{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T13:52:13Z","timestamp":1785851533733,"version":"3.56.0"},"reference-count":28,"publisher":"American Chemical Society (ACS)","issue":"30","license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF0608404"],"award-info":[{"award-number":["2022YFF0608404"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In tandem mass spectrometry (MS\/MS)-based proteomics, a significant portion of acquired spectra remains unidentified due to poor quality, which consumes excessive computational resources and increases false-positive rates during database searches. Traditional quality assessment methods rely on handcrafted features or classical machine learning that often generalize poorly across different instruments. While recent deep-learning approaches like SPEQ (spectrum quality) have introduced automation, their reliance on convolutional architectures and supervised learning limits their ability to capture global spectral dependencies and transfer across heterogeneous data sets. To address these limitations, we present a pretrained transformer framework that utilizes self-attention for automated MS\/MS quality assessment. By leveraging self-supervised pretraining to learn robust, contextualized spectral representations, our model can capture global fragment relationships and ensure superior cross-instrument transferability. Our results demonstrate that it consistently outperforms existing models like SPEQ, offering higher accuracy and enhanced generalization across diverse data sets.<\/jats:p>","DOI":"10.1021\/acsomega.6c03661","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T21:13:26Z","timestamp":1784582006000},"page":"45167-45175","source":"Crossref","is-referenced-by-count":0,"title":["A Transformer-Based\nFramework for Quality Control\nof Peptide Tandem Mass Spectra"],"prefix":"10.1021","volume":"11","author":[{"given":"Mengxiao","family":"Cao","sequence":"first","affiliation":[{"name":"China Jiliang University , , Xueyuan Street , ,","place":["Hangzhou, China, 310000"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Penghuan","family":"Liu","sequence":"additional","affiliation":[{"name":"China Jiliang University , , Xueyuan Street , ,","place":["Hangzhou, China, 310000"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"key":"2026080409260439600_cit1","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1093\/bioinformatics\/bti829","article-title":"Quality classification\nof tandem mass spectrometry data","volume":"22","author":"Salmi","year":"2006","journal-title":"Bioinformatics"},{"key":"2026080409260439600_cit2","doi-asserted-by":"publisher","first-page":"1568","DOI":"10.1093\/bioinformatics\/btab874","article-title":"SPEQ: quality assessment\nof peptide tandem mass spectra with deep\nlearning","volume":"38","author":"Gholamizoj","year":"2022","journal-title":"Bioinformatics"},{"key":"2026080409260439600_cit3","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1038\/nmeth1113","article-title":"Semi-supervised\nlearning for peptide identification from shotgun proteomics datasets","volume":"4","author":"Ka\u0308ll","year":"2007","journal-title":"Nat. Methods"},{"key":"2026080409260439600_cit4","doi-asserted-by":"publisher","first-page":"i49","DOI":"10.1093\/bioinformatics\/bth947","article-title":"Automatic quality assessment of peptide tandem mass spectra","volume":"20","author":"Bern","year":"2004","journal-title":"Bioinformatics"},{"key":"2026080409260439600_cit5","doi-asserted-by":"publisher","first-page":"2086","DOI":"10.1002\/pmic.200500309","article-title":"Improving\nthe reliability and throughput of mass spectrometry-based proteomics\nby spectrum quality filtering","volume":"6","author":"Flikka","year":"2006","journal-title":"Proteomics"},{"key":"2026080409260439600_cit6","doi-asserted-by":"publisher","first-page":"2896","DOI":"10.1021\/pr200118r","article-title":"ScanRanker Quality\nassessment of tandem mass spectra\nvia sequence tagging","volume":"10","author":"Ma","year":"2011","journal-title":"J. Proteome Res."},{"key":"2026080409260439600_cit7","doi-asserted-by":"publisher","first-page":"12690","DOI":"10.1021\/acs.analchem.7b02566","article-title":"pDeep: predicting\nMS\/MS\nspectra of peptides with deep learning","volume":"89","author":"Zhou","year":"2017","journal-title":"Anal.\nChem."},{"key":"2026080409260439600_cit8","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1038\/s41592-019-0426-7","article-title":"Prosit: proteome-wide\nprediction of peptide tandem mass spectra by deep learning","volume":"16","author":"Gessulat","year":"2019","journal-title":"Nat. Methods"},{"key":"2026080409260439600_cit9","doi-asserted-by":"publisher","first-page":"17168","DOI":"10.1038\/s41598-019-52954-4","article-title":"DeepIso: a deep learning model for\npeptide feature detection from\nLC-MS map","volume":"9","author":"Zohora","year":"2019","journal-title":"Sci. Rep."