Configuration

Baseline CNN (PyTorch)

The paper's baseline convolutional network, built with PyTorch.

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

9 evaluations · 18 results. Different protocols are not a single leaderboard.

Sorted by Accuracy (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Protocol and dataset	Accuracy	F1 (binary, positive class)	Micro F1
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks HUMAN-ENSEMBL-REGULATORY-ACCURACY: human_ensembl_regulatory, Accuracy, human_ensembl_regulatory (Genomic Benchmarks split)	93.3% (best in column)	Not reported	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks DEMO-HUMAN-OR-WORM-ACCURACY: demo_human_or_worm, Accuracy, demo_human_or_worm (Genomic Benchmarks split)	93%	Not reported	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks DEMO-CODING-VS-INTERGENOMIC-SEQS-ACCURACY: demo_coding_vs_intergenomic_seqs, Accuracy, demo_coding_vs_intergenomic_seqs (Genomic Benchmarks split)	87.6%	Not reported	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks HUMAN-NONTATA-PROMOTERS-ACCURACY: human_nontata_promoters, Accuracy, human_nontata_promoters (Genomic Benchmarks split)	84.6%	Not reported	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks HUMAN-ENHANCERS-COHN-ACCURACY: human_enhancers_cohn, Accuracy, human_enhancers_cohn (Genomic Benchmarks split)	69.5%	Not reported	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks DUMMY-MOUSE-ENHANCERS-ENSEMBL-ACCURACY: dummy_mouse_enhancers_ensembl, Accuracy, dummy_mouse_enhancers_ensembl (Genomic Benchmarks split)	69%	Not reported	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks HUMAN-ENHANCERS-ENSEMBL-ACCURACY: human_enhancers_ensembl, Accuracy, human_enhancers_ensembl (Genomic Benchmarks split)	68.9%	Not reported	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks HUMAN-OCR-ENSEMBL-ACCURACY: human_ocr_ensembl, Accuracy, human_ocr_ensembl (Genomic Benchmarks split)	68%	Not reported	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks DROSOPHILA-ENHANCERS-STARK-ACCURACY: drosophila_enhancers_stark, Accuracy, drosophila_enhancers_stark (Genomic Benchmarks split)	58.6%	Not reported	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks DEMO-CODING-VS-INTERGENOMIC-SEQS-F1: demo_coding_vs_intergenomic_seqs, F1 score, demo_coding_vs_intergenomic_seqs (Genomic Benchmarks split)	Not reported	86.8%	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks DEMO-HUMAN-OR-WORM-F1: demo_human_or_worm, F1 score, demo_human_or_worm (Genomic Benchmarks split)	Not reported	92.8% (best in column)	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks DROSOPHILA-ENHANCERS-STARK-F1: drosophila_enhancers_stark, F1 score, drosophila_enhancers_stark (Genomic Benchmarks split)	Not reported	44.5%	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks DUMMY-MOUSE-ENHANCERS-ENSEMBL-F1: dummy_mouse_enhancers_ensembl, F1 score, dummy_mouse_enhancers_ensembl (Genomic Benchmarks split)	Not reported	70.4%	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks HUMAN-ENHANCERS-COHN-F1: human_enhancers_cohn, F1 score, human_enhancers_cohn (Genomic Benchmarks split)	Not reported	67.1%	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks HUMAN-ENHANCERS-ENSEMBL-F1: human_enhancers_ensembl, F1 score, human_enhancers_ensembl (Genomic Benchmarks split)	Not reported	56.5%	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks HUMAN-ENSEMBL-REGULATORY-F1: human_ensembl_regulatory, F1 score, human_ensembl_regulatory (Genomic Benchmarks split)	Not reported	Not reported	93.3%
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks HUMAN-NONTATA-PROMOTERS-F1: human_nontata_promoters, F1 score, human_nontata_promoters (Genomic Benchmarks split)	Not reported	83.7%	Not reported
Baseline CNN (PyTorch)Evaluation	Genomic Benchmarks HUMAN-OCR-ENSEMBL-F1: human_ocr_ensembl, F1 score, human_ocr_ensembl (Genomic Benchmarks split)	Not reported	66.1%	Not reported

