Corpus Engine Towards a reproducible .science file.
← All .science files

pmid:36081670

Machine Learning and Novel Biomarkers Associated with Immune Infiltration for the Diagnosis of Esophageal Squamous Cell Carcinoma.

Jipeng Zhang · Nian Zhang · Xin Yang · Xiangbin Xin · Cheng-Hui Jia · Sen Li · Qiang Lu · Tao Jiang · Tao Wang

Journal of oncology · 2022 doi:10.1155/2022/6732780

Paper

complete

Experiment

complete

Data

partial

Analysis

complete

Execution

absent

Execution evidence has not yet been added to this .science file. Explore its methods, data and open questions to plan the next step.
Record details sci_version · id · kind · revision · content_hash · schema · created_at · updated_at · generator
id
pmid:36081670
kind
science-record
content_hash
sha256:3f05ebfab2e16c96e969d65b76bad150430c5e683214a7d25f3ec568dea79782
schema
https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json
created_at
2026-11-01T18:15:18Z
updated_at
2026-11-01T22:50:02Z
generator object · 2 fields
name
corpus-assay-engine
run_id
reading-sci-2026-11-01
paper object · 10 fields
state
complete
title
Machine Learning and Novel Biomarkers Associated with Immune Infiltration for the Diagnosis of Esophageal Squamous Cell Carcinoma.
doi
10.1155/2022/6732780
pmid
36081670
authors array · 9 items
[0]
Jipeng Zhang
[1]
Nian Zhang
[2]
Xin Yang
[3]
Xiangbin Xin
[4]
Cheng-Hui Jia
[5]
Sen Li
[6]
Qiang Lu
[7]
Tao Jiang
[8]
Tao Wang
journal
Journal of oncology
year
2022
abstract
Esophageal squamous cell carcinoma (ESCC) accounts for the main esophageal cancer type, which is related to advanced stage and poor survivals. Therefore, novel diagnostic biomarkers are critically needed. In the current research, we aimed to screen novel diagnostic biomarkers based on machine learning. The expression profiles were obtained from GEO datasets (GSE20347, GSE38129, and GSE75241) and TCGA datasets. Differentially expressed genes (DEGs) were screened between 47 ESCC and 47 nontumor samples. The LASSO regression model and SVM-RFE analysis were carried out for the identification of potential markers. ROC analysis was carried out to assess discriminatory abilities. The expressions and diagnostic values of the candidates in ESCC were demonstrated in the GSE75241 datasets and TCGA datasets. We also explore the correlations between the critical genes and cancer immune infiltrates using CIBERSORT. In this study, we identified 27 DEGs in ESCC: 5 genes were significantly elevated, and 22 genes were significantly decreased. Based on the results of the SVM-RFE and LASSO regression model, we identified five potential diagnostic biomarkers for ESCC, including GPX3, COL11A1, EREG, MMP1, and MMP12. However, the diagnostic values of only GPX3, MMP1, and MMP12 were confirmed in GSE75241 datasets. Moreover, in TCGA datasets, we further confirmed that GPX3 expression was distinctly decreased in ESCC specimens, while the expression of MMP1 and MMP12 was noticeably increased in ESCC specimens. Immune cell infiltration analysis revealed that the expression of GPX3, MMP1, and MMP12 was associated with several immune, such as T cells CD8, macrophages M2, macrophages M0, and dendritic cells activated. Overall, our findings suggested GPX3, MMP1, and MMP12 as novel diagnostic marker and correlated with immune infiltrates in ESCC patients.
claims array · 3 items
[0] object · 6 fields
id
claim-method
statement
The DEG analysis was carried out with the help of the Limma program [13]. In order to evaluate the changes in gene expression, an empirical Bayesian methodology was adopted, and moderated t-tests were utilized.
kind
methodological
target
null
evidence array · 1 item
[0] object · 3 fields
asset
source:pmid:36081670
locator
sections[4] "2.2. Identification of Differentially Expressed Genes (DEGs)" paragraph 2
quote
The DEG analysis was carried out with the help of the Limma program [13]. In order to evaluate the changes in gene expression, an empirical Bayesian methodology was adopted, and moderated t-tests were utilized.
