← All .science files
pmid:30181805
Identification of key pathways and genes in response to trastuzumab treatment in breast cancer using bioinformatics analysis.
Fanxin Zeng · Jiangping Fu · Fang Hu · Yani Tang · Xiangdong Fang · Fanwei Zeng · Yanpeng Chu
Oncotarget · 2018 doi:10.18632/oncotarget.24605
Paper
complete
Experiment
complete
Data
partial
Analysis
partial
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
paper object · 10 fields
authors array · 7 items
claims array · 2 items
[0] object · 6 fields
[1] object · 6 fields
evidence array · 4 items
[0] object · 3 fields
[1] object · 3 fields
[2] object · 3 fields
gaps array · 0 items
experiment object · 8 fields
steps array · 3 items
[0] object · 13 fields
parameters object · 0 fields
inputs array · 1 item
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
[1] object · 13 fields
parameters object · 0 fields
inputs array · 1 item
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
[2] object · 13 fields
parameters object · 0 fields
inputs array · 1 item
outputs array · 1 item
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
assets array · 5 items
[0] object · 15 fields
structure object · 4 fields
[1] object · 15 fields
structure object · 15 fields
sample_accessions array · 158 items
[2] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 61 items
[0] array · 6 items
[1] array · 6 items
[2] array · 5 items
[3] array · 5 items
[4] array · 5 items
[5] array · 5 items
[6] array · 5 items
[7] array · 5 items
[8] array · 5 items
[9] array · 5 items
[10] array · 5 items
[11] array · 5 items
[12] array · 5 items
[13] array · 5 items
[14] array · 5 items
[15] array · 5 items
[16] array · 5 items
[17] array · 5 items
[18] array · 5 items
[19] array · 5 items
[20] array · 5 items
[21] array · 5 items
[22] array · 5 items
[23] array · 5 items
[24] array · 5 items
[25] array · 5 items
[26] array · 5 items
[27] array · 5 items
[28] array · 5 items
[29] array · 5 items
[30] array · 5 items
[31] array · 6 items
[32] array · 5 items
[33] array · 5 items
[34] array · 5 items
[35] array · 5 items
[36] array · 5 items
[37] array · 5 items
[38] array · 5 items
[39] array · 5 items
[40] array · 5 items
[41] array · 5 items
[42] array · 5 items
[43] array · 5 items
[44] array · 5 items
[45] array · 5 items
[46] array · 6 items
[47] array · 6 items
[48] array · 5 items
[49] array · 6 items
[50] array · 6 items
[51] array · 6 items
[52] array · 6 items
[53] array · 6 items
[54] array · 6 items
[55] array · 6 items
[56] array · 6 items
[57] array · 6 items
[58] array · 6 items
[59] array · 6 items
[60] array · 6 items
[3] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 11 items
[0] array · 5 items
[1] array · 5 items
[2] array · 4 items
[3] array · 4 items
[4] array · 4 items
[5] array · 4 items
[6] array · 5 items
[7] array · 4 items
[8] array · 4 items
[9] array · 4 items
[10] array · 4 items
[4] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 61 items
[0] array · 6 items
[1] array · 6 items
[2] array · 5 items
[3] array · 5 items
[4] array · 5 items
[5] array · 5 items
[6] array · 5 items
[7] array · 5 items
[8] array · 5 items
[9] array · 5 items
[10] array · 5 items
[11] array · 5 items
[12] array · 5 items
[13] array · 5 items
[14] array · 5 items
[15] array · 5 items
[16] array · 5 items
[17] array · 5 items
[18] array · 5 items
[19] array · 5 items
[20] array · 5 items
[21] array · 5 items
[22] array · 5 items
[23] array · 5 items
[24] array · 5 items
[25] array · 5 items
[26] array · 5 items
[27] array · 5 items
[28] array · 5 items
[29] array · 5 items
[30] array · 5 items
[31] array · 6 items
