APF2: an improved ensemble method for pharmacogenomic variant effect prediction.

Lack of efficacy or adverse drug response are common phenomena in pharmacological therapy causing considerable morbidity and mortality. It is estimated that 20-30% of this variability in drug response stems from variations in genes encoding drug targets or factors involved in drug disposition. Leveraging such pharmacogenomic information for the preemptive identification of patients who would benefit from dose adjustments or alternative medications thus constitutes an important frontier of precision medicine. Computational methods can be used to predict the functional effects of variant of unknown significance. However, their performance on pharmacogenomic variant data has been lackluster. To overcome this limitation, we previously developed an ensemble classifier, termed APF, specifically designed for pharmacogenomic variant prediction. Here, we aimed to further improve predictions by leveraging recent key advances in the prediction of protein folding based on deep neural networks. Benchmarking of 28 variant effect predictors on 530 pharmacogenetic missense variants revealed that structural predictions using AlphaMissense were most specific, whereas APF exhibited the most balanced performance. We then developed a new tool, APF2, by optimizing algorithm parametrization of the top performing algorithms for pharmacogenomic variations and aggregating their predictions into a unified ensemble score. Importantly, APF2 provides quantitative variant effect estimates that correlate well with experimental results (R2 = 0.91, p = 0.003) and predicts the functional impact of pharmacogenomic variants with higher accuracy than previous methods, particularly for clinically relevant variations with actionable pharmacogenomic guidelines. We furthermore demonstrate better performance (92% accuracy) on an independent test set of 146 variants across 61 pharmacogenes not used for model training or validation. Application of APF2 to population-scale sequencing data from over 800,000 individuals revealed drastic ethnogeographic differences with important implications for pharmacotherapy. We thus think that APF2 holds the potential to improve the translation of genetic information into pharmacogenetic recommendations, thereby facilitating the use of Next-Generation Sequencing data for stratified medicine.

Translating pharmacogenomic sequencing data into drug response predictions-How to interpret variants of unknown significance.

The rapid development of sequencing technologies during the past 20 years has provided a variety of methods and tools to interrogate human genomic variations at the population level. Pharmacogenes are well known to be highly polymorphic and a plethora of pharmacogenomic variants has been identified in population sequencing data. However, so far only a small number of these variants have been functionally characterized regarding their impact on drug efficacy and toxicity and the significance of the vast majority remains unknown. It is therefore of high importance to develop tools and frameworks to accurately infer the effects of pharmacogenomic variants and, eventually, aggregate the effect of individual variations into personalized drug response predictions. To address this challenge, we here first describe the technological advances, including sequencing methods and accompanying bioinformatic processing pipelines that have enabled reliable variant identification. Subsequently, we highlight advances in computational algorithms for pharmacogenomic variant interpretation and discuss the added value of emerging strategies, such as machine learning and the integrative use of omics techniques that have the potential to further contribute to the refinement of personalized pharmacological response predictions. Lastly, we provide an overview of experimental and clinical approaches to validate in silico predictions. We conclude that the iterative feedback between computational predictions and experimental validations is likely to rapidly improve the accuracy of pharmacogenomic prediction models, which might soon allow for an incorporation of the entire pharmacogenetic profile into personalized response predictions.

Spectral imaging enables contrast agent-free real-time ischemia monitoring in laparoscopic surgery.

Laparoscopic surgery has evolved as a key technique for cancer diagnosis and therapy. While characterization of the tissue perfusion is crucial in various procedures, such as partial nephrectomy, doing so by means of visual inspection remains highly challenging. We developed a laparoscopic real-time multispectral imaging system featuring a compact and lightweight multispectral camera and the possibility to complement the conventional surgical view of the patient with functional information at a video rate of 25 Hz. To enable contrast agent-free ischemia monitoring during laparoscopic partial nephrectomy, we phrase the problem of ischemia detection as an out-of-distribution detection problem that does not rely on data from any other patient and uses an ensemble of invertible neural networks at its core. An in-human trial demonstrates the feasibility of our approach and highlights the potential of spectral imaging combined with advanced deep learning-based analysis tools for fast, efficient, reliable, and safe functional laparoscopic imaging.

Targeted therapy of advanced parathyroid carcinoma guided by genomic and transcriptomic profiling.

Parathyroid carcinoma (PC) is an ultra-rare malignancy with a high risk of recurrence after surgery. Tumour-directed systemic treatments for PC are not established. We used whole-genome and RNA sequencing in four patients with advanced PC to identify molecular alterations that could guide clinical management. In two cases, the genomic and transcriptomic profiles provided targets for experimental therapies that resulted in biochemical response and prolonged disease stabilization: (a) immune checkpoint inhibition with pembrolizumab based on high tumour mutational burden and a single-base substitution signature associated with APOBEC (apolipoprotein B mRNA editing enzyme, catalytic polypeptide-like) overactivation; (b) multi-receptor tyrosine kinase inhibition with lenvatinib due to overexpression of FGFR1 (Fibroblast Growth Factor Receptor 1) and RET (Ret Proto-Oncogene) and, (c) later in the course of the disease, PARP (Poly(ADP-Ribose) Polymerase) inhibition with olaparib prompted by signs of defective homologous recombination DNA repair. In addition, our data provided new insights into the molecular landscape of PC with respect to the genome-wide footprints of specific mutational processes and pathogenic germline alterations. These data underscore the potential of comprehensive molecular analyses to improve care for patients with ultra-rare cancers based on insight into disease biology.

Gene expression-based prediction of pazopanib efficacy in sarcoma.

BACKGROUND: The multi-receptor tyrosine kinase inhibitor pazopanib is approved for the treatment of advanced soft-tissue sarcoma and has also shown activity in other sarcoma subtypes. However, its clinical efficacy is highly variable, and no reliable predictors exist to select patients who are likely to benefit from this drug. PATIENTS AND METHODS: We analysed the molecular profiles and clinical outcomes of patients with pazopanib-treated sarcoma enrolled in a prospective observational study by the German Cancer Consortium, DKTK MASTER, that employs whole-genome/exome sequencing and transcriptome sequencing to inform the care of young adults with advanced cancer across histology and patients with rare cancers. RESULTS: Among 109 patients with available whole-genome/exome sequencing data, there was no correlation between clinical parameters, specific genetic alterations or mutational signatures and clinical outcome. In contrast, the analysis of a subcohort of 62 patients who underwent molecular analysis before pazopanib treatment and had transcriptome sequencing data available showed that mRNA levels of NTRK3 (hazard ratio [HR] = 0.53, p = 0.021), IGF1R (HR = 1.82, p = 0.027) and KDR (HR = 0.50, p = 0.011) were independently associated with progression-free survival (PFS). Based on the expression of these receptor tyrosine kinase genes, i.e. the features NTRK3-high, IGF1R-low and KDR-high, we developed a pazopanib efficacy predictor that stratified patients into three groups with significantly different PFS (p < 0.0001). Application of the pazopanib efficacy predictor to an independent cohort of patients with pazopanib-treated sarcoma from DKTK MASTER (n = 43) confirmed its potential to separate patient groups with significantly different PFS (p = 0.02), whereas no such association was observed in patients with sarcoma from DKTK MASTER (n = 97) or The Cancer Genome Atlas sarcoma cohort (n = 256) who were not treated with pazopanib. CONCLUSION: A score based on the combined expression of NTRK3, IGF1R and KDR allows the identification of patients with sarcoma and with good, intermediate and poor outcome following pazopanib therapy and warrants prospective investigation as a predictive tool to optimise the use of this drug in the clinic.