Sequence-based Peptide Design Service

Leveraging advanced computational biology tools and machine learning algorithms, CD ComputaBio delivers sequence-based peptide design services. We provide customized peptide engineering solutions based on client-provided target protein structures and sequence information, aiming to design peptide sequences with enhanced physicochemical properties for optimized performance in therapeutic, diagnostic, or industrial applications.

Introduction to Sequence-based Peptide Design

Compared to template-based peptide design, sequence-based peptide design emphasizes the importance of conserved sites and motifs in function and structure. By designing and modifying amino acid sequences, it optimizes properties such as peptide stability, toxicity, immunogenicity, and antibody specificity. Newly designed peptides using sequence-based methods have been widely applied in various therapeutic areas, including antimicrobial, anticancer, and antihypertensive treatments.

Fig. 1 Schematic framework of iBitter-Fuse for predicting bitter peptides. (Charoenkwan P, et al., 2021)

Tools for Sequence-based Peptide Design

Tool	Description	References
Meta-iAVP	A novel sequence-based meta-predictor with effective feature representation for accurate prediction of antiviral peptides (AVPs) from given peptide sequences.	Nantasenamat et al. (2019)
ACPred	A computational tool developed using powerful machine learning models (support vector machine and random forest) and various classes of peptide features, is available for the prediction and analysis of anticancer peptides.	Schaduangrat et al. (2019)
HLPpred-Fuse	A two-layer prediction framework is proposed, which can accurately and automatically predict hemolytic peptides (HLPs and non-HLPs) and HLP activity (high and low).	Hasan et al. (2020)
AntiBP3	Antibacterial peptide prediction, scanning, and design against gram-positive, gram-negative, and gram-variable bacteria.	Bajiya et al. (2024)

Our Services

CD ComputaBio utilizes artificial intelligence and machine learning to perform key functional sequence information mining on large-scale training data, providing sequence-based functional peptide design services. We are capable of designing a variety of functional peptides, including but not limited to:

Antimicrobial Peptides
Anti-cancer Peptides
Hemolytic Peptides

Antiviral Peptides
Antihypertensive Peptides
Cell-penetrating Peptides

Methods for Sequence-based Peptide Design

General Methods

General methods are suitable for various peptide design needs, covering a wide range of peptide optimization design and bioactivity prediction. These methods typically do not target specific diseases or pathogens but aim to improve the overall performance and function of peptides.

Specific Methods

Specific methods, on the other hand, target specific diseases or pathogens, utilizing specially designed algorithms and models to achieve precise therapeutic peptide design, developing therapeutic peptide drugs with stronger targeting and fewer side effects.

Why Choose Us?

Diverse Services - Design a variety of functional peptides according to the specific needs of customers.
Strong Customer Reputation - Won customer trust and praise with high-quality service.
Rich Experience Accumulation - Successfully completed a series of peptide design-related projects and accumulated rich case experience.

CD ComputaBio provides high-quality sequence-based peptide design services. Whether you need to design peptide sequences with specific functions or optimize the properties of existing peptide sequences, we will meet your diverse needs. If you are interested in our services, please feel free to contact us.

References:

Charoenkwan, P.; et al. iBitter-fuse: a novel sequence-based bitter peptide predictor by fusing multi-view features[J]. International Journal of Molecular Sciences. 2021, 22(16): 8958.
Schaduangrat, N.; et al. Meta-iAVP: a sequence-based meta-predictor for improving the prediction of antiviral peptides using effective feature representation[J]. International journal of molecular sciences. 2019, 20(22): 5743.
Schaduangrat, N.; et al. ACPred: a computational tool for the prediction and analysis of anticancer peptides[J]. Molecules. 2019, 24(10): 1973.
Hasan, M M.; et al. HLPpred-Fuse: improved and robust prediction of hemolytic peptide and its activity by fusing multiple feature representation[J]. Bioinformatics. 2020, 36(11): 3350-3356.
Bajiya, N.; et al. AntiBP3: A method for predicting antibacterial peptides against Gram-positive/negative/variable bacteria[J]. Antibiotics. 2024, 13(2): 168.

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

Services

Inquiry