Deep Learning in Proteomics

Wen, Bo; Zeng, Wen‐Feng; Liao, Yuxing; Shi, Zhiao; Savage, Sara R.; Jiang, Wen; Zhang, Bing

doi:10.1002/pmic.201900335

Cited by 105 publications

(94 citation statements)

References 217 publications

(345 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[1][2][3][4] In recent years, deep learning-based methods have attracted more and more attention, for both data-dependent acquisition (DDA) and data-independent acquisition (DIA) data analysis. [5][6][7][8][9][10][11][12][13][14][15][16] For DDA data analysis, the recently published pDeep, 5 Prosit, 6 and DeepMass:Prism 7 showed that integrating spectrum prediction into DDA search engines would dramatically increase the identification rates. Our recent work, pValid, 17 further demonstrated that the spectra predicted by pDeep could be applied to filter out unreliable peptide spectrum matches (PSMs), resulting in more accurate peptide identifications.…”

mentioning

confidence: 99%

pDeep3: Toward More Accurate Spectrum Prediction with Fast Few-Shot Learning

Tarn

Zeng

2021

Anal. Chem.

Self Cite

View full text Add to dashboard Cite

Spectrum prediction using deep learning has attracted a lot of attention in recent years. Although existing deep learning methods have dramatically increased the prediction accuracy, there is still considerable space for improvement, which is presently limited by the difference of fragmentation types or instrument settings. In this work, we use the few-shot learning method to fit the data online to make up for the shortcoming.The method is evaluated using ten datasets, where the instruments includes Velos, QE, Lumos, and Sciex, with collision energies being differently set. Experimental results show that few-shot learning can achieve higher prediction accuracy with almost negligible computing resources. For example, on the dataset from a untrained instrument Sciex-6600, within about 10 seconds, the prediction accuracy is increased from 69.7% to 86.4%; on the CID (collision-induced dissociation) dataset, the prediction accuracy of the model trained by HCD (higher energy collision dissociation) spectra is increased from 48.0% to 83.9%. It is also shown that, the method is not critical to data qual-1

show abstract

mentioning

confidence: 99%

pDeep3: Toward More Accurate Spectrum Prediction with Fast Few-Shot Learning

Tarn

Zeng

2021

Anal. Chem.

Self Cite

View full text Add to dashboard Cite

show abstract

“…We imagine that students and researchers with novel algorithmic ideas can use this paradigm to add their functionality in a transparent and efficient manner, without having to re-create the entire pipeline. This could especially enable increasingly powerful machine learning and deep learning technologies to be integrated into computational proteomics (Torun et al 2021;Wen et al 2020;Meyer 2021).…”

Section: Discussionmentioning

confidence: 99%

AlphaPept, a modern and open framework for MS-based proteomics

Strauss

Bludau

Zeng

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In common with other omics technologies, mass spectrometry (MS)-based proteomics produces ever-increasing amounts of raw data, making their efficient analysis a principal challenge. There is a plethora of different computational tools that process the raw MS data and derive peptide and protein identification and quantification. During the last decade, there has been dramatic progress in computer science and software engineering, including collaboration tools that have transformed research and industry. To leverage these advances, we developed AlphaPept, a Python-based open-source framework for efficient processing of large high-resolution MS data sets. Using Numba for just-in-time machine code compilation on CPU and GPU, we achieve hundred-fold speed improvements while maintaining clear syntax and rapid development speed. AlphaPept uses the Python scientific stack of highly optimized packages, reducing the code base to domain-specific tasks while providing access to the latest advances in machine learning. We provide an easy on-ramp for community validation and contributions through the concept of literate programming, implemented in Jupyter Notebooks of the different modules. A framework for continuous integration, testing, and benchmarking enforces solid software engineering principles. Large datasets can rapidly be processed as shown by the analysis of hundreds of cellular proteomes in minutes per file, many-fold faster than the data acquisiton. The AlphaPept framework can be used to build automated processing pipelines using efficient HDF5 based file formats, web-serving functionality and compatibility with downstream analysis tools. Easy access for end-users is provided by one-click installation of the graphical user interface, for advanced users via a modular Python library, and for developers via a fully open GitHub repository.

show abstract

“…Although the term NLP refers to natural languages, the same computational methods are also used to study non-natural languages such as programming code [96] , [49] , [30] . Past decades have seen a continuous trickle of statistical and machine-learning algorithms from the field of NLP into bioinformatics [67] , [117] , [66] , [6] , [34] , [60] , [88] , [109] , [117] , [105] .…”

Section: Proteins and Natural Languagementioning

confidence: 99%

The language of proteins: NLP, machine learning & protein sequences

Ofer

Brandes

Linial

2021

Computational and Structural Biotechnology Journal

207

162

View full text Add to dashboard Cite

Natural language processing (NLP) is a field of computer science concerned with automated text and language analysis. In recent years, following a series of breakthroughs in deep and machine learning, NLP methods have shown overwhelming progress. Here, we review the success, promise and pitfalls of applying NLP algorithms to the study of proteins. Proteins, which can be represented as strings of amino-acid letters, are a natural fit to many NLP methods. We explore the conceptual similarities and differences between proteins and language, and review a range of protein-related tasks amenable to machine learning. We present methods for encoding the information of proteins as text and analyzing it with NLP methods, reviewing classic concepts such as bag-of-words, k-mers/n-grams and text search, as well as modern techniques such as word embedding, contextualized embedding, deep learning and neural language models. In particular, we focus on recent innovations such as masked language modeling, self-supervised learning and attention-based models. Finally, we discuss trends and challenges in the intersection of NLP and protein research.

show abstract

Deep Learning in Proteomics

Cited by 105 publications

References 217 publications

pDeep3: Toward More Accurate Spectrum Prediction with Fast Few-Shot Learning

pDeep3: Toward More Accurate Spectrum Prediction with Fast Few-Shot Learning

AlphaPept, a modern and open framework for MS-based proteomics

The language of proteins: NLP, machine learning & protein sequences

Contact Info

Product

Resources

About