Design of Bioengineered Peptides/Proteases as Anti-cancer Reagents with Integrated Omics and Machine Learning...

Area of Science:

• Biochemistry
• Bioinformatics
• Oncology

Background:

• Cancer poses a significant global health burden, necessitating innovative therapeutic strategies.
• Existing cancer treatments face challenges including side effects and drug resistance.
• Anti-cancer peptides (ACPs) offer potential as potent, specific, and low-toxicity therapeutic agents.

Purpose of the Study:

• To present a novel, cost-effective strategy for discovering anti-cancer peptides (ACPs).
• To detail the integration of omics data with machine learning (ML) for ACP identification.
• To explore the potential of natural products as sources for novel anti-cancer therapeutics.

Main Methods:

• Collection and analysis of transcriptomic and proteomic data from natural sources (e.g., venoms).
• Application of machine learning (ML) algorithms for predictive modeling of ACP activity.
• Descriptive approaches to guide ML-based discovery of novel anti-cancer peptides.

Main Results:

• Demonstration of integrated omics and ML as a powerful approach for ACP discovery.
• Highlighting the efficiency and cost-effectiveness compared to traditional experimental methods.
• Identification of potential novel ACP candidates from natural product data.

Conclusions:

• Integrated omics and ML provide a viable and efficient strategy for discovering novel anti-cancer peptides.
• This approach accelerates the identification of promising therapeutic candidates from natural products.
• The described methodology facilitates the development of next-generation cancer therapies.