Unraveling the bioactivity of anticancer peptides as deduced from machine learning

Shoombuatong, Watshara; Schaduangrat, Nalini; Nantasenamat, Chanin

doi:10.17179/excli2018-1447

Cited by 49 publications

(30 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to examine the performance of our proposed predictor, we used five common statistical metrics including ACC, MCC, sensitivity (Sn) and specificity (Sp) 24 , 42 as described follows: where TP, TN, FP and FN represent the number of true positives, true negatives, false positive and false negatives, respectively. In addition, the area under the receiver operating characteristic (AUC) was employed as another statistical metric 39 – 41 , 43 .…”

Section: Methodsmentioning

confidence: 99%

SCORPION is a stacking-based ensemble learning framework for accurate prediction of phage virion proteins

Ahmad

Charoenkwan

Quinn

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

Fast and accurate identification of phage virion proteins (PVPs) would greatly aid facilitation of antibacterial drug discovery and development. Although, several research efforts based on machine learning (ML) methods have been made for in silico identification of PVPs, these methods have certain limitations. Therefore, in this study, we propose a new computational approach, termed SCORPION, (StaCking-based Predictior fOR Phage VIrion PrOteiNs), to accurately identify PVPs using only protein primary sequences. Specifically, we explored comprehensive 13 different feature descriptors from different aspects (i.e., compositional information, composition-transition-distribution information, position-specific information and physicochemical properties) with 10 popular ML algorithms to construct a pool of optimal baseline models. These optimal baseline models were then used to generate probabilistic features (PFs) and considered as a new feature vector. Finally, we utilized a two-step feature selection strategy to determine the optimal PF feature vector and used this feature vector to develop a stacked model (SCORPION). Both tenfold cross-validation and independent test results indicate that SCORPION achieves superior predictive performance than its constitute baseline models and existing methods. We anticipate SCORPION will serve as a useful tool for the cost-effective and large-scale screening of new PVPs. The source codes and datasets for this work are available for downloading in the GitHub repository (https://github.com/saeed344/SCORPION).

show abstract

Section: Methodsmentioning

confidence: 99%

SCORPION is a stacking-based ensemble learning framework for accurate prediction of phage virion proteins

Ahmad

Charoenkwan

Quinn

et al. 2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…From the 1186 peptides identi ed in this study, 99.4% were constituted by 5 to 20 amino acid residues, and only 21.6% do not contain a positively charged residue in their sequence. The amino acid composition of peptides is relevant for the determination of their physicochemical properties such as net charge, hydrophobicity, and structural folding, all of which are important to enable its interaction with lipid membrane of cancer cells (Shoombuatong et al, 2018).…”

Section: Amino Acid Sequences and Their Physicochemical Characteristicsmentioning

confidence: 99%

“…Hydrophobic interactions play a fundamental role in the folding mechanisms of the peptides since they are essential for the stabilization of their structure (Popp et al, 2014). Peptides with anticancer activity mainly adopt an α-helix and rarely a β-sheet structure (Shoombuatong et al, 2018). Most of the anticancer peptides adopt a conformation prior to engaging with the cancer cell membrane, to then penetrate intracellular spaces and lead to the destruction of the lipidic bilayer through pore formation and/or changes in the cell membrane charge, resulting in the nal interference with necrotic and/or apoptotic cell death pathways (Gaspar et al, 2013).…”

Section: Amino Acid Sequences and Their Physicochemical Characteristicsmentioning

confidence: 99%

In Silico Study of Physicochemical Characteristics and Anticancer Potential of Peptides Derived from Salvia Hispanica

Morales-Mendoza

Figueroa

Hernández-Álvarez

et al. 2022

Preprint

View full text Add to dashboard Cite

Peptides derived from Salvia hispanica´s protein fraction < 1 kDa, were identified and analyzed for the prediction of their physicochemical properties. The characterized peptide sequences were then submitted to a multi-criteria decision analysis to identify the peptides that possess the characteristics to potentially exert anticancer activity. Through molecular docking analysis, the potential anticancer activity of the Potentially Anticancer Peptide (PAP)-1, PAP-2, PAP-3, PAP-4 and PAP-5, was estimated by their binding interactions with cancer and apoptosis related molecules. All five evaluated PAPs exhibited strong binding interactions (<-100 kcal/mol); however, PAP-3 showed the lowest binding free energies with several of the targets. Thus, PAP-3 shows potential to be used as a nutraceutical or ingredient for functional foods that adjuvates in cancer treatment. Further in vitro and in vivo studies are required to validate the predictions obtained by the in silico analysis, and to establish the mechanism of action and the clinical potential of the peptide.

show abstract

“…Even though there are several ways of treating some of the cancer types, still there is no certain treatment for most of the cancers. Two of the major treatment strategies for cancer are radiation therapy and chemotherapy 1 , 2 . However, they are both expensive and have long term negative side effects 1 .…”

Section: Introductionmentioning

confidence: 99%

ACP-MHCNN: an accurate multi-headed deep-convolutional neural network to predict anticancer peptides

Ahmed

Muhammod

Khan

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Although advancing the therapeutic alternatives for treating deadly cancers has gained much attention globally, still the primary methods such as chemotherapy have significant downsides and low specificity. Most recently, Anticancer peptides (ACPs) have emerged as a potential alternative to therapeutic alternatives with much fewer negative side-effects. However, the identification of ACPs through wet-lab experiments is expensive and time-consuming. Hence, computational methods have emerged as viable alternatives. During the past few years, several computational ACP identification techniques using hand-engineered features have been proposed to solve this problem. In this study, we propose a new multi headed deep convolutional neural network model called ACP-MHCNN, for extracting and combining discriminative features from different information sources in an interactive way. Our model extracts sequence, physicochemical, and evolutionary based features for ACP identification using different numerical peptide representations while restraining parameter overhead. It is evident through rigorous experiments using cross-validation and independent-dataset that ACP-MHCNN outperforms other models for anticancer peptide identification by a substantial margin on our employed benchmarks. ACP-MHCNN outperforms state-of-the-art model by 6.3%, 8.6%, 3.7%, 4.0%, and 0.20 in terms of accuracy, sensitivity, specificity, precision, and MCC respectively. ACP-MHCNN and its relevant codes and datasets are publicly available at: https://github.com/mrzResearchArena/Anticancer-Peptides-CNN. ACP-MHCNN is also publicly available as an online predictor at: https://anticancer.pythonanywhere.com/.

show abstract

Unraveling the bioactivity of anticancer peptides as deduced from machine learning

Cited by 49 publications

References 102 publications

SCORPION is a stacking-based ensemble learning framework for accurate prediction of phage virion proteins

SCORPION is a stacking-based ensemble learning framework for accurate prediction of phage virion proteins

In Silico Study of Physicochemical Characteristics and Anticancer Potential of Peptides Derived from Salvia Hispanica

ACP-MHCNN: an accurate multi-headed deep-convolutional neural network to predict anticancer peptides

Contact Info

Product

Resources

About