arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.11259q-bio.BMcond-mat.stat-mechcs.LG
收藏

通过Boltzmann机的参数减少的稀疏生成建模:应用于蛋白质序列家族

Sparse generative modeling via parameter-reduction of Boltzmann machines: application to protein-sequence families

Universität Basel(巴塞尔大学);Swiss Institute of Bioinformatics(瑞士生物信息学研究所);Politecnico di Torino(都灵理工大学);Italian Institute for Genomic Medicine(意大利基因组医学研究所);Sorbonne Université(索邦大学);Université PSL(巴黎文理研究大学)

Pierre Barrat-Charlaix, Anna Paola Muntoni, Kai Shimagaki, Martin Weigt, Francesco Zamponi

摘要:

玻尔兹曼机(BM)被广泛用作生成模型。例如,成对Potts模型(PM),其是BM类的实例,提供进化相关的蛋白质序列家族的精确统计模型。它们的参数是局部场,它描述了氨基酸保守的位点特异性模式,以及两个位点的耦合,它反映了位点对之间的共同进化。这种协同进化反映了进化过程中作用于蛋白质序列的结构和功能限制。描述共同进化信号的最保守的选择是将所有可能的两位点耦合都包括在PM中。这种选择,典型的被称为直接偶联分析,已成功地预测三维结构中的残基接触,突变效应,并产生新的功能序列。然而,由此产生的PM遭受重要的过拟合效应:许多耦合是小的,嘈杂的,几乎无法解释的PM接近临界点,这意味着它是高度敏感的小参数扰动。在这项工作中,我们介绍了一个一般的参数减少过程BM,通过控制迭代抽取的统计意义不大的耦合,确定了一个基于信息的标准,选择弱或统计不支持的耦合。对于几个蛋白质家族,我们的程序允许一个删除超过$90\%$的PM耦合,同时保留了原始的密集PM的预测和生成特性,所得到的模型是远离临界,因此更强大的噪音。

英文摘要:

Boltzmann machines (BM) are widely used as generative models. For example, pairwise Potts models (PM), which are instances of the BM class, provide accurate statistical models of families of evolutionarily related protein sequences. Their parameters are the local fields, which describe site-specific patterns of amino-acid conservation, and the two-site couplings, which mirror the coevolution between pairs of sites. This coevolution reflects structural and functional constraints acting on protein sequences during evolution. The most conservative choice to describe the coevolution signal is to include all possible two-site couplings into the PM. This choice, typical of what is known as Direct Coupling Analysis, has been successful for predicting residue contacts in the three-dimensional structure, mutational effects, and in generating new functional sequences. However, the resulting PM suffers from important over-fitting effects: many couplings are small, noisy and hardly interpretable; the PM is close to a critical point, meaning that it is highly sensitive to small parameter perturbations. In this work, we introduce a general parameter-reduction procedure for BMs, via a controlled iterative decimation of the less statistically significant couplings, identified by an information-based criterion that selects either weak or statistically unsupported couplings. For several protein families, our procedure allows one to remove more than $90\%$ of the PM couplings, while preserving the predictive and generative properties of the original dense PM, and the resulting model is far away from criticality, hence more robust to noise.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