← All .science files
pmid:41311650
MASE-GC: a multi-omics autoencoder and stacking ensemble framework for gastric cancer classification.
Frontiers in cell and developmental biology · 2025 doi:10.3389/fcell.2025.1704237
Paper
partial
Experiment
partial
Data
partial
Analysis
absent
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
generator object · 3 fields
paper object · 10 fields
claims array · 1 item
gaps array · 2 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 · 0 items
outputs array · 1 item
instruments array · 0 items
reagents array · 0 items
[2] object · 13 fields
parameters object · 0 fields
inputs array · 0 items
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 · 3 items
data object · 3 fields
assets array · 8 items
[0] object · 15 fields
structure object · 1 field
[1] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 5 items
[0] array · 5 items
[1] array · 5 items
[2] array · 5 items
[3] array · 5 items
[4] array · 5 items
[2] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 6 items
[0] array · 4 items
[1] array · 4 items
[2] array · 4 items
[3] array · 4 items
[4] array · 4 items
[5] array · 4 items
[3] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 6 items
[0] array · 6 items
[1] array · 6 items
[2] array · 6 items
[3] array · 6 items
[4] array · 6 items
[5] array · 6 items
[4] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 6 items
[0] array · 6 items
[1] array · 6 items
[2] array · 6 items
[3] array · 6 items
[4] array · 6 items
[5] array · 6 items
[5] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 8 items
[0] array · 6 items
[1] array · 6 items
[2] array · 6 items
[3] array · 6 items
[4] array · 6 items
[5] array · 6 items
[6] array · 6 items
[7] array · 6 items
[6] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 7 items
[0] array · 4 items
[1] array · 4 items
[2] array · 4 items
[3] array · 4 items
[4] array · 4 items
[5] array · 4 items
[6] array · 4 items
[7] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 5 items
[0] array · 7 items
[1] array · 7 items
[2] array · 7 items
[3] array · 7 items
[4] array · 7 items
gaps array · 1 item
capability object · 3 fields
readiness object · 8 fields
axes object · 0 fields
can_run object · 3 fields
dsl_operations array · 0 items
assets array · 8 items
steps array · 1 item
must_build object · 5 fields
dsl_operations array · 0 items
converters array · 0 items
readers array · 1 item
capabilities array · 0 items
data_gaps array · 1 item
gaps array · 1 item
review object · 5 fields
machine_critique object · 7 fields
providers array · 0 items
target_providers array · 0 items
disagreements array · 0 items
agreement_basis object · 2 fields
decisive_fields array · 4 items
human_critique object · 5 fields
stages array · 7 items
[0] object · 4 fields
[1] object · 4 fields
evidence object · 1 field
provider_errors array · 4 items
[0] object · 4 fields
[1] object · 4 fields
[2] object · 4 fields
[3] object · 4 fields
[2] object · 4 fields
[3] object · 4 fields
[4] object · 4 fields
[5] object · 4 fields
[6] object · 4 fields
gaps array · 3 items
provenance object · 7 fields
entities array · 1 item
activities array · 1 item
agents array · 1 item
lineage object · 4 fields
gaps array · 14 items
Complete file
{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41311650", "kind": "science-record", "revision": 2, "content_hash": "sha256:9cad859c977176ae6f8c7090ce6a92c608df416793a0ee59070550dbd01aad3c", "created_at": "2026-11-01T10:25:54Z", "updated_at": "2026-11-01T14:01:51Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "MASE-GC: a multi-omics autoencoder and stacking ensemble framework for gastric cancer classification.", "doi": "10.3389/fcell.2025.1704237", "pmid": "41311650", "authors": null, "journal": "Frontiers in cell and developmental biology", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:41311650"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:41311650", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:41311650' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41311650", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fcell.2025.1704237", "sha256": "sha256:b330fa0d09718835e081f546f2e71c553821dd55eaf1459ddb522ce5f1d22e79", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fcell.2025.1704237", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41311650:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:637cb3afa6739caa77060919d577a0deb11b0b97450827a977fed64d746614a9", "bytes": 458, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Summary of the original multi-omics datasets.", "structure": {"pmcid": "PMC12647936", "section_index": 