[32] array · 5 items
[33] array · 5 items
[34] array · 5 items
[35] array · 5 items
[36] array · 5 items
[37] array · 5 items
[38] array · 5 items
[39] array · 5 items
[40] array · 5 items
[41] array · 5 items
[42] array · 5 items
[43] array · 5 items
[44] array · 5 items
[45] array · 5 items
[46] array · 6 items
[47] array · 6 items
[48] array · 5 items
[49] array · 6 items
[50] array · 6 items
[51] array · 6 items
[52] array · 6 items
[53] array · 6 items
[54] array · 6 items
[55] array · 6 items
[56] array · 6 items
[57] array · 6 items
[58] array · 6 items
[59] array · 6 items
[60] array · 6 items
gaps array · 2 items
analysis object · 4 fields
methods array · 3 items
[0] object · 10 fields
dsl_operations array · 3 items
missing_operations array · 0 items
parameters object · 0 fields
data_shapes array · 1 item
[1] object · 10 fields
dsl_operations array · 1 item
missing_operations array · 0 items
parameters object · 0 fields
data_shapes array · 1 item
[2] object · 10 fields
dsl_operations array · 0 items
missing_operations array · 0 items
parameters object · 0 fields
data_shapes array · 0 items
targets array · 0 items
gaps array · 1 item
capability object · 3 fields
requirements array · 1 item
[0] object · 6 fields
assay_families array · 9 items
gaps array · 0 items
readiness object · 8 fields
axes object · 3 fields
method object · 5 fields
required_operations array · 3 items
missing_operations array · 0 items
capability object · 4 fields
data object · 6 fields
accessions array · 1 item
resolved_accessions array · 1 item
statements array · 1 item
can_run object · 3 fields
dsl_operations array · 3 items
assets array · 5 items
steps array · 1 item
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
gaps array · 0 items
review object · 5 fields
machine_critique object · 5 fields
reader object · 5 fields
evidence_check object · 2 fields
usage object · 3 fields
stages array · 1 item
[0] object · 4 fields
gaps array · 3 items
provenance object · 7 fields
entities array · 3 items
activities array · 3 items
[0] object · 4 fields
used array · 3 items
[0] object · 3 fields
[1] object · 3 fields
[2] object · 3 fields
[1] object · 4 fields
agents array · 2 items
lineage object · 4 fields
gaps array · 7 items
assays array · 2 items
[0] object · 11 fields
required_operations array · 0 items
source_hashes object · 1 field
evidence array · 1 item
[1] object · 11 fields
required_operations array · 3 items
source_hashes object · 1 field
evidence array · 1 item
Complete file
{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30181805", "kind": "science-record", "revision": 8, "content_hash": "sha256:57a02dfd003e7b93cd601d9cd5d51466dab048864961289fe445ba1e42605193", "created_at": "2026-11-01T15:40:37Z", "updated_at": "2026-11-01T22:00:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of key pathways and genes in response to trastuzumab treatment in breast cancer using bioinformatics analysis.", "doi": "10.18632/oncotarget.24605", "pmid": "30181805", "authors": ["Fanxin Zeng", "Jiangping Fu", "Fang Hu", "Yani Tang", "Xiangdong Fang", "Fanwei Zeng", "Yanpeng Chu"], "journal": "Oncotarget", "year": 2018, "abstract": "Breast cancer (BC) is one of the leading causes of death among women worldwide. The gene expression profile GSE22358 was downloaded from the Gene Expression Omnibus (GEO) database, which included 154 operable early-stage breast cancer samples treated with neoadjuvant capecitabine plus docetaxel, with (34) or without trastuzumab (120), to identify gene signatures during trastuzumab treatment and uncover their potential mechanisms. The gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes pathway (KEGG) enrichment analyses were performed, and a protein-protein interaction (PPI) network of the differentially expressed genes (DEGs) was constructed by Cytoscape software. There were 2284 DEGs, including 1231 up-regulated genes enriched in DNA replication, protein N-linked glycosylation via asparagine, and response to toxic substances, while 1053 down-regulated genes were enriched in axon guidance, protein localization to plasma membrane, protein stabilization, and protein glycosylation. Eight hub genes were identified from the PPI network, including GSK3B, RAC1, PXN, ERBB2, HSP90AA1, FGF2, PIK3R1 and RAC2. Our experimental results showed that GSK3B was also highly expressed in breast cancer tissues and was associated with poor survival, as was β-catenin. In conclusion, the present study indicated that the identified DEGs and hub genes further our understanding of the molecular mechanisms underlying trastuzumab treatment in BC and highlighted GSK3B, which might be used as a molecular target for the treatment of BC.", "claims": [{"id": "claim-method", "statement": "We used a classical t test to identify DEGs with defined a P value cutoff of < 0.05 as statistically significant.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30181805", "locator": "sections[10] \"Identification of DEGs\" paragraph 2", "quote": "We used a classical t test to identify DEGs with defined a P value cutoff of < 0.05 as statistically significant."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The gene expression profiles of GSE22358 were downloaded from the GEO database. GSE22358, which was based on the Agilent GPL5325 platform (Agilent, CA, USA), was submitted by Gluck et al. The GSE22358 dataset contained 154 operable early-stage BC samples receiving neoadjuvant capecitabine plus docetaxel, with (34) or without trastuzumab (120). The raw data files used for the analysis included TXT files (Agilent platform).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30181805", "locator": "sections[9] \"Microarray data\" paragraph 2", "quote": "The gene expression profiles of GSE22358 were downloaded from the GEO database."}, {"asset": "source:pmid:30181805", "locator": "sections[9] \"Microarray data\" paragraph 2", "quote": "GSE22358, which was based on the Agilent GPL5325 platform (Agilent, CA, USA), was submitted by Gluck et al."}, {"asset": "source:pmid:30181805", "locator": "sections[9] \"Microarray data\" paragraph 2", "quote": "The GSE22358 dataset contained 154 operable early-stage BC samples receiving neoadjuvant capecitabine plus docetaxel, with (34) or without trastuzumab (120)."}, {"asset": "source:pmid:30181805", "locator": "sections[10] \"Identification of DEGs\" paragraph 2", "quote": "The raw data files used for the analysis included TXT files (Agilent platform)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "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:30181805"], "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:GSE22358"], "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:GSE22358"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30181805", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/oncotarget.24605", "sha256": "sha256:e37d4d7a04d69ce6f9e9c69d96313b5686c14ef3168aa655bc7cfaba911dc37d", "bytes": 39080, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/oncotarget.24605", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6114942", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE22358", "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=GSE22358", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE22358", "version": null, "note": "The gene expression profiles of GSE22358 were downloaded from the GEO database. GSE22358, which was based on the Agilent GPL5325 platform (Agilent, CA, USA), was submitted by Gluck et al. The GSE22358 dataset contained 154 operable early-stage BC samples receiving neoadjuvant capecitabine plus docetaxel, with (34) or without trastuzumab (120). The raw data files used for the analysis included TXT files (Agilent platform).