RDKit2D + MLP
Baseline implemented by the Therapeutics Data Commons authors over the stated molecular featurisation.
Overview
Baseline implemented by the Therapeutics Data Commons authors over the stated molecular featurisation.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
Evaluations and results
Release 2026-09-17-134cd1815de8 · 22 evaluations · 22 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| RDKit2D + MLP on TDC ADMET benchmark group TDC-AMES: Toxicity: TDC.AMES Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-AMES: Toxicity: TDC.AMESDataset subset: TDC.AMES (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.823 ± 0.011 auroc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.011 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Toxicity), row(RDKit2D + MLP), column(TDC.AMES) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-AQSOL: Absorption: TDC.AqSol Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-AQSOL: Absorption: TDC.AqSolDataset subset: TDC.AqSol (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.827 ± 0.047 mae Unit: error · Direction: lower | Uncertainty: type: standard deviation; value: 0.047 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Absorption), row(RDKit2D + MLP), column(TDC.AqSol) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-BBB: Distribution: TDC.BBB Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-BBB: Distribution: TDC.BBBDataset subset: TDC.BBB (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.889 ± 0.016 auroc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.016 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Distribution), row(RDKit2D + MLP), column(TDC.BBB) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-BIOAV: Absorption: TDC.Bioav Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-BIOAV: Absorption: TDC.BioavDataset subset: TDC.Bioav (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.672 ± 0.021 auroc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.021 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Absorption), row(RDKit2D + MLP), column(TDC.Bioav) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-CACO2: Absorption: TDC.Caco2 Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-CACO2: Absorption: TDC.Caco2Dataset subset: TDC.Caco2 (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.393 ± 0.024 mae Unit: error · Direction: lower | Uncertainty: type: standard deviation; value: 0.024 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Absorption), row(RDKit2D + MLP), column(TDC.Caco2) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-CL-HEPA: Excretion: TDC.CL-Hepa Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-CL-HEPA: Excretion: TDC.CL-HepaDataset subset: TDC.CL-Hepa (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.382 ± 0.007 spearman Unit: correlation · Direction: higher | Uncertainty: type: standard deviation; value: 0.007 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Excretion), row(RDKit2D + MLP), column(TDC.CL-Hepa) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-CL-MICRO: Excretion: TDC.CL-Micro Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-CL-MICRO: Excretion: TDC.CL-MicroDataset subset: TDC.CL-Micro (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.586 ± 0.014 spearman Unit: correlation · Direction: higher | Uncertainty: type: standard deviation; value: 0.014 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Excretion), row(RDKit2D + MLP), column(TDC.CL-Micro) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP2C9-INHIBITION: Metabolism: TDC.CYP2C9 Inhibition Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-CYP2C9-INHIBITION: Metabolism: TDC.CYP2C9 InhibitionDataset subset: TDC.CYP2C9 Inhibition (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.742 ± 0.006 auprc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.006 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Metabolism), row(RDKit2D + MLP), column(TDC.CYP2C9 Inhibition) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP2C9-SUBSTRATE: Metabolism: TDC.CYP2C9 Substrate Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-CYP2C9-SUBSTRATE: Metabolism: TDC.CYP2C9 SubstrateDataset subset: TDC.CYP2C9 Substrate (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.360 ± 0.040 auprc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.040 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Metabolism), row(RDKit2D + MLP), column(TDC.CYP2C9 Substrate) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP2D6-INHIBITION: Metabolism: TDC.CYP2D6 Inhibition Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-CYP2D6-INHIBITION: Metabolism: TDC.CYP2D6 InhibitionDataset subset: TDC.CYP2D6 Inhibition (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.616 ± 0.007 auprc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.007 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Metabolism), row(RDKit2D + MLP), column(TDC.CYP2D6 Inhibition) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP2D6-SUBSTRATE: Metabolism: TDC.CYP2D6 Substrate Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-CYP2D6-SUBSTRATE: Metabolism: TDC.CYP2D6 SubstrateDataset subset: TDC.CYP2D6 Substrate (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.677 ± 0.047 auprc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.047 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Metabolism), row(RDKit2D + MLP), column(TDC.CYP2D6 Substrate) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP3A4-INHIBITION: Metabolism: TDC.CYP3A4 Inhibition Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-CYP3A4-INHIBITION: Metabolism: TDC.CYP3A4 InhibitionDataset subset: TDC.CYP3A4 Inhibition (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.829 ± 0.007 auprc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.007 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Metabolism), row(RDKit2D + MLP), column(TDC.CYP3A4 Inhibition) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP3A4-SUBSTRATE: Metabolism: TDC.CYP3A4 Substrate Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-CYP3A4-SUBSTRATE: Metabolism: TDC.CYP3A4 SubstrateDataset subset: TDC.CYP3A4 Substrate (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.639 ± 0.012 auroc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.012 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Metabolism), row(RDKit2D + MLP), column(TDC.CYP3A4 Substrate) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-DILI: Toxicity: TDC.DILI Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-DILI: Toxicity: TDC.DILIDataset subset: TDC.DILI (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.875 ± 0.019 auroc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.019 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Toxicity), row(RDKit2D + MLP), column(TDC.DILI) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-HALF-LIFE: Excretion: TDC.Half Life Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-HALF-LIFE: Excretion: TDC.Half LifeDataset subset: TDC.Half Life (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.184 ± 0.111 spearman Unit: correlation · Direction: higher | Uncertainty: type: standard deviation; value: 0.111 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Excretion), row(RDKit2D + MLP), column(TDC.Half_Life) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-HERG: Toxicity: TDC.hERG Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-HERG: Toxicity: TDC.hERGDataset subset: TDC.hERG (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.841 ± 0.020 auroc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.020 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Toxicity), row(RDKit2D + MLP), column(TDC.hERG) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-HIA: Absorption: TDC.HIA Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-HIA: Absorption: TDC.HIADataset subset: TDC.HIA (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.972 ± 0.008 auroc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.008 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Absorption), row(RDKit2D + MLP), column(TDC.HIA) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-LD50: Toxicity: TDC.LD50 Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-LD50: Toxicity: TDC.LD50Dataset subset: TDC.LD50 (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.678 ± 0.003 mae Unit: error · Direction: lower | Uncertainty: type: standard deviation; value: 0.003 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Toxicity), row(RDKit2D + MLP), column(TDC.LD50) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-LIPO: Absorption: TDC.Lipo Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-LIPO: Absorption: TDC.LipoDataset subset: TDC.Lipo (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.574 ± 0.017 mae Unit: error · Direction: lower | Uncertainty: type: standard deviation; value: 0.017 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Absorption), row(RDKit2D + MLP), column(TDC.Lipo) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-PGP: Absorption: TDC.Pgp Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-PGP: Absorption: TDC.PgpDataset subset: TDC.Pgp (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.918 ± 0.007 auroc Unit: fraction · Direction: higher | Uncertainty: type: standard deviation; value: 0.007 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Absorption), row(RDKit2D + MLP), column(TDC.Pgp) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-PPBR: Distribution: TDC.PPBR Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-PPBR: Distribution: TDC.PPBRDataset subset: TDC.PPBR (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 9.994 ± 0.319 mae Unit: error · Direction: lower | Uncertainty: type: standard deviation; value: 0.319 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Distribution), row(RDKit2D + MLP), column(TDC.PPBR) Source checking is not independent reproduction. |
| RDKit2D + MLP on TDC ADMET benchmark group TDC-VD: Distribution: TDC.VDss Method: RDKit2D + MLPTask: TDC ADMET benchmark group TDC-VD: Distribution: TDC.VDssDataset subset: TDC.VDss (TDC ADMET benchmark group split) Scaffold split, as the ADMET benchmark group defines it. Values are the mean and standard deviation over repeated runs. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.561 ± 0.025 spearman Unit: correlation · Direction: higher | Uncertainty: type: standard deviation; value: 0.025 Scored: Not reported · Eligible: Not reported | source checkedTherapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Table 4, block(Distribution), row(RDKit2D + MLP), column(TDC.VD) Source checking is not 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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-09-17-134cd1815de8 · Record review: source checked
1 source records and release history
- Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development · Original source · arXiv 2102.09548v1; later NSF v2 discovery retrieved partially but full artifact unavailable
Technical metadata and extraction receipts
Stable ID: tdc-method-rdkit2d-plus-mlp
- areas
- molecular-interactions
- source locator
- Table 4, row(RDKit2D + MLP)
- missing metadata
- checkpoint revision: unreported; parameters: unextracted
Related records
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-AMES: Toxicity: TDC.AMES
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-AQSOL: Absorption: TDC.AqSol
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-BBB: Distribution: TDC.BBB
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-BIOAV: Absorption: TDC.Bioav
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-CACO2: Absorption: TDC.Caco2
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-CL-HEPA: Excretion: TDC.CL-Hepa
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-CL-MICRO: Excretion: TDC.CL-Micro
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP2C9-INHIBITION: Metabolism: TDC.CYP2C9 Inhibition
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP2C9-SUBSTRATE: Metabolism: TDC.CYP2C9 Substrate
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP2D6-INHIBITION: Metabolism: TDC.CYP2D6 Inhibition
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP2D6-SUBSTRATE: Metabolism: TDC.CYP2D6 Substrate
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP3A4-INHIBITION: Metabolism: TDC.CYP3A4 Inhibition
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-CYP3A4-SUBSTRATE: Metabolism: TDC.CYP3A4 Substrate
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-DILI: Toxicity: TDC.DILI
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-HALF-LIFE: Excretion: TDC.Half Life
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-HERG: Toxicity: TDC.hERG
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-HIA: Absorption: TDC.HIA
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-LD50: Toxicity: TDC.LD50
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-LIPO: Absorption: TDC.Lipo
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-PGP: Absorption: TDC.Pgp
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-PPBR: Distribution: TDC.PPBR
- model: RDKit2D + MLP on TDC ADMET benchmark group TDC-VD: Distribution: TDC.VDss