På den här sidan
'/%3e%3c/svg%3e)
Avhandlingar, Offentligt tryck · Engelska
Machine Learning for Predicting Cancer Endpoints from Bulk Omics Data : Generalizing Knowledge from Various Modalities Across Domains
Sören Richard Stahlschmidt (Författare), Jane Synnergren (Handledare), Göran Falkman, 1968- (Handledare), Benjamin Ulfenborg, 1985- (Handledare), Ole Christian Lingjærde (Opponent), Translational Bioinformatics (Medarbetare (Ospecificerad))
ISBN 9789198908008, URI https://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-25131, URN urn:nbn:se:his:diva-25131
Högskolan i Skövde Institutionen för biovetenskap (Utgivare), Högskolan i Skövde Forskningsmiljön Systembiologi (Utgivare)
utgivning
Skövde : University of Skövde, 2025147
Onlineresurs
Tillgänglighet utifrån medietyp
ämne
Medical and Health Sciences, Clinical Medicine, Cancer and Oncology, Medicin och hälsovetenskap, Klinisk medicin, Cancer och onkologi, Natural Sciences, Computer and Information Sciences, Bioinformatics (Computational Biology), Naturvetenskap, Data- och informationsvetenskap, Bioinformatik (beräkningsbiologi), Natural Sciences, Computer and Information Sciences, Other Computer and Information Science, Naturvetenskap, Data- och informationsvetenskap, Annan data- och informationsvetenskap, Bioinformatik, BioinformaticsAnnat bärarformat
ISBN 9789198790795 · ISBN 9789198790795 (Annat format)Sammanfattning
Cancer remains one of the leading causes of death and is a major burden on patients and healthcare systems. One difficulty for finding effective treatment and matching patients to the right treatment strategy is the complexity of tumor biology. Machine learning holds the potential to learn patterns from data generated by high-throughput technologies, such as RNA-sequencing, that can elucidate the mechanisms underlying cancers and make clinically relevant predictions. In this thesis, we investigate the modeling of cancer with machine learning approaches from different molecular perspectives. First, we review the literature on the fusion of biomedical modalities with multimodal deep neural networks. In this review, we provide a descriptive overview, propose a novel taxonomy, and identify relevant research gaps. Moreover, for models to be applicable to clinical practice, they must be robust to shifts in the distribution patients are sampled from. Such shifts can stem from differences in the underlying biology or technical variation introduced during the processing of the biological material. Therefore, in two studies, we investigate domain generalization of machine learning models trained with bulk RNA-sequencing data to predict cancer survival endpoints. First, we show that deep learning-based domain generalization methods developed on non-molecular data improve robustness to distributional shifts on molecular data. We test these methods by predicting overall and recurrence free survival of breast cancer patients with subgroup shifts between source and target domains. Next, we show that relative representations of normalized count values, such as binning or ranking of expression values within a single sample, can increase domain generalization. We test these approaches in three experiments on breast, brain, and ovarian cancer. In a final study, we show that cancer stage can be predicted from circulating microRNA data with machine learning models, providing a proof of concept for this application. Overall, the work in this thesis supports making machine learning models more applicable to clinical practice by providing empirical evidence of methods improving the modeling of cancer biology. Continuing to study domain generalization of models in clinical practice and to develop methods for robustness are highlighted as future work.
Detaljer
Medverkan och funktion
Sören Richard Stahlschmidt (Författare), Jane Synnergren (Handledare), Göran Falkman, 1968- (Handledare), Benjamin Ulfenborg, 1985- (Handledare), Ole Christian Lingjærde (Opponent), Translational Bioinformatics (Medarbetare (Ospecificerad))Anmärkning om akademisk avhandling
Diss. (sammanfattning), 2025Medverkan och funktion
Högskolan i Skövde Institutionen för biovetenskap (Utgivare), Högskolan i Skövde Forskningsmiljön Systembiologi (Utgivare)Identifikator
ISBN 9789198908008, URI https://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-25131, URN urn:nbn:se:his:diva-25131Indirekt identifierad av
ISBN 9789198790795har titel
Machine Learning for Predicting Cancer Endpoints from Bulk Omics Data : Generalizing Knowledge from Various Modalities Across Domainsutgivning
Skövde : University of Skövde, 2025omfång
147tillhörande media
http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-25131https://his.diva-portal.org/smash/get/diva2:1957293/FULLTEXT05Relaterad beskrivning eller innehåll
Värdpublikationanmärkning
- <p>Ett av fyra delarbeten (övriga se rubriken Delarbeten/List of papers):</p><p>3. Stahlschmidt, Sören Richard, Synnergren, Jane, and Giovannucci, Andrea (2025). “Relative Representations of RNA-seq Data Improve Domain Generalization of Machine Learning Models for Cancer Prognosis”. In: <em>Under Submission</em>.</p><p></p><p>Publications with low relevance:</p><p>5. Johansson, Markus, Stahlschmidt, Sören Richard, Heydarkhan-Hagvall, Sepideh, Jeppsson, Anders, Holmgren, Gustav, Sartipy, Peter, and Synnergren, Jane (2025). “Uncovering the transcriptomic landscape of cardiac hypertrophy using single-cell RNA sequencing and machine learning”. In: <em>Under Submission</em>.</p><p>6. Lyubetskaya, Anna et al. (2025). “In situ multi-modal characterization of pancreatic cancer reveals tumor cell identity as a defining factor of the surrounding microenvironment”. In: <em>Under Submission</em>.</p><p>7. Marzec-Schmidt, Katarzyna, Ghosheh, Nidal, Stahlschmidt, Sören Richard, Küppers-Munther, Barbara, Synnergren, Jane, and Ulfenborg, Benjamin (2023). “Artificial Intelligence Supports Automated Characterization of Differentiated Human Pluripotent Stem Cells”. In: <em>Stem Cells</em> 41.9, pp. 850–861. DOI:10. 1093/stmcls/sxad049. </p>
- Härtill 3 uppsatser
Annat bärarformat
ISBN 9789198790795 · ISBN 9789198790795 (Annat format)tillhörande media
http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-25131https://his.diva-portal.org/smash/get/diva2:1957293/FULLTEXT05Villkor för användning och åtkomst
gratisingår i bibliografi
kontrollnummer
q9jbkb73nm7d2kp0Resursens ID / Permalänk: https://libris.kb.se/q9jbkb73nm7d2kp0#it
Ladda ner metadata: JSON-LD · Turtle · RDF/XML · MARC21 (ISO 2709) · MARC21 (XML)