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The gene expression profiles of GSE22358 were downloaded from the GEO database. GSE22358, which was based on the Agilent GPL5325 platform (Agilent, CA, USA), was submitted by Gluck et al. The GSE22358 dataset contained 154 operable early-stage BC samples receiving neoadjuvant capecitabine plus docetaxel, with (34) or without trastuzumab (120). The raw data files used for the analysis included TXT files (Agilent platform).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM508516", "GSM508517", "GSM508518", "GSM508519", "GSM508520", "GSM508521", "GSM508522", "GSM508524", "GSM508525", "GSM508526", "GSM508527", "GSM508544", "GSM508545", "GSM508546", "GSM508547", "GSM508548", "GSM508549", "GSM508551", "GSM508552", "GSM508553", "GSM508554", "GSM508555", "GSM508556", "GSM508557", "GSM508558", "GSM508559", "GSM508560", "GSM508561", "GSM508562", "GSM508563", "GSM508564", "GSM508565", "GSM508566", "GSM508567", "GSM508568", "GSM508569", "GSM508570", "GSM508571", "GSM508572", "GSM508573", "GSM508574", "GSM508575", "GSM508576", "GSM508577", "GSM508578", "GSM508579", "GSM508580", "GSM508581", "GSM508582", "GSM508583", "GSM508584", "GSM508585", "GSM508586", "GSM508587", "GSM508588", "GSM508589", "GSM508590", "GSM508591", "GSM508592", "GSM508630", "GSM508631", "GSM508632", "GSM508633", "GSM508634", "GSM508635", "GSM508636", "GSM508637", "GSM508638", "GSM508639", "GSM508640", "GSM508641", "GSM508642", "GSM508643", "GSM508644", "GSM508645", "GSM508646", "GSM508647", "GSM508648", "GSM508649", "GSM508650", "GSM508651", "GSM508652", "GSM508653", "GSM508654", "GSM508655", "GSM508656", "GSM508657", "GSM508658", "GSM508659", "GSM508660", "GSM508662", "GSM508663", "GSM508664", "GSM508665", "GSM508666", "GSM508667", "GSM508668", "GSM508669", "GSM508670", "GSM508671", "GSM508672", "GSM508673", "GSM508674", "GSM508675", "GSM508676", "GSM508677", "GSM508678", "GSM508679", "GSM508680", "GSM508681", "GSM508682", "GSM508736", "GSM508737", "GSM508738", "GSM508739", "GSM508740", "GSM508741", "GSM508742", "GSM508743", "GSM508744", "GSM508745", "GSM508746", "GSM508747", "GSM508748", "GSM508749", "GSM508750", "GSM508751", "GSM508752", "GSM508753", "GSM508754", "GSM508755", "GSM508756", "GSM508757", "GSM508758", "GSM508759", "GSM508760", "GSM508761", "GSM508762", "GSM508763", "GSM508764", "GSM508765", "GSM508766", "GSM508767", "GSM508768", "GSM508769", "GSM508770", "GSM508771", "GSM508772", "GSM508773", "GSM508774", "GSM508775", "GSM508776", "GSM517353", "GSM517354", "GSM556167", "GSM556168", "GSM556169", "GSM556170"], "sample_count": 158, "group_sizes": null, "group_sizes_basis": null, "platform": "5325", "taxon": "Homo sapiens", "title": "Clinical and Pathologic Response of the Primary Tumor in Women Receiving Neoadjuvant Docetaxel-Capecitabine (+/- Trastuzumab) Chemotherapy", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30181805:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:04b77696e2651771da7cdfc81dbeef361dea776eb3f325e86517fa7e9377f447", "bytes": 4549, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Gene ontology analysis of differentially expressed genes