CoChat
Sign Up
Cited by 219Cancer Immunotherapy and BiomarkersBioinformatics and Genomic NetworksBreast Cancer Treatment Studies

Network-based machine learning approach to predict immunotherapy response in cancer patients

Open access
Kong, JungHo, Ha, Doyeon, Lee, Juhun, Kim, Inhae, Park, Minhyuk, Im, Sin-Hyeog, Shin, Kunyoo, Kim, Sanguk·2022·Nature Communications
DOI 10.1038/s41467-022-31535-6PMC PMC9240063
Open this paper in CoChat — free accountOpen PDF

Abstract

Immune checkpoint inhibitors (ICIs) have substantially improved the survival of cancer patients over the past several years. However, only a minority of patients respond to ICI treatment (~30% in solid tumors), and current ICI-response-associated biomarkers often fail to predict the ICI treatment response. Here, we present a machine learning (ML) framework that leverages network-based analyses to identify ICI treatment biomarkers (NetBio) that can make robust predictions. We curate more than 700 ICI-treated patient samples with clinical outcomes and transcriptomic data, and observe that NetBio-based predictions accurately predict ICI treatment responses in three different cancer types—melanoma, gastric cancer, and bladder cancer. Moreover, the NetBio-based prediction is superior to predictions based on other conventional ICI treatment biomarkers, such as ICI targets or tumor microenvironment-associated markers. This work presents a network-based method to effectively select immunotherapy-response-associated biomarkers that can make robust ML-based predictions for precision oncology.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41467-022-31535-6

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • PathTIGR consistently outperformed published biomarkers (PD-L1 expression (CD274), TMB, CTL.flag, TAM.M2, TIDE, NetBio, Wang et al., and Long et al.) in immunotherapy response prediction.

    “Across this comprehensive biomarker panel, PathTIGR consistently outperformed existing approaches, demonstrating particular strength in accuracy metrics critical for clinical decision-making.”

    From PathTIGR: A pathway topology-informed graph representation learning framework for immunotherapy response prediction (2026) · cites this paper as [40]

    The Discussion (page unavailable) reports that NetBio-based predictions performed better than gene-, tumor-microenvironment-, and data-driven approaches. Our copy does not address PathTIGR or its claimed comparison against the listed biomarker panel; searches for PathTIGR and the named comparators found no such result. (LLM, conf=0.76)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 66

