pith. sign in

arxiv: 2605.04376 · v1 · submitted 2026-05-06 · 💻 cs.LG

GraphPI: Efficient Protein Inference with Graph Neural Networks

Zheng Ma , Jiazhen Chen , Lei Xin , Ali Ghodsi This is my paper

Pith reviewed 2026-05-08 18:04 UTC · model grok-4.3

classification 💻 cs.LG
keywords protein inferencegraph neural networksproteomicsmass spectrometrynode classificationself-trainingpseudo-labelspercolator
0
0 comments X

The pith

GraphPI uses a graph neural network on protein-peptide-PSM graphs to infer proteins accurately across datasets without any fine-tuning.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper seeks to overcome the lack of labeled data in protein inference by framing it as node classification inside a graph that links proteins to peptides and peptide-spectrum matches. It trains a graph neural network on pseudo-labels generated by an existing algorithm and refines those labels through iterative self-training. Because the input features come from the well-normalized outputs of Percolator, the resulting model works on new datasets without retraining, which cuts computation time and lowers the chance of overfitting. A sympathetic reader would care because protein inference remains a slow step in mass-spectrometry proteomics; a single, fast, general-purpose model could let researchers analyze larger experiments more routinely.

Core claim

GraphPI models proteins as nodes in a protein-peptide-PSM graph and applies a graph neural network to classify them. The network is trained on pseudo-labels supplied by a conventional protein inference tool and then improved by self-training that keeps only high-confidence predictions. The authors show that the normalized nature of Percolator-derived features lets the same trained model deliver competitive accuracy on multiple independent test datasets while running substantially faster than standard protein inference algorithms.

What carries the argument

Graph neural network performing node classification on the protein-peptide-PSM graph, trained via pseudo-labels and self-training.

If this is right

  • A single trained model can be applied directly to any new dataset that supplies Percolator features.
  • Overall runtime for protein inference drops significantly compared with common algorithms.
  • Overfitting risk decreases because no dataset-specific retraining is performed.
  • The same architecture produces competitive results on several public test collections.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same graph-plus-self-training pattern could be tested on other sparse-label problems in bioinformatics that already have reliable but imperfect label generators.
  • Replacing the initial pseudo-label source with a more accurate or ensemble-based generator might raise final accuracy without changing the rest of the pipeline.
  • Because the model runs faster, it becomes practical to run protein inference repeatedly inside iterative experimental design loops.

Load-bearing premise

Pseudo-labels generated by an existing protein inference algorithm are accurate and unbiased enough to serve as training targets for a model that then claims better or equal performance on new data.

What would settle it

Apply the released GraphPI model to a new proteomics dataset whose ground-truth proteins are known independently and measure whether its accuracy falls below that of a standard algorithm or whether fine-tuning becomes necessary to match baseline performance.

Figures

Figures reproduced from arXiv: 2605.04376 by Ali Ghodsi, Jiazhen Chen, Lei Xin, Zheng Ma.

Figure 1
Figure 1. Figure 1: The architecture of our protein inference algorithm leveraging GNN for node clas view at source ↗
Figure 2
Figure 2. Figure 2: (a): The schema of the bidirectional tri-partite graph, with view at source ↗
Figure 3
Figure 3. Figure 3: An illustrative example of the message passing operation of GNN, where the view at source ↗
Figure 4
Figure 4. Figure 4: ROC curve (entrapment FDR vs. number of true proteins) of various models on view at source ↗
Figure 5
Figure 5. Figure 5: pAUC (partial AUC) score of various models on the benchmark datasets: (a) view at source ↗
Figure 6
Figure 6. Figure 6: (a) Inference time of the benchmarked methods on the Yeast dataset. (b) Scaling view at source ↗
Figure 7
Figure 7. Figure 7: ROC curve (entrapment FDR vs. number of true proteins) of GraphPI and view at source ↗
Figure 8
Figure 8. Figure 8: In (a)&(b), the orange circle represents a peptide with its peptide identification view at source ↗
read the original abstract

The integration of deep learning approaches in biomedical research has been transformative, enabling breakthroughs in various applications. Despite these strides, its application in protein inference is impeded by the scarcity of extensively labeled datasets, a challenge compounded by the high costs and complexities of accurate protein annotation. In this study, we introduce GraphPI, a novel framework that treats protein inference as a node classification problem. We treat proteins as interconnected nodes within a protein-peptide-PSM graph, utilizing a Graph Neural Network-based architecture to elucidate their interrelations. To address label scarcity, we train the model on a set of unlabeled public protein datasets with pseudo-labels derived from an existing protein inference algorithm, enhanced by self-training to iteratively refine labels based on confidence scores. Contrary to prevalent methodologies necessitating dataset-specific training, our research illustrates that GraphPI, due to the well normalized nature of Percolator features, exhibits universal applicability without dataset-specific fine-tuning, a feature that not only mitigates the risk of overfitting but also enhances computational efficiency. Our empirical experiments reveal notable performance on various test datasets and deliver significantly reduced computation times compared to common protein inference algorithms.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 1 minor

