// MSA path · pre-pilot screen passed

On 4LVV, the opt-in MSA path recovers what the single-sequence path misses.

Single-sequence prediction lands a rank-1 cluster at 19% binding-site overlap — neither strict nor near. The MSA-driven path on the same sequence lifts the rank-1 cluster to 50% overlap: strict@1. The pre-pilot tractability screen flags 4LVV for MSA mode on min_id 0.762 and a 11.5% diverse-tail fraction (criterion: min_id < 0.77 OR ≥ 5% homologs at 70–80% identity).

Same pipeline a paying customer runs on the Discovery tier. Bundle below: ensemble PDB, JSON pocket data, residues.csv and a branded PDF report.

single-seq

19%

neither

MSA path

50%

strict@1

Single-seq baseline from locked v0.2 benchmark · screen methodology

Example output — non-customer demo

RNA pocket discovery

THF riboswitch · 4LVV

Bound by tetrahydrofolate (PDB ligand THF). 89 nt RNA target.

v0.2 scope: cleft-binding RNA ≤500 nt|Pre-pilot screen: PASS

Download:↓ Ensemble (PDB)↓ Pocket data (JSON)↓ Full report (PDF)

// pre-pilot screenPASSMSA armmin_id 0.762 · 11.5% homologs at 70–80% identityDiverse-tail homologs present — MSA-driven prediction produces the lift

Sequence length

89 nt

Conformers sampled

Structure pLDDT (mean)

0.818

Pocket clusters

4 / 7

passing persistence floor

Predicted structure, top-3 pockets highlighted.Rank 1Rank 2Rank 3

Top-3 candidate pockets

ranked by persistence × binding-residue stability

#1Cluster 1persistence 80%

Geom. score

5.60

persistence × intersected

Residues (∩)

every frame

Residues (∪)

union, all frames

residues (union): 7, 8, 9, 35, 36, 38, 39, 40, 41, 42, 43, 44, 78, 79

residues (∩ all frames): 8, 35, 42, 43, 44, 78, 79

benchmark8/16 binding-site residues (50%) — strict recovery

#2Cluster 3persistence 80%

Geom. score

5.60

persistence × intersected

Residues (∩)

every frame

Residues (∪)

union, all frames

residues (union): 7, 34, 35, 36, 38, 39, 40, 41, 42, 44, 79, 80, 81

residues (∩ all frames): 35, 36, 38, 39, 40, 41, 79

benchmark7/16 binding-site residues (44%) — near recovery

#3Cluster 2persistence 80%

Geom. score

4.80

persistence × intersected

Residues (∩)

every frame

Residues (∪)

union, all frames

residues (union): 6, 7, 8, 35, 36, 78, 79, 80

residues (∩ all frames): 6, 7, 8, 36, 78, 79

benchmark6/16 binding-site residues (38%) — near recovery

Rotate the structure yourself

Cartoon backbone of the predicted reference frame. Top-3 pocket residues highlighted as licorice; centroid spheres mark each cluster's geometric centre across the ensemble. Hover a card to isolate that pocket. Toggle the experimental THF overlay to see where the co-crystal ligand sits relative to the rank-1 cluster.

Sequence with pocket residues highlighted

GGAGAGUAGAUGAUUCGCGUUAAGUGUGUGUGAAUGGGAUGUCGUCACACAACGAAGCGAGAGCGCGGUGAAUCAUUGCAUCCGCUCCA

Rank 1 pocket residuesRank 2 pocket residuesRank 3 pocket residuesknown binding-site residue

Methods summary

v0.2 detects cavities on the predicted 3D structure using RNA-tuned fpocket parameters (consistent with the published fpocketR approach, Veenbaas et al. PNAS 2025), samples a 5-frame ANM conformational ensemble, and ranks pockets by structural persistence weighted by binding-residue stability (score = persistence × n_residues_intersected). The cross-frame geometric ranker is the load-bearing contribution: on a 7-target cleft-binder benchmark, RNA-tuned detection alone recovers 0 of 7 at strict@1; the ensemble + ranker lifts recovery to 3 of 7 strict@1 and 6 of 7 near@1. Druggability assessment itself is left to your medicinal-chemistry workflow; we provide the geometric metadata and conformational stability metrics as inputs to it. Computational predictions only — experimental validation is required before use in drug development.

// rank-1 binding-site overlap, this target

fpocketR single-frame

6%NEITHER

→

v0.2 ensemble + ranker

50%STRICT

+44 pp · NEITHER → STRICT

Read full methodology →

Binding-mode caveat

Pipeline detects cleft-shaped binding pockets. Groove-binding modes and shallow surface-deformation binding may be missed. Contact us if your target's binding mode is groove-mediated.

Computational predictions only. Experimental validation required before drug-development use.