Human-augmented large language model-driven selection of glutathione peroxidase 4 as a candidate blood transcriptional biomarker for circulating erythroid cells.
Biomarkers
Blood transcriptomics
Erythroid cells
Gene prioritization
Generative artificial intelligence
Glutathione peroxidase 4
Large language models
Transcriptional modules
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
05 Oct 2024
05 Oct 2024
Historique:
received:
20
05
2024
accepted:
23
09
2024
medline:
6
10
2024
pubmed:
6
10
2024
entrez:
5
10
2024
Statut:
epublish
Résumé
The identification of optimal candidate genes from large-scale blood transcriptomic data is crucial for developing targeted assays to monitor immune responses. Here, we introduce a novel, optimized large language model (LLM)-based approach for prioritizing candidate biomarkers from blood transcriptional modules. Focusing on module M14.51 from the BloodGen3 repertoire, we implemented a multi-step LLM-driven workflow. Initial high-throughput screening used GPT-4, Claude 3, and Claude 3.5 Sonnet to score and rank the module's constituent genes across six criteria. Top candidates then underwent high-resolution scoring using Consensus GPT, with concurrent manual fact-checking and, when needed, iterative refinement of the scores based on user feedback. Qualitative assessment of literature-based narratives and analysis of reference transcriptome data further refined the selection process. This novel multi-tiered approach consistently identified Glutathione Peroxidase 4 (GPX4) as the top candidate gene for module M14.51. GPX4's role in oxidative stress regulation, its potential as a future drug target, and its expression pattern across diverse cell types supported its selection. The incorporation of reference transcriptome data further validated GPX4 as the most suitable candidate for this module. This study presents an advanced LLM-driven workflow with a novel optimized scoring strategy for candidate gene prioritization, incorporating human-in-the-loop augmentation. The approach identified GPX4 as a key gene in the erythroid cell-associated module M14.51, suggesting its potential utility for biomarker discovery and targeted assay development. By combining AI-driven literature analysis with iterative human expert validation, this method leverages the strengths of both artificial and human intelligence, potentially contributing to the development of biologically relevant and clinically informative targeted assays. Further validation studies are needed to confirm the broader applicability of this human-augmented AI approach.
Identifiants
pubmed: 39369090
doi: 10.1038/s41598-024-73916-5
pii: 10.1038/s41598-024-73916-5
doi:
Substances chimiques
Biomarkers
0
Phospholipid Hydroperoxide Glutathione Peroxidase
EC 1.11.1.12
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
23225Informations de copyright
© 2024. The Author(s).
Références
Geiss, G. K. et al. Direct multiplexed measurement of gene expression with color-coded probe pairs. Nat. Biotechnol.26 (3), 317–325 (2008).
pubmed: 18278033
doi: 10.1038/nbt1385
Spurgeon, S. L., Jones, R. C. & Ramakrishnan, R. High throughput gene expression measurement with real time PCR in a microfluidic dynamic array. PloS One. 3 (2), e1662 (2008).
pubmed: 18301740
pmcid: 2244704
doi: 10.1371/journal.pone.0001662
Tsang, H. F. et al. NanoString, a novel digital color-coded barcode technology: current and future applications in molecular diagnostics. Expert Rev. Mol. Diagn.17 (1), 95–103 (2017).
pubmed: 27917695
doi: 10.1080/14737159.2017.1268533
Hannouf, M. B. et al. Cost-effectiveness analysis of multigene expression profiling assays to guide adjuvant therapy decisions in women with invasive early-stage breast cancer. Pharmacogenomics J.20 (1), 27–46 (2020).
pubmed: 31130722
doi: 10.1038/s41397-019-0089-x
Byron, S. A., Van Keuren-Jensen, K. R., Engelthaler, D. M., Carpten, J. D. & Craig, D. W. Translating RNA sequencing into clinical diagnostics: opportunities and challenges. Nat. Rev. Genet.17 (5), 257–271 (2016).
pubmed: 26996076
pmcid: 7097555
doi: 10.1038/nrg.2016.10
Jiang, Y. et al. Construction of a set of novel and robust gene expression signatures predicting prostate cancer recurrence. Mol. Oncol.12 (9), 1559–1578 (2018).
pubmed: 30024105
pmcid: 6120243
doi: 10.1002/1878-0261.12359
Stark, R., Grzelak, M. & Hadfield, J. RNA sequencing: the teenage years. Nat. Rev. Genet.20 (11), 631–656 (2019).
pubmed: 31341269
doi: 10.1038/s41576-019-0150-2
Wang, Z., Gerstein, M. & Snyder, M. RNA-Seq: a revolutionary tool for transcriptomics. Nat. Rev. Genet.10 (1), 57–63 (2009).
pubmed: 19015660
pmcid: 2949280
doi: 10.1038/nrg2484
Rinchai, D. et al. A modular framework for the development of targeted Covid-19 blood transcript profiling panels. J. Transl Med.18 (1), 291 (2020).
