pHPC account registration	pHPC user guide	pHPC services	pHPC web protal

Run MMTx on clusters

Intro: MMTx is a complex text mining software distributed from NLM. MMTx is an effort to make the MetaMap program available to biomedical researchers in a generic, configurable environment. MetaMap maps arbitrary text to concepts in the UMLS Metathesaurus; or, equivalently, it discovers Metathesaurus concepts in text. With this software, text is processed through a series of modules. First it is parsed into components including sentences, paragraphs, phrases, lexical elements and tokens. Variants are generated from the resulting phrases. Candidate concepts from the UMLS Metathesaurus are retrieved and evaluated against the phrases. The best of the candidates are organized into a final mapping in such a way as to best cover the text.

for more information regarding MMTx, please visit NLM website for MMTx.

MMTx documentation is also avaiable in HPC web portal MMTx user guide

Step 1:

a. Please read how to setup your working environment .


b. Load application environment

load mmtx environment : Include "module load mmtx/default" in the module-loading blocks in your .bashrc file.
load jdk 1.5 environment : Include "module load jdk/1.5/default" in the module-loading blocks in your .bashrc file.

c. Check your modules, Type ". .bashrc" in your terminal, and then type "module list or type "which MMTx" in your terminal again, you shall be able to see:

[testy@n137 ~]$ . .bashrc
[testy@n137 ~]$ module list
Currently Loaded Modulefiles:
   1) mmtx/default 2) jdk/1.5/default
[testy@n137 ~]$ which MMTx
/pub1/nlp/mmtx/bin/MMTx
[testy@n137 ~]$ which java
/source/jdk1.5.0_01/bin/java

#!/bin/bash

#BSUB -L /bin/bash

# here define the job environment

#BSUB -J mmtx
#BSUB -q long
#BSUB -o %J.%I.out
#BSUB -e %J.%I.err

# how many computing core for each job element (use one care for each job)
#BSUB -n 1
#BSUB -u YourEmail@partners.org
#BSUB -N

# because this NLP  job performane better with large memery, you might need to use entire
# 8GB memory of the node, this commnd let each of the job use the entirenode

#BSUB -x

# getting to the working dir
workdir=/shr/home/$USER/mmtx
cd $workdir

# copy all the datafile to local /tmp
TMP=/tmp/nlp_data
 if [ -d $TMP ]; then
 rm -rf $TMP
 fi
mkdir $TMP
scp -r /pub1/nlp/nls/mmtx/data_backup $TMP/data


#submit the single MMTx analysis
MMTx --fileName=inputexample.txt --outputFileName=myoutput.mmtx

[testy@n137 ~]$ bsub < mmtx.lsf