BenevolentAI, 1 Dock72 Way, 7th Floor, Brooklyn, NY, 11205, USA.
BenevolentAI, 4-6 Maple Street, Bloomsbury, London, W1T5HD, UK.
Sci Rep. 2020 Oct 26;10(1):18250. doi: 10.1038/s41598-020-74922-z.
Incorrect drug target identification is a major obstacle in drug discovery. Only 15% of drugs advance from Phase II to approval, with ineffective targets accounting for over 50% of these failures. Advances in data fusion and computational modeling have independently progressed towards addressing this issue. Here, we capitalize on both these approaches with Rosalind, a comprehensive gene prioritization method that combines heterogeneous knowledge graph construction with relational inference via tensor factorization to accurately predict disease-gene links. Rosalind demonstrates an increase in performance of 18%-50% over five comparable state-of-the-art algorithms. On historical data, Rosalind prospectively identifies 1 in 4 therapeutic relationships eventually proven true. Beyond efficacy, Rosalind is able to accurately predict clinical trial successes (75% recall at rank 200) and distinguish likely failures (74% recall at rank 200). Lastly, Rosalind predictions were experimentally tested in a patient-derived in-vitro assay for Rheumatoid arthritis (RA), which yielded 5 promising genes, one of which is unexplored in RA.
药物靶点识别错误是药物发现的主要障碍。只有 15%的药物能从二期推进到批准，其中 50%以上的失败是由于无效靶点造成的。数据融合和计算建模的进展都独立地朝着解决这个问题的方向发展。在这里，我们利用 Rosalind 来做到这一点，Rosalind 是一种综合的基因优先级排序方法，它结合了异构知识图构建和通过张量分解进行关系推理，以准确预测疾病-基因联系。Rosalind 在五项可比的最先进算法中的性能提高了 18%-50%。在历史数据上，Rosalind 前瞻性地确定了四分之一的治疗关系最终被证明是正确的。除了疗效，Rosalind 还能够准确预测临床试验的成功（在排名 200 时召回率为 75%），并区分可能的失败（在排名 200 时召回率为 74%）。最后，Rosalind 的预测在类风湿关节炎（RA）的患者来源的体外检测中进行了实验测试，得到了 5 个有前途的基因，其中一个在 RA 中尚未被探索。
