scDiffusion: conditional generation of high-quality single-cell data using diffusion model.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39171840", "kind": "science-record", "revision": 4, "content_hash": "sha256:44d1fc540a73168989815fe906e0ffd44ad164b4fbcee49f9f6363f65503d6d2", "created_at": "2026-11-01T20:29:18Z", "updated_at": "2026-11-01T22:55:00Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "scDiffusion: conditional generation of high-quality single-cell data using diffusion model.", "doi": "10.1093/bioinformatics/btae518", "pmid": "39171840", "authors": ["Erpai Luo", "Minsheng Hao", "Lei Wei", "Xuegong Zhang"], "journal": "Bioinformatics (Oxford, England)", "year": 2024, "abstract": "MOTIVATION: Single-cell RNA sequencing (scRNA-seq) data are important for studying the laws of life at single-cell level. However, it is still challenging to obtain enough high-quality scRNA-seq data. To mitigate the limited availability of data, generative models have been proposed to computationally generate synthetic scRNA-seq data. Nevertheless, the data generated with current models are not very realistic yet, especially when we need to generate data with controlled conditions. In the meantime, diffusion models have shown their power in generating data with high fidelity, providing a new opportunity for scRNA-seq generation.\nRESULTS: In this study, we developed scDiffusion, a generative model combining the diffusion model and foundation model to generate high-quality scRNA-seq data with controlled conditions. We designed multiple classifiers to guide the diffusion process simultaneously, enabling scDiffusion to generate data under multiple condition combinations. We also proposed a new control strategy called Gradient Interpolation. This strategy allows the model to generate continuous trajectories of cell development from a given cell state. Experiments showed that scDiffusion could generate single-cell gene expression data closely resembling real scRNA-seq data. Also, scDiffusion can conditionally produce data on specific cell types including rare cell types. Furthermore, we could use the multiple-condition generation of scDiffusion to generate cell type that was out of the training data. Leveraging the Gradient Interpolation strategy, we generated a continuous developmental trajectory of mouse embryonic cells. These experiments demonstrate that scDiffusion is a powerful tool for augmenting the real scRNA-seq data and can provide insights into cell fate research.\nAVAILABILITY AND IMPLEMENTATION: scDiffusion is openly available at the GitHub repository https://github.com/EperLuo/scDiffusion or Zenodo https://zenodo.org/doi/10.5281/zenodo.13268742.", "claims": [{"id": "claim-method", "statement": "The statistical indicators consist of Spearman Correlation Coefficient (SCC), Maximum Mean Discrepancy (MMD) (Gretton et al. 2012), local inverse Simpson’s index (LISI) (Haghverdi et al. 2018). and quantile-quantile plot (QQ-plot).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39171840", "locator": "sections[6] \"2.4 Evaluation metrics\" paragraph 2", "quote": "The statistical indicators consist of Spearman Correlation Coefficient (SCC), Maximum Mean Discrepancy (MMD) (Gretton et al. 2012), local inverse Simpson’s index (LISI) (Haghverdi et al. 2018). and quantile-quantile plot (QQ-plot)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The code and datasets of scDiffusion are available at https://github.com/EperLuo/scDiffusion. The code is also accessible via Zenodo at https://zenodo.org/doi/10.5281/zenodo.13268742.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39171840", "locator": "sections[18] \"Data availability\" paragraph 2", "quote": "The code and datasets of scDiffusion are available at https://github.com/EperLuo/scDiffusion. The code is also accessible via Zenodo at https://zenodo.org/doi/10.5281/zenodo.13268742."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The average SCC of scDiffusion in three datasets was 0.984, the mean MMD score was 0.018, the mean LISI score was 0.887 and the mean AUC of the random forest was 0.697, which are similar to scGAN and scDesign3, and outperform SPARSim and SCRIP (Supplementary Fig. S2).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39171840", "locator": "sections[8] \"3.1 Realistic scRNA-seq data generation\" paragraph 3", "quote": "The average SCC of scDiffusion in three datasets was 0.984, the mean MMD score was 0.018, the mean LISI score was 0.887 and the mean AUC of the random forest was 0.697, which are similar to scGAN and scDesign3, and outperform SPARSim and SCRIP (Supplementary Fig. S2)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The average SCC of scDiffusion in three datasets was 0.984, the mean MMD score was 0.018, the mean LISI score was 0.887 and the mean AUC of the random forest was 0.697, which are similar to scGAN and scDesign3, and outperform SPARSim and SCRIP (Supplementary Fig. S2).", "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:39171840"], "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": "blocked", "blocked_on": "method:machine_learning_random_forest", "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:run_analysis blocked on method:machine_learning_random_forest", "step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39171840", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btae518", "sha256": "sha256:32c628d65d248f87627a2e2cbed5702d55bc38c6d8b8f817ce067fad58d2522d", "bytes": 47097, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btae518", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11368386", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The statistical indicators consist of Spearman Correlation Coefficient (SCC), Maximum Mean Discrepancy (MMD) (Gretton et al. 2012), local inverse Simpson’s index (LISI) (Haghverdi et al. 2018). and quantile-quantile plot (QQ-plot)."}}, {"id": "method-2", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman Correlation"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor", "method.machine_learning_random_forest"]}, "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": "R1", "expressible": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "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": ["The code and datasets of scDiffusion are available at https://github.com/EperLuo/scDiffusion. The code is also accessible via Zenodo at https://zenodo.org/doi/10.5281/zenodo.13268742."], "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:39171840"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "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": "2026-11-01T19:29:28Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 12926, "completion_tokens": 2158, "cached_tokens": 264}}, "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:39171840", "type": "paper", "label": "pmid:39171840"}, {"id": "source:pmid:39171840", "type": "manuscript", "label": "PMID 39171840 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39171840", "type": "paper", "label": "pmid:39171840"}, {"id": "source:pmid:39171840", "type": "manuscript", "label": "PMID 39171840 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39171840", "type": "extraction", "used": ["source:pmid:39171840"], "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:39171840", "parent_hash": "sha256:49f0e1dd6f3512192d099f30a14ff7200e14216bdfec95800195de7adf170d26", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "method.machine_learning_random_forest", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:machine_learning_random_forest"], "assays": [{"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["MOTIVATION: Single-cell RNA sequencing (scRNA-seq) data are important for studying", "MOTIVATION: Single-cell RNA sequencing (scRNA-seq) data are important for studying the laws of", "ll challenging to obtain enough high-quality scRNA-seq data. To mitigate the limited availability o", "oposed to computationally generate synthetic scRNA-seq data. Nevertheless, the data generated with"], "order_basis": "paper_text_order:92", "id": "assay:1"}, {"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": ["MOTIVATION: Single-cell RNA sequencing (scRNA-seq) data are important for studying"], "order_basis": "paper_text_order:92", "id": "assay:2"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["ted a continuous developmental trajectory of mouse embryonic cells. These experiments demonstra"], "order_basis": "paper_text_order:1670", "id": "assay:3"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The statistical indicators consist of Spearman Correlation Coefficient (SCC), Maximum Mean Discrepancy (MMD) (Gretton et al. 2012), local inverse Simpson’s index (LISI) (Haghverdi et al. 2018). and quantile-quantile plot (QQ-plot)."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]}