RMSCNN: A Random Multi-Scale Convolutional Neural Network for Marine Microbial Bacteriocins Identification

Cui, Zhen; Chen, Zhan-Heng; Zhang, Qinhu; Грибова, В. В.; Filaretov, Vladimir; Huang, De-Shuang

doi:10.1109/tcbb.2021.3122183

Cited by 9 publications

(16 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also compared the performance of our method with a recent deep learning-based approach RMSCNN [13] developed for the bacteriocin prediction. RMSCNN takes positive and negative training protein sequences in FASTA format as inputs, encodes all amino acids of each protein sequences to some numbers defined in a protein dictionary, then constructs a matrix of the encoded sequences.…”

Section: Resultsmentioning

confidence: 99%

“…We retrieved bacteriocin sequences (positive sequences) from two publicly available databases BAGEL [6] and BACTIBASE [7]. Non-bacteriocin sequences (negative sequences) were collected from the data used in RMSCNN [13]. Initially, we gathered a total of 483 positive and 500 negative sequences.…”

Section: Methodsmentioning

confidence: 99%

Section: Performance Comparisonmentioning

confidence: 99%

“…However, setting such a low percent identify threshold in BLASTP is very unrealistic and will increase false positive and false negative results. We also compared the performance of our method with a recent deep learning-based approach RMSCNN [13] developed for the bacteriocin prediction. RMSCNN takes positive and negative training protein sequences in FASTA format An optimal feature set-based bacteriocin prediction tool 11 as inputs, encodes all amino acids of each protein sequences to some numbers defined in a protein dictionary, then constructs a matrix of the encoded sequences.…”

Section: Performance Comparisonmentioning

confidence: 99%

“…Recently some machine learning-based bacteriocin prediction techniques were proposed that utilized the presence or absence of k -mer (i.e., subsequences of length k ) as potential features and represented peptide sequences using word embedding [11, 12]. There are also deep learning-based methods for bacteriocin prediction, for example RMSCNN [13] used a convolutional neural network [14, 15] for identifying marine microbial bacteriocins. However, these existing approaches did not consider the primary and secondary structure information of peptides that are crucial to find highly dissimilar bacteriocins.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Optimal feature selection and software tool development for bacteriocin prediction

Akhter

Miller

2022

Preprint

View full text Add to dashboard Cite

Antibiotic resistance is a major public health concern around the globe. As a result, researchers always look for new compounds to develop new antibiotic drugs for combating antibiotic-resistant bacteria. Bacteriocin becomes a promising antimicrobial agent to fight against antibiotic resistance, due to its narrow killing spectrum. Sequence matching methods are widely used to identify bacteriocins by comparing them with the known bacteriocin sequences; however, these methods often fail to detect new bacteriocin sequences due to sequences' high diversity. The ability to use a machine learning approach can help find new highly dissimilar bacteriocins for developing highly effective antibiotic drugs. The aim of this work is to identify optimal sets of features and develop a machine learning-based software tool for predicting bacteriocin protein sequences with high accuracy. We extracted potential features from known bacteriocin and non-bacteriocin sequences by considering the physicochemical and structural properties of the protein sequences. Then we reduced the feature set using statistical justifications and recursive feature elimination technique. Finally, we built support vector machine (SVM) and random forest (RF) models using the selected features and our models can achieve accuracy up to 95.54%. We compared the performance of our method with a popular sequence matching-based approach and a deep learning-based method. We also developed a software tool called Bacteriocin Prediction (BacPred) that implements the prediction model using the optimal set of features obtained from this study. The software package and its user manual are available at https://github.com/suraiya14/ML_bacteriocins/BacPred.

show abstract

Section: Resultsmentioning

confidence: 99%