state
complete
[1] object · 6 fields
id
claim-data-access
statement
The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.
kind
methodological
target
null
evidence array · 1 item
[0] object · 3 fields
asset
source:pmid:36081670
locator
sections[20] "Data Availability" paragraph 2
quote
The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.
state
complete
[2] object · 6 fields
id
claim-target-result
statement
The diagnostic abilities of GPX3, MMP1, and MMP12 in discriminating ESCC from nontumor specimens confirmed excellent diagnostic values, with an AUC of 0.939 (95% CI 0.879–0.986) in MMP12, AUC of 0.959 (95% CI 0.916–0.990) in MMP1, AUC of 0.985 (95% CI 0.963–0.100) in GPX3, AUC of 0.962 (95% CI 0.922–0.990), and AUC of 0.924 (95% CI 0.853–0.979) (Figure 4).
kind
quantitative
target object · 4 fields
value
95
unit
per cent
tolerance
null
source
The diagnostic abilities of GPX3, MMP1, and MMP12 in discriminating ESCC from nontumor specimens confirmed excellent diagnostic values, with an AUC of 0.939 (95% CI 0.879–0.986) in MMP12, AUC of 0.959 (95% CI 0.916–0.990) in MMP1, AUC of 0.985 (95% CI 0.963–0.100) in GPX3, AUC of 0.962 (95% CI 0.922–0.990), and AUC of 0.924 (95% CI 0.853–0.979) (Figure 4).
evidence array · 1 item
[0] object · 3 fields
asset
source:pmid:36081670
locator
sections[14] "3.4. Diagnostic Effectiveness of Novel Biomarkers in ESCC" paragraph 2
quote
The diagnostic abilities of GPX3, MMP1, and MMP12 in discriminating ESCC from nontumor specimens confirmed excellent diagnostic values, with an AUC of 0.939 (95% CI 0.879–0.986) in MMP12, AUC of 0.959 (95% CI 0.916–0.990) in MMP1, AUC of 0.985 (95% CI 0.963–0.100) in GPX3, AUC of 0.962 (95% CI 0.922–0.990), and AUC of 0.924 (95% CI 0.853–0.979) (Figure 4).
state
complete
gaps array · 0 items
experiment object · 8 fields
state
complete
objective
The diagnostic abilities of GPX3, MMP1, and MMP12 in discriminating ESCC from nontumor specimens confirmed excellent diagnostic values, with an AUC of 0.939 (95% CI 0.879–0.986) in MMP12, AUC of 0.959 (95% CI 0.916–0.990) in MMP1, AUC of 0.985 (95% CI 0.963–0.100) in GPX3, AUC of 0.962 (95% CI 0.922–0.990), and AUC of 0.924 (95% CI 0.853–0.979) (Figure 4).
steps array · 3 items
[0] object · 13 fields
id
read_published_estimate
order
1
name
Read the published estimate from the source
kind
other
state
complete
blocked_on
null
description
The claim, method and evidence span published with the source article.
parameters object · 0 fields
inputs array · 1 item
[0]
source:pmid:36081670
outputs array · 1 item
[0]
the published estimate and its evidence
instruments array · 0 items
reagents array · 0 items
[1] object · 13 fields
id
obtain_source_data
order
2
name
Obtain the source data from the named repository
kind
data-preparation
state
complete
blocked_on
null
description
The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.
parameters object · 0 fields
inputs array · 1 item
[0]
data:geo:GSE20347
outputs array · 1 item
[0]
the source data with its repository provenance
instruments array · 0 items
reagents array · 0 items
[2] object · 13 fields
id
run_analysis
order
3
name
Run the published analysis
kind
analysis
state
complete
blocked_on
null
description
Apply the paper's statistical method to the resolved series and compare the result with the published target.
parameters object · 0 fields
inputs array · 1 item
[0]
data:geo:GSE20347
outputs array · 1 item
[0]
the replicated result and its comparison
instruments array · 0 items
reagents array · 0 items
materials array · 0 items
instruments array · 0 items
reagents array · 0 items
conditions object · 0 fields
gaps array · 0 items
data object · 3 fields
state
partial
assets array · 4 items
[0] object · 15 fields
id
source:pmid:36081670
role
manuscript
format
xml
media_type
application/xml
uri
https://doi.org/10.1155/2022/6732780
sha256
sha256:aff288df7aeb0033472d56045067c0753fe7172ed4d627bb19231c998fe55f22
bytes
