Home   >   Demonstrators   >   DELFOS

DELFOS

Demonstrator|vrain

Description
Software platform for the identification of DNA variations relevant to genetic diagnostics
Member
Address
Camino de Vera S/N
Province
Valencia

DEMONSTRATOR INFORMATION

DESCRIPTION

The SILE method was developed within the PROS centre to support the complex process of Selection, Identification, Loading and Exploitation of variations relevant to genetic diagnosis. The Delphi platform provides technological support to the SILE method through four modules (Hermes, Ulysses, Delphi and Sibyl), all of them connected by the Conceptual Scheme of the Human Genome. Hermes supports the selection, extraction and integration of data from different repositories, Ulysses is the algorithm in charge of identifying the relevant variations, Delphi is the database where the generated knowledge is stored, and Sibyl is the interface that allows the exploration of the data stored in Delphi. Hermes and Ulysses are currently under development and the prototype consists of a series of libraries implemented in R that facilitate the extraction, integration and classification of variations. Delphi is a relational database with a web interface that allows the loading of the variations identified with Hermes and Ulysses. Sibila is the most advanced prototype, and consists of a web interface that allows the exploration of the knowledge stored in Delphi.

POSSIBILITIES

- Upload variations to the database (requires registration). - Exploration of currently stored variations.

TECHNOLOGICAL ENABLER

Artificial Intelligence and Computing
Responsible AI

Explainable AI in the Life Sciences Understanding and manipulating the genome implies understanding and manipulating life as we perceive it on our planet. This major challenge has implications for everything related to health. This line of work aims to develop platforms that are able to search, identify, retrieve and interpret relevant genomic information. This information must be obtained from constantly growing repositories, with immense volumes of data in which machine learning techniques are indispensable to select the information of value in a context of clinical diagnosis and preventive treatment that integrates genomic knowledge into medical practice as we understand it. Integrating conventional clinical information with genomic information in an AI setting is essential to develop viable and reliable precision medicine. The application of AI techniques is essential to interpret the chaos of genomic data being generated in order to determine which data are clinically relevant.