associated with trastuzumab", "structure": {"pmcid": "PMC6114942", "section_index": 3, "section_title": "Identification of DEGs", "row_count": 61, "column_count": 6}, "table": {"label": "Table 1", "caption": "Gene ontology analysis of differentially expressed genes associated with trastuzumab", "rows": [["Expression", "Category", "Term", "Count", "%", "P-Value"], ["Up-regulated", "GOTERM_BP_DIRECT", "DNA replication", "25", "2", "8.80E-05"], ["GOTERM_BP_DIRECT", "protein N-linked glycosylation via asparagine", "11", "0.9", "1.80E-04"], ["GOTERM_BP_DIRECT", "response to toxic substance", "16", "1.3", "1.10E-03"], ["GOTERM_BP_DIRECT", "mRNA 3’-end processing", "11", "0.9", "1.20E-03"], ["GOTERM_BP_DIRECT", "anaphase-promoting complex-dependent catabolic process", "14", "1.1", "1.70E-03"], ["GOTERM_BP_DIRECT", "DNA damage response, signal transduction by p53 class mediator resulting in cell cycle arrest", "12", "1", "2.00E-03"], ["GOTERM_BP_DIRECT", "cell division", "38", "3.1", "2.00E-03"], ["GOTERM_BP_DIRECT", "mRNA splicing, via spliceosome", "27", "2.2", "2.70E-03"], ["GOTERM_BP_DIRECT", "regulation of signal transduction by p53 class mediator", "18", "1.5", "2.80E-03"], ["GOTERM_BP_DIRECT", "DNA repair", "28", "2.3", "2.90E-03"], ["GOTERM_MF_DIRECT", "DNA polymerase binding", "6", "0.5", "4.00E-04"], ["GOTERM_MF_DIRECT", "ATPase activity", "25", "2", "9.80E-04"], ["GOTERM_MF_DIRECT", "protein binding", "449", "36.5", "2.50E-03"], ["GOTERM_MF_DIRECT", "microtubule binding", "25", "2", "4.70E-03"], ["GOTERM_MF_DIRECT", "poly(A) RNA binding", "96", "7.8", "6.50E-03"], ["GOTERM_MF_DIRECT", "damaged DNA binding", "11", "0.9", "6.70E-03"], ["GOTERM_MF_DIRECT", "histone deacetylase binding", "15", "1.2", "8.60E-03"], ["GOTERM_MF_DIRECT", "helicase activity", "13", "1.1", "1.00E-02"], ["GOTERM_MF_DIRECT", "sulfuric ester hydrolase activity", "5", "0.4", "1.40E-02"], ["GOTERM_MF_DIRECT", "ATP binding", "120", "9.8", "1.50E-02"], ["GOTERM_CC_DIRECT", "nucleoplasm", "238", "19.3", "2.70E-07"], ["GOTERM_CC_DIRECT", "membrane", "181", "14.7", "1.00E-04"], ["GOTERM_CC_DIRECT", "melanosome", "18", "1.5", "1.80E-04"], ["GOTERM_CC_DIRECT", "nucleus", "395", "32.1", "3.00E-04"], ["GOTERM_CC_DIRECT", "intracellular membrane-bounded organelle", "56", "4.6", "5.50E-04"], ["GOTERM_CC_DIRECT", "cytosol", "256", "20.8", "8.50E-04"], ["GOTERM_CC_DIRECT", "kinetochore", "14", "1.1", "1.20E-03"], ["GOTERM_CC_DIRECT", "nucleolus", "76", "6.2", "2.70E-03"], ["GOTERM_CC_DIRECT", "proteasome complex", "11", "0.9", "4.50E-03"], ["GOTERM_CC_DIRECT", "condensed chromosome kinetochore", "13", "1.1", "7.40E-03"], ["", "GOTERM_BP_DIRECT", "axon guidance", "20", "1.9", "1.40E-03"], ["GOTERM_BP_DIRECT", "protein localization to plasma membrane", "11", "1", "1.70E-03"], ["GOTERM_BP_DIRECT", "protein stabilization", "17", "1.6", "3.00E-03"], ["GOTERM_BP_DIRECT", "protein glycosylation", "15", "1.4", "3.00E-03"], ["GOTERM_BP_DIRECT", "regulation of phosphatidylinositol 3-kinase signaling", "12", "1.1", "3.40E-03"], ["GOTERM_BP_DIRECT", "response to cocaine", "8", "0.8", "3.60E-03"], ["GOTERM_BP_DIRECT", "ERBB2 signaling pathway", "8", "0.8", "4.20E-03"], ["GOTERM_BP_DIRECT", "substrate adhesion-dependent cell spreading", "8", "0.8", "4.20E-03"], ["GOTERM_BP_DIRECT", "centrosome localization", "5", "0.5", "4.30E-03"], ["GOTERM_BP_DIRECT", "O-glycan processing", "10", "0.9", "5.20E-03"], ["GOTERM_MF_DIRECT", "solute:proton symporter activity", "3", "0.3", "8.40E-03"], ["GOTERM_MF_DIRECT", "metallocarboxypeptidase activity", "6", "0.6", "1.40E-02"], ["GOTERM_MF_DIRECT", "ErbB-3 class receptor