Dissecting newly transcribed and old RNA using GRAND-SLAM.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29949974", "kind": "science-record", "revision": 4, "content_hash": "sha256:76417b1342728a6e4e19552a260094b38efecb048e55208fd273e6b0308593c2", "created_at": "2026-11-01T15:40:35Z", "updated_at": "2026-11-01T21:21:30Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Dissecting newly transcribed and old RNA using GRAND-SLAM.", "doi": "10.1093/bioinformatics/bty256", "pmid": "29949974", "authors": ["Christopher Jürges", "Lars Dölken", "Florian Erhard"], "journal": "Bioinformatics (Oxford, England)", "year": 2018, "abstract": "Summary: Global quantification of total RNA is used to investigate steady state levels of gene expression. However, being able to differentiate pre-existing RNA (that has been synthesized prior to a defined point in time) and newly transcribed RNA can provide invaluable information e.g. to estimate RNA half-lives or identify fast and complex regulatory processes. Recently, new techniques based on metabolic labeling and RNA-seq have emerged that allow to quantify new and old RNA: Nucleoside analogs are incorporated into newly transcribed RNA and are made detectable as point mutations in mapped reads. However, relatively infrequent incorporation events and significant sequencing error rates make the differentiation between old and new RNA a highly challenging task. We developed a statistical approach termed GRAND-SLAM that, for the first time, allows to estimate the proportion of old and new RNA in such an experiment. Uncertainty in the estimates is quantified in a Bayesian framework. Simulation experiments show our approach to be unbiased and highly accurate. Furthermore, we analyze how uncertainty in the proportion translates into uncertainty in estimating RNA half-lives and give guidelines for planning experiments. Finally, we demonstrate that our estimates of RNA half-lives compare favorably to other experimental approaches and that biological processes affecting RNA half-lives can be investigated with greater power than offered by any other method. GRAND-SLAM is freely available for non-commercial use at http://software.erhard-lab.de; R scripts to generate all figures are available at zenodo (doi: 10.5281/zenodo.1162340).", "claims": [{"id": "claim-method", "statement": "Indeed, receiver operating characteristic (ROC) analysis revealed RNA half-life log2 fold change to better agree with predicted microRNA targets than relative RNA stability.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29949974", "locator": "sections[18] \"4.7 Differential analysis of RNA half-life changes\" paragraph 3", "quote": "Indeed, receiver operating characteristic (ROC) analysis revealed RNA half-life log2 fold change to better agree with predicted microRNA targets than relative RNA stability."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Specifically, we downloaded the processed table of a random sample (GSM2666852) from GEO and converted the CPM (read counts per million) into a read count distribution for genes by multiplying all CPM values by 20 million.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29949974", "locator": "sections[9] \"3.6 Simulation\" paragraph 2", "quote": "Specifically, we downloaded the processed table of a random sample (GSM2666852) from GEO and converted the CPM (read counts per million) into a read count distribution for genes by multiplying all CPM values by 20 million."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We developed a statistical approach termed GRAND-SLAM that, for the first time, allows to estimate the proportion of old and new RNA in such an experiment.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29949974", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "GRAND-SLAM is freely available for non-commercial use at http://software.erhard-lab.de; R scripts to generate all figures are available at zenodo (doi: 10.5281/zenodo.1162340)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "We developed a statistical approach termed GRAND-SLAM that, for the first time, allows to estimate the proportion of old and new RNA in such an experiment.", "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:29949974"], "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:GSM2666852"], "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:GSM2666852"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29949974", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/bty256", "sha256": "sha256:72af617059fb96a7fb326a097cf6dea34c34fa9596aacd440ca7d2fc91d94c9e", "bytes": 44716, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/bty256", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6037110", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSM2666852", "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=GSM2666852", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSM2666852", "version": null, "note": "Specifically, we downloaded the processed table of a random sample (GSM2666852) from GEO and converted the CPM (read counts per million) into a read count distribution for genes by multiplying all CPM values by 20 million.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Specifically, we downloaded the processed table of a random sample (GSM2666852) from GEO and converted the CPM (read counts per million) into a read count distribution for genes by multiplying all CPM values by 20 million.", "access_statement_kind": "repository_route_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": "17021", "taxon": "Mus musculus", "title": "35413 mESC wt no s4U", "resolution_checked_at": "2026-10-31T18:35:45Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSM2666852 not downloaded", "asset:data:geo:GSM2666852 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Receiver operating characteristic (ROC) analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Indeed, receiver operating characteristic (ROC) analysis revealed RNA half-life log2 fold change to better agree with predicted microRNA targets than relative RNA stability."}}], "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": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Receiver operating characteristic (ROC) analysis), 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": "R1", "reachable": true, "accessions": ["GSM2666852"], "resolved_accessions": ["GSM2666852"], "statements": ["Specifically, we downloaded the processed table of a random sample (GSM2666852) from GEO and converted the CPM (read counts per million) into a read count distribution for genes by multiplying all CPM values by 20 million."], "basis": "The paper names GSM2666852 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:29949974", "data:geo:GSM2666852"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSM2666852"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:34:56Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 88504, "completion_tokens": 3584, "cached_tokens": 23056}}, "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:29949974", "type": "paper", "label": "pmid:29949974"}, {"id": "source:pmid:29949974", "type": "manuscript", "label": "PMID 29949974 full text"}, {"id": "data:geo:GSM2666852", "type": "dataset", "label": "GEO GSM2666852"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29949974", "type": "paper", "label": "pmid:29949974"}, {"id": "source:pmid:29949974", "type": "manuscript", "label": "PMID 29949974 full text"}, {"id": "data:geo:GSM2666852", "type": "dataset", "label": "GEO GSM2666852"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29949974", "type": "extraction", "used": ["source:pmid:29949974"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSM2666852", "type": "accession_resolution", "used": ["data:geo:GSM2666852"], "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:29949974", "parent_hash": "sha256:ea6c442e57755a3151f29e6fcb74c02e0e92eff950b102a27e0a571c383ac467", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSM2666852 licence not read", "asset:data:geo:GSM2666852 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["w techniques based on metabolic labeling and RNA-seq have emerged that allow to quantify new and"], "order_basis": "paper_text_order:437", "id": "assay:1"}]}