Special Issue "Contest: Open Source Cheminformatic Tool / 9th Workshop in Chemical Information"

Quicklinks

A special issue of Challenges (ISSN 2078-1547).

Deadline for manuscript submissions: closed (30 September 2014)

Special Issue Editor

Guest Editor
Dr. Luc Patiny (Website)

Director of Chemical Information, Institute of Chemical Sciences and Engineering (ISIC), Ecole Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland
Interests: chemoinformatics; chemical information; infrastructure for chemical research; online processing and data mining

Special Issue Information

Dear Colleagues,

The journal Challenges and MDPI are sponsoring a prize of 2’000 CHF (Swiss Francs) for the winner of a contest aiming at identifying the best open source cheminformatic tool of the year. In order to enter the competition, the source code has to be available in an open source format (for instance on a platform like Github). A 1 to 2 pages paper describing the software tool should be submitted to this special issue before the 15 August 2014 and will be published in the journal Challenges after editorial review.

The winner of the contest will be invited to present his/her tool at the 9th Workshop in Chemical Information at the EPFL, Lausanne, Switzerland on 12 September 2014 (see the preliminary program here), where the prize will also be awarded.

Dr. Luc Patiny
Guest Editor and organizer of the Workshop

Submission

The short papers should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form for the journal Challenges. The short papers can be submitted until the deadline. Papers will be published continuously (as soon as accepted) and will be listed together on this special issue website.

A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Challenges is an international peer-reviewed Open Access biannual journal published by MDPI.

Page charges are fully waived for the short papers submitted to this contest special issue.

Published Papers (4 papers)

View options order results:
result details:
Displaying articles 1-4
Export citation of selected articles as:

Research

Jump to: Other

Open AccessCommunication An Evolutionary Optimizer of libsvm Models
Challenges 2014, 5(2), 450-472; doi:10.3390/challe5020450
Received: 1 September 2014 / Revised: 27 October 2014 / Accepted: 29 October 2014 / Published: 24 November 2014
Cited by 7 | PDF Full-text (347 KB) | HTML Full-text | XML Full-text
Abstract
This user guide describes the rationale behind, and the modus operandi of a Unix script-driven package for evolutionary searching of optimal Support Vector Machine model parameters as computed by the libsvm package, leading to support vector machine models of maximal predictive power [...] Read more.
This user guide describes the rationale behind, and the modus operandi of a Unix script-driven package for evolutionary searching of optimal Support Vector Machine model parameters as computed by the libsvm package, leading to support vector machine models of maximal predictive power and robustness. Unlike common libsvm parameterizing engines, the current distribution includes the key choice of best-suited sets of attributes/descriptors, in addition to the classical libsvm operational parameters (kernel choice, kernel parameters, cost, and so forth), allowing a unified search in an enlarged problem space. It relies on an aggressive, repeated cross-validation scheme to ensure a rigorous assessment of model quality. Primarily designed for chemoinformatics applications, it also supports the inclusion of decoy instances, for which the explained property (bioactivity) is, strictly speaking, unknown but presumably “inactive”, thus additionally testing the robustness of a model to noise. The package was developed with parallel computing in mind, supporting execution on both multi-core workstations as well as compute cluster environments. It can be downloaded from http://infochim.u-strasbg.fr/spip.php?rubrique178. Full article
Open AccessCommunication ChEMBL Beaker: A Lightweight Web Framework Providing Robust and Extensible Cheminformatics Services
Challenges 2014, 5(2), 444-449; doi:10.3390/challe5020444
Received: 18 August 2014 / Revised: 29 October 2014 / Accepted: 5 November 2014 / Published: 17 November 2014
Cited by 2 | PDF Full-text (184 KB) | HTML Full-text | XML Full-text
Abstract ChEMBL Beaker is an open source web framework, exposing a versatile chemistry-focused API (Application Programming Interface) to support the development of new cheminformatics applications. This paper describes the current functionality offered by Beaker and outlines the future technology roadmap. Full article
Open AccessCommunication MyChEMBL: A Virtual Platform for Distributing Cheminformatics Tools and Open Data
Challenges 2014, 5(2), 334-337; doi:10.3390/challe5020334
Received: 14 August 2014 / Revised: 22 September 2014 / Accepted: 24 September 2014 / Published: 29 September 2014
Cited by 4 | PDF Full-text (177 KB) | HTML Full-text | XML Full-text
Abstract
MyChEMBL is an open virtual platform which provides a free, secure, standardised and easy to use chemoinformatics environment for bioactivity data mining, machine learning, application development, learning and teaching. The main technical features of myChEMBL along with its applications and future plans [...] Read more.
MyChEMBL is an open virtual platform which provides a free, secure, standardised and easy to use chemoinformatics environment for bioactivity data mining, machine learning, application development, learning and teaching. The main technical features of myChEMBL along with its applications and future plans are discussed here. Full article

Other

Jump to: Research

Open AccessTechnical Note jsGraph and jsNMR—Advanced Scientific Charting
Challenges 2014, 5(2), 294-295; doi:10.3390/challe5020294
Received: 1 September 2014 / Revised: 9 September 2014 / Accepted: 9 September 2014 / Published: 18 September 2014
Cited by 1 | PDF Full-text (148 KB) | HTML Full-text | XML Full-text
Abstract
The jsGraph library is a versatile javascript library that allows advanced charting to be rendered interactively in web browsers without relying on server-side image processing. jsGraph is released under the MIT license and is free of charge. While being highly customizable through [...] Read more.
The jsGraph library is a versatile javascript library that allows advanced charting to be rendered interactively in web browsers without relying on server-side image processing. jsGraph is released under the MIT license and is free of charge. While being highly customizable through an intuitive javascript API, jsGraph is optimized to render a large quantity of data in a short amount of time. jsGraphs can display line, scatter, contour or zone series. Examples can be consulted on the project home page [1]. Customization of the chart, its axis and its series is achieved through simple but comprehensive JSON configurations. Full article

Journal Contact

MDPI AG
Challenges Editorial Office
St. Alban-Anlage 66, 4052 Basel, Switzerland
challenges@mdpi.com
Tel. +41 61 683 77 34
Fax: +41 61 302 89 18
Editorial Board
Contact Details Submit to Challenges
Back to Top