DIA-NN: neural networks and interference correction enable deep proteome coverage in high throughput.

Area of Science:

• Proteomics
• Bioinformatics
• Computational Biology

Background:

• Data-independent acquisition (DIA) is a powerful technique in proteomics.
• Accurate protein identification and quantification are crucial for biological insights.
• Existing DIA processing methods can be computationally intensive and may lack sensitivity.

Purpose of the Study:

• To introduce DIA-NN, an integrated software suite for processing DIA proteomics data.
• To leverage deep neural networks and novel strategies for improved performance.
• To enhance the speed and depth of proteome coverage in high-throughput proteomics.

Main Methods:

• Development of the DIA-NN software suite.
• Implementation of deep neural networks for data analysis.
• Integration of new quantification and signal correction strategies.
• Application to data-independent acquisition proteomics experiments.

Main Results:

• DIA-NN significantly improves protein identification and quantification in DIA proteomics.
• The software demonstrates high performance, particularly for high-throughput applications.
• DIA-NN enables deep and confident proteome coverage when combined with fast chromatography.

Conclusions:

• DIA-NN offers an easy-to-use and efficient solution for DIA proteomics data processing.
• The software enhances the capabilities of conventional DIA proteomic applications.
• DIA-NN facilitates deeper and more confident proteome coverage, especially in high-throughput settings.