21742
access
open
state
resolved
reader
null
reader_status
reader_required
identifier
10.1155/2022/6732780
version
null
note
Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.
structure object · 4 fields
pmcid
PMC9448540
source
europe_pmc_fulltext
coverage
whole_body_without_references
text_hash_scope
rendered_section_body
[1] object · 15 fields
id
data:geo:GSE20347
role
raw
format
geo-series
media_type
application/vnd.ncbi.geo-series+json
uri
https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE20347
sha256
null
bytes
null
access
open
state
resolved
reader
null
reader_status
reader_required
identifier
GSE20347
version
null
note
The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.
structure object · 15 fields
repository
GEO
access_route
GEO accession URL
access_statement_verbatim
The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.
access_statement_kind
data_availability_statement
sample_accessions array · 34 items
[0]
GSM509787
[1]
GSM509788
[2]
GSM509789
[3]
GSM509790
[4]
GSM509791
[5]
GSM509792
[6]
GSM509793
[7]
GSM509794
[8]
GSM509795
[9]
GSM509796
[10]
GSM509797
[11]
GSM509798
[12]
GSM509799
[13]
GSM509800
[14]
GSM509801
[15]
GSM509802
[16]
GSM509803
[17]
GSM509804
[18]
GSM509805
[19]
GSM509806
[20]
GSM509807
[21]
GSM509808
[22]
GSM509809
[23]
GSM509810
[24]
GSM509811
[25]
GSM509812
[26]
GSM509813
[27]
GSM509814
[28]
GSM509815
[29]
GSM509816
[30]
GSM509817
[31]
GSM509818
[32]
GSM509819
[33]
GSM509820
sample_count
34
group_sizes
null
group_sizes_basis
null
platform
571
taxon
Homo sapiens
title
Analysis of gene expression in esophageal squamous cell carcinoma (ESCC)
resolution_checked_at
2026-11-01T15:39:54Z
resolution_check
identifier_resolution_only_no_download_no_licence_read
downloaded
false
licence_read
false
[2] object · 15 fields
id
data:geo:GSE38129
role
raw
format
geo-series
media_type
application/vnd.ncbi.geo-series+json
uri
https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38129
sha256
null
bytes
null
access
open
state
resolved
reader
null
reader_status
reader_required
identifier
GSE38129
version
null
note
The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.
structure object · 15 fields
repository
GEO
access_route
GEO accession URL
access_statement_verbatim
The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.
access_statement_kind
data_availability_statement
sample_accessions array · 60 items
[0]
GSM935144
[1]
GSM935145
[2]
GSM935146
[3]
GSM935147
[4]
GSM935148
[5]
GSM935149
[6]
GSM935150
[7]
GSM935151
[8]
GSM935152
[9]
GSM935153
[10]
GSM935154
[11]
GSM935155
[12]
GSM935156
[13]
GSM935157
[14]
GSM935158
[15]
GSM935159
[16]
GSM935160
[17]
GSM935161
[18]
GSM935162
[19]
GSM935163
[20]
GSM935164
[21]
GSM935165
[22]
GSM935166
[23]
GSM935167
[24]
GSM935168
[25]
GSM935169
[26]
GSM935170
[27]
GSM935171
[28]
GSM935172
[29]
GSM935173
[30]
GSM935174
[31]
GSM935175
[32]
GSM935176
[33]
GSM935177
[34]
GSM935178
[35]
GSM935179
[36]
GSM935180
[37]
GSM935181
[38]
GSM935182
[39]
GSM935183
[40]
GSM935184
[41]
GSM935185
[42]
GSM935186
[43]
GSM935187
[44]
GSM935188
[45]
GSM935189
[46]
GSM935190
[47]
GSM935191
[48]
GSM935192
[49]
GSM935193
[50]
GSM935194
[51]
GSM935195
[52]
GSM935196
[53]
GSM935197
[54]
GSM935198
[55]
GSM935199
[56]
GSM935200
[57]
GSM935201
[58]
GSM935202
[59]
GSM935203
sample_count
60
group_sizes
null
group_sizes_basis
null
platform
571
taxon
Homo sapiens
title
A pilot study of integrative genomics analysis of genes with biallelic loss and its relation to the expression of mRNA and micro-RNA in esophageal squamous cell cancer
resolution_checked_at
2026-11-01T15:39:54Z
resolution_check
identifier_resolution_only_no_download_no_licence_read
downloaded
false
licence_read
false
[3] object · 15 fields
id
data:geo:GSE75241
role
raw
format
geo-series
media_type
application/vnd.ncbi.geo-series+json
uri
https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE75241
sha256
null
bytes
null
access
open
state
resolved
reader
null
reader_status
reader_required
identifier
