Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Tasks · Molecular Property PredictionHome/Tasks/Graphs/Molecular Property Prediction

Molecular Property Prediction.

Molecular property prediction — estimating toxicity, solubility, binding affinity, or other properties from molecular structure — is the workhorse task of AI-driven drug discovery. GNNs operate on molecular graphs while transformer approaches (ChemBERTa, Uni-Mol) use SMILES strings or 3D coordinates. MoleculeNet (2018) and the Therapeutic Data Commons (TDC) provide standardized benchmarks, but the real bottleneck is distribution shift: models trained on known chemical space struggle with novel scaffolds, and the gap between leaderboard accuracy and actual wet-lab utility remains the field's central challenge.

1
Datasets
3
Results
roc_auc
Canonical metric
§ 02 · Canonical benchmark

The reference dataset.

OGB ogbg-molhiv

Molecular property prediction: predict whether a molecule inhibits HIV replication. 41K graphs from MoleculeNet. Binary classification, scaffold split, evaluated by ROC-AUC.

Primary metric: roc_auc
View full leaderboard →
§ 03 · Top 10

Leading models.

Leading models on OGB ogbg-molhiv.

#Modelroc_aucYearSource
DGN79.72026paper ↗
2GraphGPS78.82026paper ↗
3GIN+virtual node77.12026paper ↗

What were you looking for on Molecular Property Prediction?

Didn't find the model, metric, or dataset you needed? Tell us in one line. We read every message and reply within 48 hours.

§ 04 · All datasets

Tracked datasets.

1 dataset tracked for this task.

OGB ogbg-molhiv
CANONICAL
3 results · roc_auc
Top: DGN 79.7
§ 05 · Related tasks

Other tasks in Graphs.

Graph ClassificationLink PredictionNode Classification
Reply within 48 hours · No newsletter

Didn't find what you came for?

Still looking for something on Molecular Property Prediction? A missing model, a stale score, a benchmark we should cover — drop it here and we'll handle it.

Real humans read every message. We track what people are asking for and prioritize accordingly.