binding", "3", "0.3", "1.60E-02"], ["GOTERM_MF_DIRECT", "calcium-dependent protein binding", "9", "0.9", "1.60E-02"], ["GOTERM_MF_DIRECT", "protein tyrosine phosphatase activity", "12", "1.1", "1.90E-02"], ["Down-regulation", "GOTERM_MF_DIRECT", "receptor signaling protein activity", "7", "0.7", "2.00E-02"], ["", "GOTERM_MF_DIRECT", "protein phosphatase binding", "9", "0.9", "2.00E-02"], ["GOTERM_MF_DIRECT", "protein kinase binding", "31", "2.9", "2.20E-02"], ["", "GOTERM_MF_DIRECT", "zinc ion binding", "81", "7.7", "2.50E-02"], ["", "GOTERM_MF_DIRECT", "1-phosphatidylinositol-3-kinase activity", "7", "0.7", "2.70E-02"], ["", "GOTERM_CC_DIRECT", "Golgi membrane", "58", "5.5", "1.70E-05"], ["", "GOTERM_CC_DIRECT", "endoplasmic reticulum membrane", "77", "7.3", "2.50E-05"], ["", "GOTERM_CC_DIRECT", "membrane", "152", "14.4", "1.10E-03"], ["", "GOTERM_CC_DIRECT", "Golgi apparatus", "67", "6.4", "3.30E-03"], ["", "GOTERM_CC_DIRECT", "actin cytoskeleton", "22", "2.1", "8.50E-03"], ["", "GOTERM_CC_DIRECT", "cytoplasm", "317", "30.1", "1.10E-02"], ["", "GOTERM_CC_DIRECT", "mitochondrial membrane", "12", "1.1", "1.20E-02"], ["", "GOTERM_CC_DIRECT", "axon", "22", "2.1", "1.70E-02"], ["", "GOTERM_CC_DIRECT", "cis-Golgi network", "7", "0.7", "1.80E-02"], ["", "GOTERM_CC_DIRECT", "uropod", "4", "0.4", "1.90E-02"]], "row_count": 61, "column_count": 6, "numeric_cells": 186, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:30181805:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b72b4557cd1b82aee2f3de2f0920b03091151c26060c1d083a9943449eaa1463", "bytes": 862, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#T2", "version": null, "note": "KEGG pathway analysis of differentially expressed genes associated with trastuzumab", "structure": {"pmcid": "PMC6114942", "section_index": 4, "section_title": "KEGG pathway analysis", "row_count": 11, "column_count": 5}, "table": {"label": "Table 2", "caption": "KEGG pathway analysis of differentially expressed genes associated with trastuzumab", "rows": [["Category", "KEEG Term", "Count", "%", "P-Value"], ["Down-regulation", "Proteoglycans in cancer", "23", "2.2", "1.40E-03"], ["ErbB signaling pathway", "13", "1.2", "2.80E-03"], ["Bacterial invasion of epithelial cells", "12", "1.1", "3.40E-03"], ["Insulin signaling pathway", "17", "1.6", "3.70E-03"], ["Neurotrophin signaling pathway", "15", "1.4", "6.00E-03"], ["Up-regulation", "Protein processing in endoplasmic reticulum", "27", "2.2", "1.10E-04"], ["Base excision repair", "8", "0.7", "6.90E-03"], ["Pentose and glucuronate interconversions", "8", "0.7", "1.10E-02"], ["Proteasome", "8", "0.7", "3.20E-02"], ["Ascorbate and aldarate metabolism", "6", "0.5", "3.70E-02"]], "row_count": 11, "column_count": 5, "numeric_cells": 30, "header_rows": 1, "locator": "section[4]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:30181805:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:04b77696e2651771da7cdfc81dbeef361dea776eb3f325e86517fa7e9377f447", "bytes": 4549, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Gene ontology analysis of differentially expressed genes associated with trastuzumab", "structure": {"pmcid": "PMC6114942", "section_index": 10, "section_title": "Identification of DEGs", "row_count": 61, "column_count": 6}, "table": {"label": "Table 1", "caption": "Gene ontology analysis of differentially expressed genes associated with trastuzumab", "rows": [["Expression", "Category", "Term", "Count", "%", "P-Value"], ["Up-regulated", "GOTERM_BP_DIRECT", "DNA replication", "25", "2", "8.80E-05"], ["GOTERM_BP_DIRECT", "protein N-linked glycosylation via