Prediction of cardiotoxicity of drugs
We recommend that the first time users should load the WSDL file above
to SoapUI and investigate the Web Service operations in that environment.
SoapUI is a desktop application for inspecting, invoking, developing and
functional/load/compliance testing of Web Services over HTTP. It can be
downloaded free of charge from http://www.soapui.org/
Examples of client side scripts using the service
test_herg.pl (2.6 KB)
This script runs the hERG 1.0c.ws0 Web Service. It requires no input; to be used for testing in the EMBRACE WS Registry.
example.smi (269 B)
herg.pl (2.9 KB)
This script runs the hERG 1.0c.ws0 Web Service. It reads a SMI file from STDIN and produces the predictions in a simple text table.
xml-compile.pl (1.9 KB)
||Peter Fischer Hallin
Helper scripts used to initiate XML::Compile's proxys (WSDL+XSD)
# download the required scripts
perl herg.pl [-s] < example.smi
This Web Service implements hERG 1.0. It predicts cardiotoxicity of drug
molecules. The method is described in detail in the following article:
hERG Classification Model Based on a Combination of Support Vector Machine
Method and GRIND Descriptors.
Li Q, Joergensen FS, Oprea T, Brunak S, Taboureau O.
Mol Pharm: 4;5:117-127, 2008.
Alongside this Web Service the hERG method is also implemented as
a traditional paste-and-click WWW server at:
The traditional server offers extended functionality and comprehensive
documentation. It is suitable for close investigation of few molecules;
this service is recommended for high throughput projects.
The main output data type 'anndata' is reused from biological sequence
analysis where it normally contains protein or nucleotide sequences annotations.
This Web Service, however, is about molecules, not sequences. Therefore,
the names of the tags e.g. 'sequence' might seem misleading. We have
chosen to reuse some data types anyway as they have proved very versatile.
WEB SERVICE OPERATION
This Web Service is fully asynchronous; the usage is split into the
following three operations:
Input: The following parameters and data:
* sort sort the output by predicted cardiotoxicity
(no value, just presence/absence);
* moleculedata mulitple elements of type 'molecule':
* molecule answers to one molecule:
* id unique identifier for the molecule
* comment optional comment (ignored by this service)
* smiles molecule description string in SMI format
Output: Unique job identifier
Input: Unique job identifier
Output: 'jobstatus' - the status of the job
Possible values are QUEUED, ACTIVE, FINISHED, WAITING,
REJECTED, UNKNOWN JOBID or QUEUE DOWN
Input: Unique job identifier of a FINISHED job
Output: * 'annsource'
'method' name of the method, here always 'hERG';
'version' version of the method: here always 1.0c;
'ann' annotations - one element per input molecule
'sequence' standard sequence object (reused for molecules)
'id' molecule identifier
'feature' feature name, here always 'hERG';
'global' always present, indicates the whole molecule
'key' here always: main
'value' score value
'comment' answer: high, low or '-'
Questions concerning the scientific aspects of the hERG method should
go to Olivier Taboureau, firstname.lastname@example.org; technical questions concerning
the Web Service should go to Edita Bartaseviciute, email@example.com or
Kristoffer Rapacki, firstname.lastname@example.org.