MLACP 2.0: An updated machine learning tool for anticancer peptide prediction
Anticancer peptides are emerging anticancer drug that offers fewer side effects and is more effective than chemotherapy and targeted therapy. Predicting anticancer peptides from sequence information is one of the most challenging tasks in immunoinformatics. In the past ten years, machine learning-ba...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-01-01
|
| Series: | Computational and Structural Biotechnology Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2001037022003245 |
| _version_ | 1797978202156564480 |
|---|---|
| author | Le Thi Phan Hyun Woo Park Thejkiran Pitti Thirumurthy Madhavan Young-Jun Jeon Balachandran Manavalan |
| author_facet | Le Thi Phan Hyun Woo Park Thejkiran Pitti Thirumurthy Madhavan Young-Jun Jeon Balachandran Manavalan |
| author_sort | Le Thi Phan |
| collection | DOAJ |
| description | Anticancer peptides are emerging anticancer drug that offers fewer side effects and is more effective than chemotherapy and targeted therapy. Predicting anticancer peptides from sequence information is one of the most challenging tasks in immunoinformatics. In the past ten years, machine learning-based approaches have been proposed for identifying ACP activity from peptide sequences. These methods include our previous method MLACP (developed in 2017) which made a significant impact on anticancer research. MLACP tool has been widely used by the research community, however, its robustness must be improved significantly for its continued practical application. In this study, the first large non-redundant training and independent datasets were constructed for ACP research. Using the training dataset, the study explored a wide range of feature encodings and developed their respective models using seven different conventional classifiers. Subsequently, a subset of encoding-based models was selected for each classifier based on their performance, whose predicted scores were concatenated and trained through a convolutional neural network (CNN), whose corresponding predictor is named MLACP 2.0. The evaluation of MLACP 2.0 with a very diverse independent dataset showed excellent performance and significantly outperformed the recent ACP prediction tools. Additionally, MLACP 2.0 exhibits superior performance during cross-validation and independent assessment when compared to CNN-based embedding models and conventional single models. Consequently, we anticipate that our proposed MLACP 2.0 will facilitate the design of hypothesis-driven experiments by making it easier to discover novel ACPs. The MLACP 2.0 is freely available at https://balalab-skku.org/mlacp2. |
| first_indexed | 2024-04-11T05:19:12Z |
| format | Article |
| id | doaj.art-1ee053f896bb4bd88d6579394bee713a |
| institution | Directory Open Access Journal |
| issn | 2001-0370 |
| language | English |
| last_indexed | 2024-04-11T05:19:12Z |
| publishDate | 2022-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computational and Structural Biotechnology Journal |
| spelling | doaj.art-1ee053f896bb4bd88d6579394bee713a2022-12-24T04:53:39ZengElsevierComputational and Structural Biotechnology Journal2001-03702022-01-012044734480MLACP 2.0: An updated machine learning tool for anticancer peptide predictionLe Thi Phan0Hyun Woo Park1Thejkiran Pitti2Thirumurthy Madhavan3Young-Jun Jeon4Balachandran Manavalan5Computational Biology and Bioinformatics Laboratory, Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, Gyeonggi-do, Republic of KoreaDepartment of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, Gyeonggi-do, Republic of KoreaComputational Biology and Bioinformatics Laboratory, Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, Gyeonggi-do, Republic of KoreaComputational Biology Lab, Department of Genetic Engineering, SRM Institute of Science & Technology, Kattankulathur 603203, Tamil Nadu, IndiaDepartment of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, Gyeonggi-do, Republic of Korea; Corresponding authors.Computational Biology and Bioinformatics Laboratory, Department of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University, Suwon 16419, Gyeonggi-do, Republic of Korea; Corresponding authors.Anticancer peptides are emerging anticancer drug that offers fewer side effects and is more effective than chemotherapy and targeted therapy. Predicting anticancer peptides from sequence information is one of the most challenging tasks in immunoinformatics. In the past ten years, machine learning-based approaches have been proposed for identifying ACP activity from peptide sequences. These methods include our previous method MLACP (developed in 2017) which made a significant impact on anticancer research. MLACP tool has been widely used by the research community, however, its robustness must be improved significantly for its continued practical application. In this study, the first large non-redundant training and independent datasets were constructed for ACP research. Using the training dataset, the study explored a wide range of feature encodings and developed their respective models using seven different conventional classifiers. Subsequently, a subset of encoding-based models was selected for each classifier based on their performance, whose predicted scores were concatenated and trained through a convolutional neural network (CNN), whose corresponding predictor is named MLACP 2.0. The evaluation of MLACP 2.0 with a very diverse independent dataset showed excellent performance and significantly outperformed the recent ACP prediction tools. Additionally, MLACP 2.0 exhibits superior performance during cross-validation and independent assessment when compared to CNN-based embedding models and conventional single models. Consequently, we anticipate that our proposed MLACP 2.0 will facilitate the design of hypothesis-driven experiments by making it easier to discover novel ACPs. The MLACP 2.0 is freely available at https://balalab-skku.org/mlacp2.http://www.sciencedirect.com/science/article/pii/S2001037022003245Anticancer peptidesConvolutional neural networkFeature encodingsConventional classifiersBaseline modelsDataset construction |
| spellingShingle | Le Thi Phan Hyun Woo Park Thejkiran Pitti Thirumurthy Madhavan Young-Jun Jeon Balachandran Manavalan MLACP 2.0: An updated machine learning tool for anticancer peptide prediction Computational and Structural Biotechnology Journal Anticancer peptides Convolutional neural network Feature encodings Conventional classifiers Baseline models Dataset construction |
| title | MLACP 2.0: An updated machine learning tool for anticancer peptide prediction |
| title_full | MLACP 2.0: An updated machine learning tool for anticancer peptide prediction |
| title_fullStr | MLACP 2.0: An updated machine learning tool for anticancer peptide prediction |
| title_full_unstemmed | MLACP 2.0: An updated machine learning tool for anticancer peptide prediction |
| title_short | MLACP 2.0: An updated machine learning tool for anticancer peptide prediction |
| title_sort | mlacp 2 0 an updated machine learning tool for anticancer peptide prediction |
| topic | Anticancer peptides Convolutional neural network Feature encodings Conventional classifiers Baseline models Dataset construction |
| url | http://www.sciencedirect.com/science/article/pii/S2001037022003245 |
| work_keys_str_mv | AT lethiphan mlacp20anupdatedmachinelearningtoolforanticancerpeptideprediction AT hyunwoopark mlacp20anupdatedmachinelearningtoolforanticancerpeptideprediction AT thejkiranpitti mlacp20anupdatedmachinelearningtoolforanticancerpeptideprediction AT thirumurthymadhavan mlacp20anupdatedmachinelearningtoolforanticancerpeptideprediction AT youngjunjeon mlacp20anupdatedmachinelearningtoolforanticancerpeptideprediction AT balachandranmanavalan mlacp20anupdatedmachinelearningtoolforanticancerpeptideprediction |