AlphaPeptDeep: a modular deep learning framework to predict peptide properties for proteomics

Zeng, Wen‐Feng; Zhou, Xie-Xuan; Willems, Sander; Ammar, Constantin; Wahle, Maria; Bludau, Isabell; Voytik, Eugenia; Strauss, Maximilian T.; Mann, Matthias

doi:10.1038/s41467-022-34904-3

Cited by 66 publications

(87 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After adding virus protein sequences to the search database, we indeed unequivocally identified peptides of the most highly expressed viral proteins. We manually verified our findings by matching our experimental data to predictions of fragment intensities of these peptides and the extracted ion chromatograms at the MS2 level as described recently (Zeng et al, 2022) (Supplementary Figure 1E). The viral proteins were found in several lung tissue samples of four of the subjects, all of whom had either acute or organizing diffuse alveolar damage (DAD) and were among those with highest viral load as judged by qPCR (Figure 1D).…”

Section: Detection Of Sars-cov2 Peptides In Vivo In Human Lung Tissuementioning

confidence: 53%

“…To manually validate the quality of identified SARS-CoV-2 viral peptides, the corresponding fragment intensities were predicted using AlphaPeptDeep (Zeng et al, 2022) at normalized collisional energy 30, and were plotted with AlphaViz (Voytik et al, 2022), comparing them against the detected intensities at the apex elution positions. The elution profiles of the fragments in DIA data were extracted and plotted using AlphaViz.…”

Section: Bioinformatics Data Analysismentioning

confidence: 99%

See 1 more Smart Citation

Quantitative multi-organ proteomics of fatal COVID-19 uncovers tissue-specific effects beyond inflammation

Schweizer

Schaller

Zwiebel

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

SARS-CoV-2 directly damages lung tissue via its infection and replication process and indirectly due to systemic effects of the host immune system. There are few systems-wide, untargeted studies of these effects on the different tissues of the human body and nearly all of them base their conclusions on the transcriptome. Here we developed a parallelized mass spectrometry (MS)-based proteomics workflow allowing the rapid, quantitative analysis of hundreds of virus-infected and FFPE preserved tissues. The first layer of response in all tissues was dominated by circulating inflammatory molecules. To discriminated between these systemic and true tissue-specific effects, we developed an analysis pipeline revealing that proteome alterations reflect extensive tissue damage, mostly similar to non-COVID diffuse alveolar damage. The next most affected organs were kidney and liver, while the lymph-vessel system was also strongly affected. Finally, secondary inflammatory effects of the brain correlated with receptor rearrangements and the degradation of neuronal myelin. Our results establish MS-based tissue proteomics as a promising strategy to inform organ-specific therapeutic interventions following COVID-19 infections.

show abstract

Section: Detection Of Sars-cov2 Peptides In Vivo In Human Lung Tissuementioning

confidence: 53%

Section: Bioinformatics Data Analysismentioning

confidence: 99%

Quantitative multi-organ proteomics of fatal COVID-19 uncovers tissue-specific effects beyond inflammation

Schweizer

Schaller

Zwiebel

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…G) Pure fragmentation spectrum after inspecting the single fragments for correct precursor slicing and the mirrored spectrum predicted by AlphaPeptDeep (6). …”

Section: Resultsmentioning

confidence: 99%

“…Frequently used software tools such as DIA-NN (2,3) or Spectronaut (4) match peptides from a library into each of the DIA runs. These libraries were traditionally acquired experimentally with deep data dependent acquisition (DDA)-based measurements of the proteome of interest, but are now often generated directly from the DIA data (5) or in silico from the entire proteome using deep learning (6)(7)(8)(9)(10)(11). Given these advantages very deep and quantitatively accurate data sets can now routinely be generated by DIA.…”

Section: Introductionmentioning

confidence: 99%

Synchro-PASEF allows precursor-specific fragment ion extraction and interference removal in data-independent acquisition

