New proteomics tool DeepLC can predict retention times for peptides that carry as-yet unseen modifications

Researchers of the Computational Omics and Systems Biology Group, led by Prof. Lennart Martens have developed a deep learning peptide predictor that allows to predict the retention time of (previously unseen) modified peptides.

The inclusion of peptide retention time prediction is implemented in a growing number of complex liquid chromatography–mass spectrometry identification workflows, as it reduces (or even removes) peptide identification ambiguity.  

However, due to the way peptides are encoded in current prediction models, accurate retention times cannot be predicted for modified peptides. This is especially problematic for fledgling open searches, which will benefit from accurate retention time prediction for modified peptides to reduce identification ambiguity.

In the tool the researchers developed, called DeeplC, peptide encoding based on atomic composition is used, which allows the retention time of (previously unseen) modified peptides to be predicted accurately.

The researchers could show that DeepLC performs similarly to current state-of-the-art approaches for unmodified peptides and, more importantly, accurately predicts retention times for modifications not seen during training. Moreover, they could show that DeepLC’s ability to predict retention times for any modification enables potentially incorrect identifications to be flagged in an open search of a wide variety of proteome data.

Their study was recently published in the high impact journal Nature Methods, stressing the importance of their findings.

Discover the article via this link.