Les cancers de la prostate sont classés en deux catégories. Les cancers de haut grade se distinguent des cancers de bas grade par une plus forte agressivité et un pronostic plus mauvais. Lorsqu’ils deviennent résistants à l’hormonothérapie, les cancers de haut grade sont traités par une chimiothérapie basée sur les taxanes. Néanmoins, les taux de réponse restent faibles. Il existe donc un réel besoin quant à l'identification d'alternatives thérapeutiques qui soient spécifiques de ce type de tumeur. Dans cette optique, notre travail a été de proposer une telle alternative par une approche qui prenne en compte la génétique spécifique des cancers de haut grade. Nous avons exploité une signature de 86 gènes dont le niveau d’expression permet de discriminer entre les tumeurs de haut et de bas grade. Par une approche in silico originale utilisant la banque de données du NCI, nous avons identifié 382 corrélations entre le niveau d’expression de 50 gènes et la sensibilité à 139 agents antiprolifératifs. Parmi ces corrélations, nous avons identifié une signature de 9 gènes qui est spécifique de la réponse à l’oxaliplatine. Cette signature a été confirmée sur le plan fonctionnel dans les lignées cancéreuses prostatiques DU145 et LNCaP. Nous avons donc fourni la preuve de concept que notre approche permet d’identifier de nouvelles molécules pouvant être utilisées en alternative aux taxanes pour traiter spécifiquement les cancers de haut grade. Cette stratégie permet aussi d’identifier de nouveaux marqueurs (gènes) régulant la sensibilité à certains médicaments. Nos résultats démontrent par exemple le rôle des gènes SHMT, impliqués dans la régulation du métabolisme monocarboné, dans la sensibilité spécifique à l’oxaliplatine par un mécanisme qui fait intervenir, du moins en partie, une dérégulation du niveau de méthylation global de l’ADN. / Prostate cancers are classified in two categories. High grade cancers are distinguished from low grade cancers by their higher agressivity and worse prognostic. When they become refractory to hormone therapy, high grade cancers are treated with a taxane-based chemotherapy. However, response rates remain low. Therefore, there is a real need for the discovery of new therapeutic alternatives which are specific for this type of tumors. For that purpose, our work aimed at proposing such an alternative with a strategy that took into account the high grade genetic background. We exploited a signature of 86 genes for which expression level could distinguish between low grade and high grade tumours. With an original in silico approach, we searched the NCI databases and identified 382 correlations between 50 genes and the sensitivity to 139 antiproliferative agents. Among these, a signature of 9 genes was able to specifically predict cell response to oxaliplatin. This signature was validated at the functional level in two prostate cancer cell lines, DU145 and LNCaP. We have thus provided the proof-of-concept that our approach allows the identification of new drugs that can be used alternatively to taxanes in order to specifically treat high grade prostate cancers. This strategy also allows the identification of new markers (genes) regulating the sensitivity to various drugs. Our results demonstrate for example the implication of SHMT genes, which are involved in the regulation of the one-carbon metabolism, in the specific sensitivity to oxaliplatin, by a mechanism which involves, at least in part, the deregulation of the global level of DNA methylation.

Treating cancer is difficult as the disease is complex and drug responses often depend on the patient's characteristics. Precision medicine aims to solve this by selecting individualized treatments. Since this involves the analysis of large datasets, machine learning can be used to make the drug selection process more efficient. Traditionally, such models utilize bulk gene expression data. However, this potentially masks information from small cell populations and fails to address tumor heterogeneity. Therefore, this thesis applies data deconvolution methods to bulk gene expression data and estimates the corresponding cell type-specific gene expression profiles. This "increases" the resolution of the input data for the drug response prediction. A hold-out dataset, LODOCV and LOCOCV were used for the evaluation of this approach. Furthermore, all results are compared against a baseline model, which was trained on bulk data. Overall, the accuracy of the cell type-specific model did not show an improvement compared to the bulk model. It also prioritizes information from bulk samples, which makes the additional data unnecessary. The robustness of the cell type-specific model is slightly lower than that of the bulk model. Note, that these outcomes are not necessarily due to a flaw in the underlying concept, but may be connected to poor deconvolution results as the same reference matrix was used for the deconvolution of all bulk samples regardless of the cancer type or disease.