Summary. The paper introduces GraphPI, a GNN-based framework that models protein inference as node classification on a protein-peptide-PSM graph. It trains on unlabeled public datasets using pseudo-labels from an existing protein inference algorithm, augmented by self-training on high-confidence predictions, and claims that the normalized Percolator features enable universal applicability without dataset-specific fine-tuning, yielding notable performance gains and substantially lower computation times than standard methods.

Significance. If the empirical results and generalization claims hold, GraphPI could provide an efficient, scalable alternative for protein inference that reduces reliance on per-dataset retraining and lowers computational overhead in proteomics pipelines. The graph-based formulation and self-training approach for label scarcity are conceptually promising, but the absence of reported metrics, baselines, or validation details prevents assessment of whether these advantages are realized.

major comments (3)
  1. [Abstract] Abstract: the central claims of 'notable performance' and 'significantly reduced computation times' are asserted without any quantitative metrics, baseline comparisons (e.g., against Percolator or other standard algorithms), ablation studies on the self-training component, or error analysis; this leaves the empirical support for the method's superiority unverified.
  2. [Abstract] Abstract and methods description: training relies on pseudo-labels produced by an existing protein inference algorithm plus iterative self-training; this creates a circularity risk where reported improvements may simply refine the prior algorithm's decisions rather than demonstrate independent gains, and no independent ground-truth validation, cross-dataset distribution-shift experiments, or ablation removing the pseudo-label step are described to address this.
  3. [Abstract] Abstract: the claim that 'well normalized nature of Percolator features' enables 'universal applicability without dataset-specific fine-tuning' is presented as a key advantage, yet no experiments testing zero-shot transfer across datasets with varying distributions, no details on the feature normalization procedure, and no comparison to fine-tuned baselines are provided to substantiate the generalization property.
minor comments (1)
  1. [Abstract] The abstract refers to 'various test datasets' and 'common protein inference algorithms' without naming them or providing references; explicit dataset identifiers and citations would improve reproducibility.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive feedback. The comments identify important areas for clarification and strengthening of the empirical support. We respond to each major comment below and will revise the manuscript to address the concerns where possible.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claims of 'notable performance' and 'significantly reduced computation times' are asserted without any quantitative metrics, baseline comparisons (e.g., against Percolator or other standard algorithms), ablation studies on the self-training component, or error analysis; this leaves the empirical support for the method's superiority unverified.

    Authors: We agree that the abstract would be strengthened by including specific quantitative support rather than qualitative descriptors. The manuscript reports detailed results in the experiments section with tables comparing performance metrics and runtime against standard methods including Percolator. We will revise the abstract to reference these key quantitative outcomes and direct readers to the relevant tables and figures for baselines, ablations, and error analysis. revision: yes

  2. Referee: [Abstract] Abstract and methods description: training relies on pseudo-labels produced by an existing protein inference algorithm plus iterative self-training; this creates a circularity risk where reported improvements may simply refine the prior algorithm's decisions rather than demonstrate independent gains, and no independent ground-truth validation, cross-dataset distribution-shift experiments, or ablation removing the pseudo-label step are described to address this.

    Authors: The pseudo-labeling step provides initial supervision on unlabeled data, while the GNN learns additional graph-structured patterns; self-training then iterates on high-confidence model predictions. Evaluation uses held-out test portions of the datasets. We will add an explicit discussion of this validation strategy, including any ground-truth checks available in the public datasets, cross-dataset shift tests, and an ablation that removes the self-training stage to the revised manuscript. revision: yes

  3. Referee: [Abstract] Abstract: the claim that 'well normalized nature of Percolator features' enables 'universal applicability without dataset-specific fine-tuning' is presented as a key advantage, yet no experiments testing zero-shot transfer across datasets with varying distributions, no details on the feature normalization procedure, and no comparison to fine-tuned baselines are provided to substantiate the generalization property.

