Centre for Genomics Research, Discovery Sciences, BioPharmaceuticals R&D, AstraZeneca, 1 Francis Crick Avenue, CB2 0RE Cambridge, UK.
Am J Hum Genet. 2020 May 7;106(5):659-678. doi: 10.1016/j.ajhg.2020.03.012.
Access to large-scale genomics datasets has increased the utility of hypothesis-free genome-wide analyses. However, gene signals are often insufficiently powered to reach experiment-wide significance, triggering a process of laborious triaging of genomic-association-study results. We introduce mantis-ml, a multi-dimensional, multi-step machine-learning framework that allows objective assessment of the biological relevance of genes to disease studies. Mantis-ml is an automated machine-learning framework that follows a multi-model approach of stochastic semi-supervised learning to rank disease-associated genes through iterative learning sessions on random balanced datasets across the protein-coding exome. When applied to a range of human diseases, including chronic kidney disease (CKD), epilepsy, and amyotrophic lateral sclerosis (ALS), mantis-ml achieved an average area under curve (AUC) prediction performance of 0.81-0.89. Critically, to prove its value as a tool that can be used to interpret exome-wide association studies, we overlapped mantis-ml predictions with data from published cohort-level association studies. We found a statistically significant enrichment of high mantis-ml predictions among the highest-ranked genes from hypothesis-free cohort-level statistics, indicating a substantial improvement over the performance of current state-of-the-art methods and pointing to the capture of true prioritization signals for disease-associated genes. Finally, we introduce a generic mantis-ml score (GMS) trained with over 1,200 features as a generic-disease-likelihood estimator, outperforming published gene-level scores. In addition to our tool, we provide a gene prioritization atlas that includes mantis-ml's predictions across ten disease areas and empowers researchers to interactively navigate through the gene-triaging framework. Mantis-ml is an intuitive tool that supports the objective triaging of large-scale genomic discovery studies and enhances our understanding of complex genotype-phenotype associations.
大规模基因组数据集的获取增加了无假设全基因组分析的实用性。然而，基因信号通常不足以达到全实验范围的显著性，从而引发了对基因组关联研究结果进行繁琐分类的过程。我们引入了 mantis-ml，这是一个多维、多步骤的机器学习框架，允许客观评估基因与疾病研究的生物学相关性。mantis-ml 是一个自动化的机器学习框架，它采用随机半监督学习的多模型方法，通过在蛋白质编码外显子的随机平衡数据集中进行迭代学习会议，对疾病相关基因进行排名。当应用于一系列人类疾病，包括慢性肾脏病 (CKD)、癫痫和肌萎缩性侧索硬化症 (ALS) 时，mantis-ml 实现了 0.81-0.89 的平均曲线下面积 (AUC) 预测性能。至关重要的是，为了证明它作为一种可用于解释外显子全关联研究的工具的价值，我们将 mantis-ml 的预测与已发表的队列水平关联研究的数据重叠。我们发现，在无假设的队列水平统计中排名最高的基因中，高 mantis-ml 预测的显著富集，这表明它的性能明显优于当前最先进的方法，并指出了对疾病相关基因的真正优先级信号的捕获。最后，我们引入了一个基于超过 1200 个特征训练的通用 mantis-ml 分数 (GMS)，作为通用疾病可能性估计器，其性能优于已发表的基因分数。除了我们的工具，我们还提供了一个基因优先级图谱，其中包括 mantis-ml 在十个疾病领域的预测，使研究人员能够交互式地浏览基因分类框架。mantis-ml 是一个直观的工具，支持大规模基因组发现研究的客观分类，并增强了我们对复杂基因型-表型关联的理解。
