Semla: a versatile toolkit for spatially resolved transcriptomics analysis and visualization.

{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37846051", "kind": "science-record", "revision": 2, "content_hash": "sha256:fd116113635fe9b27da248e22bc9e6c7a2309f70af05a258a7b7c17c948579f1", "created_at": "2026-11-01T19:02:42Z", "updated_at": "2026-11-01T21:31:44Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Semla: a versatile toolkit for spatially resolved transcriptomics analysis and visualization.", "doi": "10.1093/bioinformatics/btad626", "pmid": "37846051", "authors": ["Ludvig Larsson", "Lovisa Franzén", "Patrik L Ståhl", "Joakim Lundeberg"], "journal": "Bioinformatics (Oxford, England)", "year": 2023, "abstract": "SUMMARY: Spatially resolved transcriptomics technologies generate gene expression data with retained positional information from a tissue section, often accompanied by a corresponding histological image. Computational tools should make it effortless to incorporate spatial information into data analyses and present analysis results in their histological context. Here, we present semla, an R package for processing, analysis, and visualization of spatially resolved transcriptomics data generated by the Visium platform, that includes interactive web applications for data exploration and tissue annotation.\nAVAILABILITY AND IMPLEMENTATION: The R package semla is available on GitHub (https://github.com/ludvigla/semla), under the MIT License, and deposited on Zenodo (https://doi.org/10.5281/zenodo.8321645). Documentation and tutorials with detailed descriptions of usage can be found at https://ludvigla.github.io/semla/.", "claims": [{"id": "claim-method", "statement": "Semla includes an approach for cell type deconvolution based on Non-Negative Least Squares (NNLS), which runs in a matter of seconds on Visium data with up to 100 000 spots (Fig. 1C, Supplementary Section S3.2).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37846051", "locator": "sections[5] \"3.2 Cell type mapping with NNLS\" paragraph 2", "quote": "Semla includes an approach for cell type deconvolution based on Non-Negative Least Squares (NNLS), which runs in a matter of seconds on Visium data with up to 100 000 spots (Fig. 1C, Supplementary Section S3.2)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "", "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:37846051"], "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:37846051", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btad626", "sha256": "sha256:3180f720b7b184cf54259100af5f49b5ce5f90076fc664a8b2d0d5ebf22688a6", "bytes": 17673, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btad626", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10597621", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Non-Negative Least Squares (NNLS)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Semla includes an approach for cell type deconvolution based on Non-Negative Least Squares (NNLS), which runs in a matter of seconds on Visium data with up to 100 000 spots (Fig. 1C, Supplementary Section S3.2)."}}], "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 (Non-Negative Least Squares (NNLS)), 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": [], "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:37846051"], "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": "2026-11-01T18:56:18Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 5, "usage": {"prompt_tokens": 5653, "completion_tokens": 1355, "cached_tokens": 256}}, "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:37846051", "type": "paper", "label": "pmid:37846051"}, {"id": "source:pmid:37846051", "type": "manuscript", "label": "PMID 37846051 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37846051", "type": "paper", "label": "pmid:37846051"}, {"id": "source:pmid:37846051", "type": "manuscript", "label": "PMID 37846051 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37846051", "type": "extraction", "used": ["source:pmid:37846051"], "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:37846051", "parent_hash": "sha256:690a3605af2c614349b43b611101af9e03304e9b22a05fc90c84ecd2fb732848", "fork_of": null, "generation": 1}, "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"]}