Compare two receptors for one compound

Sequence A → ligand → sequence B. Pick two receptors, supply one or more compounds, and the model says which receptor binds each one more tightly.

The layout is the mirror of the potency model. The ligand sits in the middle and the two receptors are the things being compared, so the question the forest answers is which receptor wins, not how tightly either binds.

A worked selectivity comparison. One ligand, a 4-anilidopiperidine, measured at two opioid receptors: pKi 10.89 at the mu receptor and 6.91 at the kappa receptor. Each receptor sequence becomes 480 numbers through ESM2 and the ligand becomes a 1,024-bit Morgan count fingerprint plus 14 descriptors. All three blocks enter a random forest as a single row, which returns which receptor the compound prefers. — **The selectivity comparison, end to end.** The ligand sits in the middle and the two receptors are what is being compared, so the row reads sequence A, ligand, sequence B. The compound shown is a real training measurement, roughly 4 log units mu-selective over kappa.

**The ligand**, measured pK_i 10.89 at OPRM1 and 6.91 at OPRK1
`CCC(=O)N(c1ccccc1)[C@H]1CCN(C[C@H](O)c2ccccc2)C[C@H]1C`

**A kappa-selective counter-example**, measured pK_i 6.27 at OPRM1 and 10.21 at OPRK1
`Oc1cccc(CCN(CCc2ccccc2)CC2CCCCC2)c1`

Paste either into the box above with OPRM1 and OPRK1 selected. The model should send them opposite ways.

Step 1

The two receptors

Search the receptor list

Receptor A Receptor B

Receptors the model was fitted on are grouped first with their held-out accuracy. Selectivity accuracy varies a great deal by receptor: across the 75 receptors carrying at least 50 held-out comparisons the median is 0.675 and 21 fall below 0.60. Closely related receptors are the hard ones.

Step 2

Compounds

One at minimum, 2 at most per run. Each compound is put to both receptors.

Ligand: draw or paste

You do not have to draw it. 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 and will draw the molecule for you. Then press the button below to read it back out.

Screen a larger list: enter your email

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

Unlocks the paste box and the file upload below ↓

We send the full results there, and let you know 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 3

How to read the confidence

Strength is defined the same way as on the potency page, the larger of the two output probabilities. What a given strength buys is not the same on the two models, so use the numbers below rather than carrying a threshold across.

Strength	Right this often	Share of comparisons
0.90 and above	96.8%	4.4%
0.80 to 0.90	89.2%	10.3%
0.70 to 0.80	78.2%	18.1%
0.60 to 0.70	70.2%	28.8%
0.50 to 0.60	56.3%	38.4%

Only report calls at or above

Step 4

Run

Two receptors that a compound genuinely cannot tell apart are two receptors the model cannot tell apart either. Muscarinic receptors sit near chance here for exactly that reason, while opioid receptors reach 0.91.