|
|
| Identifier |
000451064 |
| Title |
A graph representation of the individual exome variation with evidence from biomedical text corpora |
| Alternative Title |
Μια γραφική αναπαράσταση των παραλλαγών των εξωνίων ατόμου με στοιχεία απο τη συλλογή βιοιατρικών κειμένων |
|
Author
|
Γιαννουλάκης, Ιωάννης
|
|
Thesis advisor
|
Ηλιόπουλος, Ιωάννης
|
|
Reviewer
|
Ποταμιάς, Γεώργιος
Καντεράκης, Αλέξανδρος
|
| Abstract |
One of the most crucial steps in clinical genetics pipelines is variant annotation and
prioritization. This step usually includes the consultancy of other databases that can shed
light on the importance of the identified genomic variation. One of the genomic data sources
with a valuable wealth of information is online BioMedical publication databases such as
PubMed. Today is debatable as to which extend modern clinical genetics pipelines involved
in Next Generation Sequencing exploit this information.
Despite the plethora of available methods for information extraction from biomedical text,
they rarely take part in the annotation/prioritization step of typical Next Generation
Sequencing pipelines. This is because existing methods are not suited for mass querying the
complete genome variation of an individual. Here we present an open tool that builds a graph
from the BioC corpus consisting of all open and extensively pre-annotated PubMed articles in
less than 10 hours. In this graph, nodes represent Articles (n=27M), Chemicals (n=350K),
Diseases (n=12K), Genes (n=37K), Mutations (n=1.1M) interconnected through 190 million
edges.The graph can be queried and explored through the Cypher language that is served
and visualized through the Neo4j graph database engine. Through this engine we can query
the entirety of variants (~50K) identified in NGS experiments in a practical timescale. The
result of this query is the intersection of the graph's mutations with those of the file that have
been given as input. The articles that contain these mutations are used for topic modeling
through Top2Vec.Through the results of topic modeling, a user can easily and flexibly
investigate all existing bibliographic evidence linking the genetic profile of the individual with
known diseases and chemical/drug interactions.
|
| Language |
English |
| Subject |
Graph database |
|
Mutations |
|
Text mining |
|
Γραφική βάση δεδομένων |
|
Εξόρυξη κειμένου |
|
Μεταλλάξεις |
| Issue date |
2022-07-29 |
| Collection
|
School/Department--School of Medicine--Department of Medicine--Post-graduate theses
|
|
|
Type of Work--Post-graduate theses
|
| Views |
292 |
A graph representation of the individual exome variation with evidence from biomedical text corpora
