Integrative deep models for alternative splicing.
Integrative deep models for alternative splicing.
复制标题
DOI：
10.1093/bioinformatics/btx268
复制
发表时间：
2017-07-15
期刊：
影响因子：
--
通讯作者：
Barash Y
中科院分区：
文献类型：
--
作者：
Jha A;Gazzara MR;Barash Y
测序技术的进步突出了可变剪接（AS）在增加转录组复杂性中的作用。AS的这种作用，结合异常剪接与恶性状态的关系，激发了实验和计算两个研究流。第一个涉及无数的技术，如RNA-Seq和CLIP-Seq，以确定剪接调节因子及其推定的靶点。第二个涉及概率模型，也称为剪接代码，它直接从基因组序列推断调控机制和预测剪接结果。迄今为止，这些模型仅利用表达数据。在这项工作中，我们解决了两个相关的挑战：我们可以改进以前的模型AS结果预测，我们可以整合额外的数据来源，以提高AS监管因素的预测。我们对之前的两种建模方法（贝叶斯和深度神经网络）进行了详细的比较，剖析了数据集和目标函数的混淆效应。然后，我们开发了一个新的目标函数在外显子跳跃事件中预测AS，并表明它显着提高了模型的准确性。接下来，我们开发了一个建模框架，该框架利用迁移学习来整合CLIP-Seq、敲除和过度表达实验，这些实验本身就有噪声，并且存在缺失值。使用涉及小鼠大脑，肌肉和心脏中关键剪接因子的几个数据集，我们展示了我们的新模型提供的预测改进和生物学见解。总的来说，我们提出的框架提供了一个可扩展的综合解决方案，以改善剪接代码建模，因为大量的相关基因组数据变得可用。代码和数据可在：majiq.biociphers.org/jha_et_al_2017/补充数据可在生物信息学在线。
Advancements in sequencing technologies have highlighted the role of alternative splicing (AS) in increasing transcriptome complexity. This role of AS, combined with the relation of aberrant splicing to malignant states, motivated two streams of research, experimental and computational. The first involves a myriad of techniques such as RNA-Seq and CLIP-Seq to identify splicing regulators and their putative targets. The second involves probabilistic models, also known as splicing codes, which infer regulatory mechanisms and predict splicing outcome directly from genomic sequence. To date, these models have utilized only expression data. In this work, we address two related challenges: Can we improve on previous models for AS outcome prediction and can we integrate additional sources of data to improve predictions for AS regulatory factors. We perform a detailed comparison of two previous modeling approaches, Bayesian and Deep Neural networks, dissecting the confounding effects of datasets and target functions. We then develop a new target function for AS prediction in exon skipping events and show it significantly improves model accuracy. Next, we develop a modeling framework that leverages transfer learning to incorporate CLIP-Seq, knockdown and over expression experiments, which are inherently noisy and suffer from missing values. Using several datasets involving key splice factors in mouse brain, muscle and heart we demonstrate both the prediction improvements and biological insights offered by our new models. Overall, the framework we propose offers a scalable integrative solution to improve splicing code modeling as vast amounts of relevant genomic data become available. Code and data available at: majiq.biociphers.org/jha_et_al_2017/ Supplementary data are available at Bioinformatics online.
登录
查看更多内容
DOI：
10.1093/bioinformatics/btu277
发表时间：
2014-06-15
期刊：
Bioinformatics (Oxford, England)
影响因子：
--
作者：
Leung MK;Xiong HY;Lee LJ;Frey BJ
通讯作者：
Frey BJ
影响因子：
5.8
作者：
Xiong, Hui Yuan;Barash, Yoseph;Frey, Brendan J.
通讯作者：
Frey, Brendan J.
影响因子：
64.8
作者：
Keane, Thomas M.;Goodstadt, Leo;Danecek, Petr;White, Michael A.;Wong, Kim;Yalcin, Binnaz;Heger, Andreas;Agam, Avigail;Slater, Guy;Goodson, Martin;Furlotte, Nicholas A.;Eskin, Eleazar;Nellaker, Christoffer;Whitley, Helen;Cleak, James;Janowitz, Deborah;Hernandez-Pliego, Polinka;Edwards, Andrew;Belgard, T. Grant;Oliver, Peter L.;McIntyre, Rebecca E.;Bhomra, Amarjit;Nicod, Jerome;Gan, Xiangchao;Yuan, Wei;van der Weyden, Louise;Steward, Charles A.;Bala, Sendu;Stalker, Jim;Mott, Richard;Durbin, Richard;Jackson, Ian J.;Czechanski, Anne;Guerra-Assuncao, Jose Afonso;Donahue, Leah Rae;Reinholdt, Laura G.;Payseur, Bret A.;Ponting, Chris P.;Birney, Ewan;Flint, Jonathan;Adams, David J.
通讯作者：
Adams, David J.
影响因子：
5.8
作者：
Barash, Yoseph;Blencowe, Benjamin J.;Frey, Brendan J.
通讯作者：
Frey, Brendan J.
影响因子：
64.8
作者：
Barash, Yoseph;Calarco, John A.;Frey, Brendan J.
通讯作者：
Frey, Brendan J.