Sir Peter MacCallum Department of Oncology - Theses
Permanent URI for this collection
Search Results
1 - 2 of 2
-
ItemDefining the immune landscape in rectal cancer and its relationship to neo-adjuvant chemoradiotherapy and immunotherapy responses( 2023-07)Colorectal cancer (CRC) is the second leading cause of cancer-related mortality worldwide. Approximately 25% of these tumours are in the rectum. Rectal cancers that are locally advanced or have poor prognostic features on staging are typically treated with neo-adjuvant chemoradiotherapy prior to surgical resection. However, despite intensive efforts to improve the response rates to neo-adjuvant therapy, most patients do not achieve a complete pathological response. Patients that do achieve a complete response to neo-adjuvant therapy may be candidates for organ preservation. There has been limited progress in identifying treatment protocols with improved therapeutic efficiency, or in extending the treatment options for patients that have an incomplete response. Additional complexity is added by the inability to accurately identify which patients will respond to treatment, and deficiencies in understanding the mechanisms that drive treatment response. This thesis focuses on first reviewing the novel treatment options that have been investigated for patients with rectal cancer to date and assessing the ongoing inclination of surgeons to pursue novel therapies for their patients. Additionally personalised tumour models (tumouroids) and differentially expressed genes were assessed for the utility in predicting which patients are likely to respond to neo-adjuvant therapy. There has been recent attention on the ability of immune checkpoint blockade inhibitors to “rescue” cytotoxic mediated immune responses and extend treatment responses for patients with tumours including melanoma, non-small cell lung carcinoma and renal cell carcinoma. The use of these agents in the setting of neo-adjuvant therapy for rectal cancer remains undefined. Thus, a phase II clinical trial was established to assess the role of immune checkpoint blockade inhibition in the neo-adjuvant setting for rectal cancer, with a particular focus on the effect of this therapy on tumour response and the tumour immune landscape. Finally, the tumour microenvironment has an accepted and essential role in response to neo-adjuvant therapy. However, newly identified cells and cellular structures such as tissue resident memory cells and tertiary lymphoid structures are altering our understanding of anti-tumour immunity but remain under investigated in the setting of rectal cancer. To address this deficiency multiplex immunohistochemistry was employed to define the immune landscape of patients receiving both chemoradiotherapy and immune checkpoint blockade inhibition, with a particular focus on cell types previously under appreciated. Defining the immune landscape of these tumours in such a manner may allow a deeper understanding of the mechanisms driving therapy response and facilitate targeted patient therapy.
-
ItemAutomated discovery of interacting genomic events that impact cancer survival by using data mining and machine learning techniques( 2020)Rapid advancement in genomic technologies has driven down the cost of sequencing significantly. This efficiency has enabled large-scale cancer genomic studies to be conducted, generating a vast amount of data across different levels of omics variables. However, the tasks to extract new knowledge and information from this enormous volume of data present unique challenges. These analyses often require the application of specialised techniques for data mining, integration and interpretation to provide valuable insights. With the rise of machine learning adoption in recent decades, many advanced computational algorithms based on artificial intelligence techniques have also been proposed to analyse these genomics data. Although some of these applications have led to clinically relevant conclusions, many others are still relying on incomplete prior knowledge, or limited to only a selected number of features. These limitations raise the general question about the broader applicability of machine learning in the field of cancer genomics. This research addresses this question by assessing the application of machine learning techniques in the context of breast cancer genomics data. This assessment includes a comprehensive evaluation of computational methods for predicting cancer driver genes and the development of a novel deep learning approach for identifying breast cancer subtypes. The evaluation result of driver gene prediction algorithms suggests that the selection of the best method to be applied to a dataset will primarily be driven by the objectives of the study and the characteristics of the dataset. All of the evaluated approaches could identify well- studied genes, but not all of them performed as well on smaller datasets, subtype-specific cohorts, and in discovering novel genes. To examine the benefit of a more complex machine learning model, this thesis also presents a novel deep learning approach that integrates multi-omics data for predicting various breast cancer’ biomarkers and molecular subtypes. This method combines a semi-supervised autoencoder for dimensionality reduction, and a supervised multitask learning setup for the classifications. Taking an input of gene expression, somatic point mutation and copy number data, the algorithm predicts the ER-Status, HER2-Status and molecular subtypes of breast cancer samples. Further survival analysis of the outputs from this deep learning approach indicates that the predicted subtypes show a stronger correlation with patient prognosis compared to the original PAM50 label. While the outputs from machine learning algorithms still require further validation, the adoption of these complex computational methods in cancer genomics will become increasingly common. Collectively, the results from this thesis suggest that the machine learning analysis of ‘omics data hold great potential in automating the discovery of clinically- relevant molecular features.