Details

Generating dynamic large-scale systems-biology data from a knowledge graph
ID Atanasoski, Radoslav (Author), ID Curk, Tomaž (Mentor) More about this mentor... This link opens in a new window, ID Županič, Anže (Comentor)

.pdfPDF - Presentation file, Download (7,16 MB)
MD5: 41B521B886933BDBB2BAD497E0594497

Abstract
Multi-omics integration methods are hard to evaluate because benchmark datasets with a known ground truth are scarce, as real experimental data never comes with its generating mechanism attached. One way to obtain such data is to simulate a mechanistic dynamic model, which is the ground truth by construction. However, building and parameterising such models by hand is impractical at scale. This thesis presents a fully automated framework that builds and simulates an ordinary differential equation model directly from a biological knowledge graph, with no manual intervention. It parses the network from SBML, estimates kinetic parameters by combining the BRENDA and SABIO-RK databases with machine-learning predictions and principled statistical fallbacks, assembles an Antimony model, and simulates it under any stress and knockout conditions specified by the user, with a web interface that gathers the whole workflow into one place. The framework is demonstrated end-to-end on the Plant Stress Signalling network, a curated map of plant stress signalling built mainly on \emph{Arabidopsis thaliana}, where it produces a complete, simulatable model together with the multi-condition, multi-omics-style data it generates as candidate benchmark data. In this demonstration, each simulated stress recruits its own coherent, biologically recognisable and cleanly separable module, which is the property a multi-omics benchmark needs. A second finding is that making the network run turns the model into a demanding test of the network itself. The pipeline brings out points in the graph and its reference data that inspection alone misses, traces them from its own outputs, and can measure whether a refinement helps.

Language:English
Keywords:systems biology, kinetic modelling, knowledge graph, ordinary differential equations, kinetic parameter estimation, multi-omics, benchmark data
Work type:Master's thesis/paper
Organization:FRI - Faculty of Computer and Information Science
Year:2026
PID:20.500.12556/RUL-190441 This link opens in a new window
Publication date in RUL:29.10.2026
Views:66
Downloads:19
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:Slovenian
Title:Generiranje obsežnih dinamičnih podatkov sistemske biologije iz grafa znanja
Abstract:
Metode za integracijo večomskih podatkov je težko ovrednotiti, ker primanjkuje primerjalnih naborov podatkov z znanimi pravilnimi vrednostmi in odgovori. Pri pravih eksperimentalnih podatkih, molekularni mehanizem, ki jih je ustvaril, ni znan. Ena od poti do takšnih podatkov je simulacija mehanističnega dinamičnega modela, s katerim ciljno tvorimo sintetične podatke, ki izhajajo iz modela. Vendar je ročna gradnja in parametrizacija takšnih modelov v velikem obsegu nepraktična. V magistrskem delu predstavimo popolnoma avtomatizirano ogrodje, ki neposredno iz biološkega grafa znanja in brez ročnega posega zgradi in simulira model navadnih diferencialnih enačb. Ogrodje razčleni omrežje iz zapisa SBML, oceni kinetične parametre s kombinacijo podatkovnih baz BRENDA in SABIO-RK, napovedi strojnega učenja ter premišljenih statističnih nadomestkov, sestavi model v jeziku \emph{Antimony} in ga simulira pod poljubnimi stresnimi pogoji in pogoji izbitja genov, celoten potek dela pa združi v enotnem spletnem vmesniku. Delovanje ogrodja je v celoti prikazano na omrežju rastlinskega stresnega signaliziranja, osnovanega večinoma na rastlini \emph{Arabidopsis thaliana}. Ogrodje ustvari delujoč model, ki ga je mogoče simulirati, skupaj z večpogojnimi, večomiki podobnimi podatki, ki jih generira kot kandidatne primerjalne podatke. Pri tem prikazu vsak simulirani stres aktivira svoj skladen, biološko prepoznaven in jasno ločljiv modul, kar je prav lastnost, ki jo večomski primerjalni nabor potrebuje. Druga pomembna ugotovitev je, da poganjanje modela omogoča strogo preverjanje osnovnega omrežja. Cevovod izpostavi kritična mesta v grafu in njegovih referenčnih podatkih, jih locira iz lastnih izhodov ter lahko oceni, ali predlagana izboljšava modela pomaga.

Keywords:sistemska biologija, kinetično modeliranje, graf znanja, navadne diferencialne enačbe, ocena kinetičnih parametrov, večomika, primerjalni podatki

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back