    Authors: The normalization procedure is described in the methods. We will expand this description with the precise steps used. To further substantiate the generalization claim we will add zero-shot transfer results across datasets with differing characteristics and direct comparisons against fine-tuned variants of the model in the revised experiments section. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper trains a GNN on pseudo-labels from an external algorithm (Percolator) plus self-training, then evaluates empirically on separate test datasets while claiming universal applicability due to normalized features. No quoted step reduces a claimed prediction or result to the inputs by construction (e.g., no fitted parameter renamed as independent prediction, no self-citation chain bearing the central claim, no self-definitional loop). The derivation relies on external benchmarks and feature properties rather than tautological equivalence, making it self-contained.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The framework depends on the quality of pseudo-labels from prior algorithms and on the assumption that Percolator features are already normalized enough to support zero-shot transfer; no independent verification of these premises is supplied in the abstract.

free parameters (1)
  • pseudo-label confidence threshold
    Controls which model predictions are promoted to training labels during self-training iterations; value not stated in abstract.
axioms (1)
  • domain assumption Percolator features are sufficiently well normalized across datasets to enable universal applicability without fine-tuning
    Directly invoked in the abstract to justify the no-fine-tuning claim.

pith-pipeline@v0.9.0 · 5495 in / 1275 out tokens · 77362 ms · 2026-05-08T18:04:54.516876+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

101 extracted references · 101 canonical work pages

  1. [1]

    Nesvizhskii and Andrew Keller and Eugene Kolker and Ruedi Aebersold , doi =

    Alexey I. Nesvizhskii and Andrew Keller and Eugene Kolker and Ruedi Aebersold , doi =. Analytical Chemistry , title =. 2003 , pages=

    work page 2003

  2. [2]

    MacCoss and William Stafford Noble , doi =

    Oliver Serang and Michael J. MacCoss and William Stafford Noble , doi =. Journal of Proteome Research , title =. 2010 , pages=

    work page 2010

  3. [3]

    Dijkstra and Oliver Serang and Knut Reinert and Oliver Kohlbacher , doi =

    Julianus Pfeuffer and Timo Sachsenberg and Tjeerd M.H. Dijkstra and Oliver Serang and Knut Reinert and Oliver Kohlbacher , doi =. Journal of Proteome Research , title =. 2020 , pages=

    work page 2020

  4. [4]

    Meyer and Katrin Marcus and Christian Stephan and Oliver Kohlbacher and Martin Eisenacher , doi =

    Julian Uszkoreit and Alexandra Maerkens and Yasset Perez-Riverol and Helmut E. Meyer and Katrin Marcus and Christian Stephan and Oliver Kohlbacher and Martin Eisenacher , doi =. Journal of Proteome Research , title =. 2015 , pages=

    work page 2015

  5. [5]

    Molecular and Cellular Proteomics , year =

    Direct Maximization of Protein Identifications from Tandem Mass Spectra , author =. Molecular and Cellular Proteomics , year =. doi:10.1074/mcp.M111.012161 , publisher =

    work page doi:10.1074/mcp.m111.012161

  6. [6]

    PLoS Computational Biology , title =

    Minseung Kim and Ameen Eetemadi and Ilias Tagkopoulos , doi =. PLoS Computational Biology , title =. 2017 , pages=

    work page 2017

  7. [7]

    Canterbury and Jason Weston and William Stafford Noble and Michael J

    Lukas Käll and Jesse D. Canterbury and Jason Weston and William Stafford Noble and Michael J. MacCoss , doi =. Nature Methods , title =. 2007 , pages=

    work page 2007

  8. [8]

    Kipf and Max Welling , booktitle =

    Thomas N. Kipf and Max Welling , booktitle =. Semi-supervised classification with graph convolutional networks , year =

    work page

  9. [9]

    Advances in Neural Information Processing Systems 30 (NIPS 2017) , editor =

    Inductive Representation Learning on Large Graphs , author =. Advances in Neural Information Processing Systems 30 (NIPS 2017) , editor =. 2017 , publisher =

    work page 2017

  10. [10]

    Payne and Michael R

    Matthew The and Fredrik Edfors and Yasset Perez-Riverol and Samuel H. Payne and Michael R. Hoopmann and Magnus Palmblad and Björn Forsström and Lukas Käll , doi =. Journal of Proteome Research , title =. 2018 , pages=

    work page 2018

  11. [11]

    Proteomics , title =

    Erik Ahrné and Lars Molzahn and Timo Glatter and Alexander Schmidt , doi =. Proteomics , title =. 2013 , pages=

    work page 2013

  12. [12]

    Eddes and Laura Hohmann and Jennifer Jackson and Amelia Peterson and Simon Letarte and Philip R

