Causal Inference, Biomarker Discovery, Graph Neural Network, Feature Selection Article Swipe

PDF

Jiansong Wu , Yulong Yuan , Huangyi Kang ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2511.13295

Biomarker discovery from high-throughput transcriptomic data is crucial for advancing precision medicine. However, existing methods often neglect gene-gene regulatory relationships and lack stability across datasets, leading to conflation of spurious correlations with genuine causal effects. To address these issues, we develop a causal graph neural network (Causal-GNN) method that integrates causal inference with multi-layer graph neural networks (GNNs). The key innovation is the incorporation of causal effect estimation for identifying stable biomarkers, coupled with a GNN-based propensity scoring mechanism that leverages cross-gene regulatory networks. Experimental results demonstrate that our method achieves consistently high predictive accuracy across four distinct datasets and four independent classifiers. Moreover, it enables the identification of more stable biomarkers compared to traditional methods. Our work provides a robust, efficient, and biologically interpretable tool for biomarker discovery, demonstrating strong potential for broad application across medical disciplines.

Related Topics

Concepts

No concepts available.

Metadata

Type: preprint
Landing Page: http://arxiv.org/abs/2511.13295
PDF: https://arxiv.org/pdf/2511.13295
OA Status: green
OpenAlex ID: https://openalex.org/W4416361849

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416361849

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2511.13295

Digital Object Identifier
Title: Causal Inference, Biomarker Discovery, Graph Neural Network, Feature Selection

Work title
Type: preprint

OpenAlex work type
Publication year: 2025

Year of publication
Publication date: 2025-11-17

Full publication date if available
Authors: Jiansong Wu, Yulong Yuan, Huangyi Kang

List of authors in order
Landing page: https://arxiv.org/abs/2511.13295

Publisher landing page
PDF URL: https://arxiv.org/pdf/2511.13295

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2511.13295

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416361849
doi	https://doi.org/10.48550/arxiv.2511.13295
ids.doi	https://doi.org/10.48550/arxiv.2511.13295
ids.openalex	https://openalex.org/W4416361849
fwci
type	preprint
title	Causal Inference, Biomarker Discovery, Graph Neural Network, Feature Selection
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language
locations[0].id	pmh:oai:arXiv.org:2511.13295
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2511.13295
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2511.13295
locations[1].id	doi:10.48550/arxiv.2511.13295
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2511.13295
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5070800977
authorships[0].author.orcid	https://orcid.org/0000-0001-9648-6479
authorships[0].author.display_name	Jiansong Wu
authorships[0].author_position	middle
authorships[0].raw_author_name	Wu, Jingxin
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5009414991
authorships[1].author.orcid
authorships[1].author.display_name	Yulong Yuan
authorships[1].author_position	last
authorships[1].raw_author_name	Yuan, Yulong
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5102538332
authorships[2].author.orcid
authorships[2].author.display_name	Huangyi Kang
authorships[2].author_position	middle
authorships[2].raw_author_name	Kang, Huangyi
authorships[2].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2511.13295
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-11-19T00:00:00
display_name	Causal Inference, Biomarker Discovery, Graph Neural Network, Feature Selection
has_fulltext	False
is_retracted	False
updated_date	2025-11-28T12:08:26.507040
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2511.13295
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2511.13295
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2511.13295
primary_location.id	pmh:oai:arXiv.org:2511.13295
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2511.13295
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2511.13295
publication_date	2025-11-17
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	41, 74, 119
abstract_inverted_index.To	35
abstract_inverted_index.is	6, 61
abstract_inverted_index.it	104
abstract_inverted_index.of	28, 64, 108
abstract_inverted_index.to	26, 113
abstract_inverted_index.we	39
abstract_inverted_index.Our	116
abstract_inverted_index.The	58
abstract_inverted_index.and	20, 99, 122
abstract_inverted_index.for	8, 68, 126, 132
abstract_inverted_index.key	59
abstract_inverted_index.our	88
abstract_inverted_index.the	62, 106
abstract_inverted_index.data	5
abstract_inverted_index.four	96, 100
abstract_inverted_index.from	2
abstract_inverted_index.high	92
abstract_inverted_index.lack	21
abstract_inverted_index.more	109
abstract_inverted_index.that	48, 79, 87
abstract_inverted_index.tool	125
abstract_inverted_index.with	31, 52, 73
abstract_inverted_index.work	117
abstract_inverted_index.broad	133
abstract_inverted_index.graph	43, 54
abstract_inverted_index.often	15
abstract_inverted_index.these	37
abstract_inverted_index.across	23, 95, 135
abstract_inverted_index.causal	33, 42, 50, 65
abstract_inverted_index.effect	66
abstract_inverted_index.method	47, 89
abstract_inverted_index.neural	44, 55
abstract_inverted_index.stable	70, 110
abstract_inverted_index.strong	130
abstract_inverted_index.(GNNs).	57
abstract_inverted_index.address	36
abstract_inverted_index.coupled	72
abstract_inverted_index.crucial	7
abstract_inverted_index.develop	40
abstract_inverted_index.enables	105
abstract_inverted_index.genuine	32
abstract_inverted_index.issues,	38
abstract_inverted_index.leading	25
abstract_inverted_index.medical	136
abstract_inverted_index.methods	14
abstract_inverted_index.neglect	16
abstract_inverted_index.network	45
abstract_inverted_index.results	85
abstract_inverted_index.robust,	120
abstract_inverted_index.scoring	77
abstract_inverted_index.However,	12
abstract_inverted_index.accuracy	94
abstract_inverted_index.achieves	90
abstract_inverted_index.compared	112
abstract_inverted_index.datasets	98
abstract_inverted_index.distinct	97
abstract_inverted_index.effects.	34
abstract_inverted_index.existing	13
abstract_inverted_index.methods.	115
abstract_inverted_index.networks	56
abstract_inverted_index.provides	118
abstract_inverted_index.spurious	29
abstract_inverted_index.Biomarker	0
abstract_inverted_index.GNN-based	75
abstract_inverted_index.Moreover,	103
abstract_inverted_index.advancing	9
abstract_inverted_index.biomarker	127
abstract_inverted_index.datasets,	24
abstract_inverted_index.discovery	1
abstract_inverted_index.gene-gene	17
abstract_inverted_index.inference	51
abstract_inverted_index.leverages	80
abstract_inverted_index.mechanism	78
abstract_inverted_index.medicine.	11
abstract_inverted_index.networks.	83
abstract_inverted_index.potential	131
abstract_inverted_index.precision	10
abstract_inverted_index.stability	22
abstract_inverted_index.biomarkers	111
abstract_inverted_index.conflation	27
abstract_inverted_index.cross-gene	81
abstract_inverted_index.discovery,	128
abstract_inverted_index.efficient,	121
abstract_inverted_index.estimation	67
abstract_inverted_index.innovation	60
abstract_inverted_index.integrates	49
abstract_inverted_index.predictive	93
abstract_inverted_index.propensity	76
abstract_inverted_index.regulatory	18, 82
abstract_inverted_index.application	134
abstract_inverted_index.biomarkers,	71
abstract_inverted_index.demonstrate	86
abstract_inverted_index.identifying	69
abstract_inverted_index.independent	101
abstract_inverted_index.multi-layer	53
abstract_inverted_index.traditional	114
abstract_inverted_index.(Causal-GNN)	46
abstract_inverted_index.Experimental	84
abstract_inverted_index.biologically	123
abstract_inverted_index.classifiers.	102
abstract_inverted_index.consistently	91
abstract_inverted_index.correlations	30
abstract_inverted_index.disciplines.	137
abstract_inverted_index.demonstrating	129
abstract_inverted_index.incorporation	63
abstract_inverted_index.interpretable	124
abstract_inverted_index.relationships	19
abstract_inverted_index.identification	107
abstract_inverted_index.transcriptomic	4
abstract_inverted_index.high-throughput	3
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	3
citation_normalized_percentile