Background

Noncoding sequences have been demonstrated to possess regulatory functions. Its classification is challenging because they do not show well-defined nucleotide patterns that can correlate with their biological functions. Genomic signal processing techniques like Fourier transform have been employed to characterize coding and noncoding sequences. This transformation in a systematic whole-genome noncoding library, such as the ENCODE database, can provide evidence of a periodic behaviour in the noncoding sequences that correlates with their regulatory functions.

Objective

The objective of this study was to classify different noncoding regulatory regions through their frequency spectra.

Methods

We computed machine learning algorithms to classify the noncoding regulatory sequences frequency spectra.

Results

The sequences from different regulatory regions, cell lines, and chromosomes possessed distinct frequency spectra, and that machine learning classifiers (such as those of the support vector machine type) could successfully discriminate among regulatory regions, thus correlating the frequency spectra with their biological functions

Conclusion

Our work supports the idea that there are patterns in the noncoding sequences of the genome.

中文翻译：

---

非编码人类基因组序列的频谱表征。

背景

非编码序列已被证明具有调节功能。它的分类具有挑战性，因为它们没有显示出与其生物学功能相关的明确定义的核苷酸模式。像傅立叶变换这样的基因组信号处理技术已被用来表征编码和非编码序列。在系统的全基因组非编码库（例如 ENCODE 数据库）中的这种转换可以提供非编码序列中与其调节功能相关的周期性行为的证据。

客观的

本研究的目的是通过频谱对不同的非编码调控区域进行分类。

方法

我们计算了机器学习算法来对非编码调节序列频谱进行分类。

结果

来自不同调控区域、细胞系和染色体的序列具有不同的频谱，机器学习分类器（例如支持向量机类型的分类器）可以成功区分调控区域，从而将频谱与其生物学功能相关联

结论

我们的工作支持基因组的非编码序列中存在模式的想法。