    John Klimek and James S. Eddes and Laura Hohmann and Jennifer Jackson and Amelia Peterson and Simon Letarte and Philip R. Gafken and Jonathan E. Katz and Parag Mallick and Hookeun Lee and Alexander Schmidt and Reto Ossola and Jimmy K. Eng and Ruedi Aebersold and Daniel B. Martin , doi =. Journal of Proteome Research , title =. 2008 , pages=

    work page 2008

  13. [13]

    Moran and Bin Ma , doi =

    Shenheng Guan and Michael F. Moran and Bin Ma , doi =. Molecular and Cellular Proteomics , title =. 2019 , pages=

    work page 2019

  14. [14]

    Messner and Spyros I

    Vadim Demichev and Christoph B. Messner and Spyros I. Vernardis and Kathryn S. Lilley and Markus Ralser , doi =. Nature Methods , title =. 2020 , pages=

    work page 2020

  15. [15]

    Ziaur Rahman and Ngoc Hieu Tran and Lei Xin and Baozhen Shan and Ming Li , doi =

    Fatema Tuz Zohora and M. Ziaur Rahman and Ngoc Hieu Tran and Lei Xin and Baozhen Shan and Ming Li , doi =. Scientific Reports , title =. 2019 , publisher=

    work page 2019

  16. [16]

    Elias and Steven P

    Joshua E. Elias and Steven P. Gygi , doi =. Nature Methods , title =. 2007 , pages=

    work page 2007

  17. [17]

    Proceedings of the National Academy of Sciences of the United States of America , title =

    Ngoc Hieu Tran and Xianglilan Zhang and Lei Xin and Baozhen Shan and Ming Li , doi =. Proceedings of the National Academy of Sciences of the United States of America , title =. 2017 , pages=

    work page 2017

  18. [18]

    Nature Machine Intelligence , title =

    Rui Qiao and Ngoc Hieu Tran and Lei Xin and Xin Chen and Ming Li and Baozhen Shan and Ali Ghodsi , doi =. Nature Machine Intelligence , title =. 2021 , pages=

    work page 2021

  19. [19]

    Nature Methods , title =

    Ngoc Hieu Tran and Rui Qiao and Lei Xin and Xin Chen and Chuyi Liu and Xianglilan Zhang and Baozhen Shan and Ali Ghodsi and Ming Li , doi =. Nature Methods , title =. 2019 , pages=

    work page 2019

  20. [20]

    Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition , title =

    Guansong Pang and Cheng Yan and Chunhua Shen and Anton van den Hengel and Xiao Bai , doi =. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition , title =. 2020 , pages=

    work page 2020

  21. [21]

    Keppler and Samuel M

    Dominique Kreutz and Andrea Bileck and Kerstin Plessl and Denise Wolrab and Michael Groessl and Bernhard K. Keppler and Samuel M. Meier and Christopher Gerner , doi =. Chemistry - A European Journal , title =. 2017 , pages=

    work page 2017

  22. [22]

    Meier and Dominique Kreutz and Lilli Winter and Matthias H.M

    Samuel M. Meier and Dominique Kreutz and Lilli Winter and Matthias H.M. Klose and Klaudia Cseh and Tamara Weiss and Andrea Bileck and Beatrix Alte and Johanna C. Mader and Samir Jana and Annesha Chatterjee and Arindam Bhattacharyya and Michaela Hejl and Michael A. Jakupec and Petra Heffeter and Walter Berger and Christian G. Hartinger and Bernhard K. Kepp...

    work page 2017

  23. [23]

    Pervushin and Siu Kwan Sze and Jodhbir S

    Anandalakshmi Venkatraman and Bamaprasad Dutta and Elavazhagan Murugan and Hao Piliang and Rajamani Lakshminaryanan and Anita Chan Sook Yee and Konstantin V. Pervushin and Siu Kwan Sze and Jodhbir S. Mehta , doi =. Journal of Proteome Research , title =. 2017 , pages=

    work page 2017

  24. [24]

    Clinical Proteomics , title =

    Mamatha Bhat and Sergi Clotet-Freixas and Cristina Baciu and Elisa Pasini and Ahmed Hammad and Tommy Ivanics and Shelby Reid and Amirhossein Azhie and Marc Angeli and Anand Ghanekar and Sandra Fischer and Gonzalo Sapisochin and Ana Konvalinka , doi =. Clinical Proteomics , title =. 2021 , pages=

    work page 2021

  25. [25]

    Lupton and Charles Bayly-Jones and Laura D’Andrea and Cheng Huang and Ralf B

    Christopher J. Lupton and Charles Bayly-Jones and Laura D’Andrea and Cheng Huang and Ralf B. Schittenhelm and Hari Venugopal and James C. Whisstock and Michelle L. Halls and Andrew M. Ellisdon , doi =. Nature Structural and Molecular Biology , title =. 2021 , pages=

    work page 2021

  26. [26]

    Bijnsdorp and Franziska Böttger and Sander R

    Madiha Mumtaz and Irene V. Bijnsdorp and Franziska Böttger and Sander R. Piersma and Thang V. Pham and Samiullah Mumtaz and Ruud H. Brakenhoff and M. Waheed Akhtar and Connie R. Jimenez , doi =. Clinical Proteomics , title =. 2022 , pages=

    work page 2022

  27. [27]

    Vincent , doi =

    Veronique Fischer and Vincent Hisler and Elisabeth Scheer and Elisabeth Lata and Bastien Morlet and Damien Plassard and Dominique Helmlinger and Didier Devys and László Tora and Stephane D. Vincent , doi =. Nucleic Acids Research , title =. 2022 , pages=

    work page 2022

  28. [28]

    McAlear and Yang Yue and Takumi Higaki and Sarah E

    Takashi Hotta and Thomas S. McAlear and Yang Yue and Takumi Higaki and Sarah E. Haynes and Alexey I. Nesvizhskii and David Sept and Kristen J. Verhey and Susanne Bechstedt and Ryoma Ohi , doi =. Current Biology , title =. 2022 , pages=

    work page 2022

  29. [29]

    Redox Biology , volume=

    SARS-CoV-2 ORF8 reshapes the ER through forming mixed disulfides with ER oxidoreductases , author=. Redox Biology , volume=. doi:10.1016/j.redox.2022.102388 , year=

    work page doi:10.1016/j.redox.2022.102388 2022

  30. [30]

    Williams and Oliver Daumke and Bernard Payrastre and Sonia Severin and Marc Nazaré and Volker Haucke , doi =

    Wen Ting Lo and Hassane Belabed and Murat Kücükdisli and Juliane Metag and Yvette Roske and Polina Prokofeva and Yohei Ohashi and André Horatscheck and Davide Cirillo and Michael Krauss and Christopher Schmied and Martin Neuenschwander and Jens Peter von Kries and Guillaume Médard and Bernhard Kuster and Olga Perisic and Roger L. Williams and Oliver Daumk...

    work page 2023

  31. [31]

    BMC Genomics , title =

    Yanting Su and Yuanyuan Guo and Jieyu Guo and Ting Zeng and Ting Wang and Wu Liu , doi =. BMC Genomics , title =. 2023 , pages=

    work page 2023

  32. [32]

    En Chi Hsu and Meghan A. Rice and Abel Bermudez and Fernando Jose Garcia Marques and Merve Aslan and Shiqin Liu and Ali Ghoochani and Chiyuan Amy Zhang and Yun Sheng Chen and Aimen Zlitni and Sahil Kumar and Rosalie Nolley and Frezghi Habte and Michelle Shen and Kashyap Koul and Donna M. Peehl and Amina Zoubeidi and Sanjiv S. Gambhir and Christian A. Kund...

    work page 2020

  33. [33]

    International Journal of Molecular Sciences , title =

    Ilaria Cela and Maria Concetta Cufaro and Maurine Fucito and Damiana Pieragostino and Paola Lanuti and Michele Sallese and Piero Del Boccio and Adele Di Matteo and Nerino Allocati and Vincenzo De Laurenzi and Luca Federici , doi =. International Journal of Molecular Sciences , title =. 2022 , pages=

    work page 2022

  34. [34]

    Grant and Benjamin Diament and Barbara Frewen and J

    Sean McIlwain and Kaipo Tamura and Attila Kertesz-Farkas and Charles E. Grant and Benjamin Diament and Barbara Frewen and J. Jeffry Howbert and Michael R. Hoopmann and Lukas Käll and Jimmy K. Eng and Michael J. MacCoss and William Stafford Noble , doi =. Journal of Proteome Research , title =. 2014 , pages=

    work page 2014

  35. [35]

    2009 , note =

    Ramakrishnan, S and Vogel, C , title =. 2009 , note =

    work page 2009

  36. [36]

    Eng and Michael R

    Jimmy K. Eng and Michael R. Hoopmann and Tahmina A. Jahan and Jarrett D. Egertson and William S. Noble and Michael J. MacCoss , doi =. Journal of the American Society for Mass Spectrometry , title =. 2015 , pages=

    work page 2015

  37. [37]

    and Cebron, Nicolas and Dill, Fabian and Gabriel, Thomas R

    Berthold, Michael R. and Cebron, Nicolas and Dill, Fabian and Gabriel, Thomas R. and K. KNIME: The Konstanz Information Miner , journal =. 2009 , volume =

    work page 2009

  38. [38]