All 18 result rows with coverage, uncertainty and sources

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
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks DEMO-CODING-VS-INTERGENOMIC-SEQS-ACCURACY: demo_coding_vs_intergenomic_seqs, Accuracy Dataset subset: demo_coding_vs_intergenomic_seqs (Genomic Benchmarks split)	87.6% Accuracy percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks DEMO-CODING-VS-INTERGENOMIC-SEQS-ACCURACY: demo_coding_vs_intergenomic_seqs, Accuracy The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(demo_coding_vs_intergenomic_seqs), column(Baseline CNN (PyTorch) Accuracy)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks DEMO-CODING-VS-INTERGENOMIC-SEQS-F1: demo_coding_vs_intergenomic_seqs, F1 score Dataset subset: demo_coding_vs_intergenomic_seqs (Genomic Benchmarks split)	86.8% F1 (binary, positive class) percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks DEMO-CODING-VS-INTERGENOMIC-SEQS-F1: demo_coding_vs_intergenomic_seqs, F1 score The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(demo_coding_vs_intergenomic_seqs), column(Baseline CNN (PyTorch) F1 score)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks DEMO-HUMAN-OR-WORM-ACCURACY: demo_human_or_worm, Accuracy Dataset subset: demo_human_or_worm (Genomic Benchmarks split)	93% Accuracy percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks DEMO-HUMAN-OR-WORM-ACCURACY: demo_human_or_worm, Accuracy The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(demo_human_or_worm), column(Baseline CNN (PyTorch) Accuracy)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks DEMO-HUMAN-OR-WORM-F1: demo_human_or_worm, F1 score Dataset subset: demo_human_or_worm (Genomic Benchmarks split)	92.8% F1 (binary, positive class) percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks DEMO-HUMAN-OR-WORM-F1: demo_human_or_worm, F1 score The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(demo_human_or_worm), column(Baseline CNN (PyTorch) F1 score)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks DROSOPHILA-ENHANCERS-STARK-ACCURACY: drosophila_enhancers_stark, Accuracy Dataset subset: drosophila_enhancers_stark (Genomic Benchmarks split)	58.6% Accuracy percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks DROSOPHILA-ENHANCERS-STARK-ACCURACY: drosophila_enhancers_stark, Accuracy The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(drosophila_enhancers_stark), column(Baseline CNN (PyTorch) Accuracy)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks DROSOPHILA-ENHANCERS-STARK-F1: drosophila_enhancers_stark, F1 score Dataset subset: drosophila_enhancers_stark (Genomic Benchmarks split)	44.5% F1 (binary, positive class) percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks DROSOPHILA-ENHANCERS-STARK-F1: drosophila_enhancers_stark, F1 score The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(drosophila_enhancers_stark), column(Baseline CNN (PyTorch) F1 score)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks DUMMY-MOUSE-ENHANCERS-ENSEMBL-ACCURACY: dummy_mouse_enhancers_ensembl, Accuracy Dataset subset: dummy_mouse_enhancers_ensembl (Genomic Benchmarks split)	69% Accuracy percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks DUMMY-MOUSE-ENHANCERS-ENSEMBL-ACCURACY: dummy_mouse_enhancers_ensembl, Accuracy The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(dummy_mouse_enhancers_ensembl), column(Baseline CNN (PyTorch) Accuracy)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks DUMMY-MOUSE-ENHANCERS-ENSEMBL-F1: dummy_mouse_enhancers_ensembl, F1 score Dataset subset: dummy_mouse_enhancers_ensembl (Genomic Benchmarks split)	70.4% F1 (binary, positive class) percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks DUMMY-MOUSE-ENHANCERS-ENSEMBL-F1: dummy_mouse_enhancers_ensembl, F1 score The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(dummy_mouse_enhancers_ensembl), column(Baseline CNN (PyTorch) F1 score)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks HUMAN-ENHANCERS-COHN-ACCURACY: human_enhancers_cohn, Accuracy Dataset subset: human_enhancers_cohn (Genomic Benchmarks split)	69.5% Accuracy percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks HUMAN-ENHANCERS-COHN-ACCURACY: human_enhancers_cohn, Accuracy The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(human_enhancers_cohn), column(Baseline CNN (PyTorch) Accuracy)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks HUMAN-ENHANCERS-COHN-F1: human_enhancers_cohn, F1 score Dataset subset: human_enhancers_cohn (Genomic Benchmarks split)	67.1% F1 (binary, positive class) percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks HUMAN-ENHANCERS-COHN-F1: human_enhancers_cohn, F1 score The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(human_enhancers_cohn), column(Baseline