BACKGROUND The ability to confidently predict health outcomes from gene expression would catalyze a revolution in molecular diagnostics. Yet, the goal of developing actionable, robust, and reproducible predictive signatures of phenotypes such as clinical outcome has not been attained in almost any disease area. Here, we report a comprehensive analysis spanning prediction tasks from ulcerative colitis, atopic dermatitis, diabetes, to many cancer subtypes for a total of 24 binary and multiclass prediction problems and 26 survival analysis tasks. We systematically investigate the influence of gene subsets, normalization methods and prediction algorithms. Crucially, we also explore the novel use of deep representation learning methods on large transcriptomics compendia, such as GTEx and TCGA, to boost the performance of state-of-the-art methods. The resources and findings in this work should serve as both an up-to-date reference on attainable performance, and as a benchmarking resource for further research. RESULTS Approaches that combine large numbers of genes outperformed single gene methods consistently and with a significant margin, but neither unsupervised nor semi-supervised representation learning techniques yielded consistent improvements in out-of-sample performance across datasets. Our findings suggest that using l2-regularized regression methods applied to centered log-ratio transformed transcript abundances provide the best predictive analyses overall. CONCLUSIONS Transcriptomics-based phenotype prediction benefits from proper normalization techniques and state-of-the-art regularized regression approaches. In our view, breakthrough performance is likely contingent on factors which are independent of normalization and general modeling techniques; these factors might include reduction of systematic errors in sequencing data, incorporation of other data types such as single-cell sequencing and proteomics, and improved use of prior knowledge.

中文翻译：

---

标准机器学习方法在转录组数据表型预测方面优于深度表示学习。


背景技术通过基因表达自信地预测健康结果的能力将催化分子诊断的革命。然而，几乎所有疾病领域都尚未实现开发可操作、稳健且可重复的表型预测特征（例如临床结果）的目标。在这里，我们报告了涵盖从溃疡性结肠炎、特应性皮炎、糖尿病到许多癌症亚型的预测任务的综合分析，总共 24 个二元和多类预测问题以及 26 个生存分析任务。我们系统地研究了基因子集、归一化方法和预测算法的影响。至关重要的是，我们还探索了深度表示学习方法在大型转录组学百科全书（例如 GTEx 和 TCGA）上的新用途，以提高最先进方法的性能。这项工作中的资源和研究结果应作为可达到的绩效的最新参考，并作为进一步研究的基准资源。结果结合大量基因的方法始终优于单基因方法，并且有显着的优势，但无监督或半监督表示学习技术都没有在跨数据集的样本外性能方面产生一致的改进。我们的研究结果表明，使用应用于中心对数比转换转录物丰度的 l2 正则化回归方法可以提供总体上最好的预测分析。结论基于转录组学的表型预测受益于适当的标准化技术和最先进的正则化回归方法。 我们认为，突破性的表现可能取决于独立于标准化和通用建模技术的因素；这些因素可能包括减少测序数据中的系统错误、纳入其他数据类型（例如单细胞测序和蛋白质组学）以及改进对现有知识的利用。