Dataset Information

Systematic selection of chemical fingerprint features improves the Gibbs energy prediction of biochemical reactions.

ABSTRACT:

Motivation

Accurate and wide-ranging prediction of thermodynamic parameters for biochemical reactions can facilitate deeper insights into the workings and the design of metabolic systems.

Results

Here, we introduce a machine learning method with chemical fingerprint-based features for the prediction of the Gibbs free energy of biochemical reactions. From a large pool of 2D fingerprint-based features, this method systematically selects a small number of relevant ones and uses them to construct a regularized linear model. Since a manual selection of 2D structure-based features can be a tedious and time-consuming task, requiring expert knowledge about the structure-activity relationship of chemical compounds, the systematic feature selection step in our method offers a convenient means to identify relevant 2D fingerprint-based features. By comparing our method with state-of-the-art linear regression-based methods for the standard Gibbs free energy prediction, we demonstrated that its prediction accuracy and prediction coverage are most favorable. Our results show direct evidence that a number of 2D fingerprints collectively provide useful information about the Gibbs free energy of biochemical reactions and that our systematic feature selection procedure provides a convenient way to identify them.

Availability and implementation

Our software is freely available for download at http://sfb.kaust.edu.sa/Pages/Software.aspx.

Supplementary information

Supplementary data are available at Bioinformatics online.

SUBMITTER: Alazmi M

PROVIDER: S-EPMC6662295 | biostudies-literature | 2019 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Systematic selection of chemical fingerprint features improves the Gibbs energy prediction of biochemical reactions.

Alazmi Meshari M Kuwahara Hiroyuki H Soufan Othman O Ding Lizhong L Gao Xin X

Bioinformatics (Oxford, England) 20190801 15

<h4>Motivation</h4>Accurate and wide-ranging prediction of thermodynamic parameters for biochemical reactions can facilitate deeper insights into the workings and the design of metabolic systems.<h4>Results</h4>Here, we introduce a machine learning method with chemical fingerprint-based features for the prediction of the Gibbs free energy of biochemical reactions. From a large pool of 2D fingerprint-based features, this method systematically selects a small number of relevant ones and uses them ...[more]

PMID: 30590445

Similar Datasets

Project description:BACKGROUND: One central goal of computational systems biology is the mathematical modelling of complex metabolic reaction networks. The first and most time-consuming step in the development of such models consists in the stoichiometric reconstruction of the network, i. e. compilation of all metabolites, reactions and transport processes relevant to the considered network and their assignment to the various cellular compartments. Therefore an information system is required to collect and manage data from different databases and scientific literature in order to generate a metabolic network of biochemical reactions that can be subjected to further computational analyses. RESULTS: The computer program METANNOGEN facilitates the reconstruction of metabolic networks. It uses the well-known database of biochemical reactions KEGG of biochemical reactions as primary information source from which biochemical reactions relevant to the considered network can be selected, edited and stored in a separate, user-defined database. Reactions not contained in KEGG can be entered manually into the system. To aid the decision whether or not a reaction selected from KEGG belongs to the considered network METANNOGEN contains information of SWISSPROT and ENSEMBL and provides Web links to a number of important information sources like METACYC, BRENDA, NIST, and REACTOME. If a reaction is reported to occur in more than one cellular compartment, a corresponding number of reactions is generated each referring to one specific compartment. Transport processes of metabolites are entered like chemical reactions where reactants and products have different compartment attributes. The list of compartmentalized biochemical reactions and membrane transport processes compiled by means of METANNOGEN can be exported as an SBML file for further computational analysis. METANNOGEN is highly customizable with respect to the content of the SBML output file, additional data-fields, the graphical input form, highlighting of project specific search terms and dynamically generated Web-links. CONCLUSION: METANNOGEN is a flexible tool to manage information for the design of metabolic networks. The program requires Java Runtime Environment 1.4 or higher and about 100 MB of free RAM and about 200 MB of free HD space. It does not require installation and can be directly Java-webstarted from http://3d-alignment.eu/metannogen/.

Dataset Information

Systematic selection of chemical fingerprint features improves the Gibbs energy prediction of biochemical reactions.

Motivation

Results

Availability and implementation

Supplementary information

Publications

Systematic selection of chemical fingerprint features improves the Gibbs energy prediction of biochemical reactions.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure