CoChat
Sign Up
Cited by 4

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Building a large gene expression-cancer knowledge base with limited human annotations

Marchesin, Stefano, Menotti, Laura, Giachelle, Fabio, Silvello, Gianmaria, Alonso, Omar·2023·Database
DOI 10.1093/database/baad061PMC PMC10533344
Open this paper in CoChat — free account

Abstract

Cancer prevention is one of the most pressing challenges that public health needs to face. In this regard, data-driven research is central to assist medical solutions targeting cancer. To fully harness the power of data-driven research, it is imperative to have well-organized machine-readable facts into a knowledge base (KB). Motivated by this urgent need, we introduce the Collaborative Oriented Relation Extraction (CORE) system for building KBs with limited manual annotations. CORE is based on the combination of distant supervision and active learning paradigms and offers a seamless, transparent, modular architecture equipped for large-scale processing. We focus on precision medicine and build the largest KB on ‘fine-grained’ gene expression–cancer associations—a key to complement and validate experimental data for cancer research. We show the robustness of CORE and discuss the usefulness of the provided KB. Database URL https://zenodo.org/record/7577127

Overview

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 · 10.1093/database/baad061

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Verification

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?

  • CoreKB stores over 230,000 gene expression-cancer associations automatically generated by the CORE system.

    “CoreKB stores over 230, 000 gene expression-cancer associations, automatically generated by the Collaborative Oriented Relation Extraction (CORE) system [9].”

    From Provenance-driven nanopublications: representing source lineage and trust networks for multi-source assertions (2025) · cites this paper as [9]

    The Search platform section says COREKB provides access to the knowledge base generated by CORE. But Table 4 in Implementation and experiments > Knowledge base creation reports 153,016 facts in its largest version, KB3—not over 230,000 gene expression–cancer associations. (LLM, conf=0.88)

    Checked by a reasoning model — may be wrong.

    Experimental — accuracy not yet measured

  • CORE harvests text from the literature, identifies sentences containing pairs of relevant entities, and extracts fine-grained aspects from them to generate gene expression-cancer associations that can be published as facts-defined as Gene-Cancer Status (GCS).

    “CORE harvests text from the literature, identifies sentences containing pairs of relevant entities, and extracts fine-grained aspects from them to generate gene expression-cancer associations that can be published as facts -defined as Gene-Cancer Status (GCS).”

    From Provenance-driven nanopublications: representing source lineage and trust networks for multi-source assertions (2025) · cites this paper as [9]

    The CORE system > Overview (page unavailable) says CORE collects scientific literature, identifies sentences containing relevant entity pairs, and extracts aspects to produce facts for a knowledge base. Manual annotation and Relation extraction describe the gene expression–cancer aspects and how retained sentences populate that knowledge base. Our copy does not define those facts as “Gene-Cancer Status (GCS)”; it instead defines GCC as gene–cancer context and CCS as change of cancer status. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • Aggregating evidence enables the CORE system to formulate a fact that reflects the most likely scientific consensus, thereby increasing its reliability.

    “Aggregating this evidence enables the system to formulate a fact that reflects the most likely scientific consensus, thereby increasing its reliability.”

    From Provenance-driven nanopublications: representing source lineage and trust networks for multi-source assertions (2025) · cites this paper as [9]

    The CORE system > Overview explains that CORE aggregates sentences about the same entities and assigns higher probabilities to aspect values that recur consistently. Reliability testing says it checks for sufficient, noncontradictory evidence before tagging facts as reliable. But that section also cautions that the resulting gene classes are not definitive; the paper does not establish that a tagged fact reflects the broader scientific consensus. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • CORE is a Knowledge Base Construction (KBC) system based on the combination of ML-based models and domain-expert feedback.

    “CORE is a Knowledge Base Construction (KBC) system based on the combination of ML-based models and domain-expert feedback [9].”

    From Provenance-driven nanopublications: representing source lineage and trust networks for multi-source assertions (2025) · cites this paper as [9]

  • A CoreKB fact may be deemed unreliable if it fails one of the two reliability criteria defined by the CORE system: one sufficiency criterion (with two conditions) and one consistency criterion.

    “A CoreKB fact may be deemed unreliable if it fails one of the two reliability criteria defined by the CORE system: one sufficiency criterion (with two conditions) and one consistency criterion.”

    From Provenance-driven nanopublications: representing source lineage and trust networks for multi-source assertions (2025) · cites this paper as [9]

Self-check

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

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

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 73

  1. Manzoni, 2016, Genome, transcriptome and proteome: the rise of omics data and their integration in biomedical sciences, Brief. Bioinformatics, 19, 286, 10.1093/bib/bbw114 · DOI
  2. Borry, 2018, The challenges of the expanded availability of genomic information: an agenda-setting paper, J. Community Genet., 9, 103, 10.1007/s12687-017-0331-7 · DOI
  3. Neary, 2021, Identifying gene expression patterns associated with drug-specific survival in cancer patients, Sci. Rep., 11, 1, 10.1038/s41598-021-84211-y · DOI
  4. Dugger, 2018, Drug development in the era of precision medicine, Nat. Rev. Drug. Discov., 17, 183, 10.1038/nrd.2017.226 · DOI · Paper page
  5. Li, 2020, A review of precision oncology knowledgebases for determining the clinical actionability of genetic variants, Front. Cell Dev. Biol., 8, 1
  6. Liu, 2016, Learning for biomedical information extraction: methodological review of recent advances, CoRR, 1606.07993, 1
  7. Weikum, 2021, Machine knowledge: creation and curation of comprehensive knowledge bases, Found. Trends Databases, 10, 108, 10.1561/1900000064 · DOI
  8. Wright, 2022, BioAct: biomedical knowledge base construction using active learning, bioRxiv
  9. Ernst, 2018, HighLife: Higher-arity fact harvesting, pp. 1013
  10. Mintz, 2009, Distant supervision for relation extraction without labeled data, pp. 1003
  11. Surdeanu, 2012, Multi-instance multi-label learning for relation extraction, pp. 455
  12. Settles, 1995, Active learning literature survey, Science, 10, 237
  13. Olsson, 2009, A literature survey of active machine learning in the context of natural language processing, SICS Technical Report, 1, 1
  14. Angeli, 2014, Combining distant and partial supervision for relation extraction, pp. 1556
  15. Sterckx, 2014, Using active learning and semantic clustering for noise reduction in distant supervision, pp. 1
  16. Park, 2019, GENT2: an updated gene expression database for normal and tumor tissues, BMC Medical Genom., 12, 1, 10.1186/s12920-019-0514-7 · DOI
  17. Shaul, 2016, MERAV: a tool for comparing gene expression across human tissues and cell types, Nucleic Acids Res., 44, 560, 10.1093/nar/gkv1337 · DOI
  18. Zhang, 2011, International cancer genome consortium data portal - a one-stop shop for cancer genomics data, Database J. Biol. Databases Curation, 2011
  19. Weinstein, 2013, The Cancer Genome Atlas Pan-Cancer Analysis Project, Nat. Genet., 45, 1113, 10.1038/ng.2764 · DOI · Paper page
  20. Dingerdissen, 2018, BioMuta and BioXpress: mutation and expression knowledgebases for cancer biomarker discovery, Nucleic Acids Res., 46, D1128, 10.1093/nar/gkx907 · DOI
  21. Dingerdissen, 2020, OncoMX: a knowledgebase for exploring cancer biomarkers in the context of related cancer and healthy data, JCO Clin. Cancer Inform., 4, 210, 10.1200/CCI.19.00117 · DOI
  22. Gupta, 2018, DEXTER: disease-expression relation extraction from text, Database J. Biol. Databases Curation, 2018
  23. Lee, 2013, CoMAGC: a corpus with multi-faceted annotations of gene-cancer relations, BMC Bioinform., 14, 10.1186/1471-2105-14-323 · DOI
  24. Lee, 2014, OncoSearch: cancer gene search engine with literature evidence, Nucleic Acids Res., 42, 416, 10.1093/nar/gku368 · DOI
  25. Piñero González, 2020, The DisGeNET knowledge platform for disease genomics: 2019 update, Nucleic Acids Res., 48, D845
  26. Bundschus, 2010, Digging for knowledge with information extraction: a case study on human gene-disease associations, pp. 1845
  27. Giachelle, 2023, Searching for reliable facts over a medical knowledge base, 10.1145/3539618.3591822 · DOI · Paper page
  28. Ciardiello, 2014, Delivering precision medicine in oncology today and in future—the promise and challenges of personalised cancer medicine: a position paper by the European Society for Medical Oncology (ESMO), Ann. Oncol., 25, 1673, 10.1093/annonc/mdu217 · DOI
  29. Nalejska, 2014, Prognostic and predictive biomarkers: tools in personalized oncology, Mol Diagn Ther., 18, 273, 10.1007/s40291-013-0077-9 · DOI
  30. Fabian, 2010, Regulation of mRNA translation and stability by microRNAs, Annu. Rev. Biochem., 79, 351, 10.1146/annurev-biochem-060308-103103 · DOI · Paper page
  31. Blenkiron, 2007, miRNAs in cancer: approaches, aetiology, diagnostics and therapy, Hum. Mol. Genet., 16, R106, 10.1093/hmg/ddm056 · DOI
  32. Lehmann, 2015, Dbpedia - a large-scale, multilingual knowledge base extracted from wikipedia, Semantic Web, 6, 167, 10.3233/SW-140134 · DOI
  33. Bollacker, 2008, Freebase: a collaboratively created graph database for structuring human knowledge, pp. 1247
  34. Suchanek, 2007, Yago: a core of semantic knowledge, pp. 697
  35. Vrandecic, 2014, Wikidata: a free collaborative knowledgebase, Commun. ACM, 57, 78, 10.1145/2629489 · DOI
  36. Doan, 2012, Principles of Data Integration
  37. Lenzerini, 2002, Data integration: a theoretical perspective, pp. 233
  38. Ilyas, 2019, Data Cleaning, 10.1145/3310205 · DOI
  39. Li, 2022, A survey on deep learning for named entity recognition, IEEE Trans. Knowl. Data Eng., 34, 50, 10.1109/TKDE.2020.2981314 · DOI
  40. Sevgili, 2022, Neural entity linking: a survey of models based on deep learning, Semantic Web, 13, 527, 10.3233/SW-222986 · DOI
  41. Shen, 2023, Entity linking meets deep learning: techniques and solutions, IEEE Trans. Knowl. Data Eng., 35, 2556
  42. Kumar, 2017, A survey of deep learning methods for relation extraction, CoRR, 1705.03645, 1
  43. Smirnova, 2019, Relation extraction using distant supervision: a survey, ACM Comput. Surv., 51, 10.1145/3241741 · DOI
  44. Shi, 2019, Simple BERT models for relation extraction and semantic role labeling, CoRR, 1904.05255, 1
  45. Hogan, 2021, Knowledge graphs, ACM Comput. Surv., 54
  46. Deshpande, 2013, Building, maintaining, and using knowledge bases: a report from the trenches, pp. 1209
  47. Dong, 2014, Knowledge vault: a web-scale approach to probabilistic knowledge fusion, pp. 601
  48. Grubb, 2022, On reliability scores for knowledge graphs, pp. 1
  49. Ilyas, 2022, Saga: a platform for continuous construction and serving of knowledge at scale, pp. 2259
  50. Fridman Noy, 2019, Industry-scale knowledge graphs: lessons and challenges, Commun. ACM, 62, 36, 10.1145/3331166 · DOI
  51. Haber, 2007, Cancer: drivers and passengers, Nature, 446, 145, 10.1038/446145a · DOI
