Task

PBMC cell-type classification

PBMC cell classification assesses predictive performance and resource use under a common computing environment.

Sources

2 evaluations · 2 results

Overview

Datasets

PBMC bacterial-sepsis data are used for the principal all-gene comparison.

Metrics

Accuracy and, in broader experiments, precision, recall and F1, alongside memory/runtime.

Allowed inputs

Single-cell gene-expression profiles.

Sources

Evaluation procedure diagram

How it worksComputational evaluation flow

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

Sources

scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24; Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24; Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

2 evaluations · 2 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Pipeline: scaLR	Task: PBMC cell-type classification Dataset: PBMCs-BS	0.942 Cell-type accuracy unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source scaLR: PBMC cell-type classification All features and samples from PBMCs-BS. Aggregation: Not reported scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Table 2, scaLR row, Cell type Accuracy column
Pipeline: scVI + scANVI	Task: PBMC cell-type classification Dataset: PBMCs-BS	0.939 Cell-type accuracy unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source scVI + scANVI: PBMC cell-type classification All features and samples from PBMCs-BS; comparison pipeline combines scVI and scANVI. Aggregation: Not reported scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Table 2, Svi-tools (scVI & scANVI) row, Cell type Accuracy column

Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.

Methods and evaluation design

Procedure, tasks and evaluated configurations

How it works

Evaluation methodology

PBMC bacterial-sepsis data are used for the principal all-gene comparison. Accuracy and, in broader experiments, precision, recall and F1, alongside memory/runtime. scVI/scANVI, SingleCellNet, CellTypist, ACTINN and devCellPy.

Sources

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

No source-reviewed explanatory claims are recorded here yet.

Limitations and conditions

The paper contains separate cell-state and cell-type outcomes and larger cross-cohort evaluations. These should not be merged into one PBMC protocol.
Sources
scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24

Profile review details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Stable record: reported-task-b46b7b839bff93

Specifications

Inputs, training, access and other details

Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Data, procedure and scoring
Property	Description and evidence
Datasets	PBMC bacterial-sepsis data are used for the principal all-gene comparison. Sources scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24
Splits	Input cells are divided into training, validation and testing subsets, with dataset sizes in Table 1. The Methods do not specify donor-disjoint grouping for the PBMC comparison. Sources scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Table 1; Methods: Data processing and Training
Metrics	Accuracy and, in broader experiments, precision, recall and F1, alongside memory/runtime. Sources scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24
Baselines	scVI/scANVI, SingleCellNet, CellTypist, ACTINN and devCellPy. Sources scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24
Leakage controls	Feature-selection models use training data and validation data; the final classifier is selected with validation performance. The inspected PBMC comparison and data-processing sections do not specify donor-disjoint or batch-disjoint partitions, so a cell split cannot be treated as a held-out-donor experiment. · Not reported in inspected sources Sources scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Methods: Data processing, Feature extraction, Training and tool comparisons; cached paragraphs 63–82
Uncertainty	The PBMC cell-type comparison reports classification metrics, but its results, figure captions and comparison methods do not define repeated-seed dispersion or a donor/sample-level confidence-interval procedure for those metrics. · Not reported in inspected sources Sources scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · PBMC comparison results; associated figure captions; Methods: comparison of scaLR with other pipelines
Entity type	Paper-specific computational evaluation protocol. Sources scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24
Organisms	Human PBMCs. Sources scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24
Assays	Single-cell bacterial-sepsis expression with cell-type annotations. Sources scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24
Allowed inputs	Single-cell gene-expression profiles. Sources scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24
Adaptation	Supervised neural-network cell-type classification; validation data select the training checkpoint. Sources scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Methods: Feature extraction and Training

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.

Paper or primary resource	Version	Reference
scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery	version of record	Read source DOI: 10.1093/bib/bbaf243

Historical gaps recorded on 2026-09-17

The catalogue now holds 2 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.

Complete raw table acquired. Celltype accuracy is distinct from cellstate and time/memory. Time formatting and hardware need review before efficiency comparisons; no new timing claim accepted. Structured extraction pending.

Search and extraction details

source found structured extraction pending

Searches

scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery primary paper benchmark results

Evidence locations

Table2 PBMC celltype versuscellstate blocks

Evidence table

Inspect claims, sources and review details

Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.

One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.