CNN (PyTorch) F1 score)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks HUMAN-ENHANCERS-ENSEMBL-ACCURACY: human_enhancers_ensembl, Accuracy Dataset subset: human_enhancers_ensembl (Genomic Benchmarks split)	68.9% Accuracy percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks HUMAN-ENHANCERS-ENSEMBL-ACCURACY: human_enhancers_ensembl, Accuracy The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(human_enhancers_ensembl), column(Baseline CNN (PyTorch) Accuracy)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks HUMAN-ENHANCERS-ENSEMBL-F1: human_enhancers_ensembl, F1 score Dataset subset: human_enhancers_ensembl (Genomic Benchmarks split)	56.5% F1 (binary, positive class) percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks HUMAN-ENHANCERS-ENSEMBL-F1: human_enhancers_ensembl, F1 score The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(human_enhancers_ensembl), column(Baseline CNN (PyTorch) F1 score)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks HUMAN-ENSEMBL-REGULATORY-ACCURACY: human_ensembl_regulatory, Accuracy Dataset subset: human_ensembl_regulatory (Genomic Benchmarks split)	93.3% Accuracy percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks HUMAN-ENSEMBL-REGULATORY-ACCURACY: human_ensembl_regulatory, Accuracy The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(human_ensembl_regulatory), column(Baseline CNN (PyTorch) Accuracy)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks HUMAN-ENSEMBL-REGULATORY-F1: human_ensembl_regulatory, F1 score Dataset subset: human_ensembl_regulatory (Genomic Benchmarks split)	93.3% Micro F1 percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks HUMAN-ENSEMBL-REGULATORY-F1: human_ensembl_regulatory, F1 score The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(human_ensembl_regulatory), column(Baseline CNN (PyTorch) F1 score)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks HUMAN-NONTATA-PROMOTERS-ACCURACY: human_nontata_promoters, Accuracy Dataset subset: human_nontata_promoters (Genomic Benchmarks split)	84.6% Accuracy percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks HUMAN-NONTATA-PROMOTERS-ACCURACY: human_nontata_promoters, Accuracy The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(human_nontata_promoters), column(Baseline CNN (PyTorch) Accuracy)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks HUMAN-NONTATA-PROMOTERS-F1: human_nontata_promoters, F1 score Dataset subset: human_nontata_promoters (Genomic Benchmarks split)	83.7% F1 (binary, positive class) percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks HUMAN-NONTATA-PROMOTERS-F1: human_nontata_promoters, F1 score The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(human_nontata_promoters), column(Baseline CNN (PyTorch) F1 score)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks HUMAN-OCR-ENSEMBL-ACCURACY: human_ocr_ensembl, Accuracy Dataset subset: human_ocr_ensembl (Genomic Benchmarks split)	68% Accuracy percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks HUMAN-OCR-ENSEMBL-ACCURACY: human_ocr_ensembl, Accuracy The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(human_ocr_ensembl), column(Baseline CNN (PyTorch) Accuracy)
Configuration: Baseline CNN (PyTorch)	Task: Genomic Benchmarks HUMAN-OCR-ENSEMBL-F1: human_ocr_ensembl, F1 score Dataset subset: human_ocr_ensembl (Genomic Benchmarks split)	66.1% F1 (binary, positive class) percent · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Baseline CNN (PyTorch) on Genomic Benchmarks HUMAN-OCR-ENSEMBL-F1: human_ocr_ensembl, F1 score The paper's own three-layer convolutional baseline, trained on each dataset's training split and scored on its test split. Architecture is in Table 1. Aggregation: Not reported Genomic benchmarks: a collection of datasets for genomic sequence classification · Table 2, row(human_ocr_ensembl), column(Baseline CNN (PyTorch) F1 score)

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

Evidence

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

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.

0 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-11-02-a7f03c9e55a5
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-11-02-a7f03c9e55a5 · Record review: source checked

1 source record and release history

Genomic benchmarks: a collection of datasets for genomic sequence classification · Original source · PMC10150520

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: genomic-benchmarks-method-baseline-cnn-pytorch

areas: dna-genomes
source locator: Table 2, column(Baseline CNN (PyTorch))
missing metadata: checkpoint revision: reason: unreported; parameters: reason: unextracted

Related records

Suggest a correction