Since protein-protein interactions (PPIs) are highly involved in most cellular processes, and many diseases are associated with aberrant PPI, inhibition of PPI are new therapeutic approaches. The discovery of PPI inhibitors that mimic natural protein chaperone structures is a promising strategy for the development of PPI inhibitors. It is obvious that the nature is three-dimensional and therefore recognizes small molecules in a complementary three-dimensional (3D)-fashion, they may be more selective for their targets (especially in PPIs) if drugs are also three-dimensional. BOC Sciences has designed a proprietary 3D mimetics PPI library to recognize small molecules in a complementary 3D-fashion.
Figure 1. The interface definition. (Renaud. N.; et al. 2021)
Library Design
3D structures of protein complexes provide essential information for deciphering biological processes at the molecular scale. The large number of PPIs offers the possibility to train deep learning models to predict their biological relevance, and 3D convolutional neural networks (CNNs)-based data mining of PPIs.
BOC Sciences has introduced a general, configurable deep learning framework for data mining PPIs using 3D CNNs
- Firstly, we map atomic and residue-level features calculated from 3D atomic coordinates of biomolecular complexes
- Then, the 3D CNN is efficiently trained using a dataset containing millions of PPIs with support for classification and regression
- In this step of ranking the docking models, the 3D structures of a given individual protein are simulated by modeling their interaction mode by generating typically tens of thousands of candidate conformations (models)
- Finally, compounds with diverse and well-developed 3D shapes are obtained
Figure 2. Classification of biological and crystal interfaces. (Renaud. N.; et al. 2021)
3D Mimetics PPI Library Characteristics
- No PAINS or toxic substances/unwanted functions: filtered by strict ‘Ro5-like’ physicochemical and most stringent in-house structural filters
- Bioactivity and safety confirmed by preclinical studies and clinical trials
- Structural diversity, medicinal activity, and cellular penetration
- Structural document, IC50, and other chemical and biological data are provided
- All compounds are continually updated
- All of these compounds with Tanimoto index ≥ 0.85
- Compound cherry-picking service is provided
What We Deliver
- Delivered within 2 weeks in any customer-preferred format
- Powders, dry films or DMSO solutions formatted in vials, 96 or 384-well plates
- All compounds have a minimum purity of 90% assessed by 1H NMR and HPLC
- Analytical data is provided
BOC Sciences provides professional, rapid and high-quality services of 3D Mimetics PPI Library design at competitive prices for global customers. Personalized and customized services of 3D Mimetics PPI Library design can satisfy any innovative scientific study demands. Our clients have direct access to our staff and prompt feedback to their inquiries. If you are interested in our services, please contact us immediately!
Reference
- Renaud. N.; et al. DeepRank: A deep learning framework for data mining 3D protein-protein interfaces. Nature Communications. 2021: 7068.