GSE75241
version
null
note
The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.
structure object · 15 fields
repository
GEO
access_route
GEO accession URL
access_statement_verbatim
The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.
access_statement_kind
data_availability_statement
sample_accessions array · 30 items
[0]
GSM1946756
[1]
GSM1946757
[2]
GSM1946758
[3]
GSM1946759
[4]
GSM1946760
[5]
GSM1946761
[6]
GSM1946762
[7]
GSM1946763
[8]
GSM1946764
[9]
GSM1946765
[10]
GSM1946766
[11]
GSM1946767
[12]
GSM1946768
[13]
GSM1946769
[14]
GSM1946770
[15]
GSM1946771
[16]
GSM1946772
[17]
GSM1946773
[18]
GSM1946774
[19]
GSM1946775
[20]
GSM1946776
[21]
GSM1946777
[22]
GSM1946778
[23]
GSM1946779
[24]
GSM1946780
[25]
GSM1946781
[26]
GSM1946782
[27]
GSM1946783
[28]
GSM1946784
[29]
GSM1946785
sample_count
30
group_sizes
null
group_sizes_basis
null
platform
5175
taxon
Homo sapiens
title
Gene expression profile of esophageal squamous cell carcinoma
resolution_checked_at
2026-11-01T15:39:55Z
resolution_check
identifier_resolution_only_no_download_no_licence_read
downloaded
false
licence_read
false
gaps array · 6 items
[0]
asset:data:geo:GSE20347 not downloaded
[1]
asset:data:geo:GSE20347 licence not read
[2]
asset:data:geo:GSE38129 not downloaded
[3]
asset:data:geo:GSE38129 licence not read
[4]
asset:data:geo:GSE75241 not downloaded
[5]
asset:data:geo:GSE75241 licence not read
analysis object · 4 fields
state
complete
methods array · 3 items
[0] object · 10 fields
id
method-1
family
differential_expression
specific
limma_voom
label
Differential expression analysis
dsl_operations array · 3 items
[0]
normalise_counts
[1]
differential_expression_fit
[2]
fdr_bh
missing_operations array · 0 items
parameters object · 0 fields
data_shapes array · 1 item
[0]
count_matrix_with_condition
evidence object · 3 fields
score
1
band
verbatim
quote
The DEG analysis was carried out with the help of the Limma program [13]. In order to evaluate the changes in gene expression, an empirical Bayesian methodology was adopted, and moderated t-tests were utilized.
[1] object · 10 fields
id
method-2
family
machine_learning
specific
support_vector_machine
label
Machine learning
dsl_operations array · 3 items
[0]
train_classifier
[1]
cross_validate
[2]
roc_auc
missing_operations array · 0 items
parameters object · 0 fields
data_shapes array · 1 item
[0]
labelled_feature_matrix
evidence object · 3 fields
score
0.7
band
medium
quote
SVM
[2] object · 10 fields
id
method-3
family
diagnostic_evaluation
specific
roc
label
Diagnostic test evaluation
dsl_operations array · 6 items
[0]
confusion_counts
[1]
roc_curve
[2]
sensitivity_specificity
[3]
solve_confusion_matrix
[4]
classification_metrics
[5]
published_precision_envelope
missing_operations array · 0 items
parameters object · 0 fields
data_shapes array · 1 item
[0]
reference_standard_and_test
evidence object · 3 fields
score
0.7
band
medium
quote
ROC analysis
targets array · 1 item
[0] object · 8 fields
id
target-published-estimate
claim_id
claim-target-result
operation
classification_metrics
unit
per cent
tolerance
null
state
complete
note
The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none.
gaps array · 0 items
capability object · 3 fields
state
complete
requirements array · 1 item
[0] object · 6 fields
capability_id
capability:computational_analysis
label
Computational analysis platform
assay_families array · 9 items
[0]
meta_analysis
[1]
machine_learning
[2]
survival_analysis
[3]
statistical_regression
[4]
pca
[5]
molecular_docking
[6]
network_analysis
[7]
differential_expression
[8]
gwas
candidate
Automated Assays Laravel application and simulated adapters
gaps array · 0 items
readiness object · 8 fields
state
complete
tier
R1
blocked_on
nothing:replicable_now
axes object · 3 fields
method object · 5 fields
tier
R1
expressible
true
required_operations array · 3 items
[0]
normalise_counts
[1]
differential_expression_fit
[2]
fdr_bh
missing_operations array · 0 items
basis