    Chambers and Brendan MacLean and Robert Burke and Dario Amodei and Daniel L

    Matthew C. Chambers and Brendan MacLean and Robert Burke and Dario Amodei and Daniel L. Ruderman and Steffen Neumann and Laurent Gatto and Bernd Fischer and Brian Pratt and Jarrett Egertson and Katherine Hoff and Darren Kessner and Natalie Tasman and Nicholas Shulman and Barbara Frewen and Tahmina A. Baker and Mi Youn Brusniak and Christopher Paulse and D...

    work page 2012

  39. [39]

    Hannes L. Röst and Timo Sachsenberg and Stephan Aiche and Chris Bielow and Hendrik Weisser and Fabian Aicheler and Sandro Andreotti and Hans Christian Ehrlich and Petra Gutenbrunner and Erhan Kenar and Xiao Liang and Sven Nahnsen and Lars Nilse and Julianus Pfeuffer and George Rosenberger and Marc Rurik and Uwe Schmitt and Johannes Veit and Mathias Walzer...

    work page 2016

  40. [40]

    Herman and Carl G

    Kimberly D. Herman and Carl G. Wright and Helen M. Marriott and Sam C. McCaughran and Kieran A. Bowden and Mark O. Collins and Stephen A. Renshaw and Lynne R. Prince , doi =. Frontiers in Immunology , title =. 2022 , publisher=

    work page 2022

  41. [41]

    Vizeacoumar and Renuka Dahiya and Sara L

    Amr El Zawily and Frederick S. Vizeacoumar and Renuka Dahiya and Sara L. Banerjee and Kalpana K. Bhanumathy and Hussain Elhasasna and Glinton Hanover and Jessica C. Sharpe and Malkon G. Sanchez and Paul Greidanus and R. Greg Stacey and Kyung Mee Moon and Ilya Alexandrov and Juha P. Himanen and Dimitar B. Nikolov and Humphrey Fonge and Aaron P. White and L...

    work page 2023

  42. [42]

    Jaffray and Michael H

    Ellis G. Jaffray and Michael H. Tatham and Barbara Mojsa and Magda Liczmanska and Alejandro Rojas-Fernandez and Yili Yin and Graeme Ball and Ronald T. Hay , doi =. Journal of Cell Biology , title =. 2023 , pages=

    work page 2023

  43. [43]

    Saltzman and Mei Leng and Bhoomi Bhatt and Purba Singh and Doug W

    Alexander B. Saltzman and Mei Leng and Bhoomi Bhatt and Purba Singh and Doug W. Chan and Lacey Dobrolecki and Hamssika Chandrasekaran and Jong M. Choi and Antrix Jain and Sung Y. Jung and Michael T. Lewis and Matthew J. Ellis and Anna Malovannaya , doi =. Molecular and Cellular Proteomics , title =. 2018 , pages=

    work page 2018

  44. [44]

    Leigh Anderson and Norman G

    N. Leigh Anderson and Norman G. Anderson , doi =. Molecular & cellular proteomics : MCP , title =. 2002 , pages=

    work page 2002

  45. [45]

    Diamandis , doi =

    Eleftherios P. Diamandis , doi =. Molecular and Cellular Proteomics , title =. 2004 , pages=

    work page 2004

  46. [46]

    Hopkins and Colin R

    Andrew L. Hopkins and Colin R. Groom , doi =. Nature Reviews Drug Discovery , title =. 2002 , pages=

    work page 2002

  47. [47]

    Schiöth , doi =

    Mathias Rask-Andersen and Markus Sällman Almén and Helgi B. Schiöth , doi =. Nature Reviews Drug Discovery , title =. 2011 , pages=

    work page 2011

  48. [48]

    Nucleic Acids Research , title =

    Minoru Kanehisa and Susumu Goto and Shuichi Kawashima and Yasushi Okuno and Masahiro Hattori , doi =. Nucleic Acids Research , title =. 2004 , pages=

    work page 2004

  49. [49]

    Ball and Judith A

    Michael Ashburner and Catherine A. Ball and Judith A. Blake and David Botstein and Heather Butler and J. Michael Cherry and Allan P. Davis and Kara Dolinski and Selina S. Dwight and Janan T. Eppig and Midori A. Harris and David P. Hill and Laurie Issel-Tarver and Andrew Kasarskis and Suzanna Lewis and John C. Matese and Joel E. Richardson and Martin Ringw...

