SD2: spatially resolved transcriptomics deconvolution through integration of dropout and spatial information.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36063455", "kind": "science-record", "revision": 8, "content_hash": "sha256:92a6a4efe45cf81e890453987384d077580ca835389f77d0981cdd0a5e78c2a7", "created_at": "2026-11-01T18:15:16Z", "updated_at": "2026-11-01T23:48:16Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "SD2: spatially resolved transcriptomics deconvolution through integration of dropout and spatial information.", "doi": "10.1093/bioinformatics/btac605", "pmid": "36063455", "authors": ["Haoyang Li", "Hanmin Li", "Juexiao Zhou", "Xin Gao"], "journal": "Bioinformatics (Oxford, England)", "year": 2022, "abstract": "MOTIVATION: Unveiling the heterogeneity in the tissues is crucial to explore cell-cell interactions and cellular targets of human diseases. Spatial transcriptomics (ST) supplies spatial gene expression profile which has revolutionized our biological understanding, but variations in cell-type proportions of each spot with dozens of cells would confound downstream analysis. Therefore, deconvolution of ST has been an indispensable step and a technical challenge toward the higher-resolution panorama of tissues.\nRESULTS: Here, we propose a novel ST deconvolution method called SD2 integrating spatial information of ST data and embracing an important characteristic, dropout, which is traditionally considered as an obstruction in single-cell RNA sequencing data (scRNA-seq) analysis. First, we extract the dropout-based genes as informative features from ST and scRNA-seq data by fitting a Michaelis-Menten function. After synthesizing pseudo-ST spots by randomly composing cells from scRNA-seq data, auto-encoder is applied to discover low-dimensional and non-linear representation of the real- and pseudo-ST spots. Next, we create a graph containing embedded profiles as nodes, and edges determined by transcriptional similarity and spatial relationship. Given the graph, a graph convolutional neural network is used to predict the cell-type compositions for real-ST spots. We benchmark the performance of SD2 on the simulated seqFISH+ dataset with different resolutions and measurements which show superior performance compared with the state-of-the-art methods. SD2 is further validated on three real-world datasets with different ST technologies and demonstrates the capability to localize cell-type composition accurately with quantitative evidence. Finally, ablation study is conducted to verify the contribution of different modules proposed in SD2.\nAVAILABILITY AND IMPLEMENTATION: The SD2 is freely available in github (https://github.com/leihouyeung/SD2) and Zenodo (https://doi.org/10.5281/zenodo.7024684).\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.", "claims": [{"id": "claim-method", "statement": "Through the comparison with ground truth, we observed that SD2 outperformed the other three methods in root mean square error (RMSE) and Jensen–Shannon Divergence (JSD).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36063455", "locator": "sections[8] \"3.2 Benchmark evaluation\" paragraph 5", "quote": "Through the comparison with ground truth, we observed that SD2 outperformed the other three methods in root mean square error (RMSE) and Jensen–Shannon Divergence (JSD)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The seqFISH+ dataset is collected from GSE98674 and corresponded scRNA-seq dataset is collected from GSE6036. The MERFISH datasets are collected from https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248/ and scRNA-seq data is from https://github.com/rdong08/spatialDWLS_dataset/tree/main/datasets. ST and scRNA-seq data from PDAC are collected from GSE111672. ST data from adult mouse brain are collected from 10X Genomics and the corresponding scRNA-seq data are collected from allen institute which are sequenced by smart-seq. The ST data of mouse kidney are collected from 10X Genomics and scRNA-seq data are from GSE157079.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36063455", "locator": "sections[14] \"Data Availability\" paragraph 2", "quote": "The seqFISH+ dataset is collected from GSE98674 and corresponded scRNA-seq dataset is collected from GSE6036. The MERFISH datasets are collected from https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248/ and scRNA-seq data is from https://github.com/rdong08/spatialDWLS_dataset/tree/main/datasets. ST and scRNA-seq data from PDAC are collected from GSE111672. ST data from adult mouse brain are collected from 10X Genomics and the corresponding scRNA-seq data are collected from allen institute which are sequenced by smart-seq. The ST data of mouse kidney are collected from 10X Genomics and scRNA-seq data are from GSE157079."