[pt] Prever com precisão a resposta a drogas para uma dada amostra baseado em características moleculares pode ajudar a otimizar o desenvolvimento de drogas e explicar mecanismos por trás das respostas aos tratamentos. Nessa dissertação, dois estudos de caso foram gerados, cada um aplicando diferentes dados genômicos para a previsão de resposta a drogas. O estudo de caso 1 avaliou dados de perfis de metilação de DNA como um tipo de característica molecular que se sabe ser responsável por causar tumorigênese e modular a resposta a tratamentos. Usando perfis de metilação de 987 linhagens celulares do genoma completo na base de dados Genomics of Drug Sensitivity in Cancer (GDSC), utilizamos algoritmos de aprendizado de máquina para avaliar o potencial preditivo de respostas citotóxicas para oito drogas contra o câncer. Nós comparamos a performance de cinco algoritmos de classificação e quatro algoritmos de regressão representando metodologias diversas, incluindo abordagens tree-, probability-, kernel-, ensemble- e distance-based. Aplicando sub-amostragem artificial em graus variados, essa pesquisa procura avaliar se o treinamento baseado em resultados relativamente extremos geraria melhoria no desempenho. Ao utilizar algoritmos de classificação e de regressão para prever respostas discretas ou contínuas, respectivamente, nós observamos consistentemente excelente desempenho na predição quando os conjuntos de treinamento e teste consistiam em dados de linhagens celulares. Algoritmos de classificação apresentaram melhor desempenho quando nós treinamos os modelos utilizando linhagens celulares com valores de resposta a drogas relativamente extremos, obtendo valores de area-under-the-receiver-operating-characteristic-curve de até 0,97. Os algoritmos de regressão tiveram melhor desempenho quando treinamos os modelos utilizado o intervalo completo de valores de resposta às drogas, apesar da dependência das métricas de desempenho utilizadas. O estudo de caso 2 avaliou dados de RNA-seq, dados estes comumente utilizados no estudo da eficácia de drogas. Aplicando uma abordagem de aprendizado semi-supervisionado, essa pesquisa busca avaliar o impacto da combinação de dados rotulados e não-rotulados para melhorar a predição do modelo. Usando dados rotulados de RNA-seq do genoma completo de uma média de 125 amostras de tumor AML rotuladas da base de dados Beat AML (separados por tipos de droga) e 151 amostras de tumor AML não-rotuladas na base de dados The Cancer Genome Atlas (TCGA), utilizamos uma estrutura de modelo semi-supervisionado para prever respostas citotóxicas para quatro drogas contra câncer. Modelos semi-supervisionados foram gerados, avaliando várias combinações de parâmetros e foram comparados com os algoritmos supervisionados de classificação. / [en] Accurately predicting drug responses for a given sample based on molecular features may help to optimize drug-development pipelines and explain mechanisms behind treatment responses. In this dissertation, two case studies were generated, each applying different genomic data to predict drug response. Case study 1 evaluated DNA methylation profile data as one type of molecular feature that is known to drive tumorigenesis and modulate treatment responses. Using genome-wide, DNA methylation profiles from 987 cell lines in the Genomics of Drug Sensitivity in Cancer (GDSC) database, we used machine-learning algorithms to evaluate the potential to predict cytotoxic responses for eight anti-cancer drugs. We compared the performance of five classification algorithms and four regression algorithms representing diverse methodologies, including tree-, probability-, kernel-, ensemble- and distance-based approaches. By applying artificial subsampling in varying degrees, this research aims to understand whether training based on relatively extreme outcomes would yield improved performance. When using classification or regression algorithms to predict discrete or continuous responses, respectively, we consistently observed excellent predictive performance when the training and test sets consisted of cell-line data. Classification algorithms performed best when we trained the models using cell lines with relatively extreme drug-response values, attaining area-under-the-receiver-operating-characteristic-curve values as high as 0.97. The regression algorithms performed best when we trained the models using the full range of drug-response values, although this depended on the performance metrics we used. Case study 2 evaluated RNA-seq data as one of the most popular molecular data used to study drug efficacy. By applying a semi-supervised learning approach, this research aimed to understand the impact of combining labeled and unlabeled data to improve model prediction. Using genome-wide RNA-seq labeled data from an average of 125 AML tumor samples in the Beat AML database (varying by drug type) and 151 unlabeled AML tumor samples in The Cancer Genome Atlas (TCGA) database, we used a semi-supervised model structure to predict cytotoxic responses for four anti-cancer drugs. Semi-supervised models were generated, while assessing several parameter combinations and were compared against supervised classification algorithms.