},{"key":"2026080409260439600_cit10","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning\napplied to document recognition","volume":"86","author":"Le Cun","year":"1998","journal-title":"Proc. IEEE"},{"key":"2026080409260439600_cit11","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv"},{"key":"2026080409260439600_cit12","article-title":"BERT: Pre-training of Deep Bidirectional\nTransformers for Language Understanding","author":"Devlin","year":"2019","journal-title":"arXiv"},{"key":"2026080409260439600_cit13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008724","article-title":"Spec2Vec: Improved mass spectral\nsimilarity scoring through learning of structural relationships","volume":"17","author":"Huber","year":"2021","journal-title":"PLoS Comput. Biol."},{"key":"2026080409260439600_cit14","first-page":"25514","article-title":"De novo mass spectrometry peptide\nsequencing with a transformer model","volume-title":"Proceedings\nof the 39th International Conference on Machine Learning","author":"Yilmaz","year":"2022"},{"key":"2026080409260439600_cit15","doi-asserted-by":"publisher","first-page":"2300011","DOI":"10.1002\/pmic.202300011","article-title":"Leveraging\ntransformers-based language models in proteome bioinformatics","volume":"23","author":"Le","year":"2023","journal-title":"Proteomics"},{"key":"2026080409260439600_cit16","doi-asserted-by":"publisher","first-page":"810","DOI":"10.2174\/0115748936283134240109054157","article-title":"DeepPTM: protein post-translational\nmodification prediction from\nprotein sequences by combining deep protein language model with vision\ntransformers","volume":"19","author":"Soylu","year":"2024","journal-title":"Curr. Bioinf."},{"key":"2026080409260439600_cit17","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1038\/s41597-024-04068-4","article-title":"A multi-species\nbenchmark for training and validating\nmass spectrometry proteomics machine learning models","volume":"11","author":"Wen","year":"2024","journal-title":"Sci. Data"},{"key":"2026080409260439600_cit18","doi-asserted-by":"publisher","first-page":"5277","DOI":"10.1038\/ncomms6277","article-title":"MS-GF+ makes progress\ntowards a universal database\nsearch tool for proteomics","volume":"5","author":"Kim","year":"2014","journal-title":"Nat. Commun."},{"key":"2026080409260439600_cit19","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1021\/acs.jproteome.9b00328","article-title":"ThermoRawFileParser: modular, scalable,\nand cross-platform RAW file conversion","volume":"19","author":"Hulstaert","year":"2020","journal-title":"J. Proteome\nRes."},{"key":"2026080409260439600_cit20","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1021\/acs.jproteome.9b00555","article-title":"Repeat-preserving decoy\ndatabase for false discovery rate estimation in peptide identification","volume":"19","author":"Moosa","year":"2020","journal-title":"J. Proteome Res."},{"key":"2026080409260439600_cit21","doi-asserted-by":"publisher","first-page":"2699","DOI":"10.1093\/nar\/gky092","article-title":"UniProt: the universal protein knowledgebase","volume":"46","author":"UniProt Consortium","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"2026080409260439600_cit22","article-title":"Gaussian Error\nLinear Units (Gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv"},{"key":"2026080409260439600_cit23","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv"},{"key":"2026080409260439600_cit24","article-title":"Adam: A method for stochastic\noptimization","author":"Kingma","year":"2015","journal-title":"arXiv"},{"key":"2026080409260439600_cit25","article-title":"Focal loss for\ndense object\ndetection","author":"Lin","year":"2017","journal-title":"arXiv"},{"key":"2026080409260439600_cit26","article-title":"Sgdr:\nStochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv"},{"key":"2026080409260439600_cit27","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1038\/s41592-019-0427-6","article-title":"High-quality MS\/MS spectrum prediction\nfor data-dependent and data-independent acquisition data analysis","volume":"16","author":"Tiwary","year":"2019","journal-title":"Nat. Methods"},{"key":"2026080409260439600_cit28","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1038\/s41592-022-01496-1","article-title":"A learned\nembedding\nfor efficient joint analysis of millions of mass spectra","volume":"19","author":"Bittremieux","year":"2022","journal-title":"Nat. Methods"}],"container-title":["ACS Omega"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acsomega.6c03661","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/30\/45167\/66068333\/acsomega.6c03661.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/acsodf\/article-pdf\/11\/30\/45167\/66068333\/acsomega.6c03661.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T13:26:19Z","timestamp":1785849979000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/acsodf\/article\/11\/30\/45167\/5222613\/A-Transformer-Based-Framework-for-Quality-Control"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"references-count":28,"journal-issue":{"issue":"30","published-online":{"date-parts":[[2026,7,20]]},"published-print":{"date-parts":[[2026,8,4]]}},"URL":"https:\/\/doi.org\/10.1021\/acsomega.6c03661","relation":{},"ISSN":["2470-1343"],"issn-type":[{"value":"2470-1343","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]}}}