Example of output
SOAP tutorial
Contact us

Welcome to MetaLocGramN

The MetaLocGramN is a method for subcellular localization prediction of Gram-negative proteins.

Example output http://iimcb.genesilico.pl/MetaLocGramN/result/775191


Magnus M, Pawlowski M, Bujnicki JM (2012) MetaLocGramN: a meta-predictor of protein subcellular localization for Gram-negative bacteria BBA - Proteins and Proteomics

Read online: http://www.sciencedirect.com/science/article/pii/S1570963912001185


2014/10/20 We highly recommend to use our service via MetaLocGramN_client (Soap client for MLGN).

The client can be downloaded from our GitHub repository.


If you want to learn more about the protein subcellular localization prediction you can find some info at http://en.wikipedia.org/wiki/Protein_subcellular_localization_prediction

Info about MetaLocGramN is also there!


Do you like python? And do you know PyPi?. PyPi is a repository of software for the Python programming language.

You can find MetaLocGramN over there!

Read more https://pypi.python.org/pypi/MetaLocGramN/0.99!

The installation is very straightforward ..
  sudo pip install MetaLocGramN
.. and a first usage could be ..
  $ ipython

  In [1]: from MetaLocGramN import *
  In [2]: run_example()
  # job_id: 1X820N
  # status: queue
  # status: primary prediction::in progress
  # status: primary prediction::in progress
  # status: primary prediction::done
  # status: consenus::done
  # status: done
  primary methods: CELLO,cytoplasmic,0.6138,0.036,0.1346,0.0612,0.1546, \
  PSLpred,extracellular,0.2,0.531, \


We have improved the SOAP server! MetaLocGramN can be invoked via SOAP (Simple Object Access Protocol), which makes it easily accessible for users from their own scripts written in their preferred languages. Check out our SOAP tutorial to learn how to use it!


Follow us on Twitter.
twitter logo


MetaLocGramN in BioCatalogue.org!
biocatalog logo

How does MetaLocGramN work?

The MetaLocGramN is a gateway to a number of primary prediction methods (various types: signal peptide, beta-barrel, transmembrane helices and subcellular localization predictors).

The MetaLocGramN integrates the primary methods and based on their outputs provides overall consensus prediction.

To make a prediction for your protein sequence use Submit or SOAP client

The dataset created to benchmark methods and train MetaLocGramN can be downloaded at dataset.fasta

How does MetaLocGramN perform?

In our benchmark, the MetaLocGramN performed better in comparison to other SCL predictive methods, since the average Matthews correlation coefficient reached 0.806 that enhanced the predictive capability by 12% (compared to PSORTb3).

Happy predictions!

Marcin Magnus,
Marcin Pawlowski,
Janusz M. Bujnicki