The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom.
capability object · 4 fields
tier
R1
capability_id
capability:computational_analysis
availability_state
owned
basis
The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here.
data object · 6 fields
tier
R1
reachable
true
accessions array · 3 items
[0]
GSE20347
[1]
GSE38129
[2]
GSE75241
resolved_accessions array · 3 items
[0]
GSE20347
[1]
GSE38129
[2]
GSE75241
statements array · 1 item
[0]
The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.
basis
The paper names GSE20347, GSE38129, GSE75241 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read.
can_run object · 3 fields
dsl_operations array · 3 items
[0]
normalise_counts
[1]
differential_expression_fit
[2]
fdr_bh
assets array · 2 items
[0]
source:pmid:36081670
[1]
data:geo:GSE20347
steps array · 1 item
[0]
run_analysis
must_build object · 5 fields
dsl_operations array · 0 items
converters array · 0 items
readers array · 0 items
capabilities array · 0 items
data_gaps array · 1 item
[0]
data:geo:GSE20347
gaps array · 0 items
review object · 5 fields
state
partial
machine_critique object · 5 fields
kind
extraction_review
reader object · 5 fields
model
MiniMax-M3.1-Flash
provider
minimax
provider_family
minimax
read_at
2026-11-01T18:04:20Z
independence
single_reader
evidence_check object · 2 fields
method
verbatim
availability
verbatim
calls
5
usage object · 3 fields
prompt_tokens
7503
completion_tokens
1943
cached_tokens
264
stages array · 1 item
[0] object · 4 fields
id
extraction
state
complete
reader
MiniMax-M3.1-Flash
provider
minimax
gaps array · 3 items
[0]
review.independent_reader
[1]
review.machine_critique
[2]
review.human_critique
execution object · 5 fields
state
absent
status
not_run
mode
null
runs array · 0 items
gaps array · 1 item
[0]
execution.not_run
provenance object · 7 fields
entities array · 3 items
[0] object · 3 fields
id
pmid:36081670
type
paper
label
pmid:36081670
[1] object · 3 fields
id
source:pmid:36081670
type
manuscript
label
PMID 36081670 full text
[2] object · 3 fields
id
data:geo:GSE20347
type
dataset
label
GEO GSE20347
activities array · 3 items
[0] object · 4 fields
id
activity-reading-sci-2026-11-01
type
classification
used array · 3 items
[0] object · 3 fields
id
pmid:36081670
type
paper
label
pmid:36081670
[1] object · 3 fields
id
source:pmid:36081670
type
manuscript
label
PMID 36081670 full text
[2] object · 3 fields
id
data:geo:GSE20347
type
dataset
label
GEO GSE20347
agent
agent:corpus-assay-engine
[1] object · 4 fields
id
activity-read-36081670
type
extraction
used array · 1 item
[0]
source:pmid:36081670
agent
agent:minimax-reader
[2] object · 4 fields
id
activity-resolve-GSE20347
type
accession_resolution
used array · 1 item
[0]
data:geo:GSE20347
agent
agent:corpus-assay-engine
agents array · 2 items
[0] object · 3 fields
id
agent:corpus-assay-engine
type
software
label
Corpus assay engine
[1] object · 3 fields
id
agent:minimax-reader
type
software
label
MiniMax literature reader
source_run_id
reading-sci-2026-11-01
dsl_catalogue_fingerprint
343fb30756ba6ec3
capability_table_fingerprint
2cb3e42f047d2ecf
snapshot_id
ba34b49490d9bfaf
lineage object · 4 fields
parent_id
pmid:36081670
parent_hash
sha256:95fbe32675f9b838675c6c133d70904654002f5e1bea033344b88f89e10c79e8
fork_of
null
gaps array · 10 items
[0]
asset:data:geo:GSE20347 licence not read
[1]
asset:data:geo:GSE20347 not downloaded
[2]
asset:data:geo:GSE38129 licence not read
[3]
asset:data:geo:GSE38129 not downloaded
[4]
asset:data:geo:GSE75241 licence not read
[5]
asset:data:geo:GSE75241 not downloaded
[6]
execution.not_run
[7]
review.human_critique
[8]
review.independent_reader
[9]
review.machine_critique
assays array · 1 item
[0] object · 11 fields
role
analysis
definition_id
differential_expression
definition_version
f2132e96ae6c7a4e
required_operations array · 3 items
[0]
normalise_counts
[1]
differential_expression_fit
[2]
fdr_bh
support_state
supported
source_hashes object · 1 field
dsl_catalogue
f2132e96ae6c7a4e