    work page 2000

  50. [50]

    Holmes , doi =

    Dawn E. Holmes , doi =. Learning and Analytics in Intelligent Systems , title =. 2022 , pages=

    work page 2022

  51. [51]

    BMC Bioinformatics , title =

    Yong Fuga Li and Predrag Radivojac , doi =. BMC Bioinformatics , title =. 2012 , pages=

    work page 2012

  52. [52]

    Neapolitan , doi =

    Richard E. Neapolitan , doi =. Probabilistic Methods for Bioinformatics: With an Introduction to Bayesian Networks , title =

    work page

  53. [53]

    E Ahmed , doi =

    S. E Ahmed , doi =. Technometrics , title =

    work page

  54. [54]

    L.; Anderson, N

    Anderson, N. L.; Anderson, N. G. The human plasma proteome: history, character, and diagnostic prospects. 2002

    work page 2002

  55. [55]

    Diamandis, E. P. Mass spectrometry as a diagnostic and a cancer biomarker discovery tool: Opportunities and potential limitations. 2004

    work page 2004

  56. [56]

    L.; Groom, C

    Hopkins, A. L.; Groom, C. R. The druggable genome. Nature Reviews Drug Discovery 2002, 1, 727--730

    work page 2002

  57. [57]

    M.; Serang, O.; Reinert, K.; Kohlbacher, O

    Pfeuffer, J.; Sachsenberg, T.; Dijkstra, T. M.; Serang, O.; Reinert, K.; Kohlbacher, O. EPIFANY: A Method for Efficient High-Confidence Protein Inference. Journal of Proteome Research 2020, 19, 1060--1072

    work page 2020

  58. [58]

    J.; Noble, W

    Serang, O.; MacCoss, M. J.; Noble, W. S. Efficient marginalization to compute protein posterior probabilities from shotgun mass spectrometry data. Journal of Proteome Research 2010, 9, 5346--5357

    work page 2010

  59. [59]

    I.; Keller, A.; Kolker, E.; Aebersold, R

    Nesvizhskii, A. I.; Keller, A.; Kolker, E.; Aebersold, R. A statistical model for identifying proteins by tandem mass spectrometry. Analytical Chemistry 2003, 75, 4646--4658

    work page 2003

  60. [60]

    E.; Marcus, K.; Stephan, C.; Kohlbacher, O.; Eisenacher, M

    Uszkoreit, J.; Maerkens, A.; Perez-Riverol, Y.; Meyer, H. E.; Marcus, K.; Stephan, C.; Kohlbacher, O.; Eisenacher, M. PIA: An Intuitive Protein Inference Engine with a Web-Based User Interface. Journal of Proteome Research 2015, 14, 2988--2997

    work page 2015

  61. [61]

    Ahmed, S. E. Bayesian Networks and Decision Graphs. Technometrics 2008, 50

    work page 2008

  62. [62]

    Neapolitan, R. E. Probabilistic methods for bioinformatics: With an introduction to bayesian networks; 2009

    work page 2009

  63. [63]

    F.; Ma, B

    Guan, S.; Moran, M. F.; Ma, B. Prediction of LC-MS/MS properties of peptides from sequence by deep learning. Molecular and Cellular Proteomics 2019, 18, 2099--2107

    work page 2019

  64. [64]

    T.; Rahman, M

    Zohora, F. T.; Rahman, M. Z.; Tran, N. H.; Xin, L.; Shan, B.; Li, M. DeepIso: A Deep Learning Model for Peptide Feature Detection from LC-MS map. Scientific Reports 2019, 9, 1--13

    work page 2019

  65. [65]

    B.; Vernardis, S

    Demichev, V.; Messner, C. B.; Vernardis, S. I.; Lilley, K. S.; Ralser, M. DIA-NN: neural networks and interference correction enable deep proteome coverage in high throughput. Nature Methods 2020, 17, 41--44

    work page 2020

  66. [66]

    H.; Zhang, X.; Xin, L.; Shan, B.; Li, M

    Tran, N. H.; Zhang, X.; Xin, L.; Shan, B.; Li, M. De novo peptide sequencing by deep learning. Proceedings of the National Academy of Sciences of the United States of America 2017, 114, 8247--8252

    work page 2017

  67. [67]

    H.; Xin, L.; Chen, X.; Li, M.; Shan, B.; Ghodsi, A

    Qiao, R.; Tran, N. H.; Xin, L.; Chen, X.; Li, M.; Shan, B.; Ghodsi, A. Computationally instrument-resolution-independent de novo peptide sequencing for high-resolution devices. Nature Machine Intelligence 2021, 3, 420--425

    work page 2021

  68. [68]