}], "state": "complete"}, {"id": "claim-target-result", "statement": "SD2 outperformed SPOTLight, DSTG, and cell2location on the simulated seqFISH+ benchmark, achieving an RMSE of 0.06 and a JSD of 0.21.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36063455", "locator": "sections[8] \"3.2 Benchmark evaluation\" paragraph 5", "quote": "Through the comparison with ground truth, we observed that SD2 outperformed the other three methods in root mean square error (RMSE) and Jensen–Shannon Divergence (JSD)."}, {"asset": "source:pmid:36063455", "locator": "sections[8] \"3.2 Benchmark evaluation\" paragraph 5", "quote": "In particular, SD2 has RMSE of 0.06 and JSD of 0.21 which shows the most similar pattern compared with ground truth (Fig. 2A)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "SD2 outperformed SPOTLight, DSTG, and cell2location on the simulated seqFISH+ benchmark, achieving an RMSE of 0.06 and a JSD of 0.21.", "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:36063455"], "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:GSE111672"], "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:GSE111672"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36063455", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bioinformatics/btac605", "sha256": "sha256:ada04be3a74dcb50ee6ffe70b9c4d5ba7a908266817be89b0c66289c0a52ca39", "bytes": 33627, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bioinformatics/btac605", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9789790", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE111672", "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=GSE111672", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE111672", "version": null, "note": "The seqFISH+ dataset is collected from GSE98674 and corresponded scRNA-seq dataset is collected from GSE6036. The MERFISH datasets are collected from https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248/ and scRNA-seq data is from https://github.com/rdong08/spatialDWLS_dataset/tree/main/datasets. ST and scRNA-seq data from PDAC are collected from GSE111672. ST data from adult mouse brain are collected from 10X Genomics and the corresponding scRNA-seq data are collected from allen institute which are sequenced by smart-seq. The ST data of mouse kidney are collected from 10X Genomics and scRNA-seq data are from GSE157079.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The seqFISH+ dataset is collected from GSE98674 and corresponded scRNA-seq dataset is collected from GSE6036. The MERFISH datasets are collected from https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248/ and scRNA-seq data is from https://github.com/rdong08/spatialDWLS_dataset/tree/main/datasets. ST and scRNA-seq data from PDAC are collected from GSE111672. ST data from adult mouse brain are collected from 10X Genomics and the corresponding scRNA-seq data are collected from allen institute which are sequenced by smart-seq. The ST data of mouse kidney are collected from 10X Genomics and scRNA-seq data are from GSE157079.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3036909", "GSM3036910", "GSM3036911", "GSM3405527", "GSM3405528", "GSM3405529", "GSM3405530", "GSM3405531", "GSM3405532", "GSM3405533", "GSM3405534", "GSM4100717", "GSM4100718", "GSM4100719", "GSM4100720", "GSM4100721", "GSM4100722", "GSM4100723", "GSM4100724", "GSM4100725", "GSM4100726", "GSM4100727", "GSM4100728"], "sample_count": 23, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "Integrating microarray-based spatial transcriptomics and single-cell RNA-seq reveals tissue architecture in pancreatic ductal adenocarcinomas", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE157079", "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=GSE157079", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE157079", "version": null, "note": "The seqFISH+ dataset is collected from GSE98674 and corresponded scRNA-seq dataset is collected from GSE6036. The MERFISH datasets are collected from https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248/ and scRNA-seq data is from https://github.com/rdong08/spatialDWLS_dataset/tree/main/datasets. ST and scRNA-seq data from PDAC are collected from GSE111672. ST data from adult mouse brain are collected from 10X Genomics and the corresponding scRNA-seq data are collected from allen institute which are sequenced by smart-seq. The ST data of mouse kidney are collected from 10X Genomics and scRNA-seq data are from GSE157079.