3, "section_title": "Dataset", "row_count": 5, "column_count": 5}, "table": {"label": "TABLE 1", "caption": "Summary of the original multi-omics datasets.", "rows": [["Dataset", "SC samples", "Normal samples", "Number of features", "Platform"], ["Exon expression", "415", "35", "239,322", "NGS"], ["mRNA expression", "415", "35", "20,530", "NGS"], ["miRNA expression", "387", "41", "2,178", "NGS"], ["DNA methylation", "396", "29", "48,577", "Microarray"]], "row_count": 5, "column_count": 5, "numeric_cells": 12, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:41311650:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:879c40f5397ca46c1707e8726b42ae2caeb6d8fcf6c71a901c32d2808b310f07", "bytes": 522, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#T2", "version": null, "note": "Summary of the aligned and balanced multi-omics datasets after applying the SMOTE-Tomek algorithm.", "structure": {"pmcid": "PMC12647936", "section_index": 5, "section_title": "Dataset balancing", "row_count": 6, "column_count": 4}, "table": {"label": "TABLE 2", "caption": "Summary of the aligned and balanced multi-omics datasets after applying the SMOTE-Tomek algorithm.", "rows": [["Dataset", "SC samples", "Normal samples", "Number of features"], ["Exon expression", "415", "415", "239,322"], ["mRNA expression", "415", "359", "20,530"], ["miRNA expression", "387", "438", "2,178"], ["DNA methylation", "396", "396", "48,577"], ["Integrated multi-omics", "367", "367", "658,086"]], "row_count": 6, "column_count": 4, "numeric_cells": 15, "header_rows": 1, "locator": "section[5]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:41311650:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:954c7f3d01c6a7a5c82edd46ec52a43c98074d15031f0335cfc63ed2cda4c11f", "bytes": 616, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#T3", "version": null, "note": "Performance comparison of MASE-GC on single-omics and integrated multi-omics for validation splits.", "structure": {"pmcid": "PMC12647936", "section_index": 19, "section_title": "Performance comparison of MASE-GC on single-omics and multi-omics data", "row_count": 6, "column_count": 6}, "table": {"label": "TABLE 3", "caption": "Performance comparison of MASE-GC on single-omics and integrated multi-omics for validation splits.", "rows": [["Data Type", "Accuracy", "Precision", "Recall", "F1-Score", "Specificity"], ["Exon", "0.9512", "0.9735", "0.9708", "0.9721", "0.7405"], ["mRNA", "0.9634", "0.9798", "0.9785", "0.9791", "0.7567"], ["miRNA", "0.9395", "0.9712", "0.9587", "0.9649", "0.7283"], ["DNA methylation", "0.946", "0.9795", "0.9612", "0.9702", "0.7541"], ["Integrated multi-omics", "0.9818", "0.9852", "0.9928", "0.989", "0.8253"]], "row_count": 6, "column_count": 6, "numeric_cells": 25, "header_rows": 1, "locator": "section[19]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:41311650:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:778b29d226e245fa63c1cd21a00067aaade46c0ecdfc271bcce95c3b71a01942", "bytes": 604, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[2]#T4", "version": null, "note": "Performance comparison of MASE-GC on single-omics and integrated multi-omics for test splits.", "structure": {"pmcid": "PMC12647936", "section_index": 19, "section_title": "Performance comparison of MASE-GC on single-omics and multi-omics data", "row_count": 6, "column_count": 6}, "table": {"label": "TABLE 4", "caption": "Performance comparison of MASE-GC on single-omics and integrated multi-omics for test splits.", "rows": [["Data type", "Accuracy", "Precision", "Recall", "F1-Score", "Specificity"], ["Exon", "0.9498", "0.9721", "0.9696", "0.9708", "0.7392"], ["mRNA", "0.962", "0.9782", "0.977", "0.9776", "0.755"], ["miRNA", "0.9381", "0.9698", "0.9571", "0.9633", "0.727"], ["DNA methylation", "0.9447", "0.978", "0.9596", "0.9688", "0.7528"], ["Integrated multi-omics", "0.981", "0.9845", "0.992", "0.9883", "0.824"]], "row_count": 6, "column_count": 6, "numeric_cells": 25, "header_rows": 1, "locator": "section[19]/table-wrap[2]#T4"}}, {"id": "asset:table:pmid:41311650:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:033d3ef49299bd10a2b2a2d089aed14983ef2ddcc34c65f6fc58a42d05644a08", "bytes": 661, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#T5", "version": null, "note": "Ablation results on the test split.", "structure": {"pmcid": "PMC12647936", "section_index": 20, "section_title": "Ablation experiment", "row_count": 8, "column_count": 6}, "table": {"label": "TABLE 5", "caption": "Ablation results on the test split.", "rows": [["Setting", "Accuracy", "Precision", "Recall", "F1-Score", "Specificity"], ["MASE-GC", "0.981", "0.9845", "0.992", "0.9883", "0.824"], ["w/o