Advancing Proteomic Analyses with Graph-Based Deep Learning: Protein Inference and DIA De Novo Peptide Sequencing
thesis · 2025
thesis · 2025. Zheng Ma
| Date | 2025-08-15 |
| Type | thesis |
| Publisher | PhD thesis |
| Contribution | algorithm |
| Supervisor | Ali Ghodsi |
| Link | https://dspacemainprd01.lib.uwaterloo.ca/server/api/core/bitstreams/2cd3373a-a4cd-4536-8cec-464a86330205/content |
Methods and tools
- DIANovo: Transformer-based de novo sequencer for DIA: disentangles coeluted/multiplexed precursor spectra. Presented in Zheng Ma’s arXiv preprint (2024) and his PhD thesis (2025).
Trained on
- DIA_urine_proteomics_biomarker_discovery_abdominal-pain (as deposited) · PASS00706
- Evaluating the influence of MS-acquisition parameters on DDA label-free proteomics analyses (as deposited) · PXD019777
- Ultra-fast label-free quantification and comprehensive proteome coverage with narrow-window data-ind (PXD046386) (as deposited) · PXD046386
- Ultra-fast label-free quantification and comprehensive proteome coverage with narrow-window data-ind (PXD046444) (as deposited) · PXD046444
- Ultra-fast label-free quantification and comprehensive proteome coverage with narrow-window data-independent acquisition (as deposited) · PXD046453
- Untargeted data independent acquisition proteomics analysis using Orbitrap mass spectrometers and DIA-Umpire (as deposited) · PXD003179
Evaluated on
- Chorus project 1105 (as deposited) · 1105
- Evaluating the influence of MS-acquisition parameters on DDA label-free proteomics analyses (as deposited) · PXD019777
- Narrow-window DIA: Ultra-fast quantitative analysis of comprehensive proteomes with high sequencing depth. Dilution Seri (as deposited) · PXD046283
- PXD026600 (as deposited) · PXD026600
- PXD046471 (as deposited) · PXD046471
- Ultra-fast label-free quantification and comprehensive proteome coverage with narrow-window data-ind (PXD046386) (as deposited) · PXD046386
- Ultra-fast label-free quantification and comprehensive proteome coverage with narrow-window data-independent acquisition (as deposited) · PXD046453
Data used
Data this paper ran on, where the catalog has not recorded whether for training or for evaluation.
- A systematic screening pipeline identifies a new regulator of tyrosinated microtubule dynamics (as deposited) · PXD030448
- An Unbiased Strategy for Selecting Effective Combinations of Therapeutic Targets Supports the Development of a Novel Bis (as deposited) · PXD023034
- Combined Protein Signature of ALDH1A1, LGALS3, LGALS3BP Predicts Cancer Recurrence Post-Liver Transplantation Beyond Mil (as deposited) · PXD022881
- Investigation of the arsenic regulated proteome of PML bodies (as deposited) · PXD030330
- Kinobead profiling of PITCOINs1-3 (as deposited) · PXD032284
- PXD036171 (as deposited) · PXD036171
- Protein markers in Oral Squamous Cell Carcinoma (OSCC) (as deposited) · PXD025701
- Proteomics Analysis of Trop2 Xenograft Prostate Tumors (as deposited) · PXD039272
- Proteomics analysis of amyloid corneal aggregates from lattice corneal dystrophy patients (as deposited) · PXD006640
- Proteomics investigation of Nucleostemin role in Nucleo-phosmin mutated OCI-AML 3 cell line (as deposited) · PXD034012
- Response Profiling Using Shotgun Proteomics Enables Establishing Global Metallodrug Mechanisms of Action - cytoplasmic p (as deposited) · PXD004789
- SARS-CoV-2 ORF8 interactome in the secretory pathway (as deposited) · PXD032035
- SUPT3H-less SAGA coactivator can assemble and function without significantly perturbing RNA polymerase II transcription (as deposited) · PXD026991
- Structural analysis of neurofibromin by crosslinking mass spectrometry (as deposited) · PXD023593
- Targeting the Scaffold Protein Plectin by an Organometallic as a Strategy to Inhibit Tumour Invasive (PXD005388) (as deposited) · PXD005388
- Targeting the Scaffold Protein Plectin by an Organometallic as a Strategy to Inhibit Tumour Invasiveness- whole cell lys (as deposited) · PXD010319
- ¬The EGFR/ErbB inhibitor neratinib promotes apoptosis and clearance by airway macrophages (as deposited) · PXD035125