ACP-MLC: A two-level prediction engine for identification of anticancer peptides and multi-label classification of their functional types

Deng, Hua; Ding, Meng; Wang, Yimeng; Li, Weihua; Liu, Guixia; Tang, Yun

doi:10.1016/j.compbiomed.2023.106844

Cited by 14 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Obviously, there is no one-size-fits-all solution for all classes. In general, combining a multitude of encoding and machine learning techniques within the same task could increase classification performance, while a robust feature selection could help to obtain more powerful classifiers by removing unnecessary features [68] . The most relevant ones can then be analyzed to determine whether they contribute positively or negatively to the classification [68] .…”

Section: Discussionmentioning

confidence: 99%

“…In general, combining a multitude of encoding and machine learning techniques within the same task could increase classification performance, while a robust feature selection could help to obtain more powerful classifiers by removing unnecessary features [68] . The most relevant ones can then be analyzed to determine whether they contribute positively or negatively to the classification [68] . Moreover, the examination of amino acid composition revealed distinctive preferences within certain groups, enabling discrimination based on specific sequence motifs.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of bioactive peptides: A systematic benchmark of models and encodings

Bizzotto,

Zampieri,

Treu

et al. 2024

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Classification of bioactive peptides: A systematic benchmark of models and encodings

Bizzotto,

Zampieri,

Treu

et al. 2024

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

“…ACP-MLC is a two-level prediction engine that accurately identifies ACPs and classifies their functional types, achieving the high performance in both tasks. 101 The model "ANNprob-ACPs" outperformed existing approaches in accuracy and effectiveness in discovering ACPs. Significant improvement was shown in identifying ACPs with high accuracy rates in both cross-validation and independent tests.…”

Section: T H Imentioning

confidence: 99%

“…The main finding of this study includes a three channel end-to-end model incorporating data augmentation techniques and feature extraction methods. ACP-MLC is a two-level prediction engine that accurately identifies ACPs and classifies their functional types, achieving the high performance in both tasks . The model “ANNprob-ACPs” outperformed existing approaches in accuracy and effectiveness in discovering ACPs.…”

Section: Ai Models For Acpsmentioning

confidence: 99%

Advancing Peptide-Based Cancer Therapy with AI: In-Depth Analysis of State-of-the-Art AI Models

Bhattarai,

Tayara,

Chong

2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Anticancer peptides (ACPs) play a vital role in selectively targeting and eliminating cancer cells. Evaluating and comparing predictions from various machine learning (ML) and deep learning (DL) techniques is challenging but crucial for anticancer drug research. We conducted a comprehensive analysis of 15 ML and 10 DL models, including the models released after 2022, and found that support vector machines (SVMs) with feature combination and selection significantly enhance overall performance. DL models, especially convolutional neural networks (CNNs) with light gradient boosting machine (LGBM) based feature selection approaches, demonstrate improved characterization. Assessment using a new test data set (ACP10) identifies ACPred, MLACP 2.0, AI4ACP, mACPred, and AntiCP2.0_AAC as successive optimal predictors, showcasing robust performance. Our review underscores current prediction tool limitations and advocates for an omnidirectional ACP prediction framework to propel ongoing research.

show abstract

“…In the work of ANNprob-ACPs, the authors determined that physicochemical properties of QSO, along with compositional properties of DPC, AAC, and PAAC are directly linked to the peptide’s action. A similar study is presented in ref , which uses a simpler two-level ML-based model for classification and target cancer tissue prediction. In the ACPred-BMF model, the top five features identified as the most important for ACP predictions are charge-negative (D, E residues), p K a , isoelectric point, charge-N (G, A, V, L, I, F, W, Y, N, Q, M, S, T, C, P), and aromatic (F, W, Y, H).…”

Section: Introductionmentioning

confidence: 99%

Identification of Anticancer Peptides from the Genome of Candida albicans: in Silico Screening, in Vitro and in Vivo Validations

Cheong,

Zuo,

Chen

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Anticancer peptides (ACPs) are promising future therapeutics, but their experimental discovery remains time-consuming and costly. To accelerate the discovery process, we propose a computational screening workflow to identify, filter, and prioritize peptide sequences based on predicted class probability, antitumor activity, and toxicity. The workflow was applied to identify novel ACPs with potent activity against colorectal cancer from the genome sequences of Candida albicans. As a result, four candidates were identified and validated in the HCT116 colon cancer cell line. Among them, PCa1 and PCa2 emerged as the most potent, displaying IC 50 values of 3.75 and 56.06 μM, respectively, and demonstrating a 4-fold selectivity for cancer cells over normal cells. In the colon xenograft nude mice model, the administration of both peptides resulted in substantial inhibition of tumor growth without causing significant adverse effects. In conclusion, this work not only contributes a proven computational workflow for ACP discovery but also introduces two peptides, PCa1 and PCa2, as promising candidates poised for further development as targeted therapies for colon cancer. The method as a web service is available at https://app.cbbio.online/acpep/home and the source code at https:// github.com/cartercheong/AcPEP_classification.git.

show abstract

ACP-MLC: A two-level prediction engine for identification of anticancer peptides and multi-label classification of their functional types

Cited by 14 publications

References 44 publications

Classification of bioactive peptides: A systematic benchmark of models and encodings

Classification of bioactive peptides: A systematic benchmark of models and encodings

Advancing Peptide-Based Cancer Therapy with AI: In-Depth Analysis of State-of-the-Art AI Models

Identification of Anticancer Peptides from the Genome of Candida albicans: in Silico Screening, in Vitro and in Vivo Validations

Contact Info

Product

Resources

About