Skip to main content

A tool to predict exosomal miRNA

Project description

EmiRPred

A computational tool for predicting exosomal and non-exosomal miRNA

Introduction

EmiRPred is a tool for the classifcation of miRNA into exosomal and non-exosomal. It uses similarity-based methods (BLAST and MERCI for motif-search) combined with Extra Tree Classifier built on the best performing compoisition-based features extracted using One hot encoding, Term Frequency - Inverse Document Frequency, and Reverse Complement RNA strand compositions. EmiRPred is also available as a web-server at https://webs.iiitd.edu.in/raghava/emirpred. Please read/cite the content about EmiRPred for complete information including algorithm behind the approach.

Import EmiRPred

import emirpred

Requirements

  • scikit-learn=1.2.2
  • Pandas
  • Numpy
  • Joblib
  • Argparse

No additional package/tool is required for model = 1 (default model), however for model = 2, please download blast (version - blast: 2.12.0+) from https://blast.ncbi.nlm.nih.gov/doc/blast-help/downloadblastdata.html

Minimum USAGE

To know about the available option for the standlone, type the following command:

emirpred -h

To run the example, type the following command:

emirpred -f example_seq.fa -o output

Here, -f argument is to enter the input file in Fasta format and -o argument is for giving the path to the output directory. By default, the package uses model (-m) = 1 which employs only ML algorithm (Extra Tree Classifier) to classify the miRNA sequences, which generates a prediction file "classification_ML.csv" in the specified output directory. If model (-m) = 2 is selected, then the hybrid model is employed (ML + MERCI + BLAST) to classify the miRNA sequences, which generates a prediction file "classification_hybrid.csv" in the specified output directory.

Full Usage

usage: emirpred [-h] --file FILE --output OUTPUT [--model MODEL] [--threshold THRESHOLD]
Please provide following arguments for successful run
required arguments:
  --file FILE, -f FILE                   Path to fasta file
  --output OUTPUT, -o OUTPUT             Path to output

optional arguments:

  --model MODEL, -m MODEL                Model selection: 1 for ML only, 2 for ML + BLAST + MERCI (By default model = 1)
  --threshold THRESHOLD, -t THRESHOLD    Threshold for classification (can be any value between 0-1 for model = 1 (by default = 0.5) and 0-2 for model = 2 (by default = 0.52))

For help:
  -h, --help            show this help message and exit

Standalone minimum usage

python3 emirpred.py -f example_seq.fa -o output

Arguments description

Input File: It allow users to provide input in FASTA format.

Output File: Program will save the results to this folder

Model: User can pick which model to run, model = 1 runs only ML model (ET classifier), whereas model = 2 runs hybrid model (ML + BLAST + MERCI), by default the tool runs model = 1

Threshold: User can provide threshold for classification (can be any value between 0-1 for model = 1 (by default = 0.5) and 0-2 for model = 2 (by default = 0.52))

EmiRPred Package Files

It contantain following files, brief description of these files given below

INSTALLATION : Installations instructions

LICENSE : License information

README.md : This file provide information about this package

emirpred_et_model.pkl : This file contains the pickled version of model

emirpred.py : Main python program

example_input.fa : Example file contain nucleotide sequences in FASTA format

blast_db : Database for BLAST search

MERCI_motif_locator.pl : To locate exosomal motifs within the query sequences

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

emirpred-1.1.1.tar.gz (1.4 MB view details)

Uploaded Source

Built Distribution

emirpred-1.1.1-py3-none-any.whl (1.5 MB view details)

Uploaded Python 3

File details

Details for the file emirpred-1.1.1.tar.gz.

File metadata

  • Download URL: emirpred-1.1.1.tar.gz
  • Upload date:
  • Size: 1.4 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.8.17

File hashes

Hashes for emirpred-1.1.1.tar.gz
Algorithm Hash digest
SHA256 fa5499b4589012b7c7cebc909c3e106046a756ece8d863743f9cb0e58dc02bb1
MD5 2427b8679921b04cb5fb1e9bd6a79d7e
BLAKE2b-256 5ffd4a9f267d0507c796657d89cffb4192030bd1beaafd8e6a0df10961ac82c0

See more details on using hashes here.

File details

Details for the file emirpred-1.1.1-py3-none-any.whl.

File metadata

  • Download URL: emirpred-1.1.1-py3-none-any.whl
  • Upload date:
  • Size: 1.5 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.8.17

File hashes

Hashes for emirpred-1.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 3d240503c8269310c8c19e8c00d951b5236cbc1bf13389fa3253e3caec783831
MD5 89904e6536e9922331fc78cb480a198c
BLAKE2b-256 c598ee8b0ac445702967d20d0bbc3f3cf3011f71744bfb02f6668e589a1b8e47

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page