Anticancer peptides (ACPs) are a class of molecules that have gained
significant attention in the field of cancer research and therapy. ACPs are
short chains of amino acids, the building blocks of proteins, and they possess
the ability to selectively target and kill cancer cells. One of the key
advantages of ACPs is their ability to selectively target cancer cells while
sparing healthy cells to a greater extent. This selectivity is often attributed
to differences in the surface properties of cancer cells compared to normal
cells. That is why ACPs are being investigated as potential candidates for
cancer therapy. ACPs may be used alone or in combination with other treatment
modalities like chemotherapy and radiation therapy. While ACPs hold promise as
a novel approach to cancer treatment, there are challenges to overcome,
including optimizing their stability, improving selectivity, and enhancing
their delivery to cancer cells, continuous increasing in number of peptide
sequences, developing a reliable and precise prediction model. In this work, we
propose an efficient transformer-based framework to identify anticancer
peptides for by performing accurate a reliable and precise prediction model.
For this purpose, four different transformer models, namely ESM, ProtBert,
BioBERT, and SciBERT are employed to detect anticancer peptides from amino acid
sequences. To demonstrate the contribution of the proposed framework, extensive
experiments are carried on widely-used datasets in the literature, two versions
of AntiCp2, cACP-DeepGram, ACP-740. Experiment results show the usage of
proposed model enhances classification accuracy when compared to the
state-of-the-art studies. The proposed framework, ESM, exhibits 96.45 of
accuracy for AntiCp2 dataset, 97.66 of accuracy for cACP-DeepGram dataset, and
88.51 of accuracy for ACP-740 dataset, thence determining new state-of-the-art.
Anticancer peptides (ACPs) have emerged as a promising field in cancer research and therapy. These short chains of amino acids offer the potential to selectively target and kill cancer cells, while minimizing harm to healthy cells. This selectivity is due to differences in the surface properties of cancer cells compared to normal cells.
One of the key challenges in ACP research is optimizing their stability, selectivity, and delivery to cancer cells. Additionally, with the continuous increase in the number of peptide sequences, developing a reliable and precise prediction model becomes crucial.
In this work, a transformer-based framework is proposed to identify anticancer peptides with high accuracy. Four different transformer models, namely ESM, ProtBert, BioBERT, and SciBERT, are utilized to detect anticancer peptides from amino acid sequences. These models have been previously applied in various fields, showcasing the multi-disciplinary nature of this research.
To evaluate the effectiveness of the proposed framework, extensive experiments are conducted on well-established datasets such as AntiCp2, cACP-DeepGram, and ACP-740. The results demonstrate that the proposed model surpasses the state-of-the-art studies in terms of classification accuracy.
The ESM model achieves an impressive accuracy of 96.45% for the AntiCp2 dataset, 97.66% for the cACP-DeepGram dataset, and 88.51% for the ACP-740 dataset. These results indicate a new state-of-the-art in the field of anticancer peptide prediction.
This research highlights the potential of transformer-based models in identifying anticancer peptides and their importance in advancing cancer treatment. The integration of interdisciplinary approaches, combining knowledge from protein science, bioinformatics, and machine learning, is crucial for further advancements in this field.