asparagine", "11", "0.9", "1.80E-04"], ["GOTERM_BP_DIRECT", "response to toxic substance", "16", "1.3", "1.10E-03"], ["GOTERM_BP_DIRECT", "mRNA 3’-end processing", "11", "0.9", "1.20E-03"], ["GOTERM_BP_DIRECT", "anaphase-promoting complex-dependent catabolic process", "14", "1.1", "1.70E-03"], ["GOTERM_BP_DIRECT", "DNA damage response, signal transduction by p53 class mediator resulting in cell cycle arrest", "12", "1", "2.00E-03"], ["GOTERM_BP_DIRECT", "cell division", "38", "3.1", "2.00E-03"], ["GOTERM_BP_DIRECT", "mRNA splicing, via spliceosome", "27", "2.2", "2.70E-03"], ["GOTERM_BP_DIRECT", "regulation of signal transduction by p53 class mediator", "18", "1.5", "2.80E-03"], ["GOTERM_BP_DIRECT", "DNA repair", "28", "2.3", "2.90E-03"], ["GOTERM_MF_DIRECT", "DNA polymerase binding", "6", "0.5", "4.00E-04"], ["GOTERM_MF_DIRECT", "ATPase activity", "25", "2", "9.80E-04"], ["GOTERM_MF_DIRECT", "protein binding", "449", "36.5", "2.50E-03"], ["GOTERM_MF_DIRECT", "microtubule binding", "25", "2", "4.70E-03"], ["GOTERM_MF_DIRECT", "poly(A) RNA binding", "96", "7.8", "6.50E-03"], ["GOTERM_MF_DIRECT", "damaged DNA binding", "11", "0.9", "6.70E-03"], ["GOTERM_MF_DIRECT", "histone deacetylase binding", "15", "1.2", "8.60E-03"], ["GOTERM_MF_DIRECT", "helicase activity", "13", "1.1", "1.00E-02"], ["GOTERM_MF_DIRECT", "sulfuric ester hydrolase activity", "5", "0.4", "1.40E-02"], ["GOTERM_MF_DIRECT", "ATP binding", "120", "9.8", "1.50E-02"], ["GOTERM_CC_DIRECT", "nucleoplasm", "238", "19.3", "2.70E-07"], ["GOTERM_CC_DIRECT", "membrane", "181", "14.7", "1.00E-04"], ["GOTERM_CC_DIRECT", "melanosome", "18", "1.5", "1.80E-04"], ["GOTERM_CC_DIRECT", "nucleus", "395", "32.1", "3.00E-04"], ["GOTERM_CC_DIRECT", "intracellular membrane-bounded organelle", "56", "4.6", "5.50E-04"], ["GOTERM_CC_DIRECT", "cytosol", "256", "20.8", "8.50E-04"], ["GOTERM_CC_DIRECT", "kinetochore", "14", "1.1", "1.20E-03"], ["GOTERM_CC_DIRECT", "nucleolus", "76", "6.2", "2.70E-03"], ["GOTERM_CC_DIRECT", "proteasome complex", "11", "0.9", "4.50E-03"], ["GOTERM_CC_DIRECT", "condensed chromosome kinetochore", "13", "1.1", "7.40E-03"], ["", "GOTERM_BP_DIRECT", "axon guidance", "20", "1.9", "1.40E-03"], ["GOTERM_BP_DIRECT", "protein localization to plasma membrane", "11", "1", "1.70E-03"], ["GOTERM_BP_DIRECT", "protein stabilization", "17", "1.6", "3.00E-03"], ["GOTERM_BP_DIRECT", "protein glycosylation", "15", "1.4", "3.00E-03"], ["GOTERM_BP_DIRECT", "regulation of phosphatidylinositol 3-kinase signaling", "12", "1.1", "3.40E-03"], ["GOTERM_BP_DIRECT", "response to cocaine", "8", "0.8", "3.60E-03"], ["GOTERM_BP_DIRECT", "ERBB2 signaling pathway", "8", "0.8", "4.20E-03"], ["GOTERM_BP_DIRECT", "substrate adhesion-dependent cell spreading", "8", "0.8", "4.20E-03"], ["GOTERM_BP_DIRECT", "centrosome localization", "5", "0.5", "4.30E-03"], ["GOTERM_BP_DIRECT", "O-glycan processing", "10", "0.9", "5.20E-03"], ["GOTERM_MF_DIRECT", "solute:proton symporter activity", "3", "0.3", "8.40E-03"], ["GOTERM_MF_DIRECT", "metallocarboxypeptidase activity", "6", "0.6", "1.40E-02"], ["GOTERM_MF_DIRECT", "ErbB-3 class receptor binding", "3", "0.3", "1.60E-02"], ["GOTERM_MF_DIRECT", "calcium-dependent protein binding", "9", "0.9", "1.60E-02"], ["GOTERM_MF_DIRECT", "protein tyrosine phosphatase activity", "12", "1.1", "1.90E-02"], ["Down-regulation", "GOTERM_MF_DIRECT", "receptor signaling protein activity", "7", "0.7", "2.00E-02"], ["", "GOTERM_MF_DIRECT", "protein phosphatase binding", "9", "0.9", "2.00E-02"], ["GOTERM_MF_DIRECT", "protein kinase binding", "31", "2.9", "2.20E-02"], ["", "GOTERM_MF_DIRECT", "zinc ion binding", "81", "7.7", "2.50E-02"], ["", "GOTERM_MF_DIRECT", "1-phosphatidylinositol-3-kinase