Docking one compound into every characterized binding site answers the reverse screening question directly and takes 40.5 hours. A pharmacophore retrieval step in front of the docking cuts the panel to tens of proteins in 44 milliseconds, and the docking then runs only on what retrieval returns.
Screen a molecule How it worksA screening campaign asks which of many ligands bind one target. The reverse question asks which of many targets bind one ligand. It is the question that arises once a molecule exists: what else does it hit, what explains a phenotype, what accounts for a toxicity, and what could the compound be repurposed against. It is also the only question available for a molecule a generative method proposes, because a designed structure has no measured target at all.
Inverse docking answers it by docking the ligand into a panel of pockets and ranking the panel. The panels have stayed small because the cost is linear in the panel size. On twenty performance cores, AutoDock Vina at exhaustiveness 16 takes 5.1 seconds for a drug-sized ligand, so a panel of 60 sites is five minutes and the 28,579 sites indexed here are 40.5 hours for a single molecule.
The ligand-based answer is cheap: chemically similar molecules tend to bind the same proteins, so a target can be predicted by similarity to annotated ligands. That returns a protein name. A name cannot be inspected, scored, or optimized against.
The two are better used in series than treated as alternatives. A ligand that resembles a molecule someone has already crystallized is likely to bind where that molecule binds, so the crystallographic record narrows the panel before any docking is attempted.
Every co-crystal ligand in the Protein Data Bank, carrying the UniProt accessions it was solved against.
Fingerprint the query, compare it to every indexed ligand, pool the proteins its nearest neighbors were crystallized against.
AutoDock Vina into each retrieved site, in a box drawn around that site's own ligand envelope.
Read the surviving poses in three dimensions, with the score and the burial of each.
Both sides of every comparison are the same calculation. The query and each of the 27,797 indexed ligands are predicted from two-dimensional structure by PharmCast, which returns a three-point pharmacophore fingerprint 10,549 bits wide without generating a conformer ensemble. That is what makes the query side take 4 milliseconds, and it is why a query can be compared against the whole index rather than against cluster representatives.
The search itself is exhaustive. All 10,549 bits are compared by Tanimoto over packed bit vectors against all 27,797 indexed ligands, with no folding, no hashing, no dimensionality reduction and no approximate nearest neighbor structure. The scan takes 40 milliseconds and has no parameter that could be tuned to flatter a benchmark.
Describing the atoms that line a pocket needs coordinates good enough to place every one of them, and the rule for that work is X-ray at 1.8 angstroms with a free R factor at or below 0.23. Establishing which ligand sat in which protein needs none of it: a 3.1 angstrom cryo-EM map answers that perfectly well. Retrieval therefore admits X-ray at 2.5 angstroms with a free R factor at or below 0.28, and cryo-EM at 4.0 angstroms, in both cases carrying a component of 250 to 900 daltons. Enumerating the archive under those two rules gives 61,935 X-ray entries and 12,620 cryo-EM entries.
Separating the two rules took coverage from 3,670 target sites to 28,579, an increase of 7.8 fold, and the gain falls on the receptors and large complexes solved by cryo-EM. The glucagon-like peptide 1 receptor is the clearest case: it carries 31 entries holding a drug-like ligand and not one of them satisfies the 1.8 angstrom rule, so under that rule the receptor is absent from the panel and no amount of searching can return it.
Three thousand molecules were held out and screened. Each query was removed from the index by InChIKey connectivity layer first, so a molecule that had itself been deposited could not retrieve its own target through its own deposition. The question asked of each pool is whether the molecule's known target is inside it.
| Nearest ligands pooled | Proteins in the pool | Fraction finding the target | Docking time | Against all 28,579 |
|---|---|---|---|---|
| 1 | 3.1 | 0.363 | 16 s | 9,214 fold less |
| 5 | 21.1 | 0.488 | 108 s | 1,353 fold less |
| 10 | 44.4 | 0.538 | 3.8 min | 643 fold less |
| 25 | 104.5 | 0.608 | 8.9 min | 274 fold less |
| 50 | 186.3 | 0.661 | 15.8 min | 153 fold less |
Pooling more neighbors buys accuracy and costs docking, and the exchange is steep at both ends: one neighbor docks 3.1 proteins and finds the target 36.3 percent of the time, fifty docks 186.3 and finds it 66.1 percent. Five neighbors is the operating point where the whole pipeline finishes in about two minutes.
Run in batches on a single core the retrieval stage screens 96,487 molecules per hour, which is 2,315,688 in a day. A generative run can therefore be triaged in full, with docking spent only on what survives.
Thirty eight complexes were redocked into their own receptors, with the deposited pose discarded and a fresh conformer generated, so nothing but the location of the site reaches the docker. A pose counts as correct within 2.00 angstroms of the deposited coordinates.
| Over 38 complexes | Count |
|---|---|
| Search generates a correct pose | 27 |
| Scoring puts it first | 14 |
| Scoring puts it in the first three | 23 |
Sampling is ahead of scoring at this scale, which is why the poses come back for inspection rather than as a single number. Every pose is also rescored with the Vinardo function and the pool re-ranked by Vinardo alone and by the mean of the two ranks.
Both are themselves deposited, so both were removed from the index before their own query ran. Each found its target through a different molecule.
| Molecule | True target | Rank of 27,797 | Retrieved through | Similarity |
|---|---|---|---|---|
| Orforglipron | Glucagon-like peptide 1 receptor | 1 | component UK1 | 0.901 |
| Daraxonrasib | KRAS and cyclophilin A tri-complex | 4 | component A1AOI | 0.836 |
Daraxonrasib is the harder of the two and shows what the site definition has to carry. Its site is an interface between two proteins rather than a pocket in either one, deposited as the tri-complex at 1.65 angstroms. Docking it into KRAS alone cannot reproduce the binding, because half the site is missing.
Muskal, S. M. and Nicola, G. Reverse Screening: Identify Targets That a Ligand Might Interact With. In preparation, 2026.
The fingerprint both sides of every comparison are made with: Muskal, S. M. and McGregor, M. J. PharmCast: rapid generation of three-dimensional pharmacophore fingerprints from two-dimensional structure without conformer generation. bioRxiv, 2026. doi: 10.64898/2026.09.02.748999