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The seqFISH+ dataset is collected from GSE98674 and corresponded scRNA-seq dataset is collected from GSE6036. The MERFISH datasets are collected from https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248/ and scRNA-seq data is from https://github.com/rdong08/spatialDWLS_dataset/tree/main/datasets. ST and scRNA-seq data from PDAC are collected from GSE111672. ST data from adult mouse brain are collected from 10X Genomics and the corresponding scRNA-seq data are collected from allen institute which are sequenced by smart-seq. The ST data of mouse kidney are collected from 10X Genomics and scRNA-seq data are from GSE157079.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4752160", "GSM4752161", "GSM4752162", "GSM4752163", "GSM4752164", "GSM4752165", "GSM4752166", "GSM4752167", "GSM4752168", "GSM4752169", "GSM4752170", "GSM4752171", "GSM4752172"], "sample_count": 13, "group_sizes": null, "group_sizes_basis": null, "platform": "21493;21103", "taxon": "Mus musculus", "title": "Single cell resolution regulatory landscape of the mouse kidney highlights cellular differentiation programs and renal disease targets", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE98674", "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=GSE98674", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE98674", "version": null, "note": "The seqFISH+ dataset is collected from GSE98674 and corresponded scRNA-seq dataset is collected from GSE6036. The MERFISH datasets are collected from https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248/ and scRNA-seq data is from https://github.com/rdong08/spatialDWLS_dataset/tree/main/datasets. ST and scRNA-seq data from PDAC are collected from GSE111672. ST data from adult mouse brain are collected from 10X Genomics and the corresponding scRNA-seq data are collected from allen institute which are sequenced by smart-seq. The ST data of mouse kidney are collected from 10X Genomics and scRNA-seq data are from GSE157079.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The seqFISH+ dataset is collected from GSE98674 and corresponded scRNA-seq dataset is collected from GSE6036. The MERFISH datasets are collected from https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248/ and scRNA-seq data is from https://github.com/rdong08/spatialDWLS_dataset/tree/main/datasets. ST and scRNA-seq data from PDAC are collected from GSE111672. ST data from adult mouse brain are collected from 10X Genomics and the corresponding scRNA-seq data are collected from allen institute which are sequenced by smart-seq. The ST data of mouse kidney are collected from 10X Genomics and scRNA-seq data are from GSE157079.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2609303", "GSM2609304", "GSM2609305", "GSM2609306", "GSM2609307", "GSM2609308", "GSM2609309", "GSM2609310", "GSM2609311", "GSM2609312", "GSM2609313"], "sample_count": 11, "group_sizes": null, "group_sizes_basis": null, "platform": "17021", "taxon": "Mus musculus", "title": "Combinatorial Signal Preception in the BMP Pathway", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE6036", "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=GSE6036", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6036", "version": null, "note": "The seqFISH+ dataset is collected from GSE98674 and corresponded scRNA-seq dataset is collected from GSE6036. The MERFISH datasets are collected from https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248/ and scRNA-seq data is from https://github.com/rdong08/spatialDWLS_dataset/tree/main/datasets. ST and scRNA-seq data from PDAC are collected from GSE111672. ST data from adult mouse brain are collected from 10X Genomics and the corresponding scRNA-seq data are collected from allen institute which are sequenced by smart-seq. The ST data of mouse kidney are collected from 10X Genomics and scRNA-seq data are from GSE157079.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The seqFISH+ dataset is collected from GSE98674 and corresponded scRNA-seq dataset is collected from GSE6036. The MERFISH datasets are collected from https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248/ and scRNA-seq data is from https://github.com/rdong08/spatialDWLS_dataset/tree/main/datasets. ST and scRNA-seq data from PDAC are collected from GSE111672. ST data from adult mouse brain are collected from 10X Genomics and the corresponding scRNA-seq data are collected from allen institute which are sequenced by smart-seq. The ST data of mouse kidney are collected from 10X Genomics and scRNA-seq data are from GSE157079.