  1. [1]Gide TN Wilmott JS Scolyer RA Long GV Primary and acquired resistance to immune checkpoint inhibitors in metastatic melanoma Clin. Cancer Res. 2018 24 1260 1270 29127120
  2. [2]Havel JJ Chowell D Chan TA The evolving landscape of biomarkers for checkpoint inhibitor immunotherapy Nat. Rev. Cancer 2019 19 133 150 30755690 PMC6705396
  3. [3]Bai R Lv Z Xu D Cui J Predictive biomarkers for cancer immunotherapy with immune checkpoint inhibitors Biomark. Res. 2020 8 34 32864131 PMC7450548
  4. [4]Chan TA Development of tumor mutation burden as an immunotherapy biomarker: Utility for the oncology clinic Ann. Oncol. 2019 30 44 56 30395155 PMC6336005
  5. [5]Topalian SL Safety, Activity, and Immune Correlates of Anti–PD-1 Antibody in Cancer N. Engl. J. Med. 2012 366 2443 2454 22658127 PMC3544539
  6. [6]Xu Y The association of PD-L1 expression with the efficacy of anti-PD-1/PD-L1 immunotherapy and survival of non-small cell lung cancer patients: A meta-analysis of randomized controlled trials Transl. Lung Cancer Res. 2019 8 413 428 31555516 PMC6749123
  7. [8]Brahmer J Nivolumab versus docetaxel in advanced squamous-cell non-small-cell lung cancer N. Engl. J. Med. 2015 373 123 135 26028407 PMC4681400
  8. [9]Hanna, G. J. et al. Frameshift events predict anti-PD-1/L1 response in head and neck cancer. JCI Insight3, e98811(2018). PMC5916245 29467336
  9. [12]Litchfield K Meta-analysis of tumor- and T cell-intrinsic mechanisms of sensitization to checkpoint inhibition Cell 2021 184 596 614.e14 33508232 PMC7933824
  10. [13]Auslander N Robust prediction of response to immune checkpoint blockade therapy in metastatic melanoma Nat. Med. 2018 24 1545 1549 30127394 PMC6693632
  11. [14]Jiang P Signatures of T cell dysfunction and exclusion predict cancer immunotherapy response Nat. Med. 2018 24 1550 1558 30127393 PMC6487502
  12. [15]Lee JS Synthetic lethality-mediated precision oncology via the tumor transcriptome Cell 2021 184 2487 2502.e13 33857424 PMC9310669
  13. [16]Lapuente-Santana Ó van Genderen M Hilbers PAJ Finotello F Eduati F Interpretable systems biomarkers predict response to immune-checkpoint inhibitors Patterns 2021 2 100293 34430923 PMC8369166
  14. [19]Menche J Uncovering disease-disease relationships through the incomplete interactome Science (1979) 2015 347 1257601 1257601 PMC4435741 25700523
  15. [20]Fernández-Torras, A., Duran-Frigola, M. & Aloy, P. Encircling the regions of the pharmacogenomic landscape that determine drug response. Genome Med.11, 17 (2019). PMC6436215 30914058
  16. [21]Hofree M Shen JP Carter H Gross A Ideker T Network-based stratification of tumor mutations Nat. Methods 2013 10 1108 1115 24037242 PMC3866081
  17. [23]Kong, J. H. et al. Network-based machine learning in colorectal and bladder organoid models predicts anti-cancer drug efficacy in patients. Nat. Commun.11, 5485 (2020). PMC7599252 33127883
  18. [24]Szklarczyk D STRING v11: Protein-protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets Nucleic Acids Res. 2019 47 D607 D613 30476243 PMC6323986
  19. [25]Shin, D., Lee, J., Gong, J. R. & Cho, K. H. Percolation transition of cooperative mutational effects in colorectal tumorigenesis. Nat. Commun.8, 1270 (2017). PMC5668266 29097710
  20. [26]Jassal, B. et al. The reactome pathway knowledgebase. Nucleic Acids Res.48, D498–D503 (2020). PMC7145712 31691815
  21. [27]Gide TN Distinct immune cell populations define response to anti-PD-1 monotherapy and anti-PD-1/Anti-CTLA-4 combined therapy Cancer Cell 2019 35 238 255.e6 30753825
  22. [29]Kim ST Comprehensive molecular characterization of clinical responses to PD-1 inhibition in metastatic gastric cancer Nat. Med. 2018 24 1449 1458 30013197
  23. [30]Mariathasan S TGFβ attenuates tumour response to PD-L1 blockade by contributing to exclusion of T cells Nature 2018 554 544 548 29443960 PMC6028240
  24. [31]Prat A Immune-related gene expression profiling after PD-1 blockade in non–small cell lung carcinoma, head and neck squamous cell carcinoma, and melanoma Cancer Res. 2017 77 3540 3550 28487385
  25. [33]Huang AC A single dose of neoadjuvant PD-1 blockade predicts clinical outcomes in resectable melanoma Nat. Med. 2019 25 454 461 30804515 PMC6699626
  26. [34]Sakellaropoulos T A deep learning framework for predicting response to therapy in cancer Cell Rep. 2019 29 3367 3373.e4 31825821
  27. [35]Tomczak K Czerwińska P Wiznerowicz M The Cancer Genome Atlas (TCGA): an immeasurable source of knowledge Wspolczesna Onkologia 2015 1A 68 77 PMC4322527 25691825
  28. [36]Thorsson V The immune landscape of cancer Immunity 2018 48 812 830.e14 29628290 PMC5982584
  29. [37]Akbani R Genomic classification of cutaneous melanoma Cell 2015 161 1681 96 26091043 PMC4580370
  30. [38]Im JH FGF2 alters macrophage polarization, tumour immunity and growth and can be targeted during radiotherapy Nat. Commun. 2020 11 4064 32792542 PMC7426415
  31. [39]Bird JJ Helper T cell differentiation is controlled by the cell cycle Immunity 1998 9 229 237 9729043
  32. [40]Taber, A. et al. Molecular correlates of cisplatin-based chemotherapy response in muscle invasive bladder cancer by integrated multi-omics analysis. Nat. Commun.11, 4858 (2020). PMC7519650 32978382
  33. [41]Shim JH HLA-corrected tumor mutation burden and homologous recombination deficiency for the prediction of response to PD-(L)1 blockade in advanced non-small-cell lung cancer patients Ann. Oncol. 2020 31 902 911 32320754
