← All .science files
pmid:33002137
A content-based dataset recommendation system for researchers-a case study on Gene Expression Omnibus (GEO) repository.
Braja Gopal Patra · Kirk Roberts · Hulin Wu
Database : the journal of biological databases and curation · 2020 doi:10.1093/database/baaa064
Paper
complete
Experiment
partial
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 · 3 items
claims array · 2 items
[0] object · 6 fields
[1] object · 6 fields
evidence array · 1 item
[0] 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 · 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 · 1 item
data object · 3 fields
assets array · 5 items
[0] object · 15 fields
structure object · 4 fields
[1] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 3 items
[0] array · 2 items
[1] array · 2 items
[2] array · 2 items
[2] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 12 items
[0] array · 2 items
[1] array · 7 items
[2] array · 7 items
[3] array · 7 items
[4] array · 7 items
[5] array · 7 items
[6] array · 7 items
[7] array · 7 items
[8] array · 7 items
[9] array · 7 items
[10] array · 7 items
[11] array · 7 items
[3] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 14 items
[0] array · 3 items
[1] array · 4 items
[2] array · 7 items
[3] array · 7 items
[4] array · 7 items
[5] array · 7 items
[6] array · 7 items
[7] array · 7 items
[8] array · 7 items
[9] array · 7 items
[10] array · 7 items
[11] array · 7 items
[12] array · 7 items
[13] array · 7 items
[4] object · 16 fields
structure object · 5 fields
table object · 8 fields
rows array · 8 items
[0] array · 4 items
[1] array · 9 items
[2] array · 10 items
[3] array · 10 items
[4] array · 10 items
[5] array · 10 items
[6] array · 10 items
[7] array · 10 items
gaps array · 0 items
analysis object · 4 fields
methods array · 1 item
[0] 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 · 0 items
missing_operations array · 0 items
capability object · 4 fields
data object · 6 fields
accessions array · 0 items
resolved_accessions array · 0 items
statements array · 1 item
can_run object · 3 fields
dsl_operations array · 0 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 · 1 item
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 · 6 items
Complete file
{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33002137", "kind": "science-record", "revision": 4, "content_hash": "sha256:1fd006e0a41e93c19d7ebc127469a0bc92198eb714ff617c1ef4f4fc2a0726ec", "created_at": "2026-11-01T15:41:12Z", "updated_at": "2026-11-01T21:23:53Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A content-based dataset recommendation system for researchers-a case study on Gene Expression Omnibus (GEO) repository.", "doi": "10.1093/database/baaa064", "pmid": "33002137", "authors": ["Braja Gopal Patra", "Kirk Roberts", "Hulin Wu"], "journal": "Database : the journal of biological databases and curation", "year": 2020, "abstract": "It is a growing trend among researchers to make their data publicly available for experimental reproducibility and data reusability. Sharing data with fellow researchers helps in increasing the visibility of the work. On the other hand, there are researchers who are inhibited by the lack of data resources. To overcome this challenge, many repositories and knowledge bases have been established to date to ease data sharing. Further, in the past two decades, there has been an exponential increase in the number of datasets added to these dataset repositories. However, most of these repositories are domain-specific, and none of them can recommend datasets to researchers/users. Naturally, it is challenging for a researcher to keep track of all the relevant repositories for potential use. Thus, a dataset recommender system that recommends datasets to a researcher based on previous publications can enhance their productivity and expedite further research. This work adopts an information retrieval (IR) paradigm for dataset recommendation. We hypothesize that two fundamental differences exist between dataset recommendation and PubMed-style biomedical IR beyond the corpus. First, instead of keywords, the query is the researcher, embodied by his or her publications. Second, to filter the relevant datasets from non-relevant ones, researchers are better represented by a set of interests, as opposed to the entire body of their research. This second approach is implemented using a non-parametric clustering technique. These clusters are used to recommend datasets for each researcher using the cosine similarity between the vector representations of publication clusters and datasets. The maximum normalized discounted cumulative gain at 10 (NDCG@10), precision at 10 (p@10) partial and p@10 strict of 0.89, 0.78 and 0.61, respectively, were obtained using the proposed method after manual evaluation by five researchers. As per the best of our knowledge, this is the first study of its kind on content-based dataset recommendation. We hope that this system will further promote data sharing, offset the researchers' workload in identifying the right dataset and increase the reusability of biomedical datasets. Database URL: http://genestudy.org/recommends/#/.", "claims": [{"id": "claim-method", "statement": "Later, normalized discounted cumulative gain (NDCG) at 10 and Precision at 10 (P@10) were calculated to evaluate different systems.