The deep learning-based tools PointNovo and SMSNet showed an increased peptide recall across different enzymes and datasets compared to spectrum-graph-based approaches. In this study, we evaluated five recently developed de novo sequencing algorithms (Novor, pNovo 3, DeepNovo, SMSNet, and PointNovo) in their ability to identify and assemble antibody sequences. Deep learning-based approaches have been developed and applied more frequently to increase the accuracy of de novo sequencing. De novo sequencing based on mass spectrometry is a useful method to obtain the amino acid sequence of peptides and proteins without a priori knowledge. Sequence information of antibodies is helpful for understanding antibody-antigen interactions and ensuring their affinity and specificity. Their ability to recognize and bind to specific molecule structures makes them essential research tools and therapeutic agents. Monoclonal antibodies (mAbs) are biotechnologically produced proteins with various applications in research, therapeutics, and diagnostics. The online version of this article (doi:10.1007/s1336-0) contains supplementary material, which is available to authorized users. The speed surpasses the acquisition speed of today’s mass spectrometer and, therefore, opens a new possibility to de novo sequence in real time while the spectrometer is acquiring the spectral data.
Novor can de novo sequence more than 300 MS/MS spectra per second on a laptop computer. On the testing datasets, Novor sequenced 7%–37% more correct residues than the state-of-the-art de novo sequencing tool, PEAKS, while being an order of magnitude faster. The software program was also carefully optimized. To further improve the speed, a two-stage algorithmic approach, namely dynamic programming and refinement, is used.
The decision tree model also enables efficient score calculation and contributes to the speed improvement. Important knowledge about peptide fragmentation is extracted automatically from the library and incorporated into the scoring functions. To improve the accuracy, Novor’s scoring functions are based on two large decision trees built from a peptide spectral library with more than 300,000 spectra with machine learning. This study presents a new software tool, Novor, to greatly improve both the speed and accuracy of today’s peptide de novo sequencing analyses.
De novo sequencing software has been widely used in proteomics to sequence new peptides from tandem mass spectrometry data.
0 kommentar(er)
