Peptide ADMET Prediction Service

While oral administration of peptide drugs offers significant advantages in safety and patient compliance, challenges such as poor stability, susceptibility to enzymatic degradation, and limited permeability severely restrict bioavailability. Leveraging advanced artificial intelligence technologies and an extensive peptide database, CD ComputaBio offers professional peptide ADMET prediction services to enhance the success rate of drug development.

Introduction to Peptide ADMET Prediction

The goal of peptide design is to create therapeutic molecules with specific biological activities. Therefore, comprehensively evaluating their absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties, as well as their pharmacokinetics (PK) behavior, is crucial for predicting drug efficacy and safety. With the advancement of artificial intelligence technologies and the continuous expansion of peptide databases, significant progress has been made in computational ADMET prediction, providing more accurate guidance for assessing the in vivo stability and guiding structural improvements of peptide drugs.

Fig.1 Peptide stability prediction. (Wang F, et al.; 2023)

Computational Tools for Peptide ADMET Prediction

Tool	Description	References
PEPlife	An online tool to predict the half-life of natural or modified peptides in blood, providing guidance for improving peptide drug stability.	Mathur et al. (2016)
BChemRF-CPPred	Utilizing an artificial neural network, a support vector machine, and a Gaussian process classifier to differentiate cell-penetrating peptides (CPPs) from non-CPPs, based on structure- and sequence-based descriptors extracted from PDB and FASTA formats.	Santana et al. (2021)
Multi_CycGT	A deep learning-based multimodal model for predicting the membrane permeability of cyclic peptides.	Cao et al. (2024)

Our Services

CD ComputaBio supports clients in the early stages of drug development by comprehensively evaluating the ADMET properties of peptide drugs, aiding in optimizing drug design, reducing development risks, and significantly improving development efficiency. We are capable of predicting various properties, which include, but are not limited to:

Absorption: HIA/Human intestinal absorption, Papp/Caco-2 permeability.
Distribution: VD/Volume Distribution, BBB/Blood brain barrier penetration, PPB/Plasma protein binding.
Metabolism: CYP1A2-Inhibitor, CYP1A2-Substrate, CYP3A4-Inhibitor CYP3A4-Substrate.
Excretion: CL/Clearance, T1/2/Half-life.
Toxicity: hERG blockers, DILI/Drug Induced Liver Injury, AMES (Ames mutagenicity), Carcinogenicity, Skin sensitization.

Workflow of Peptide ADMET Prediction Service

Data Collection and Preparation

Collect data such as peptide sequences, structural information, and experimental parameters, and organize the collected data into input files required by the computational model.

ADMET Property Prediction

Utilize computational models (such as support vector machines, random forests, deep learning models, etc.) to predict the absorption, distribution, metabolism, excretion, and toxicity properties of peptide drugs.

Result Analysis

Based on the scoring results predicted by the model (such as ADMET property scores, drug similarity scores, etc.), provide constructive suggestions for peptide optimization to improve their biological activity, stability, and delivery properties.

Our Advantages

Rich Database Support - Base predictions on an extensive peptide database to ensure reliability and accuracy.
Customization and Flexibility - Provide flexible solutions to meet different research objectives.
High-quality Results - Our advanced technologies and rigorous processes ensure high-quality prediction results.

Unlock the full potential of your peptide drug candidates with CD ComputaBio's ADMET prediction services. If you are interested in our peptide ADMET prediction service or have any questions, please contact us. We look forward to working with you to accelerate your peptide drug discovery and development.

References:

Wang, F.; et al. Advancing oral delivery of biologics: Machine learning predicts peptide stability in the gastrointestinal tract[J]. International Journal of Pharmaceutics. 2023, 634: 122643.
Mathur, D.; et al. PEPlife: a repository of the half-life of peptides[J]. Scientific reports. 2016, 6(1): 36617.
Santana, K.; et al. Predicting cell-penetrating peptides using machine learning algorithms and navigating in their chemical space[J]. Scientific reports. 2021, 11(1): 7628.
Cao, L.; et al. Multi_cycgt: a deep learning-based multimodal model for predicting the membrane permeability of cyclic peptides[J]. Journal of Medicinal Chemistry. 2024, 67(3): 1888-1899.

For research use only. Not intended for any clinical use.

Services

Inquiry