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33002137", "locator": "sections[17] \"Recommendation system\" paragraph 3", "quote": "Later, normalized discounted cumulative gain (NDCG) at 10 and Precision at 10 (P@10) were calculated to evaluate different systems."}], "state": "complete"}, {"id": "claim-data-access", "statement": "For the present experiment, metadata such as title, summary, submission date and name of dataset creator(s) were collected from GEO and indexed in a database, as shown in Figure 2. We also collected the PMIDs of articles associated with each dataset.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33002137", "locator": "sections[3] \"GEO Datasets\" paragraph 6", "quote": "For the present experiment, metadata such as title, summary, submission date and name of dataset creator(s) were collected from GEO and indexed in a database, as shown in Figure 2. We also collected the PMIDs of articles associated with each dataset."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:33002137"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33002137", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/database/baaa064", "sha256": "sha256:6aab330a90fcc34b1a6bf7362953fac82af65f330b229c17f3b08fa52e651924", "bytes": 51910, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/database/baaa064", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7659921", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:33002137:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bbb4b1f548effabc9e52124cf8aa486c394aaac2827fdda88faa52413641aef2", "bytes": 316, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Statistics of datasets collected from GEO", "structure": {"pmcid": "PMC7659921", "section_index": 3, "section_title": "GEO Datasets", "row_count": 3, "column_count": 2}, "table": {"label": "Table 1.", "caption": "Statistics of datasets collected from GEO", "rows": [["Datasets", "122 222"], ["Datasets with articles", "89 533"], ["Total articles", "92 884 (Mean : 0.76, Max : 10, Unique : 61 228)"]], "row_count": 3, "column_count": 2, "numeric_cells": 3, "header_rows": 0, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33002137:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1b30b883fa6a7e82b59422532aa09cb5219fb35c578197cc79f6ab34a63a501a", "bytes": 1367, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T2", "version": null, "note": "Number of clusters with varying α values for proposed α based on our initial evaluation. Abbreviations: P: Proposed, a: total number of clusters, b: number of clusters which contains more than one paper, c: number of clusters which contains only one paper", "structure": {"pmcid": "PMC7659921", "section_index": 13, "section_title": "MIDR System (Separate)", "row_count": 12, "column_count": 7}, "table": {"label": "Table 2.", "caption": "Number of clusters with varying α values for proposed α based on our initial evaluation. Abbreviations: P: Proposed, a: total number of clusters, b: number of clusters which contains more than one paper, c: number of clusters which contains only one paper", "rows": [["Researcher ID (No. of papers)", "Number of clusters (a, b, c) for different α values"], ["", "α = 0.3", "α = 1.0", "α = 2.0", "α = 3.0", "α = 10.0", "α = P"], ["1 (53)", "16, 9, 7", "8, 7, 1", "6, 3, 3", "5, 2, 3", "3, 2, 1", "8, 5, 3 (1.37)"], ["2 (32)", "15, 10, 5", "10, 8, 2", "8, 6, 2", "7, 5, 2", "4, 2, 2", "8, 6, 2 (1.77)"], ["3 (48)", "15, 8, 7", "9, 4, 5", "3, 3, 0", "6, 2, 4", "2, 1, 1", "6, 3, 3 (1.44)"], ["4 (22)", "15, 4, 11", "10, 5, 5", "6, 4, 2", "5, 3, 2", "4, 1, 3", "7, 4, 3 (2.13)"], ["5 (7)", "5, 2, 3", "5, 2, 3", "4, 3, 1", "5, 2, 3", "3, 3, 0", "5, 2, 3 (3.8)"], ["6 (76)", "11, 10, 1", "6, 5, 1", "3, 3, 0", "2, 2, 0", "2, 1, 1", "5, 5, 0 (1.14)"], ["7 (13)", "7, 3, 4", "5, 4, 1", "3, 3, 0", "2, 2, 0", "2, 2, 0", "2, 2, 0 (2.77)"], ["8 (193)", "16, 15, 1", "6, 5, 1", "8, 4, 4", "5, 2, 3", "4, 1, 3", "7, 6, 1 (0.72)"], ["9 (291)", "23, 23, 0", "9, 8, 1", "6, 6, 0", "6, 3, 3", "3, 1, 2", "14, 14, 0 (0.59)"], ["10 (54)", "20, 11, 9", "12, 10, 2", "9, 8, 1", "6, 6, 0", "2, 2, 0", "9, 8, 1 (1.36)"]], "row_count": 12, "column_count": 7, "numeric_cells": 75, "header_rows": 2, "locator": "section[13]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:33002137:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:049a33f04e69780a3c08812022233b85184d07f6969450711b74f22bfd180150", "bytes": 1384, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#T3", "version": null, "note": "Mean IACCS and ICCS for K-Means and DPMM (with different cluster sizes as mentioned in Table 