A Bayesian model for single cell transcript expression analysis on MERFISH data.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30875429", "kind": "science-record", "revision": 3, "content_hash": "sha256:4b85b645ea4b855bcc20455b50ab27d5206ab327ab863f1379b37ab791d35341", "created_at": "2026-11-01T17:32:42Z", "updated_at": "2026-11-01T21:22:04Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A Bayesian model for single cell transcript expression analysis on MERFISH data.", "doi": "10.1093/bioinformatics/bty718", "pmid": "30875429", "authors": ["Johannes Köster", "Myles Brown", "X Shirley Liu"], "journal": "Bioinformatics (Oxford, England)", "year": 2019, "abstract": "MOTIVATION: Multiplexed error-robust fluorescence in-situ hybridization (MERFISH) is a recent technology to obtain spatially resolved gene or transcript expression profiles in single cells for hundreds to thousands of genes in parallel. So far, no statistical framework to analyze MERFISH data is available.\nRESULTS: We present a Bayesian model for single cell transcript expression analysis on MERFISH data. We show that the model successfully captures uncertainty in MERFISH data and eliminates systematic biases that can occur in raw RNA molecule counts obtained with MERFISH. Our model accurately estimates transcript expression and additionally provides the full probability distribution and credible intervals for each transcript. We further show how this enables MERFISH to scale towards the whole genome while being able to control the uncertainty in obtained results.\nAVAILABILITY AND IMPLEMENTATION: The presented model is implemented on top of Rust-Bio (Köster, 2016) and available open-source as MERFISHtools (https://merfishtools.github.io). It can be easily installed via Bioconda (Grüning et al., 2018). The entire analysis performed in this paper is provided as a fully reproducible Snakemake (Köster and Rahmann, 2012) workflow via Zenodo (https://doi.org/10.5281/zenodo.752340).\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.", "claims": [{"id": "claim-method", "statement": "We present a Bayesian model for single cell transcript expression analysis on MERFISH data.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30875429", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We present a Bayesian model for single cell transcript expression analysis on MERFISH data."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Supplementary data are available at Bioinformatics online.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30875429", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "Supplementary data are available at Bioinformatics online."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We show that the model successfully captures uncertainty in MERFISH data and eliminates systematic biases that can occur in raw RNA molecule counts obtained with MERFISH.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:30875429", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We show that the model successfully captures uncertainty in MERFISH data and eliminates systematic biases that can occur in raw RNA molecule counts obtained with MERFISH."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "We show that the model successfully captures uncertainty in MERFISH data and eliminates systematic biases that can occur in raw RNA molecule counts obtained with MERFISH.", "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:30875429"], "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:30875429", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/bty718", "sha256": "sha256:43cbbfebb75f654eef427fcd3599bad339d781b11ececf4bae36389fd443ad40", "bytes": 1314, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/bty718", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6419903", "source": "ncbi_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Bayesian model", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We present a Bayesian model for single cell transcript expression analysis on MERFISH data."}}], "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 (Bayesian model), 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": ["Supplementary data are available at Bioinformatics online."], "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:30875429"], "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": "2026-11-01T16:58:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 1908, "completion_tokens": 966, "cached_tokens": 128}}, "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:30875429", "type": "paper", "label": "pmid:30875429"}, {"id": "source:pmid:30875429", "type": "manuscript", "label": "PMID 30875429 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30875429", "type": "paper", "label": "pmid:30875429"}, {"id": "source:pmid:30875429", "type": "manuscript", "label": "PMID 30875429 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30875429", "type": "extraction", "used": ["source:pmid:30875429"], "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:30875429", "parent_hash": "sha256:e8b218a9e956c86c5c1725e75e10ddc9145127bd7a23b074d69c71a8fc7cdd20", "fork_of": null, "generation": 2}, "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"]}