Method

3DCNN

Three-dimensional convolutional network that voxelises a molecular structure into a 1 Å grid of one-hot atom types and applies four 3D convolution layers and two fully connected layers.

14 evaluations · 14 results

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

14 evaluations · 14 results. Different protocols are not a single leaderboard.

Sorted by Spearman (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	Spearman	AUROC	MAE	Accuracy	Pearson	RMSE
3DCNNEvaluation	ATOM3D PSR-GLOBAL-RS: Protein structure ranking, global Spearman, ATOM3D PSR (ATOM3D split)	0.789 (best in column)	Not reported	Not reported	Not reported	Not reported	Not reported
3DCNNEvaluation	ATOM3D LBA-RS: Ligand binding affinity, global Spearman correlation, ATOM3D LBA (ATOM3D split)	0.553	Not reported	Not reported	Not reported	Not reported	Not reported
3DCNNEvaluation	ATOM3D PSR-MEAN-RS: Protein structure ranking, mean Spearman within a target, ATOM3D PSR (ATOM3D split)	0.431	Not reported	Not reported	Not reported	Not reported	Not reported
3DCNNEvaluation	ATOM3D RSR-GLOBAL-RS: RNA structure ranking, global Spearman, ATOM3D RSR (ATOM3D split)	0.372	Not reported	Not reported	Not reported	Not reported	Not reported
3DCNNEvaluation	ATOM3D RSR-MEAN-RS: RNA structure ranking, mean Spearman within a target, ATOM3D RSR (ATOM3D split)	0.264	Not reported	Not reported	Not reported	Not reported	Not reported
3DCNNEvaluation	ATOM3D LBA-RMSE: Ligand binding affinity, root mean squared error, ATOM3D LBA (ATOM3D split)	Not reported	Not reported	Not reported	Not reported	Not reported	1.42
3DCNNEvaluation	ATOM3D LBA-RP: Ligand binding affinity, global Pearson correlation, ATOM3D LBA (ATOM3D split)	Not reported	Not reported	Not reported	Not reported	0.55	Not reported
3DCNNEvaluation	ATOM3D LEP-AUROC: Ligand efficacy prediction, ATOM3D LEP (ATOM3D split)	Not reported	0.589	Not reported	Not reported	Not reported	Not reported
3DCNNEvaluation	ATOM3D MSP: Mutation stability prediction, ATOM3D MSP (ATOM3D split)	Not reported	0.574	Not reported	Not reported	Not reported	Not reported
3DCNNEvaluation	ATOM3D PIP: Protein interface prediction, ATOM3D PIP (ATOM3D split)	Not reported	0.844 (best in column)	Not reported	Not reported	Not reported	Not reported
3DCNNEvaluation	ATOM3D RES: Residue identity, ATOM3D RES (ATOM3D split)	Not reported	Not reported	Not reported	0.451	Not reported	Not reported
3DCNNEvaluation	ATOM3D SMP-EGAP: Small molecule properties, HOMO-LUMO gap, ATOM3D SMP (ATOM3D split)	Not reported	Not reported	0.58 (best in column)	Not reported	Not reported	Not reported
3DCNNEvaluation	ATOM3D SMP-MU: Small molecule properties, dipole moment, ATOM3D SMP (ATOM3D split)	Not reported	Not reported	0.754	Not reported	Not reported	Not reported
3DCNNEvaluation	ATOM3D SMP-U0AT: Small molecule properties, atomization energy, ATOM3D SMP (ATOM3D split)	Not reported	Not reported	3.86	Not reported	Not reported	Not reported

