularly in diagnosis and choice of treatment. Typical Big Data (e.g. results of next generation sequencing, or high-throughput proteomic and epigenetic analyses) contains high-dimensional data including many parameters which can be continuous or categorical. Additionally, this data can be from serial (longitudinal) measurements taken over time from the same patients. One difficulty in interpreting this data for defining clinically useful information is that multiple different changes may be responsible for the onset of a disease, as exemplified by the efforts of The Cancer Genome Atlas project. Hence, there is a need to develop methodology able to analyse different changes in high-dimensional data containing categorical and longitudinal continuous data in order to identify prognostic, diagnostic and therapeutic targets, e.g., to solve the task of classification of diseased/healthy patients, particularly for early diagnosis.In collaboration with Professor Zaikin the team developed a methodology for representation of serial data containing categorical and continuous parameters in the form of networks, the longitudinal analysis of network dynamics, and hence, the construction of longitudinal network biomarkers, generating diagnostic, prognostic and drugable targets. Using this very universal methodology the team could represent multidimensional data of one patient in the form of a network or graph, even if apriori no links between biomarkers are established.
The team achieved the following methodological results: (1) New longitudinal multimarker models; (2) New network analysis approaches, based on synolitic networks; (3) Applied obtained expertise in Graph-based biomarkers to other diseases; (4) Applied obtained expertise to develop approaches to study a human body as a supernetwork of networks
The developed approaches potentially enable earlier detection of cancer (and or other diseases), and, hence, significant reduction of mortality. From methodological point of view, synolitic networks allow us to represent multiple markers of one patient in the form of a network, and, hence, identify hidden topological changes and assigned to them network onco-marker.
REC name
London - Bloomsbury Research Ethics Committee
REC reference
20/LO/0449
Date of REC Opinion
17 Apr 2020
REC opinion
Favourable Opinion