Prediction of disease-free survival for precision medicine using cooperative learning on multi-omic data.

In precision medicine, both predicting the disease susceptibility of an individual and forecasting its disease-free survival are areas of key research. Besides the classical epidemiological predictor variables, data from multiple (omic) platforms are increasingly available. To integrate this wealth of information, we propose new methodology to combine both cooperative learning, a recent approach to leverage the predictive power of several datasets, and polygenic hazard score models. Polygenic hazard score models provide a practitioner with a more differentiated view of the predicted disease-free survival than the one given by merely a point estimate, for instance computed with a polygenic risk score. Our aim is to leverage the advantages of cooperative learning for the computation of polygenic hazard score models via Cox's proportional hazard model, thereby improving the prediction of the disease-free survival. In our experimental study, we apply our methodology to forecast the disease-free survival for Alzheimer's disease (AD) using three layers of data. One layer contains epidemiological variables such as sex, APOE (apolipoprotein E, a genetic risk factor for AD) status and 10 leading principal components. Another layer contains selected genomic loci, and the last layer contains methylation data for selected CpG sites. We demonstrate that the survival curves computed via cooperative learning yield an AUC of around $0.7$, above the state-of-the-art performance of its competitors. Importantly, the proposed methodology returns (1) a linear score that can be easily interpreted (in contrast to machine learning approaches), and (2) a weighting of the predictive power of the involved data layers, allowing for an assessment of the importance of each omic (or other) platform. Similarly to polygenic hazard score models, our methodology also allows one to compute individual survival curves for each patient.

Inhibition of Cyp1a Protects Mice against Anthracycline Cardiomyopathy.

Background: Anthracyclines such as doxorubicin (Dox) are highly effective anti-tumor agents, but their use is limited by dose-dependent cardiomyopathy and heart failure. Our laboratory previously reported that induction of cytochrome P450 family 1 (Cyp1) enzymes contributes to acute Dox cardiotoxicity in zebrafish and in mice, and that potent Cyp1 inhibitors prevent cardiotoxicity. However, the role of Cyp1 enzymes in chronic Dox cardiomyopathy, as well as the mechanisms underlying cardioprotection associated with Cyp1 inhibition, have not been fully elucidated. Methods: The Cyp1 pathway was evaluated using a small molecule Cyp1 inhibitor in wild-type (WT) mice, or Cyp1-null mice ( Cyp1a1/1a2 -/- , Cyp1b1 -/- , and Cyp1a1/1a2/1b1 -/- ). Low-dose Dox was administered by serial intraperitoneal or intravenous injections, respectively. Expression of Cyp1 isoforms was measured by RT-qPCR, and myocardial tissue was isolated from the left ventricle for RNA sequencing. Cardiac function was evaluated by transthoracic echocardiography. Results: In WT mice, Dox treatment was associated with a decrease in Cyp1a2 and increase in Cyp1b1 expression in the heart and in the liver. Co-treatment of WT mice with Dox and the novel Cyp1 inhibitor YW-130 protected against cardiac dysfunction compared to Dox treatment alone. Cyp1a1/1a2 -/- and Cyp1a1/1a2/1b1 -/- mice were protected from Dox cardiomyopathy compared to WT mice. Male, but not female, Cyp1b1 -/- mice had increased cardiac dysfunction following Dox treatment compared to WT mice. RNA sequencing of myocardial tissue showed upregulation of Fundc1 and downregulation of Ccl21c in Cyp1a1/1a2 -/- mice treated with Dox, implicating changes in mitophagy and chemokine-mediated inflammation as possible mechanisms of Cyp1a-mediated cardioprotection. Conclusions: Taken together, this study highlights the potential therapeutic value of Cyp1a inhibition in mitigating anthracycline cardiomyopathy.

Tissue-Specific Human Extracellular Matrix Scaffolds Promote Pancreatic Tumour Progression and Chemotherapy Resistance.

Over 80% of patients with pancreatic ductal adenocarcinoma (PDAC) are diagnosed at a late stage and are locally advanced or with concurrent metastases. The aggressive phenotype and relative chemo- and radiotherapeutic resistance of PDAC is thought to be mediated largely by its prominent stroma, which is supported by an extracellular matrix (ECM). Therefore, we investigated the impact of tissue-matched human ECM in driving PDAC and the role of the ECM in promoting chemotherapy resistance. Decellularized human pancreata and livers were recellularized with PANC-1 and MIA PaCa-2 (PDAC cell lines), as well as PK-1 cells (liver-derived metastatic PDAC cell line). PANC-1 cells migrated into the pancreatic scaffolds, MIA PaCa-2 cells were able to migrate into both scaffolds, whereas PK-1 cells were able to migrate into the liver scaffolds only. These differences were supported by significant deregulations in gene and protein expression between the pancreas scaffolds, liver scaffolds, and 2D culture. Moreover, these cell lines were significantly more resistant to gemcitabine and doxorubicin chemotherapy treatments in the 3D models compared to 2D cultures, even after confirmed uptake by confocal microscopy. These results suggest that tissue-specific ECM provides the preserved native cues for primary and metastatic PDAC cells necessary for a more reliable in vitro cell culture.