evidence array · 1 item
[0]
The DEG analysis was carried out with the help of the Limma program [13]. In order to evaluate the changes in gene expression, an empirical Bayesian methodology was adopted, and moderated t-tests were utilized.
order_basis
analysis_only
id
assay:1
Complete file
{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36081670", "kind": "science-record", "revision": 5, "content_hash": "sha256:3f05ebfab2e16c96e969d65b76bad150430c5e683214a7d25f3ec568dea79782", "created_at": "2026-11-01T18:15:18Z", "updated_at": "2026-11-01T22:50:02Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Machine Learning and Novel Biomarkers Associated with Immune Infiltration for the Diagnosis of Esophageal Squamous Cell Carcinoma.", "doi": "10.1155/2022/6732780", "pmid": "36081670", "authors": ["Jipeng Zhang", "Nian Zhang", "Xin Yang", "Xiangbin Xin", "Cheng-Hui Jia", "Sen Li", "Qiang Lu", "Tao Jiang", "Tao Wang"], "journal": "Journal of oncology", "year": 2022, "abstract": "Esophageal squamous cell carcinoma (ESCC) accounts for the main esophageal cancer type, which is related to advanced stage and poor survivals. Therefore, novel diagnostic biomarkers are critically needed. In the current research, we aimed to screen novel diagnostic biomarkers based on machine learning. The expression profiles were obtained from GEO datasets (GSE20347, GSE38129, and GSE75241) and TCGA datasets. Differentially expressed genes (DEGs) were screened between 47 ESCC and 47 nontumor samples. The LASSO regression model and SVM-RFE analysis were carried out for the identification of potential markers. ROC analysis was carried out to assess discriminatory abilities. The expressions and diagnostic values of the candidates in ESCC were demonstrated in the GSE75241 datasets and TCGA datasets. We also explore the correlations between the critical genes and cancer immune infiltrates using CIBERSORT. In this study, we identified 27 DEGs in ESCC: 5 genes were significantly elevated, and 22 genes were significantly decreased. Based on the results of the SVM-RFE and LASSO regression model, we identified five potential diagnostic biomarkers for ESCC, including GPX3, COL11A1, EREG, MMP1, and MMP12. However, the diagnostic values of only GPX3, MMP1, and MMP12 were confirmed in GSE75241 datasets. Moreover, in TCGA datasets, we further confirmed that GPX3 expression was distinctly decreased in ESCC specimens, while the expression of MMP1 and MMP12 was noticeably increased in ESCC specimens. Immune cell infiltration analysis revealed that the expression of GPX3, MMP1, and MMP12 was associated with several immune, such as T cells CD8, macrophages M2, macrophages M0, and dendritic cells activated. Overall, our findings suggested GPX3, MMP1, and MMP12 as novel diagnostic marker and correlated with immune infiltrates in ESCC patients.", "claims": [{"id": "claim-method", "statement": "The DEG analysis was carried out with the help of the Limma program [13]. In order to evaluate the changes in gene expression, an empirical Bayesian methodology was adopted, and moderated t-tests were utilized.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36081670", "locator": "sections[4] \"2.2. Identification of Differentially Expressed Genes (DEGs)\" paragraph 2", "quote": "The DEG analysis was carried out with the help of the Limma program [13]. In order to evaluate the changes in gene expression, an empirical Bayesian methodology was adopted, and moderated t-tests were utilized."