HLAB: learning the BiLSTM features from the ProtBert-encoded proteins for the class I HLA-peptide binding prediction

Abstract

Human Leukocyte Antigen (HLA) is a type of molecule residing on the surfaces of most human cells and exerts an essential role in the immune system responding to the invasive items. The T cell antigen receptors may recognize the HLA-peptide complexes on the surfaces of cancer cells and destroy these cancer cells through toxic T lymphocytes. The computational determination of HLA-binding peptides will facilitate the rapid development of cancer immunotherapies. This study hypothesized that the natural language processing-encoded peptide features may be further enriched by another deep neural network. The hypothesis was tested with the Bi-directional Long Short-Term Memory-extracted features from the pretrained Protein Bidirectional Encoder Representations from Transformers-encoded features of the class I HLA (HLA-I)-binding peptides. The experimental data showed that our proposed HLAB feature engineering algorithm outperformed the existing ones in detecting the HLA-I-binding peptides. The extensive evaluation data show that the proposed HLAB algorithm outperforms all the seven existing studies on predicting the peptides binding to the HLA-A*01:01 allele in AUC and achieves the best average AUC values on the six out of the seven k-mers (k=8,9,...,14, respectively represent the prediction task of a polypeptide consisting of k amino acids) except for the 9-mer prediction tasks. The source code and the fine-tuned feature extraction models are available at http://www.healthinformaticslab.org/supp/resources.php.

IUP-BERT: Identification of Umami Peptides Based on BERT Features

“…The receiver operating characteristic curve (ROC) is a curve drawn according to a series of different classification methods (boundary value or decision threshold), with the true positive rate (sensitivity) as the ordinate and false positive rate (specificity) as the abscissa. ROC displays the relationship between true positives and false positives at different confidence levels [ 12 , 35 , 49 ]. Nevertheless, the ROC curve cannot clearly indicate which classifier is more superior.…”

“…With a global receptive field, BERT can effectively capture more global context information than the convolutional neural network-based models. Recently, BERT has achieved gratifying results in the prediction of various functional peptides, such as bitter peptides [ 33 ], antimicrobial peptides [ 34 ], and human leukocyte antigen peptides [ 35 ]. Soft symmetric alignment (SSA) has defined a brand-new method to compare arbitrary-length sequences within vectors [ 36 ].…”

CcBHLA: pan-specific peptide–HLA class I binding prediction via Convolutional and BiLSTM features

“…It is well known that the position of amino acids in a peptide is essential information, which affects and even determines the spatial structure and function of a peptide. Models designed to process natural language generally have the ability to extract contextual information and have been applied to peptide processing [28][29][30]. Therefore, we explore whether CNN can be combined with a natural language processing model to bring better performance.…”

CollagenTransformer: End-to-End Transformer Model to Predict Thermal Stability of Collagen Triple Helices Using an NLP Approach

“…This nonsequential method of training could be relevant to collagen, where short-range (sequential) and long-range (nonsequential) interactions play a role in the structure. , The transformer framework has increasingly become the model of choice for NLP-type of problems in language and science applications and has most recently been used in AlphaFold 2 to predict protein structures. , While transformer models are powerful, since they can be generalized to a variety of applications and modalities (sequence regression problems, sequence to sequence translation, such as secondary structure prediction, and other needs including field predictions , ), they can also be difficult to train and often require large amounts of data. This has been exemplified in recent developments of very large language models based on these architectures, sometimes reaching hundreds of billions of parameters. − Further, to our best knowledge, while a few very recent examples exist of the application of these transformer models to predict the structure or binding properties of some other protein systems, − they have thus far not been used to directly predict biophysical properties of proteins.…”