  34. [42]Strickler JH Hanks BA Khasraw M Tumor mutational burden as a predictor of immunotherapy response: Is more always better? Clin. Cancer Res. 2021 27 1236 1241 33199494 PMC9912042
  35. [43]Leiserson MDM Pan-cancer network analysis identifies combinations of rare somatic mutations across pathways and protein complexes Nat. Genet. 2015 47 106 14 25501392 PMC4444046
  36. [44]Cheng F Comprehensive characterization of protein–protein interactions perturbed by disease mutations Nat. Genet. 2021 53 342 353 33558758 PMC8237108
  37. [45]Kim D Evolutionary coupling analysis identifies the impact of disease-associated variants at less-conserved sites Nucleic Acids Res. 2019 47 e94 e94 31199866 PMC6895274
  38. [46]Han SK Kong J Kim S Lee JH Han DH Exomic and transcriptomic alterations of hereditary gingival fibromatosis Oral. Dis. 2019 25 1374 1383 30907493
  39. [47]Yang, J. S. et al. Spatial and functional organization of mitochondrial protein network. Sci. Rep.3, 1403 (2013). PMC3590558 23466738
  40. [48]Kim J Rewiring of PDZ domain-ligand interaction network contributed to eukaryotic evolution PLoS Genet. 2012 8 e1002510 22346764 PMC3276551
  41. [49]Choi DS The protein interaction network of extracellular vesicles derived from human colorectal cancer cells J. Proteome Res. 2012 11 1144 1151 22149170
  42. [50]Jeon J Network clustering revealed the systemic alterations of mitochondrial protein expression PLoS Comput. Biol. 2011 7 e1002093 21738461 PMC3127811
  43. [51]Han SK Kim I Hwang J Kim S Network modules of the cross-species genotype-phenotype map reflect the clinical severity of human diseases PLoS ONE 2015 10 e0136300 26301634 PMC4547739
  44. [52]Kim, I. et al. Link clustering explains non-central and contextually essential genes in protein interaction networks. Sci. Rep.9, 11672 (2019). PMC6690968 31406201
  45. [53]Kim J Kim I Han SK Bowie JU Kim S Network rewiring is an important mechanism of gene essentiality change Sci. Rep. 2012 2 900 23198090 PMC3509348
  46. [54]Cowen L Ideker T Raphael BJ Sharan R Network propagation: A universal amplifier of genetic associations Nat. Rev. Genet. 2017 18 551 562 28607512
  47. [55]Guney E Oliva B Exploiting protein-protein interaction networks for genome-wide disease-gene prioritization PLoS ONE 2012 7 e43557 23028459 PMC3448640
  48. [56]Erten S Bebek G Ewing RM Koyutürk M DADA: degree-aware algorithms for network-based disease gene prioritization BioData Min. 2011 4 19 21699738 PMC3143097
  49. [57]Angell HK Bruni D Carl Barrett J Herbst R Galon J The immunoscore: colon cancer and beyond Clin. Cancer Res. 2020 26 332 339 31413009
  50. [58]DeNardo DG Ruffell B Macrophages as regulators of tumour immunity and immunotherapy Nat. Rev. Immunol. 2019 19 369 382 30718830 PMC7339861
  51. [59]Luca BA Atlas of clinically distinct cell states and ecosystems across human solid tumors Cell 2021 184 5482 5496.e28 34597583 PMC8526411
  52. [60]Johnson WE Li C Rabinovic A Adjusting batch effects in microarray expression data using empirical Bayes methods Biostatistics 2007 8 118 27 16632515
  53. [61]Yu S Liu D Shen B Shi M Feng J Immunotherapy strategy of EGFR mutant lung cancer Am. J. Cancer Res 2018 8 2106 2115 30416860 PMC6220136
  54. [62]Colaprico A TCGAbiolinks: an R/Bioconductor package for integrative analysis of TCGA data Nucleic Acids Res. 2016 44 e71 e71 26704973 PMC4856967
  55. [63]Wang, X. & Li, M. Correlate tumor mutation burden with immune signatures in human cancers. BMC Immunol.20, 4 (2019). PMC6329192 30634925
  56. [64]Robinson MD Oshlack A A scaling normalization method for differential expression analysis of RNA-seq data Genome Biol. 2010 11 R25 20196867 PMC2864565
  57. [65]Robinson, M. D., McCarthy, D. J. & Smyth, G. K. edgeR: a bioconductor package for differential expression analysis of digital gene expression data. Bioinformatics26, 139–140 (2009). PMC2796818 19910308
  58. [68]Sharifi-Noghabi H Peng S Zolotareva O Collins CC Ester M AITL: adversarial inductive transfer learning with input and output space adaptation for pharmacogenomics Bioinformatics 2020 36 i380 i388 32657371 PMC7355265
  59. [69]Majumder B Predicting clinical response to anticancer drugs using an ex vivo platform that captures tumour heterogeneity Nat. Commun. 2015 6 6169 25721094 PMC4351621
  60. [70]Geeleher, P., Cox, N. J. & Huang, R. S. Clinical drug response can be predicted using baseline gene expression levels and in vitro drug sensitivity in cell lines. Genome Biol.15, R47 (2014). PMC4054092 24580837
  61. [71]Ding Z Zu S Gu J Evaluating the molecule-based prediction of clinical drug responses in cancer Bioinformatics 2016 32 2891 2895 27354694
  62. [72]Hagberg, A. A., Schult, D. A. & Swart, P. J. Exploring network structure, dynamics, and function using NetworkX. in 7th Python in Science Conference (SciPy 2008) (2008).
  63. [75]Seabold, S. & Perktold, J. Statsmodels: Econometric and Statistical Modeling with Python. Proceedings of the 9th Python in Science Conference (2010), 92–96.
  64. [78]Lakatos E Evolutionary dynamics of neoantigens in growing tumors Nat. Genet. 2020 52 1057 1066 32929288 PMC7610467
  65. [80]Zhang N Predicting anticancer drug responses using a dual-layer integrated cell line-drug network model PLoS Comput. Biol. 2015 11 e1004498 26418249 PMC4587957
  66. [82]Kong J Ha D Lee J Network-based machine learning approach to predict immunotherapy response in cancer patients Zenodo 2022 10.5281/zenodo.6602221 PMC9240063 35764641 · DOI