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36081670", "locator": "sections[20] \"Data Availability\" paragraph 2", "quote": "The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The diagnostic abilities of GPX3, MMP1, and MMP12 in discriminating ESCC from nontumor specimens confirmed excellent diagnostic values, with an AUC of 0.939 (95% CI 0.879–0.986) in MMP12, AUC of 0.959 (95% CI 0.916–0.990) in MMP1, AUC of 0.985 (95% CI 0.963–0.100) in GPX3, AUC of 0.962 (95% CI 0.922–0.990), and AUC of 0.924 (95% CI 0.853–0.979) (Figure 4).", "kind": "quantitative", "target": {"value": 95.0, "unit": "per cent", "tolerance": null, "source": "The diagnostic abilities of GPX3, MMP1, and MMP12 in discriminating ESCC from nontumor specimens confirmed excellent diagnostic values, with an AUC of 0.939 (95% CI 0.879–0.986) in MMP12, AUC of 0.959 (95% CI 0.916–0.990) in MMP1, AUC of 0.985 (95% CI 0.963–0.100) in GPX3, AUC of 0.962 (95% CI 0.922–0.990), and AUC of 0.924 (95% CI 0.853–0.979) (Figure 4)."}, "evidence": [{"asset": "source:pmid:36081670", "locator": "sections[14] \"3.4. Diagnostic Effectiveness of Novel Biomarkers in ESCC\" paragraph 2", "quote": "The diagnostic abilities of GPX3, MMP1, and MMP12 in discriminating ESCC from nontumor specimens confirmed excellent diagnostic values, with an AUC of 0.939 (95% CI 0.879–0.986) in MMP12, AUC of 0.959 (95% CI 0.916–0.990) in MMP1, AUC of 0.985 (95% CI 0.963–0.100) in GPX3, AUC of 0.962 (95% CI 0.922–0.990), and AUC of 0.924 (95% CI 0.853–0.979) (Figure 4)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The diagnostic abilities of GPX3, MMP1, and MMP12 in discriminating ESCC from nontumor specimens confirmed excellent diagnostic values, with an AUC of 0.939 (95% CI 0.879–0.986) in MMP12, AUC of 0.959 (95% CI 0.916–0.990) in MMP1, AUC of 0.985 (95% CI 0.963–0.100) in GPX3, AUC of 0.962 (95% CI 0.922–0.990), and AUC of 0.924 (95% CI 0.853–0.979) (Figure 4).", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:36081670"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE20347"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE20347"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36081670", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2022/6732780", "sha256": "sha256:aff288df7aeb0033472d56045067c0753fe7172ed4d627bb19231c998fe55f22", "bytes": 21742, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2022/6732780", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9448540", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE20347", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE20347", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE20347", "version": null, "note": "The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM509787", "GSM509788", "GSM509789", "GSM509790", "GSM509791", "GSM509792", "GSM509793", "GSM509794", "GSM509795", "GSM509796", "GSM509797", "GSM509798", "GSM509799", "GSM509800", "GSM509801", "GSM509802", "GSM509803", "GSM509804", "GSM509805", "GSM509806", "GSM509807", "GSM509808", "GSM509809", "GSM509810", "GSM509811", "GSM509812", "GSM509813", "GSM509814", "GSM509815", "GSM509816", "GSM509817", "GSM509818", "GSM509819", "GSM509820"], "sample_count": 34, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Analysis of gene expression in esophageal squamous cell carcinoma (ESCC)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE38129", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38129", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE38129", "version": null, "note": "The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM935144", "GSM935145", "GSM935146", "GSM935147", "GSM935148", "GSM935149", "GSM935150", "GSM935151", "GSM935152", "GSM935153", "GSM935154", "GSM935155", "GSM935156", "GSM935157", "GSM935158", "GSM935159", "GSM935160", "GSM935161", "GSM935162", "GSM935163", "GSM935164", "GSM935165", "GSM935166", "GSM935167", "GSM935168", "GSM935169", "GSM935170", "GSM935171", "GSM935172", "GSM935173", "GSM935174", "GSM935175", "GSM935176", "GSM935177", "GSM935178", "GSM935179", "GSM935180", "GSM935181", "GSM935182", "GSM935183", "GSM935184", "GSM935185", "GSM935186", "GSM935187", "GSM935188", "GSM935189", "GSM935190", "GSM935191", "GSM935192", "GSM935193", "GSM935194", "GSM935195", "GSM935196", "GSM935197", "GSM935198", "GSM935199", "GSM935200", "GSM935201", "GSM935202", "GSM935203"], "sample_count": 60, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "A pilot study of integrative