pubmed: 32736569
pmcid: 7393249
doi: 10.1186/s12967-020-02456-z
Brummaier, T. et al. Design of a targeted blood transcriptional panel for monitoring immunological changes accompanying pregnancy. Front. Immunol.15, 1319949 (2024).
pubmed: 38352867
pmcid: 10861739
doi: 10.3389/fimmu.2024.1319949
Toufiq, M. et al. Harnessing large language models (LLMs) for candidate gene prioritization and selection. J. Transl Med.21 (1), 728 (2023).
pubmed: 37845713
pmcid: 10580627
doi: 10.1186/s12967-023-04576-8
Rinchai, D. et al. Definition of erythroid cell-positive blood transcriptome phenotypes associated with severe respiratory syncytial virus infection. Clin. Transl Med.10 (8), e244 (2020).
pubmed: 33377660
pmcid: 7733317
doi: 10.1002/ctm2.244
Hong, S. et al. Longitudinal profiling of human blood transcriptome in healthy and lupus pregnancy. J. Exp. Med.216 (5), 1154–1169 (2019).
pubmed: 30962246
pmcid: 6504211
doi: 10.1084/jem.20190185
Altman, M. C. et al. Development of a fixed module repertoire for the analysis and interpretation of blood transcriptome data. Nat. Commun.12 (1), 4385 (2021).
pubmed: 34282143
pmcid: 8289976
doi: 10.1038/s41467-021-24584-w
Rawat, A. et al. A neutrophil-driven inflammatory signature characterizes the blood transcriptome fingerprint of Psoriasis. Front. Immunol.11, 587946 (2020).
pubmed: 33329570
pmcid: 7732684
doi: 10.3389/fimmu.2020.587946
Rinchai, D. et al. High–temporal resolution profiling reveals distinct immune trajectories following the first and second doses of COVID-19 mRNA vaccines. Sci. Adv.8 (45), eabp9961 (2022).
pubmed: 36367935
pmcid: 9651857
doi: 10.1126/sciadv.abp9961
Novershtern, N. et al. Densely interconnected transcriptional circuits control cell states in human hematopoiesis. Cell. 144 (2), 296–309 (2011).
pubmed: 21241896
pmcid: 3049864
doi: 10.1016/j.cell.2011.01.004
Linsley, P. S., Speake, C., Whalen, E. & Chaussabel, D. Copy number loss of the interferon gene cluster in melanomas is linked to reduced T cell infiltrate and poor patient prognosis. PloS One. 9 (10), e109760 (2014).
pubmed: 25314013
pmcid: 4196925
doi: 10.1371/journal.pone.0109760
Zhao, L. et al. Late-stage tumors induce anemia and immunosuppressive extramedullary erythroid progenitor cells. Nat. Med.24 (10), 1536–1544 (2018).
pubmed: 30297899
pmcid: 6211844
doi: 10.1038/s41591-018-0205-5
Bernardes, J. P. et al. Longitudinal multi-omics analyses identify responses of Megakaryocytes, Erythroid Cells, and plasmablasts as Hallmarks of severe COVID-19. Immunity. 53 (6), 1296–1314e9 (2020).
pubmed: 33296687
pmcid: 7689306
doi: 10.1016/j.immuni.2020.11.017
Ouled-Haddou, H. et al. A new role of glutathione peroxidase 4 during human erythroblast enucleation. Blood Adv.4 (22), 5666–5680 (2020).
pubmed: 33211827
pmcid: 7686909
doi: 10.1182/bloodadvances.2020003100
Rademacher, M., Kuhn, H. & Borchert, A. Expression silencing of Glutathione Peroxidase 4 in mouse erythroleukemia cells delays in Vitro Erythropoiesis. Int. J. Mol. Sci.22 (15), 7795 (2021).
pubmed: 34360557
pmcid: 8345999
doi: 10.3390/ijms22157795
Altamura, S. et al. Glutathione peroxidase 4 and vitamin E control reticulocyte maturation, stress erythropoiesis and iron homeostasis. Haematologica. 105 (4), 937–950 (2020).
pubmed: 31248967
pmcid: 7109755
doi: 10.3324/haematol.2018.212977
Xu, C. et al. The glutathione peroxidase Gpx4 prevents lipid peroxidation and ferroptosis to sustain Treg cell activation and suppression of antitumor immunity. Cell. Rep.35 (11), 109235 (2021).
pubmed: 34133924
doi: 10.1016/j.celrep.2021.109235
Brault, C. et al. Glutathione peroxidase 4 is reversibly induced by HCV to control lipid peroxidation and to increase virion infectivity. Gut. 65 (1), 144–154 (2016).
pubmed: 25516417
doi: 10.1136/gutjnl-2014-307904
Cueto-Ureña, C. et al. Glutathione peroxidase gpx1 to gpx8 genes expression in experimental brain tumors reveals gender-dependent patterns. Genes. 14 (9), 1674 (2023).
pubmed: 37761814
pmcid: 10530768
doi: 10.3390/genes14091674
Sha, R. et al. Predictive and prognostic impact of ferroptosis-related genes ACSL4 and GPX4 on breast cancer treated with neoadjuvant chemotherapy. EBioMedicine. 71, 103560 (2021).