    H.; Qiao, R.; Xin, L.; Chen, X.; Liu, C.; Zhang, X.; Shan, B.; Ghodsi, A.; Li, M

    Tran, N. H.; Qiao, R.; Xin, L.; Chen, X.; Liu, C.; Zhang, X.; Shan, B.; Ghodsi, A.; Li, M. Deep learning enables de novo peptide sequencing from data-independent-acquisition mass spectrometry. Nature Methods 2019, 16, 63--66

    work page 2019

  69. [69]

    J.; Noble, W

    Spivak, M.; Weston, J.; Tomazela, D.; MacCoss, M. J.; Noble, W. S. Direct Maximization of Protein Identifications from Tandem Mass Spectra. Molecular and Cellular Proteomics 2012, 11, M111.012161

    work page 2012

  70. [70]

    E.; Gygi, S

    Elias, J. E.; Gygi, S. P. Target-decoy search strategy for increased confidence in large-scale protein identifications by mass spectrometry. Nature Methods 2007, 4, 207--214

    work page 2007

  71. [71]

    DeepPep: Deep proteome inference from peptide profiles

    Kim, M.; Eetemadi, A.; Tagkopoulos, I. DeepPep: Deep proteome inference from peptide profiles. PLoS Computational Biology 2017, 13, e1005661

    work page 2017

  72. [72]

    N.; Welling, M

    Kipf, T. N.; Welling, M. Semi-supervised classification with graph convolutional networks. 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings. 2017

    work page 2017

  73. [73]

    Inductive Representation Learning on Large Graphs

    Hamilton, W.; Ying, Z.; Leskovec, J. Inductive Representation Learning on Large Graphs. Advances in Neural Information Processing Systems 30 (NIPS 2017). 2017; pp 1025--1035

    work page 2017

  74. [74]

    D.; Weston, J.; Noble, W

    Käll, L.; Canterbury, J. D.; Weston, J.; Noble, W. S.; MacCoss, M. J. Semi-supervised learning for peptide identification from shotgun proteomics datasets. Nature Methods 2007, 4, 923--925

    work page 2007

  75. [75]

    Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection

    Pang, G.; Yan, C.; Shen, C.; van den Hengel, A.; Bai, X. Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2020; pp 12173--12182

    work page 2020

  76. [76]

    K.; Hoopmann, M

    Eng, J. K.; Hoopmann, M. R.; Jahan, T. A.; Egertson, J. D.; Noble, W. S.; MacCoss, M. J. A Deeper Look into Comet - Implementation and Features. Journal of the American Society for Mass Spectrometry 2015, 26, 1865--1874

    work page 2015

  77. [77]

    K.; Meier, S

    Kreutz, D.; Bileck, A.; Plessl, K.; Wolrab, D.; Groessl, M.; Keppler, B. K.; Meier, S. M.; Gerner, C. Response Profiling Using Shotgun Proteomics Enables Global Metallodrug Mechanisms of Action To Be Established. Chemistry - A European Journal 2017, 23, 1881--1890

    work page 2017

  78. [78]

    Meier, S. M. et al. An Organoruthenium Anticancer Agent Shows Unexpected Target Selectivity For Plectin. Angewandte Chemie - International Edition 2017, 56, 8267--8271

    work page 2017

  79. [79]

    Venkatraman, A.; Dutta, B.; Murugan, E.; Piliang, H.; Lakshminaryanan, R.; Yee, A. C. S.; Pervushin, K. V.; Sze, S. K.; Mehta, J. S. Proteomic Analysis of Amyloid Corneal Aggregates from TGFBI-H626R Lattice Corneal Dystrophy Patient Implicates Serine-Protease HTRA1 in Mutation-Specific Pathogenesis of TGFBIp. Journal of Proteome Research 2017, 16, 2899--2913

    work page 2017

  80. [80]

    Combined proteomic/transcriptomic signature of recurrence post-liver transplantation for hepatocellular carcinoma beyond Milan

    Bhat, M.; Clotet-Freixas, S.; Baciu, C.; Pasini, E.; Hammad, A.; Ivanics, T.; Reid, S.; Azhie, A.; Angeli, M.; Ghanekar, A.; Fischer, S.; Sapisochin, G.; Konvalinka, A. Combined proteomic/transcriptomic signature of recurrence post-liver transplantation for hepatocellular carcinoma beyond Milan. Clinical Proteomics 2021, 18, 1--16

    work page 2021

Showing first 80 references.