Identification of efflux proteins based on contextual representations with deep bidirectional transformer encoders

Taju, Semmy Wellem; Shah, Syed Muazzam Ali; Ou, Yu‐Yen

doi:10.1016/j.ab.2021.114416

Cited by 2 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models were pre-trained exclusively using a plain text corpus. Learning representations of language sentences can provide effective feature representations for protein sequences [ 27 ]. This study employed the BERT-base-uncased pre-trained model, which consists of 12 layers, 768 hidden units, and 12 attention heads, and requires 110 million parameters.…”

Section: Methodsmentioning

confidence: 99%

“…In another study, Zhang et al leveraged the pre-training strategy in the field of antibacterial peptide prediction, developing a novel method for antibacterial peptide recognition based on BERT [ 26 ]. Taju et al used the contextualized word embeddings from BERT and the support vector machine classifier to identify efflux proteins [ 27 ]. Moreover, Charoenkwan et al introduced a BERT-based model, BERT4Bitter, that enhances the prediction of bitter peptides solely based on their amino acid sequence [ 23 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A BERT-based approach for identifying anti-inflammatory peptides using sequence information

Xu,

Wang,

Yang

et al. 2024

Heliyon

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A BERT-based approach for identifying anti-inflammatory peptides using sequence information

Xu,

Wang,

Yang

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…Membrane proteins [50], efflux proteins [51], ion transporters [52], transient receptor potential channels [24], glucose transporters [53], α-helical transmembrane proteins [54] 2.6 Related works with different features…”

Section: Features Related Workmentioning

confidence: 99%

Recent advances in features generation for membrane protein sequences: From multiple sequence alignment to pre‐trained language models

Ou,

Ho,

Chang

2023

Proteomics

View full text Add to dashboard Cite

Membrane proteins play a crucial role in various cellular processes and are essential components of cell membranes. Computational methods have emerged as a powerful tool for studying membrane proteins due to their complex structures and properties that make them difficult to analyze experimentally. Traditional features for protein sequence analysis based on amino acid types, composition, and pair composition have limitations in capturing higher‐order sequence patterns. Recently, multiple sequence alignment (MSA) and pre‐trained language models (PLMs) have been used to generate features from protein sequences. However, the significant computational resources required for MSA‐based features generation can be a major bottleneck for many applications. Several methods and tools have been developed to accelerate the generation of MSAs and reduce their computational cost, including heuristics and approximate algorithms. Additionally, the use of PLMs such as BERT has shown great potential in generating informative embeddings for protein sequence analysis. In this review, we provide an overview of traditional and more recent methods for generating features from protein sequences, with a particular focus on MSAs and PLMs. We highlight the advantages and limitations of these approaches and discuss the methods and tools developed to address the computational challenges associated with features generation. Overall, the advancements in computational methods and tools provide a promising avenue for gaining deeper insights into the function and properties of membrane proteins, which can have significant implications in drug discovery and personalized medicine.

show abstract

Identification of efflux proteins based on contextual representations with deep bidirectional transformer encoders

Cited by 2 publications

References 26 publications

A BERT-based approach for identifying anti-inflammatory peptides using sequence information

A BERT-based approach for identifying anti-inflammatory peptides using sequence information

Recent advances in features generation for membrane protein sequences: From multiple sequence alignment to pre‐trained language models

Contact Info

Product

Resources

About