Your browser does not allow JavaScript!
JavaScript is necessary for the proper functioning of this website. Please enable JavaScript or use a modern browser.
Open Science Slovenia
Open Science
DiKUL
slv
|
eng
Search
Browse
New in RUL
About RUL
In numbers
Help
Sign in
Topološki pristopi k analizi bioloških podatkov
ID
Đurđević, Marija
(
Author
),
ID
Mramor Kosta, Nežka
(
Mentor
)
More about this mentor...
,
ID
Zupan, Blaž
(
Comentor
)
PDF - Presentation file,
Download
(1,87 MB)
MD5: 6AF567A58F1135DF951891945D2F929A
PID:
20.500.12556/rul/e43a67ed-de9b-4784-853e-9e96b5d8addf
Image galllery
Abstract
Podatki o genski izraženosti rakavega tkiva imajo napovedno vrednost pri napovedovanju bolnikovega kliničnega izida. Na področju rakavih bolezni je pomembno ugotavljanje podkategorije v posamezni kategoriji raka. V magistrski nalogi smo se za reševanje tega problema odločili za implementacijo algoritmov, ki temeljijo na računski topologiji. Cilj naloge je, da z računanjem vztrajne homologije na podatkih o genski izraženosti rakavega tkiva ugotovimo nove podskupine ter poskusimo napovedovati preživetje bolnikov v skupinah. Podatki, ki smo jih analizirali, izhajajo iz podatkovne zbirke mednarodnega konzorcija za genske raziskave raka ICGC. Na omenjenih podatkih smo gradili simplicialne komplekse pri različnih resolucijah z uporabo algoritma Vietoris-Rips. Nato smo računali vztrajno homologijo in izrisovali vztrajne diagrame. Z namenom, da čim bolj natančno ločimo podkategorije raka, smo razvili metodo za računanje intervala zaupanja na vztrajnih diagramih. Na ta način smo uspešno odkrili nekaj novih podskupin ter napovedali klinični izid bolnikov. Uspeh metod smo ovrednotili na podatkih z več različnih tipov raka ter rezultate uspešno primerjali z drugimi metodami nenadzorovanega učenja.
Language:
Slovenian
Keywords:
topologija
,
topološka analiza podatkov
,
simplicialni kompleks
,
Vietoris-Rips
,
rak
,
klasifikacijske metode
,
krivulja preživetja
Work type:
Master's thesis/paper
Organization:
FRI - Faculty of Computer and Information Science
Year:
2016
PID:
20.500.12556/RUL-86016
Publication date in RUL:
04.10.2016
Views:
1677
Downloads:
398
Metadata:
Cite this work
Plain text
BibTeX
EndNote XML
EndNote/Refer
RIS
ABNT
ACM Ref
AMA
APA
Chicago 17th Author-Date
Harvard
IEEE
ISO 690
MLA
Vancouver
:
Copy citation
Share:
Secondary language
Language:
English
Title:
Topological Approach to Analyses of Omics Data
Abstract:
Genes expression is often a good indicator for prediction of patient's clinical results. In diseases such as cancer is inevitable to identify subcategories of phenotype. The goal of the Thesis is to use persistent homology on cancer tissue gene expression to identify new subgroups and try to predict the survival of patients in corresponding groups. We analyse the date from the International Consortium for Cancer Research. Simplicial complexes were built different resolutions using Vietoris-Rips algorithm. We counted the persistent homology and draw persistent diagrams. We developed a method for calculating confidence interval on persistent diagrams to precisely divide cancer subcategories. This method gave us promising results by discovering new subcategories and was accurate in prediction of patient clinical results. Results were obtained on data of different cancer types. Results were compared with different unsupervised learning methods.
Keywords:
topology
,
topological data analysis
,
simplicial complex
,
Vietoris-Rips
,
cancer
,
classification methods
,
survival curves
Similar documents
Similar works from RUL:
Similar works from other Slovenian collections:
Back