Skowronek

Krohs

Lubeck

et al. 2022

Preprint

View full text Add to dashboard Cite

Data-independent acquisition (DIA) methods have become increasingly popular in mass spectrometry (MS)-based proteomics because they enable continuous acquisition of fragment spectra for all precursors simultaneously. However, these advantages come with the challenge of correctly reconstructing the precursor-fragment relationships in these highly convoluted spectra for reliable identification and quantification. Here we introduce a scan mode for the combination of trapped ion mobility spectrometry (TIMS) with parallel accumulation - serial fragmentation (PASEF) that seamlessly and continuously follows the natural shape of the ion cloud in ion mobility and peptide precursor mass dimensions. Termed synchro-PASEF, it increases the detected fragment ion current several-fold at sub-second cycle times. Consecutive quadrupole selection windows move synchronously through the mass and ion mobility range, defining precursor-quadrupole relationships. In this process, the quadrupole slices through the peptide precursors, which separates fragment ion signals of each precursor into adjacent synchro-PASEF scans. This precisely defines precursor - fragment relationships in ion mobility and mass dimensions and effectively deconvolutes the DIA fragment space. Importantly, the partitioned parts of the fragment ion transitions provide a further dimension of specificity via a lock and key mechanism. This is also advantageous for quantification, where signals from interfering precursors in the DIA selection window do not affect all partitions of the fragment ion, allowing to retain only the specific parts for quantification. Overall, we establish the defining features of synchro-PASEF and explore its potential for proteomic analyses.

show abstract

“…The further exploration of the potential of IMS for PTM analysis and the development of more accurate prediction models for a wide range of PTMs, similar to those for unmodified peptides (13, 32, 33), is currently limited by the availability of comprehensive experimental data. Here, we set out to investigate the effect of 22 different naturally-occurring PTMs on the collision cross section of peptides, including 21 sets of modified peptides synthesized as part of the ProteomeTools project (34, 35) and an additional set of O-GlcNAcylated peptides.…”

Section: Introductionmentioning

confidence: 99%

Peptide collision cross sections of 22 post-translational modifications

Will

Oliinyk

Meier

2022

Preprint

View full text Add to dashboard Cite

Recent advances have rekindled the interest in ion mobility spectrometry as an additional dimension of separation in mass spectrometry (MS)– based proteomics. It separates ions according to their size and shape in the gas phase. Here, we set out to investigate the effect of 22 different post-translational modifications (PTMs) on the collision cross section (CCS) of peptides. In total, we analyzed about 4700 pairs of matching modified and unmodified peptide ions by trapped ion mobility spectrometry (TIMS). Linear alignment based on spike-in reference peptides resulted in highly reproducible CCS values with a median coefficient of variation of 0.3%. On a global level, we observed a redistribution in the m/z vs. ion mobility space for modified peptides upon changes in their charge state. Pairwise comparison between modified and unmodified peptides of the same charge state revealed median shifts in CCS between −1.1% (lysine formylation) and +4.5% (O-GlcNAcylation). In general, increasing modified peptide masses were correlated with higher CCS values, in particular within homologous PTM series. However, investigating the ion populations in more detail, we found that the change in CCS can vary substantially for a given PTM depending on the gas phase structure of its unmodified counterpart. In conclusion, our study shows PTM– and sequence–specific effects on the cross section of peptides, which could be further leveraged for proteome–wide PTM analysis.

show abstract

AlphaPeptDeep: a modular deep learning framework to predict peptide properties for proteomics

Cited by 66 publications

References 56 publications

Quantitative multi-organ proteomics of fatal COVID-19 uncovers tissue-specific effects beyond inflammation

Quantitative multi-organ proteomics of fatal COVID-19 uncovers tissue-specific effects beyond inflammation

Synchro-PASEF allows precursor-specific fragment ion extraction and interference removal in data-independent acquisition

Peptide collision cross sections of 22 post-translational modifications

Contact Info

Product

Resources

About