All 14 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
Method: 3DCNN	Task: ATOM3D LBA-RMSE: Ligand binding affinity, root mean squared error Dataset subset: ATOM3D LBA (ATOM3D split)	1.42 RMSE unit-unreported · lower Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D LBA-RMSE: Ligand binding affinity, root mean squared error Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(LBA RMSE), column(3DCNN)
Method: 3DCNN	Task: ATOM3D LBA-RP: Ligand binding affinity, global Pearson correlation Dataset subset: ATOM3D LBA (ATOM3D split)	0.55 Pearson unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D LBA-RP: Ligand binding affinity, global Pearson correlation Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(glob. RP), column(3DCNN)
Method: 3DCNN	Task: ATOM3D LBA-RS: Ligand binding affinity, global Spearman correlation Dataset subset: ATOM3D LBA (ATOM3D split)	0.553 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D LBA-RS: Ligand binding affinity, global Spearman correlation Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(glob. RS), column(3DCNN)
Method: 3DCNN	Task: ATOM3D LEP-AUROC: Ligand efficacy prediction Dataset subset: ATOM3D LEP (ATOM3D split)	0.589 AUROC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D LEP-AUROC: Ligand efficacy prediction Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 5, row(LEP AUROC), column(3DCNN)
Method: 3DCNN	Task: ATOM3D MSP: Mutation stability prediction Dataset subset: ATOM3D MSP (ATOM3D split)	0.574 AUROC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D MSP: Mutation stability prediction Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 4, row(MSP AUROC), column(3DCNN)
Method: 3DCNN	Task: ATOM3D PIP: Protein interface prediction Dataset subset: ATOM3D PIP (ATOM3D split)	0.844 AUROC unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D PIP: Protein interface prediction Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 4, row(PIP AUROC), column(3DCNN)
Method: 3DCNN	Task: ATOM3D PSR-GLOBAL-RS: Protein structure ranking, global Spearman Dataset subset: ATOM3D PSR (ATOM3D split)	0.789 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D PSR-GLOBAL-RS: Protein structure ranking, global Spearman Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 6, row(glob. RS), column(3DCNN)
Method: 3DCNN	Task: ATOM3D PSR-MEAN-RS: Protein structure ranking, mean Spearman within a target Dataset subset: ATOM3D PSR (ATOM3D split)	0.431 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D PSR-MEAN-RS: Protein structure ranking, mean Spearman within a target Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 6, row(PSR mean RS), column(3DCNN)
Method: 3DCNN	Task: ATOM3D RES: Residue identity Dataset subset: ATOM3D RES (ATOM3D split)	0.451 Accuracy fraction · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D RES: Residue identity Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 4, row(RES accuracy), column(3DCNN)
Method: 3DCNN	Task: ATOM3D RSR-GLOBAL-RS: RNA structure ranking, global Spearman Dataset subset: ATOM3D RSR (ATOM3D split)	0.372 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D RSR-GLOBAL-RS: RNA structure ranking, global Spearman Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 6, row(glob. RS), column(3DCNN)
Method: 3DCNN	Task: ATOM3D RSR-MEAN-RS: RNA structure ranking, mean Spearman within a target Dataset subset: ATOM3D RSR (ATOM3D split)	0.264 Spearman unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D RSR-MEAN-RS: RNA structure ranking, mean Spearman within a target Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 6, row(RSR mean RS), column(3DCNN)
Method: 3DCNN	Task: ATOM3D SMP-EGAP: Small molecule properties, HOMO-LUMO gap Dataset subset: ATOM3D SMP (ATOM3D split)	0.58 MAE unit-unreported · lower Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D SMP-EGAP: Small molecule properties, HOMO-LUMO gap Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 3, row(SMP εgap [eV]), column(3DCNN)
Method: 3DCNN	Task: ATOM3D SMP-MU: Small molecule properties, dipole moment Dataset subset: ATOM3D SMP (ATOM3D split)	0.754 MAE unit-unreported · lower Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D SMP-MU: Small molecule properties, dipole moment Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 3, row(µ [D]), column(3DCNN)
Method: 3DCNN	Task: ATOM3D SMP-U0AT: Small molecule properties, atomization energy Dataset subset: ATOM3D SMP (ATOM3D split)	3.86 MAE unit-unreported · lower Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source 3DCNN on ATOM3D SMP-U0AT: Small molecule properties, atomization energy Trained and scored under the ATOM3D split for this task. Asterisks in the paper mark a run whose training data differed. Aggregation: Not reported ATOM3D: Tasks On Molecules in Three Dimensions · Table 3, row(U0at [eV]), column(3DCNN)

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

Use this method

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this method. 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

ATOM3D: Tasks On Molecules in Three Dimensions · Original source · Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: atom3d-method-3dcnn

areas: molecular-interactions
source locator: Table 3, column(3DCNN)
missing metadata: checkpoint revision: reason: unreported; parameters: reason: unextracted
provenance note: Implemented and trained by the ATOM3D authors.

Related records

Suggest a correction