genomics analysis of genes with biallelic loss and its relation to the expression of mRNA and micro-RNA in esophageal squamous cell cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE75241", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE75241", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE75241", "version": null, "note": "The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1946756", "GSM1946757", "GSM1946758", "GSM1946759", "GSM1946760", "GSM1946761", "GSM1946762", "GSM1946763", "GSM1946764", "GSM1946765", "GSM1946766", "GSM1946767", "GSM1946768", "GSM1946769", "GSM1946770", "GSM1946771", "GSM1946772", "GSM1946773", "GSM1946774", "GSM1946775", "GSM1946776", "GSM1946777", "GSM1946778", "GSM1946779", "GSM1946780", "GSM1946781", "GSM1946782", "GSM1946783", "GSM1946784", "GSM1946785"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Gene expression profile of esophageal squamous cell carcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE20347 not downloaded", "asset:data:geo:GSE20347 licence not read", "asset:data:geo:GSE38129 not downloaded", "asset:data:geo:GSE38129 licence not read", "asset:data:geo:GSE75241 not downloaded", "asset:data:geo:GSE75241 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The DEG analysis was carried out with the help of the Limma program [13]. In order to evaluate the changes in gene expression, an empirical Bayesian methodology was adopted, and moderated t-tests were utilized."}}, {"id": "method-2", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "SVM"}}, {"id": "method-3", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.7, "band": "medium", "quote": "ROC analysis"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "classification_metrics", "expected_value": 95.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE20347", "GSE38129", "GSE75241"], "resolved_accessions": ["GSE20347", "GSE38129", "GSE75241"], "statements": ["The data used to support the findings of this study are included within the article. Additional data can be made available from the corresponding author upon request."], "basis": "The paper names GSE20347, GSE38129, GSE75241 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:36081670", "data:geo:GSE20347"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE20347"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:04:20Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 7503, "completion_tokens": 1943, "cached_tokens": 264}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:36081670", "type": "paper", "label": "pmid:36081670"}, {"id": "source:pmid:36081670", "type": "manuscript", "label": "PMID 36081670 full text"}, {"id": "data:geo:GSE20347", "type": "dataset", "label": "GEO GSE20347"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36081670", "type": "paper", "label": "pmid:36081670"}, {"id": "source:pmid:36081670", "type": "manuscript", "label": "PMID 36081670 full text"}, {"id": "data:geo:GSE20347", "type": "dataset", "label": "GEO GSE20347"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36081670", "type": "extraction", "used": ["source:pmid:36081670"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE20347", "type": "accession_resolution", "used": ["data:geo:GSE20347"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:36081670", "parent_hash": "sha256:95fbe32675f9b838675c6c133d70904654002f5e1bea033344b88f89e10c79e8", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE20347 licence not read", "asset:data:geo:GSE20347 not downloaded", "asset:data:geo:GSE38129 licence not read", "asset:data:geo:GSE38129 not downloaded", "asset:data:geo:GSE75241 licence not read", "asset:data:geo:GSE75241 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The DEG analysis was carried out with the help of the Limma program [13]. In order to evaluate the changes in gene expression, an empirical Bayesian methodology was adopted, and moderated t-tests were utilized."], "order_basis": "analysis_only", "id": "assay:1"}]}