2).", "structure": {"pmcid": "PMC7659921", "section_index": 17, "section_title": "Recommendation system", "row_count": 14, "column_count": 7}, "table": {"label": "Table 3.", "caption": "Mean IACCS and ICCS for K-Means and DPMM (with different cluster sizes as mentioned in Table 2).", "rows": [["", "K-Means", ""], ["", "Clusters = 2", "Clusters = 5", "DPMM"], ["", "Words", "MeSH terms", "Words", "MeSH terms", "Words", "MeSH terms"], ["Researcher ID (No. of papers)", "IACSS, ICSS", "IACSS, ICSS", "IACSS, ICSS", "IACSS, ICSS", "IACSS, ICSS", "IACSS, ICSS"], ["1 (53)", "0.14, 0.37", "0.12, 0.56", "0.20, 0.26", "0.12, 0.27", "0.22, 0.19", "0.20, 0.32"], ["2 (32)", "0.09, 0.37", "0.09, 0.42", "0.14, 0.16", "0.14, 0.23", "0.22, 0.11", "0.11, 0.12"], ["3 (48)", "0.16, 0.43", "0.16, 0.56", "0.16, 0.25", "0.16, 0.29", "0.24, 0.22", "0.17, 0.37"], ["4 (22)", "0.12, 0.24", "0.09, 0.51", "0.21, 0.11", "0.15, 0.20", "0.20, 0.10", "0.16, 0.15"], ["5 (7)", "0.16, 0.13", "0.14, 0.19", "0.18, 0.04", "0.11, 0.08", "0.45, 0.08", "0.28, 0.13"], ["6 (76)", "0.17, 0.54", "0.19, 0.64", "0.20, 0.31", "0.22, 0.36", "0.20, 0.18", "0.23, 0.19"], ["7 (13)", "0.33, 0.14", "0.47, 0.30", "0.32, 0.17", "0.45, 0.30", "0.34, 0.14", "0.47, 0.30"], ["8 (193)", "0.10, 0.61", "0.16, 0.76", "0.17, 0.31", "0.21, 0.60", "0.17, 0.25", "0.21, 0.43"], ["9 (291)", "0.07, 0.55", "0.09, 0.64", "0.09, 0.40", "0.11, 0.54", "0.23, 0.13", "0.14, 0.19"], ["10 (54)", "0.07, 0.31", "0.15, 0.57", "0.11, 0.19", "0.23, 0.33", "0.17, 0.10", "0.20, 0.24"]], "row_count": 14, "column_count": 7, "numeric_cells": 72, "header_rows": 4, "locator": "section[17]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:33002137:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c2baffa6d8634c98d2ca4a1305d482c2df6493a650aadc6f9e6d948df18bae6e", "bytes": 913, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#T4", "version": null, "note": "NDCG@10, partial and strict P@10 values of the different dataset recommendation systems based on three evaluators. Abbreviations: Partial: P; Strict: S", "structure": {"pmcid": "PMC7659921", "section_index": 18, "section_title": "Results", "row_count": 8, "column_count": 10}, "table": {"label": "Table 4.", "caption": "NDCG@10, partial and strict P@10 values of the different dataset recommendation systems based on three evaluators. Abbreviations: Partial: P; Strict: S", "rows": [["Researcher ID (No. of papers)", "Baseline", "MIDR", "MIDR (separate)"], ["NDCG@10", "P@10 (P)", "P@10 (S)", "NDCG@10", "P@10 (P)", "P@10 (S)", "NDCG@10", "P@10 (P)", "P@10 (S)"], ["1 (53)", "0.82", "0.80", "0.30", "0.92", "0.90", "0.40", "0.74", "0.56", "0.32"], ["2 (32)", "0.81", "0.76", "0.50", "0.95", "0.80", "0.70", "0.52", "0.38", "0.20"], ["3 (48)", "0.76", "0.60", "0.28", "0.80", "0.60", "0.34", "0.60", "0.25", "0.13"], ["4 (22)", "0.78", "0.48", "0.36", "0.80", "0.60", "0.60", "0.48", "0.34", "0.22"], ["5 (7)", "0.85", "0.80", "0.80", "1.00", "1.00", "1.00", "0.78", "0.70", "0.70"], ["Average", "0.80", "0.69", "0.45", "0.89", "0.78", "0.61", "0.62", "0.45", "0.31"]], "row_count": 8, "column_count": 10, "numeric_cells": 68, "header_rows": 2, "locator": "section[18]/table-wrap[1]#T4"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Normalized discounted cumulative gain at 10 (NDCG@10) and Precision at 10 (P@10)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Later, normalized discounted cumulative gain (NDCG) at 10 and Precision at 10 (P@10) were calculated to evaluate different systems."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Normalized discounted cumulative gain at 10 (NDCG@10) and Precision at 10 (P@10)), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["For the present experiment, metadata such as title, summary, submission date and name of dataset creator(s) were collected from GEO and indexed in a database, as shown in Figure 2. We also collected the PMIDs of articles associated with each dataset."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:33002137", "asset:table:pmid:33002137:1", "asset:table:pmid:33002137:2", "asset:table:pmid:33002137:3", "asset:table:pmid:33002137:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:22:54Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 34331, "completion_tokens": 1676, "cached_tokens": 11520}}, "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:33002137", "type": "paper", "label": "pmid:33002137"}, {"id": "source:pmid:33002137", "type": "manuscript", "label": "PMID 33002137 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33002137", "type": "paper", "label": "pmid:33002137"}, {"id": "source:pmid:33002137", "type": "manuscript", "label": "PMID 33002137 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33002137", "type": "extraction", "used": ["source:pmid:33002137"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:33002137", "parent_hash": "sha256:448bc8e6bc3b2f30836ad847321b0760adcb9a0303e8c4bbf6d7ae2aaa41780a", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"]}