  52. Maglott, 2011, Entrez Gene: gene-centered information at NCBI, Nucleic Acids Res., 39, 52, 10.1093/nar/gkq1237 · DOI
  53. Bodenreider, 2004, The Unified Medical Language System (UMLS): integrating biomedical terminology, Nucleic Acids Res., 32, 267, 10.1093/nar/gkh061 · DOI · Paper page
  54. Wei, 2013, PubTator: a web-based text mining tool for assisting biocuration, Nucleic Acids Res., 41, 518, 10.1093/nar/gkt441 · DOI
  55. Wei, 2016, Beyond accuracy: creating interoperable and scalable text-mining web services, Bioinform., 32, 1907, 10.1093/bioinformatics/btv760 · DOI
  56. Wei, 2019, PubTator central: automated concept annotation for biomedical full text articles, Nucleic Acids Res., 47, W587, 10.1093/nar/gkz389 · DOI · Paper page
  57. Lipscomb, 2000, Medical Subject Headings (MeSH), Bulletin of the Medical Library Association, 88
  58. Beltagy, 2019, SciBERT: a pretrained language model for scientific text, pp. 3613
  59. Ammar, 2018, Construction of the Literature Graph in Semantic Scholar, pp. 84
  60. Lewis, 1994, Heterogeneous uncertainty sampling for supervised learning, pp. 148
  61. Bravo, 2015, Extraction of relations between genes and diseases from text and large-scale data analysis: implications for translational research, BMC Bioinform., 16, 10.1186/s12859-015-0472-9 · DOI
  62. Bundschus, 2008, Extraction of semantic biomedical relations from text using conditional random fields, BMC Bioinform., 9, 10.1186/1471-2105-9-207 · DOI
  63. Marchesin, 2022, TBGA: a large-scale gene-disease association dataset for biomedical relation extraction, BMC Bioinform., 23, 10.1186/s12859-022-04646-6 · DOI
  64. Testa, 2001, AKT plays a central role in tumorigenesis, Proc. of the National Academy of Sciences, 98, 10983, 10.1073/pnas.211430998 · DOI · Paper page
  65. Cohen, 2013, The AKT genes and their roles in various disorders, American Journal of Medical Genetics Part A, 161, 2931, 10.1002/ajmg.a.36101 · DOI
  66. Braicu, 2019, A comprehensive review on MAPK: a promising therapeutic target in Cancer, Cancers, 11, 10.3390/cancers11101618 · DOI
  67. Bromberg, 1999, Stat3 as an Oncogene, Cell, 98, 295, 10.1016/S0092-8674(00)81959-5 · DOI · Paper page
  68. Slamon, 1989, Studies of the HER-2/neu proto-oncogene in human breast and ovarian cancer, Science, 244, 707, 10.1126/science.2470152 · DOI
  69. Velu, 1987, Epidermal-growth-factor-dependent transformation by a human EGF receptor proto-oncogene, Science, 238, 1408, 10.1126/science.3500513 · DOI
  70. Kroemer, 1997, The proto-oncogene Bcl-2 and its role in regulating apoptosis, Nat. Med., 3, 614, 10.1038/nm0697-614 · DOI · Paper page
  71. Eliyahu, 1984, Participation of p53 cellular tumour antigen in transformation of normal embryonic cells, Nature, 312, 646, 10.1038/312646a0 · DOI
  72. Baker, 1989, Chromosome 17 deletions and p53 gene mutations in colorectal carcinomas, Science, 244, 217, 10.1126/science.2649981 · DOI
  73. Soussi, 2015, TP53: an oncogene in disguise, Cell Death & Differentiation, 22, 1239, 10.1038/cdd.2015.53 · DOI · Paper page

Cited by

Sorted by citations

Metadata

Authors
Marchesin, S., Menotti, L., Giachelle, F., Silvello, G., & Alonso, O.
Venue
Database
Publisher
Oxford University Press (OUP)
Published
2023-01-01
Volume
2023
ISSN
1758-0463
DOI
10.1093/database/baad061
PMC
PMC10533344
Cited by
4
References
3
Language
en
Licence
creativecommons.org/licenses/by/4.0/ (vor, 269 d)

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