CzeekS is powerful software tool, developed by Kyoto Constella Technologies, for high-speed screening of compound-protein interactions using Chemical Genomics-Based Virtual Screening (CGBVS). Thanks to the CGBVS technology, active compounds can be predicted from the binding patterns obtained from the interaction (chemogenomics data) of proteins (biological space) and compounds (chemical space). A scientific paper explaning the CGBVS, with a case study, is available (published as open access) for further details:
Yabuuchi et al. “Analysis of multiple compound-protein interactions reveals novel bioactive molecules.” Molecular systems biology 7.1 (2011): 472. (LINK)
CzeekS provides a wide list of models ready to be used, and the user can build new models, or refine the existing ones, using his/her own in-house assay data. The actually available models are the following:
| Model | Target proteins | Interactions | Details (Proteins and protein groups) |
|---|---|---|---|
| GPCR | 242 | 158,405 | Class Aα, Class Aβ, Class Aδ, Class Aγ, Class B, Class C |
| Kinase | 412 | 154,079 | AGC, CAMK, CMGC, STE, TK, TKL, others |
| Ion channel | 218 | 142,282 | Voltage-gated, Ligand-gated, others |
| Transporter | 148 | 112,659 | Electrochemical, ATPase, ATP-binding cassette, others |
| Nuclear receptor | 41 | 139,051 | NR1, NR2, NR3, NR4, NR5 |
| Protease | 229 | 141,691 | Endopeptidase, Exopeptidase |
A further set of models have been recently added, the ChEMBL models – based on data obtained from ChEMBL database (Release 21) and offered for free:
| Model | Target proteins | Interactions | Details (Proteins and protein groups) |
|---|---|---|---|
| GPCR | 213 | 64,827 | Class Aα, Class Aβ, Class Aδ, Class Aγ, Class B, Class C |
| Kinase | 272 | 45,041 | AGC, CAMK, CMGC, STE, TK, TKL, others |
| Ion channel | 135 | 16,040 | Voltage-gated, Ligand-gated, others |
| Transporter | 80 | 8,491 | Electrochemical, ATPase, ATP-binding cassette, others |
| Nuclear receptor | 38 | 15,252 | NR1, NR2, NR3, NR4, NR5 |
| Protease | 180 | 27,678 | Endopeptidase, Exopeptidase |
Some of CzeekS features:
- Command line interface (cli): enables high speed and highly accurate in silico compound screening.
- Multi-target screening: scoring against multiple protein targets can be done taking compound selectivity into account.
- Search for the target protein of a particular compound: scoring against all the proteins present in a selected model can be implemented in a compound-by-compound basis, allowing the search for the target protein.
- Creation of new or refinement of existing models through the addition of client’s data: prediction models can be refined through the addition client’s assay data. Prediction accuracy of the learning model is expected to increase by the addition of client’s data.
- Line-up of various prediction models: in addition to standard models (GPCR, Kinase, Ion channel, Transporter, Nuclear receptor, Protease), models focusing on subfamilies are also included. Models can be chosen according to the client’s specific needs.
- Multi-core CPUs support (OpenMP Parallelization): running CzeekS in systems with multi-core CPUs enables much faster CGBVS calculations.
Kode Chemoinformatics is an official redistributor for CzeekS, please contact us for information on licensing and pricing of this software. Please visit the product’s page on Kyoto Constella website for further details.
This software is redistributed by Kode Chemoinformatics on behalf of Kyoto Constella Technologies.
