Unraveling the bioactivity of anticancer peptides as deduced from machine learning

Abstract

Cancer imposes a global health burden as it represents one of the leading causes of morbidity and mortality while also giving rise to significant economic burden owing to the associated expenditures for its monitoring and treatment. In spite of advancements in cancer therapy, the low success rate and recurrence of tumor has necessitated the ongoing search for new therapeutic agents. Aside from drugs based on small molecules and protein-based biopharmaceuticals, there has been an intense effort geared towards the development of peptide-based therapeutics owing to its favorable and intrinsic properties of being relatively small, highly selective, potent, safe and low in production costs. In spite of these advantages, there are several inherent weaknesses that are in need of attention in the design and development of therapeutic peptides. An abundance of data on bioactive and therapeutic peptides have been accumulated over the years and the burgeoning area of artificial intelligence has set the stage for the lucrative utilization of machine learning to make sense of these large and high-dimensional data. This review summarizes the current state-of-the-art on the application of machine learning for studying the bioactivity of anticancer peptides along with future outlook of the field. Data and R codes used in the analysis herein are available on GitHub at https://github.com/Shoombuatong2527/anticancer-peptides-review.

Keywords: QSAR; anticancer; anticancer peptides; antitumor; bioactivity; cancer; host defense peptides; machine learning.

Table 1. List of selected major databases available for bioactive and therapeutic peptides.

Table 2. Summary of the OECD principles for the development of robust QSAR models.

Table 3. Summary of all datasets used in this research for evaluating anticancer peptide prediction.

Table 4. Summary of all peptide features and their feature groups in this research.

Table 5. Summary of existing methods for predicting anticancer peptides.

Table 6. Performance benchmark comparing various computational methods evaluated by 5- and 10-fold cross-validation and jackknife test.

Figure 1. Strengths and weaknesses of therapeutic peptides. Concepts summarized from Fosgerau and Hoffmann, 2015.

Figure 2. Bar plot of the number of antibacterial peptides (ABP), anticancer peptides (ACP), antifungal peptides (AFP), antiparasitic peptides (APP) and antiviral peptides (AVP). Data is collected from the antimicrobial peptide database (APD3) (Wang et al., 2016).

Figure 3. Bar plot showing the peptide length distribution in percentage for antibacterial peptides (ABP), anticancer peptides (ACP), antifungal peptides (AFP), antiparasitic peptides (APP) and antiviral peptides (AVP) collected from the Antimicrobial Peptide Database (APD3) (Wang et al., 2016).

Figure 4. Heat map showing the amino acid compositions in percentage for antibacterial peptides (ABP), anticancer peptides (ACP), antifungal peptides (AFP), antiparasitic peptides (APP) and antiviral peptides (AVP). Data was collected from the Antimicrobial Peptide Database (APD3) (Wang et al., 2016).

Figure 5. Structures of human-derived anticancer peptides