Iterative random forests to discover predictive and stable high-order interactions.
Iterative random forests to discover predictive and stable high-order interactions.
复制标题
DOI：
10.1073/pnas.1711236115
复制
发表时间：
2018-02-20
影响因子：
11.1
通讯作者：
Yu B
中科院分区：
文献类型：
--
作者：
Basu S;Kumbier K;Brown JB;Yu B
我们开发了一种预测、稳定和可解释的工具：迭代随机森林算法（iRF）。iRF发现生物分子之间的高阶相互作用，其计算代价与随机森林相同。我们通过在转录调控和选择性剪接的两个数据示例中发现生物分子之间已知的和有希望的相互作用来证明iRF的有效性，这些相互作用高达五阶和六阶。基因组学已经彻底改变了生物学，使我们能够对整个转录组、蛋白质的全基因组结合位点和许多其他分子过程进行研究。然而，个体基因组分析测量的是作为较大分子机器组成部分在体内相互作用的元素。了解这些高阶相互作用如何驱动基因表达提出了一个实质性的统计挑战。在随机森林（RFs）和随机交叉树（RITs）的基础上，通过广泛的生物学模拟，我们开发了迭代随机森林算法（iRF）。iRF训练一个特征加权的决策树集合来检测稳定的高阶相互作用，其计算代价与RF相同。我们在两个预测问题中展示了iRF在高阶相互作用发现中的效用：早期果蝇胚胎中的增强子活性和人类来源细胞系中初级转录本的选择性剪接。在果蝇中，在iRF鉴定为稳定的20个成对转录因子相互作用（在超过一半的bootstrap重复中返回）中，80%的相互作用先前已被报道为物理相互作用。此外，三阶相互作用，例如塞尔达（Zld），巨人（Gt）和扭曲（Twi）之间的相互作用，表明高阶关系是后续实验的候选对象。在人源性细胞中，iRF重新发现了H3K36me3在染色质介导的剪接调节中的核心作用，并发现了有趣的5级和6级相互作用，表明多价核小体在剪接调节中具有特定作用。通过将相互作用的顺序与识别的计算成本解耦，iRF为研究基因组生物学的分子机制开辟了额外的途径。
We developed a predictive, stable, and interpretable tool: the iterative random forest algorithm (iRF). iRF discovers high-order interactions among biomolecules with the same order of computational cost as random forests. We demonstrate the efficacy of iRF by finding known and promising interactions among biomolecules, of up to fifth and sixth order, in two data examples in transcriptional regulation and alternative splicing. Genomics has revolutionized biology, enabling the interrogation of whole transcriptomes, genome-wide binding sites for proteins, and many other molecular processes. However, individual genomic assays measure elements that interact in vivo as components of larger molecular machines. Understanding how these high-order interactions drive gene expression presents a substantial statistical challenge. Building on random forests (RFs) and random intersection trees (RITs) and through extensive, biologically inspired simulations, we developed the iterative random forest algorithm (iRF). iRF trains a feature-weighted ensemble of decision trees to detect stable, high-order interactions with the same order of computational cost as the RF. We demonstrate the utility of iRF for high-order interaction discovery in two prediction problems: enhancer activity in the early Drosophila embryo and alternative splicing of primary transcripts in human-derived cell lines. In Drosophila, among the 20 pairwise transcription factor interactions iRF identifies as stable (returned in more than half of bootstrap replicates), 80% have been previously reported as physical interactions. Moreover, third-order interactions, e.g., between Zelda (Zld), Giant (Gt), and Twist (Twi), suggest high-order relationships that are candidates for follow-up experiments. In human-derived cells, iRF rediscovered a central role of H3K36me3 in chromatin-mediated splicing regulation and identified interesting fifth- and sixth-order interactions, indicative of multivalent nucleosomes with specific roles in splicing regulation. By decoupling the order of interactions from the computational cost of identification, iRF opens additional avenues of inquiry into the molecular mechanisms underlying genome biology.
登录
查看更多内容
DOI：
10.1073/pnas.231608898
发表时间：
2002-01-22
影响因子：
11.1
作者：
Berman, BP;Nibu, Y;Eisen, MB
通讯作者：
Eisen, MB
影响因子：
9.8
作者：
Li XY;MacArthur S;Bourgon R;Nix D;Pollard DA;Iyer VN;Hechmer A;Simirenko L;Stapleton M;Luengo Hendriks CL;Chu HC;Ogawa N;Inwood W;Sementchenko V;Beaton A;Weiszmann R;Celniker SE;Knowles DW;Gingeras T;Speed TP;Eisen MB;Biggin MD
通讯作者：
Biggin MD
影响因子：
2.1
作者：
Kooperberg, C;Ruczinski, I;Hsu, L
通讯作者：
Hsu, L
影响因子：
30.8
作者：
Kolasinska-Zwierz P;Down T;Latorre I;Liu T;Liu XS;Ahringer J
通讯作者：
Ahringer J
影响因子：
8.8
作者：
Breeze CE;Paul DS;van Dongen J;Butcher LM;Ambrose JC;Barrett JE;Lowe R;Rakyan VK;Iotchkova V;Frontini M;Downes K;Ouwehand WH;Laperle J;Jacques PÉ;Bourque G;Bergmann AK;Siebert R;Vellenga E;Saeed S;Matarese F;Martens JHA;Stunnenberg HG;Teschendorff AE;Herrero J;Birney E;Dunham I;Beck S
通讯作者：
Beck S