Rank compounds against one target

Ligand A → sequence → ligand B. Pick a target, supply two or more compounds, and the model orders them for that target.

Nothing is scored on its own and then subtracted. The forest is handed the whole comparison as one row, ligand A, the sequence, ligand B, in that precise order, and returns which ligand is the more potent of the two, with the strength of that call. Every pair of the compounds you supply is put to it that way, in both ligand orders, and the two answers are averaged.

A worked potency comparison. Two ligands measured at the dopamine D2 receptor, a substituted benzamide at pKi 11.52 and an aryloxy-alkylamine at pKi 3.00. Each ligand becomes a 1,024-bit Morgan count fingerprint plus 14 descriptors; the target sequence becomes 480 numbers through ESM2. All three blocks enter a random forest as a single row, which returns which ligand is more potent. — **The potency comparison, end to end.** Both ligands and the target enter as one row, in the order ligand A, sequence, ligand B. Nothing is scored on its own and subtracted. The two compounds shown are real training measurements at the dopamine D2 receptor, 8.5 log units apart.

A, measured pK_i 11.52 at DRD2
`CCN1CCC[C@H]1CNC(=O)c1cc(Br)cc(OC)c1OC`

B, measured pK_i 3.00 at DRD2
`COc1cccc(CCc2ccccc2OCCN2CCc3ccccc3C2)c1`

Both structures paste into the box above with DRD2 selected.

The model is ligand, sequence, ligand, and the steps below follow that order: the first compound, then the target, then the second compound.

Step 1

Ligand A

Ligand A: draw or paste

To paste a SMILES string use the editor's Open Structure button, the folder icon at the top left, and choose Paste from clipboard. It accepts SMILES. Then press the button below to read the structure back out.

Step 2

Sequence, the target

Target

Targets the model was fitted on are grouped first, with their held-out accuracy and comparison count. Names below that group are recognized but were not in the training set, and a result for one of them is unvalidated.

Or paste your own target sequence

A sequence the model was not trained on is scored and flagged. It is not covered by any accuracy figure on this site.

Step 3

Ligand B

Ligand B: draw or paste

Or screen a list at this target

Instead of the two editors, give a list. Every pair is scored, so n compounds is n(n−1)/2 comparisons. 2 at most per run.

Screen a larger list: enter your email

Drawing structures never needs an email. Pasting or uploading a list of compounds does, and the report is emailed back.

Unlocks the paste box and the file upload below ↓

Results go to that address, and we use it to say when the models change.

Or paste a SMILES list, one per line, optional name after a space or tab

up to 2 structures per run

Step 4

How to read the confidence

Every answer carries one number, its prediction strength, from 0.5, a coin flip, to 1.0. These are the accuracies measured for each band on the held-out set, and they set the colors in the result.

Strength	Right this often	Share of comparisons
0.90 and above	99.4%	3.3%
0.80 to 0.90	97.1%	9.1%
0.70 to 0.80	92.1%	16.7%
0.60 to 0.70	81.9%	28.0%
0.50 to 0.60	62.7%	42.9%

Only report comparisons at or above

The cutoff does not change the order. Every comparison counts toward the ranking; the cutoff sets which are reported as firm.

Step 5

Run

Accuracy on this page is measured over comparisons between targets the model was fitted on, 235 of them with a held-out score. A target the model was never fitted on cannot be scored here.