Repository files navigation

This repository contains the official implementation of Deepred-Mt, along withinstructions for reproducing results presented in"Deepred-Mt: Deep Representation Learning for Predicting C-to-U RNA Editing in Plant Mitochondria",by A. A. Edera, I. Small, D. H. Milone, andM. V. Sanchez-Puerta.Download PDF.

In land plants, the editosome is a highly sophisticated molecular machine ableto convert post-transcriptionally cytidines into uridines (C-to-U) at highlyspecific RNA positions called editing sites. This RNA editing seems to be partially governed bycis elements, which still remain recalcitrant to characterization.

Deepred-Mt is a novel neural network able to predict C-to-U editing sites inangiosperm mitochondria. Given an RNA sequence, consisting of a centralcytidine flanked by 20 nucleotides on each side, Deepred-Mt scores howprobable its editing is.

The score is computed from complexcis elements or motifs automaticallyextracted from the flanking bases by a multi-layer convolutional neuralnetwork, whose full architecture is schematically shown below.

To submit RNA/DNA sequences for predicting their C-to-U editing sites withDeepred-Mt, use the following link:

Submit sequences

Note 1: To be able to submit, you must be logged in with a Google Account(e.g.,Gmail).

Note 2: If difficulties are experienced when submitting sequences, try touseGoogle Chrome as the web browser.

If you encounter problems when submitting sequences please reportan issue.

To install Deepred-Mt on your computer, the following dependencies must beinstalled:

• Python 3.7
• pip
• Git
• Conda

First, create and activate a new Conda environment

conda create -n deepredmt python=3.7conda activate deepredmt

Next, install Deepred-Mt from the sources

pip install -U"deepredmt @ git+https://github.com/aedera/deepredmt.git"

Once installed, Deepred-Mt can be executed on the command line to predictC-to-U editing sites from a desired FASTAfile.Hereis an example FASTA file calledseqs.fas:

deepredmt seqs.fas

This command extracts cytidines from the FASTA file to make predictions basedon their surrounding nucleotides.

The following notebooks reproduce experiments in the article.

Description	Notebook
Use Deepred-Mt on the command line to predict C-to-U editing sites from a given FASTA file
Compare the predictive performance of Deepred-Mt and state-of-the art methods for predicting editing sites
Train Deepred-Mt from scratch

The experiments reported in the manuscript used three datasets built fromtheseFASTA files, extracted from nucleotide sequences encoding mitochondrial proteins from 21 plant species. In these files, 'E' nucleotides indicateC-to-U editing sites identified by using published RNAseq data, obtained from theEuropean Nucleotide Archive.

More information on the data format is providedhere.

In our experiments, Deepred-Mt was compared to two state-of-the-art methods for predicting editingsites: PREP-Mt and PREPACT. The following figure shows precision-recall curvesobtained from the predictions of each method. Deepred-Mt achieves the highestF1 scores and the best areas under the curves (AUPRC) for two predictivescenarios: one excluding synonymous sites (dashed lines) and other includingthem (solid lines).

Contributions from anyone are welcome. You can start by adding a new entryhere.

Deepred-Mt is licensed under the MIT license. SeeLICENSE for more details.