pubmed: 34482070
pmcid: 8417304
doi: 10.1016/j.ebiom.2021.103560
Weaver, K. & Skouta, R. The selenoprotein glutathione peroxidase 4: from Molecular mechanisms to Novel Therapeutic opportunities. Biomedicines. 10 (4), 891 (2022).
pubmed: 35453641
pmcid: 9027222
doi: 10.3390/biomedicines10040891
Garnham, R. et al. ST3 beta-galactoside alpha-2,3-sialyltransferase 1 (ST3Gal1) synthesis of Siglec ligands mediates anti-tumour immunity in prostate cancer. Commun. Biol.7 (1), 276 (2024).
pubmed: 38448753
pmcid: 10918101
doi: 10.1038/s42003-024-05924-0
Lin, W. D. et al. Sialylation of CD55 by ST3GAL1 facilitates Immune Evasion in Cancer. Cancer Immunol. Res.9 (1), 113–122 (2021).
pubmed: 33177111
doi: 10.1158/2326-6066.CIR-20-0203
Zang, Y. et al. Eukaryotic Translation Initiation Factor 3b is both a Promising Prognostic Biomarker and a potential therapeutic target for patients with Clear Cell Renal Cell Carcinoma. J. Cancer. 8 (15), 3049–3061 (2017).
pubmed: 28928896
pmcid: 5604456
doi: 10.7150/jca.19594
Liu, C. et al. The expression of eukaryotic translation initiation factor 3B and its correlation with tumor characteristics as well as prognosis in non-small cell lung cancer patients: a retrospective study. J. BUON Off J. Balk. Union Oncol.25 (5), 2350–2357 (2020).
Rinchai, D. & Chaussabel, D. Assessing the potential relevance of CEACAM6 as a blood transcriptional biomarker [Internet]. F1000Research; [cited 2024 Apr 2]. (2022). https://f1000research.com/articles/11-1294
Rinchai, D. & Chaussabel, D. A training curriculum for retrieving, structuring, and aggregating information derived from the biomedical literature and large-scale data repositories. [Internet]. F1000Research; [cited 2024 Apr 2]. (2022). https://f1000research.com/articles/11-994
Ingold, I. et al. Selenium utilization by GPX4 is required to Prevent Hydroperoxide-Induced ferroptosis. Cell. 172 (3), 409–422e21 (2018).
pubmed: 29290465
doi: 10.1016/j.cell.2017.11.048
Seibt, T. M., Proneth, B. & Conrad, M. Role of GPX4 in ferroptosis and its pharmacological implication. Free Radic Biol. Med.133, 144–152 (2019).
pubmed: 30219704
doi: 10.1016/j.freeradbiomed.2018.09.014
Canli, Ö. et al. Glutathione peroxidase 4 prevents necroptosis in mouse erythroid precursors. Blood. 127 (1), 139–148 (2016).
pubmed: 26463424
pmcid: 4705604
doi: 10.1182/blood-2015-06-654194
Hambright, W. S., Fonseca, R. S., Chen, L., Na, R. & Ran, Q. Ablation of ferroptosis regulator glutathione peroxidase 4 in forebrain neurons promotes cognitive impairment and neurodegeneration. Redox Biol.12, 8–17 (2017).
pubmed: 28212525
pmcid: 5312549
doi: 10.1016/j.redox.2017.01.021
Carlson, B. A. et al. Glutathione peroxidase 4 and vitamin E cooperatively prevent hepatocellular degeneration. Redox Biol.9, 22–31 (2016).
pubmed: 27262435
pmcid: 4900515
doi: 10.1016/j.redox.2016.05.003
Zhang, Y. et al. Imidazole Ketone Erastin Induces Ferroptosis and slows Tumor Growth in a mouse lymphoma model. Cell. Chem. Biol.26 (5), 623–633e9 (2019).
pubmed: 30799221
pmcid: 6525071
doi: 10.1016/j.chembiol.2019.01.008
Yang, W. S. et al. Regulation of ferroptotic cancer cell death by GPX4. Cell. 156 (1–2), 317–331 (2014).
pubmed: 24439385
pmcid: 4076414
doi: 10.1016/j.cell.2013.12.010
Sui, X. et al. RSL3 drives ferroptosis through GPX4 inactivation and ROS production in Colorectal Cancer. Front. Pharmacol.9, 1371 (2018).
pubmed: 30524291
pmcid: 6262051
doi: 10.3389/fphar.2018.01371
Harder, B. et al. Molecular mechanisms of Nrf2 regulation and how these influence chemical modulation for disease intervention. Biochem. Soc. Trans.43 (4), 680–686 (2015).
pubmed: 26551712
pmcid: 4613518
doi: 10.1042/BST20150020
Hangauer, M. J. et al. Drug-tolerant persister cancer cells are vulnerable to GPX4 inhibition. Nature. 551 (7679), 247–250 (2017).
pubmed: 29088702
pmcid: 5933935
doi: 10.1038/nature24297