Cited by

Sorted by citations

Authors
Kong, J., Ha, D., Lee, J., Kim, I., Park, M., Im, S.-H., Shin, K., & Kim, S.
Affiliations
  • Pohang University of Science and Technology (KR)
  • ImmunoBiome, Inc. (Korea) (KR)
Corresponding author
Kim, Sanguk
ORCID
Venue
Nature Communications
Publisher
Springer Science and Business Media LLC
Published
2022-06-28
Volume
13
Issue
1
Pages
3703-3703
ISSN
2041-1723 (ISSN-L)
DOI
10.1038/s41467-022-31535-6
PMC
PMC9240063
OpenAlex
W4283662269
Cited by
219
References
14
Citations by year
2026: 39 · 2025: 67 · 2024: 64 · 2023: 45 · 2022: 3
FWCI
18.73
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Communications (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Seoul National University Open Repository (Seoul National University) (submittedVersion)
Funders
  • National Research Foundation (2021R1A2B5B01001903, 2020R1A6A1A03047902)
  • Pohang University of Science and Technology (2021R1A2B5B01001903, 2019-0-01906)
  • Ministry of Oceans and Fisheries ((20150242))
  • Institute for Information and Communications Technology Promotion (2019-0-01906)
Topics
  • Health Sciences › Medicine › Oncology › Cancer Immunotherapy and Biomarkers
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Cancer Research › Breast Cancer Treatment Studies
Keywords
immune checkpoint inhibitors, immunotherapy response prediction, precision oncology, transcriptomic data, melanoma, gastric cancer, bladder cancer, tumor microenvironment, treatment biomarkers
MeSH terms
Machine Learning, Humans, Immunologic Factors, Immunotherapy, Melanoma, Biomarkers, Tumor, Precision Medicine, Tumor Microenvironment

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review