activity", "7", "0.7", "2.70E-02"], ["", "GOTERM_CC_DIRECT", "Golgi membrane", "58", "5.5", "1.70E-05"], ["", "GOTERM_CC_DIRECT", "endoplasmic reticulum membrane", "77", "7.3", "2.50E-05"], ["", "GOTERM_CC_DIRECT", "membrane", "152", "14.4", "1.10E-03"], ["", "GOTERM_CC_DIRECT", "Golgi apparatus", "67", "6.4", "3.30E-03"], ["", "GOTERM_CC_DIRECT", "actin cytoskeleton", "22", "2.1", "8.50E-03"], ["", "GOTERM_CC_DIRECT", "cytoplasm", "317", "30.1", "1.10E-02"], ["", "GOTERM_CC_DIRECT", "mitochondrial membrane", "12", "1.1", "1.20E-02"], ["", "GOTERM_CC_DIRECT", "axon", "22", "2.1", "1.70E-02"], ["", "GOTERM_CC_DIRECT", "cis-Golgi network", "7", "0.7", "1.80E-02"], ["", "GOTERM_CC_DIRECT", "uropod", "4", "0.4", "1.90E-02"]], "row_count": 61, "column_count": 6, "numeric_cells": 186, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}], "gaps": ["asset:data:geo:GSE22358 not downloaded", "asset:data:geo:GSE22358 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "classical t test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We used a classical t test to identify DEGs with defined a P value cutoff of < 0.05 as statistically significant."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE22358"], "resolved_accessions": ["GSE22358"], "statements": ["The gene expression profiles of GSE22358 were downloaded from the GEO database. GSE22358, which was based on the Agilent GPL5325 platform (Agilent, CA, USA), was submitted by Gluck et al. The GSE22358 dataset contained 154 operable early-stage BC samples receiving neoadjuvant capecitabine plus docetaxel, with (34) or without trastuzumab (120). The raw data files used for the analysis included TXT files (Agilent platform)."], "basis": "The paper names GSE22358 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:30181805", "data:geo:GSE22358", "asset:table:pmid:30181805:1", "asset:table:pmid:30181805:2", "asset:table:pmid:30181805:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE22358"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:12:12Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 34133, "completion_tokens": 830, "cached_tokens": 784}}, "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:30181805", "type": "paper", "label": "pmid:30181805"}, {"id": "source:pmid:30181805", "type": "manuscript", "label": "PMID 30181805 full text"}, {"id": "data:geo:GSE22358", "type": "dataset", "label": "GEO GSE22358"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30181805", "type": "paper", "label": "pmid:30181805"}, {"id": "source:pmid:30181805", "type": "manuscript", "label": "PMID 30181805 full text"}, {"id": "data:geo:GSE22358", "type": "dataset", "label": "GEO GSE22358"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30181805", "type": "extraction", "used": ["source:pmid:30181805"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE22358", "type": "accession_resolution", "used": ["data:geo:GSE22358"], "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:30181805", "parent_hash": "sha256:9802737b024ed9b3cbe332403c0ad7b324b4ebb4cefab414c7f2996a72094a70", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE22358 licence not read", "asset:data:geo:GSE22358 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "clinical_trial", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["4 operable early-stage breast cancer samples treated with neoadjuvant capecitabine plus docetaxel, with (34) or without trastuzumab (120), to identify gene signatur"], "order_basis": "paper_text_order:324", "id": "assay:1"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]}