Biology subjects

Koufariotis, L. T.

Publications and source records attributed to Koufariotis, L. T..

4 recordsLinked to original sources

bioRxiv2025

Explainable machine learning identifies features and thresholds predictive of immunotherapy response

BackgroundImmunotherapy has improved patient survival for multiple cancer types, including melanoma. While a variety of molecular features have been linked to response to immune checkpoint inhibitors (ICI) treatment, clinically established biomarkers, such as tumour mutation burden (TMB) and PD-L1 expression, have shown limitations in accurately categorising responders versus non-responders. Due to the complex nature of ICI response, which includes cancer intrinsic and extrinsic features within the tumour microenvironment (TME), using a single biomarker to predict response is insufficient, necessitating the need to identify accurate clinical and multi-omic molecular predictors. MethodsWe integrate clinical, DNA and RNA sequencing data from four datasets, comprising 138 melanoma patients treated with ICI, to develop machine learning models for predicting ICI response. The performance of each model was evaluated using an independent dataset of patients with cutaneous melanoma (n=53). Interactions between trained models and features were rationalised using the explainability method SHAP. ResultsThe most optimal model was the multi-omic random forest model, with AUC-ROC of 0.78 when predicting response in the independent test dataset. Using SHAP, we predicted thresholds for mutational signatures, neoantigen load, immune cell-type abundance and immune receptor LAG3 expression. The relationship between these influential features and their SHAP scores revealed numerical thresholds constituting good and poor patient response. ConclusionsThis approach highlights patient response to ICI is influenced by both cancer intrinsic and extrinsic features, as well as identifies candidate biomarkers that could inform the use of ICI and potentially assist in the selection of combination therapy in melanoma treatment.

bioinformatics↗

bioRxiv2024

Type I interferon drives a cellular state inert to TCR-stimulation and could impede effective T-cell differentiation in cancer

Head and neck squamous cell carcinoma (HNSCC) arises from the mucosal epithelium of the oral cavity, pharynx, or larynx and is linked to exposure to classical carcinogens and human papillomavirus (HPV) infection. Due to molecular, immunological, and clinical disparities between HPV+ and HPV-HNSCC, they are recognized as distinct cancer types. While immune checkpoint inhibition (ICI) has demonstrated efficacy in recurrent/metastatic HNSCC, response variability persists irrespective of HPV status. To gain insights into the CD8+ T-cell landscape of HPV-HNSCC, we performed multimodal sequencing (RNA and TCR) of CD8+ tumor-infiltrating lymphocytes (TILs) from treatment-naive HPV-HNSCC patients. Additionally, we subjected cells to ex vivo TCR-stimulation, facilitating the tracing of clonal transcriptomic responses. Our analysis revealed a subset of CD8+ TILs highly enriched for interferon-stimulated genes (ISG), which were found to be clonally related to a subset of granzyme K (GZMK)-expressing cells. Trajectory inference suggests ISG transition via GZMK cells towards terminal effector states. However, unlike GZMK cells, which rapidly an effector-like phenotype in response to TCR stimulation, ISG cells remain transcriptionally inert. Consequently, ISG cells may impede effective T-cell differentiation within the TME. Although, the functional consequences of ISG cells are poorly understood, we revealed that they possess receptors and ligands enabling cell-cell communication networks with key TME immunomodulators such as dendritic cells. Additionally, ISG cells were found to be a core feature across various tumor entities and were specifically enriched within tumor tissue. Thus, our findings illuminate the complexity of T-cell heterogeneity in HPV-HNSCC and reveal an overlooked population of IFN-stimulated CD8+ TILs. Further exploration of their functional significance may offer insights into therapeutic strategies for HPV-HNSCC and other cancer types.

immunology↗

bioRxiv2022

Generalising uncertainty improves accuracy and safety of deep learning analytics applied to oncology

Trust and transparency are critical for deploying deep learning (DL) models into the clinic. DL application poses generalisation obstacles since training/development datasets often have different data distributions to clinical/production datasets that can lead to incorrect predictions with underestimated uncertainty. To investigate this pitfall, we benchmarked one pointwise and three approximate Bayesian DL models used to predict cancer of unknown primary with three independent RNA-seq datasets covering 10,968 samples across 57 primary cancer types. Our results highlight simple and scalable Bayesian DL significantly improves the generalisation of uncertainty estimation (e.g., p-value = 0.0013 for calibration). Moreover, we demonstrate Bayesian DL substantially improves accuracy under data distributional shifts when utilising uncertainty thresholding by designing a prototypical metric that evaluates the expected (accuracy) loss when deploying models from development to production, which we call the Area between Development and Production curve (ADP). In summary, Bayesian DL is a hopeful avenue of research for generalising uncertainty, which improves performance, transparency, and therefore safety of DL models for deployment in real-world.

bioinformatics↗

bioRxiv2021

Genomic analysis of patient-derived xenograft models reveals intra-tumor heterogeneity in endometrial cancer and can predict tumor growth inhibition with talazoparib

BackgroundEndometrial cancer (EC) is a major gynecological cancer with increasing incidence. It comprised of four molecular subtypes with differing etiology, prognoses, and response to chemotherapy. In the future, clinical trials testing new single agents or combination therapies will be targeted to the molecular subtype most likely to respond. Pre-clinical models that faithfully represent the molecular subtypes of EC are urgently needed, we sought to develop and characterize a panel of novel EC patient-derived xenograft (PDX) models. MethodsHere, we report whole exome or whole genome sequencing of 11 PDX models and the matched primary tumor. Analysis of multiple PDX lineages and passages was performed to study tumor heterogeneity across lineages and/or passages. Based on recent reports of frequent defects in the homologous recombination (HR) pathway in EC, we assessed mutational signatures and HR deficiency scores and correlated these with in vivo responses to the PARP inhibitor (PARPi) talazoparib in six PDXs representing the different molecular subtypes of EC. ResultsPDX models were successfully generated from all four molecular subtypes of EC and uterine carcinosarcomas, and they recapitulated morphology and the molecular landscape of primary tumors without major genomic drift. We also observed a wide range of inter-tumor and intra-tumor heterogeneity, well captured by different PDX lineages, which could lead to different treatment responses. An in vivo response to talazoparib was detected in two p53mut models consistent with stable disease, however both lacked the HR deficiency genomic signature. ConclusionsEC PDX models represent the four molecular subtypes of disease and can capture intra-tumoral heterogeneity of the original primary tumor. PDXs of the p53mut molecular subtype showed sensitivity to PARPi, however, deeper and more durable responses will likely require combination of PARPi with other agents.

genomics↗