SVM", "0.9774", "0.9786", "0.9848", "0.9812", "0.8097"], ["w/o RF", "0.9638", "0.9754", "0.9693", "0.9725", "0.7856"], ["w/o DT", "0.9652", "0.9761", "0.9715", "0.9732", "0.7894"], ["w/o AdaBoost", "0.9756", "0.9817", "0.9805", "0.9809", "0.8008"], ["w/o CNN", "0.9589", "0.9703", "0.9647", "0.9675", "0.7712"], ["No-Meta (XGBoost)", "0.9715", "0.9789", "0.9764", "0.9778", "0.7936"]], "row_count": 8, "column_count": 6, "numeric_cells": 35, "header_rows": 1, "locator": "section[20]/table-wrap[1]#T5"}}, {"id": "asset:table:pmid:41311650:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f7953e19087fc801ca350c41f2dbf6ebc1cc313294ba442b161716358552516c", "bytes": 1067, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[1]#T6", "version": null, "note": "Performance comparison of MASE-GC and baseline methods.", "structure": {"pmcid": "PMC12647936", "section_index": 21, "section_title": "Comparison of MASE-GC with the baseline method", "row_count": 7, "column_count": 4}, "table": {"label": "TABLE 6", "caption": "Performance comparison of MASE-GC and baseline methods.", "rows": [["Setting", "Dataset", "Results", "References"], ["Residual network (ResNet)", "TCGA gastric cancer (mRNA, methylation, CNV)", "AUC: 0.971", "He et al. (2016)"], ["Graph neural network (GNN)", "TCGA-STAD (mRNA, CNV, clinical info, methylation)", "AUC: 0.976 ± 0.007", "Kipf and Welling (2017)"], ["DeepKEGG", "TCGA-BRCA, LIHC, PRAD, BLCA (multi-omics pathways)", "BRCA:0.876LIHC: 0.947PRAD: 0.79BLCA: 0.961", "Lan et al. (2024)"], ["CRIA", "TCGA-STAD (mRNA, CNV)", "Accuracy: 0.9732Precision: 0.9779Recall: 0.9857F1-score: 0.9812Specificity: 0.819", "Li et al. (2024)"], ["CMIM", "TCGA-STAD (mRNA, CNV)", "Accuracy: 0.9740Precision: 0.9865Recall: 0.9946F1-score: 0.9820Specificity: 0.812", "Pettini et al. (2021)"], ["MASE-GC", "TCGA-STAD (exon, mRNA, mature miRNA, and DNA methylation)", "Accuracy: 0.981Precision: 0.9845Recall: 0.992F1-score: 0.9883Specificity: 0.824", "Proposed model"]], "row_count": 7, "column_count": 4, "numeric_cells": 11, "header_rows": 1, "locator": "section[21]/table-wrap[1]#T6"}}, {"id": "asset:table:pmid:41311650:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b7db50edfae6853bb363304c05bb72e9d0589786d67318fc620cfe57d8c43b6f", "bytes": 518, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[1]#T7", "version": null, "note": "Performance of MASE-GC on external GC cohorts.", "structure": {"pmcid": "PMC12647936", "section_index": 22, "section_title": "Performance of MASE-GC on external datasets", "row_count": 5, "column_count": 7}, "table": {"label": "TABLE 7", "caption": "Performance of MASE-GC on external GC cohorts.", "rows": [["Dataset", "Data type", "Accuracy", "Precision", "Recall", "F1-Score", "Specificity"], ["GSE62254", "mRNA", "0.963", "0.972", "0.981", "0.976", "0.762"], ["GSE15459", "mRNA", "0.961", "0.971", "0.978", "0.974", "0.758"], ["GSE84437", "mRNA", "0.964", "0.974", "0.982", "0.978", "0.764"], ["ICGC", "Multi-omics", "0.958", "0.969", "0.975", "0.969", "0.755"]], "row_count": 5, "column_count": 7, "numeric_cells": 23, "header_rows": 1, "locator": "section[22]/table-wrap[1]#T7"}}], "gaps": ["asset:source:pmid:41311650 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41311650", "asset:table:pmid:41311650:1", "asset:table:pmid:41311650:2", "asset:table:pmid:41311650:3", "asset:table:pmid:41311650:4", "asset:table:pmid:41311650:5", "asset:table:pmid:41311650:6", "asset:table:pmid:41311650:7"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41311650"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [], "target_providers": [], "agreement": false, "disagreements": [], "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": [{"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}]}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked", "review.machine_critique.providers"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:eec410861ca13745fa4bdae0f3f0349d6f1135481e3e231eb9b0b0011cddb7dd", "type": "sep_package", "label": "SEP v1 package for pmid:41311650"}], "activities": [{"id": "activity:conversion:pmid:41311650", "type": "conversion", "used": ["package:eec410861ca13745fa4bdae0f3f0349d6f1135481e3e231eb9b0b0011cddb7dd"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:41311650", "parent_hash": "sha256:85debeaf96e51f9d3febf29d8f8f9a53132814cc4c6df3db849c52cc2ca27869", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41311650 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "review.machine_critique.providers", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:41311650' does not resolve to a declared asset", "targets"]}