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-11-01T23:38:31Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE111672 not downloaded", "asset:data:geo:GSE111672 licence not read", "asset:data:geo:GSE157079 not downloaded", "asset:data:geo:GSE157079 licence not read", "asset:data:geo:GSE98674 not downloaded", "asset:data:geo:GSE98674 licence not read", "asset:data:geo:GSE6036 not downloaded", "asset:data:geo:GSE6036 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "root mean square error (RMSE) and Jensen–Shannon Divergence (JSD)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Through the comparison with ground truth, we observed that SD2 outperformed the other three methods in root mean square error (RMSE) and Jensen–Shannon Divergence (JSD)."}}], "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 (root mean square error (RMSE) and Jensen–Shannon Divergence (JSD)), 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": ["GSE98674", "GSE6036", "GSE111672", "GSE157079"], "resolved_accessions": ["GSE98674", "GSE111672", "GSE157079"], "statements": ["The seqFISH+ dataset is collected from GSE98674 and corresponded scRNA-seq dataset is collected from GSE6036. The MERFISH datasets are collected from https://datadryad.org/stash/dataset/doi:10.5061/dryad.8t8s248/ and scRNA-seq data is from https://github.com/rdong08/spatialDWLS_dataset/tree/main/datasets. ST and scRNA-seq data from PDAC are collected from GSE111672. ST data from adult mouse brain are collected from 10X Genomics and the corresponding scRNA-seq data are collected from allen institute which are sequenced by smart-seq. The ST data of mouse kidney are collected from 10X Genomics and scRNA-seq data are from GSE157079."], "basis": "The paper names GSE98674, GSE111672, GSE157079 in GSE and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:36063455", "data:geo:GSE111672"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE111672"]}, "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": "2026-11-01T18:03:43Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9191, "completion_tokens": 2489, "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:36063455", "type": "paper", "label": "pmid:36063455"}, {"id": "source:pmid:36063455", "type": "manuscript", "label": "PMID 36063455 full text"}, {"id": "data:geo:GSE111672", "type": "dataset", "label": "GEO GSE111672"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36063455", "type": "paper", "label": "pmid:36063455"}, {"id": "source:pmid:36063455", "type": "manuscript", "label": "PMID 36063455 full text"}, {"id": "data:geo:GSE111672", "type": "dataset", "label": "GEO GSE111672"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36063455", "type": "extraction", "used": ["source:pmid:36063455"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE111672", "type": "accession_resolution", "used": ["data:geo:GSE111672"], "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:36063455", "parent_hash": "sha256:c99305879c59e328e1e4d3b31e27e66f802ab444d6ac187ec085508acb4d1e4c", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE111672 licence not read", "asset:data:geo:GSE111672 not downloaded", "asset:data:geo:GSE157079 licence not read", "asset:data:geo:GSE157079 not downloaded", "asset:data:geo:GSE6036 licence not read", "asset:data:geo:GSE6036 not downloaded", "asset:data:geo:GSE98674 licence not read", "asset:data:geo:GSE98674 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": 0.99, "evidence": ["SD2: spatially resolved transcriptomics deconvolution through integration of dropout", "cellular targets of human diseases. Spatial transcriptomics (ST) supplies spatial gene expression profil", "considered as an obstruction in single-cell RNA sequencing data (scRNA-seq) analysis. First, we extract"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"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": ["raditionally considered as an obstruction in single-cell RNA sequencing data (scRNA-seq) analysis. First, we extract", "truction in single-cell RNA sequencing data (scRNA-seq) analysis. First, we extract the dropout-bas", "ed genes as informative features from ST and scRNA-seq data by fitting a Michaelis-Menten function.", "do-ST spots by randomly composing cells from scRNA-seq data, auto-encoder is applied to discover lo"], "order_basis": "paper_text_order:797", "id": "assay:2"}]}