Shulou(Shulou.com)06/01 Report--

This article mainly introduces the use of PLEK tools, has a certain reference value, interested friends can refer to, I hope you can learn a lot after reading this article, the following let the editor take you to understand it.

In the previous article, we introduced CPC and CNCI, two software that can be used to predict lncRNA sequences. Among them, CPC based on sequence alignment has a better classification effect for species with relatively comprehensive annotation information, but the running speed is relatively slow. CNCI distinguishes coding and non-coding transcripts based on the triplet base composition of the sequence, and the effect is also good for species that lack annotation information, but when there are insertion deletions in the sequence, the classification effect becomes very poor.

In the data generated by high-throughput sequencing, there will be some sequencing errors, although the proportion is very low, but based on the assembly of such sequences to get transcripts and then to predict lncRNA, for the software CNCI, it will have a considerable impact.

In order to overcome the above problems, we need a lncRNA prediction software that runs fast and can reduce the impact of sequencing errors to a certain extent. PLEK software is developed based on this starting point. PLEK software distinguishes coding and non-coding transcripts by the kmer composition of sequences, and does not need to be compared, so it runs faster, and its performance is relatively stable because of its low probability of being affected by sequencing errors.

In this paper, the developer evaluates the impact of sequencing errors on the accuracy of each software, and the results are as follows

It can be seen that with the increase of the proportion of sequencing errors, the accuracy of CNCI decreases sharply, while the results of PLEK and CPC are relatively stable.

At the same time, the transcript data of mice were used to evaluate the accuracy of each software classification. The results are as follows.

From the perspective of protein-coded transcripts, the accuracy of CPC is the highest, and the probability of misjudgment of PLEK is the highest; from the perspective of non-coding transcripts, the accuracy of CNCI is the highest and that of phyloCSF is the highest.

Overall, the accuracy of PLEK is between CPC and CNCI, but considering the impact of sequencing errors, the advantage of PLEK will be more obvious.

In this paper, the running efficiency of each software is also compared, and the results are as follows.

You can see that PLEK runs the fastest. The source code of the software is hosted on sourceforge at the following URL

Https://sourceforge.net/projects/plek/files/

The installation method is as follows

Wget https://sourceforge.net/projects/plek/files/PLEK.1.2.tar.gztar xzvf PLEK.1.2.tar.gzcd PLEK.1.2python PLEK_setup.py

The basic usage is as follows

Python PLEK.py\-fasta transcript.fa\-out output\-thread 10

You only need to input the fasta file corresponding to the transcript. The contents of the output file output are shown below

The first column represents whether the transcript is coding or non-coding, the second column is a scoring value, a score greater than 0 is coding, a value less than zero is non-coding, and the third column is the sequence identifier in the fasta file.

The built-in svm model is called by default. If you have known mRNA and lncRNA transcripts of the species, you can also build your own model as follows

Python PLEKModelling.py\-mRNA mRNAs.fa\-lncRNA lncRNAs.fa\-prefix 20190129

After a successful run, two files with suffixes .model and .range are generated. When forecasting, you can specify the svm model through parameters, using the following

Python PLEK.py\-fasta transcript.fa\-out output\-model 20190129.model-range 20190129.range\-thread 10 Thank you for reading this article carefully. I hope the article "what's the use of PLEK tools" shared by the editor will be helpful to you? at the same time, I also hope you will support us and pay attention to the industry information channel. More related knowledge is waiting for you to learn!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.