17 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims	scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery Original source ↗ Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24; Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24; Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24 Version: version of record Retrieved: 2026-09-16T10:44:03.403844+00:00	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `829afab6a4e30997c608745d3eb280105b8c5c4e601020ffdc55c866144527ca` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps Allowed inputs: Single-cell gene-expression profiles. Datasets: PBMC bacterial-sepsis data are used for the principal all-gene comparison. Metrics: Accuracy and, in broader experiments, precision, recall and F1, alongside memory/runtime. Individual claims	scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery Original source ↗ Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24; Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24; Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24 Version: version of record Retrieved: 2026-09-16T10:44:03.403844+00:00	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `829afab6a4e30997c608745d3eb280105b8c5c4e601020ffdc55c866144527ca` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Computational evaluation flow Individual claims	scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery Original source ↗ Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24; Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24; Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24 Version: version of record Retrieved: 2026-09-16T10:44:03.403844+00:00	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `829afab6a4e30997c608745d3eb280105b8c5c4e601020ffdc55c866144527ca` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Datasets PBMC bacterial-sepsis data are used for the principal all-gene comparison. Individual claims	scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery Original source ↗ Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24 Version: version of record Retrieved: 2026-09-16T10:44:03.403844+00:00	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `829afab6a4e30997c608745d3eb280105b8c5c4e601020ffdc55c866144527ca` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Splits Input cells are divided into training, validation and testing subsets, with dataset sizes in Table 1. The Methods do not specify donor-disjoint grouping for the PBMC comparison. Individual claims	scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery Original source ↗ Table 1; Methods: Data processing and Training Version: version of record Retrieved: 2026-09-16T10:44:03.403844+00:00	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `829afab6a4e30997c608745d3eb280105b8c5c4e601020ffdc55c866144527ca` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Adaptation Supervised neural-network cell-type classification; validation data select the training checkpoint. Individual claims	scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery Original source ↗ Methods: Feature extraction and Training Version: version of record Retrieved: 2026-09-16T10:44:03.403844+00:00	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `829afab6a4e30997c608745d3eb280105b8c5c4e601020ffdc55c866144527ca` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Metrics Accuracy and, in broader experiments, precision, recall and F1, alongside memory/runtime. Individual claims	scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery Original source ↗ Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24 Version: version of record Retrieved: 2026-09-16T10:44:03.403844+00:00	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `829afab6a4e30997c608745d3eb280105b8c5c4e601020ffdc55c866144527ca` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Baselines scVI/scANVI, SingleCellNet, CellTypist, ACTINN and devCellPy. Individual claims	scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery Original source ↗ Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24 Version: version of record Retrieved: 2026-09-16T10:44:03.403844+00:00	source checked automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `829afab6a4e30997c608745d3eb280105b8c5c4e601020ffdc55c866144527ca` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Leakage controls Feature-selection models use training data and validation data; the final classifier is selected with validation performance. The inspected PBMC comparison and data-processing sections do not specify donor-disjoint or batch-disjoint partitions, so a cell split cannot be treated as a held-out-donor experiment. Individual claims	scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery Original source ↗ Methods: Data processing, Feature extraction, Training and tool comparisons; cached paragraphs 63–82 Version: version of record Retrieved: 2026-09-16T10:44:03.403844+00:00	unreported automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `829afab6a4e30997c608745d3eb280105b8c5c4e601020ffdc55c866144527ca` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Uncertainty The PBMC cell-type comparison reports classification metrics, but its results, figure captions and comparison methods do not define repeated-seed dispersion or a donor/sample-level confidence-interval procedure for those metrics. Individual claims	scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery Original source ↗ PBMC comparison results; associated figure captions; Methods: comparison of scaLR with other pipelines Version: version of record Retrieved: 2026-09-16T10:44:03.403844+00:00	unreported automated source review · 2026-09-16 Audit details Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: `attributes.profile.facts.5.value` Source artifact SHA-256: `829afab6a4e30997c608745d3eb280105b8c5c4e601020ffdc55c866144527ca` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: needs review

2 source records and release history

scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Original source · version of record
scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery · Original source · version of record

Download this release

Technical metadata and extraction receipts

Stable ID: reported-task-b46b7b839bff93

areas: cells-tissues
tasks: PBMC cell-type classification
entity level: task
version: Not reported
task: PBMC cell-type classification
scope note: Paper-specific evaluation task; protocol completeness requires further extraction.
benchmark research: review date: 2026-09-17; status: source_found_structured_extraction_pending; primary sources: evidence-expansion-p2-scalr-2025-829afab6a4e3; inspected locators: Table2 PBMC celltype versuscellstate blocks; searched queries: scaLR: a low-resource deep neural network-based platform for single cell analysis and biomarker discovery primary paper benchmark results; gaps: Complete raw table acquired. Celltype accuracy is distinct from cellstate and time/memory. Time formatting and hardware need review before efficiency comparisons; no new timing claim accepted. Structured extraction pending.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
historical missing metadata: protocol version: not_reported_in_legacy_extract; split: not_reported_in_legacy_extract
metadata review scope: historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
legacy kinds: benchmark
entity classification: review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: scalr-2025; source locator: Results: Performance evaluation using all genes; robustness evaluations; cached text lines 13–14, 22–24; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.

Related records

dataset: PBMCs-BS
benchmark: scaLR: PBMC cell-type classification
benchmark: scVI + scANVI: PBMC cell-type classification

Suggest a correction