AI-native RNA pocket discovery · structural ranking

Candidate druggable pockets on RNA targets, from sequence

We identify candidate druggable cleft pockets on RNA targets from sequence — calibrated for small-molecule drug discovery. Predicted 3D structure, conformational ensemble and a ranked top-3 shortlist, with honest scope. EU-based, GDPR-compliant.

Request Early AccessSee worked examples
Live 3D
Rank 1 · 71% strictRank 2Rank 3
Open 2GDI demo →
AUGCUAGCUAGCUAGCUAGCUAGCUAGCUAGCUA  ·  GCUAGCUAGCUAGCUAGCUAGCUAGCUAGCUAG  ·  CUAGCUAGCUAGCUAGCUAGCUAGCUAGCUAGC  ·  UAGCUAGCUAGCUAGCUAGCUAGCUAGCUAGCU  ·  AUGCUAGCUAGCUAGCUAGCUAGCUAGCUAGCUA  ·  GCUAGCUAGCUAGCUAGCUAGCUAGCUAGCUAG  ·  CUAGCUAGCUAGCUAGCUAGCUAGCUAGCUAGC  ·  UAGCUAGCUAGCUAGCUAGCUAGCUAGCUAGCU  · 
3 / 7
Strict @1 with our ensemble + ranker (vs 0/7 single-frame fpocketR)
6 / 7
Near @1 with our ensemble + ranker (vs 2/7 single-frame fpocketR)
EU
Malta-based · GDPR · zero-retention option

// What we built

Why ensemble ranking matters for RNA pocket discovery

v0.2 architectural contribution

The field has converged on the answer that standard cavity detection over-predicts on RNA — fpocket’s default parameters mistake the polar grooves of duplex RNA for binding pockets. The Weeks lab formalised this as an RNA-tuned wrapper, fpocketR (Veenbaas et al., PNAS 2025), and we use the same RNA-tuned parameters. Detection alone, however, is not where customer recovery happens.

On the same seven cleft-binder targets, the single-frame fpocketR-style detection (and ours — the two are empirically equivalent) leaves the rank-1 pocket at the experimental binding site in only 2 of 7 cases at near-recovery and 0 of 7 at strict. The v0.2 contribution is what we add on top: a five-frame ANM conformational ensemble, cross-frame pocket clustering, and a cluster ranker based on persistence × binding-residue stability. Both ranker features are RNA-applicable by construction.

Rank-1 recovery on 7 cleft-binder targets3 / 7 strict· 6 / 7 near — with our ensemble + geometric ranker0 / 7 strict· 2 / 7 near — with fpocketR-style single-frame detection alone

Locked benchmark, deterministic re-run. Per-target lift figures and the full comparison table (vanilla fpocket / fpocketR params / our params / ensemble + ranker) on the methodology page. strict@1 = rank-1 cluster overlaps the experimental binding site by ≥ 50% of residues; near@1 = ≥ 30%.

Read full methodology

// Capabilities

What the platform actually does

One integrated workflow, end to end. Sequence in, ranked top-3 pocket shortlist out, with full per-cluster metadata and a customer-facing PDF report.

013D structure prediction from sequence
Predict the 3D tertiary structure of any RNA target from sequence alone. AI-driven prediction, deterministic outputs, suitable for downstream pocket detection. Single-sequence prediction is the default; an MSA-driven path is available for targets with diverse-tail evolutionary signal.
02Conformational ensemble generation
Sample a five-frame conformational ensemble around the predicted structure to capture the kind of motion that drives pocket formation. Deterministic, low-frequency-mode-driven sampling — chosen over short MD because force-field equilibration drift demoted real binding-site clusters in our pilots.
03RNA-applicable cavity detection and pocket ranking
Detect cavities across the ensemble using RNA-tuned parameters (consistent with the published fpocketR approach, Veenbaas et al. 2025) and rank them with our cross-frame geometric scoring function (persistence × binding-residue stability). The v0.2 contribution is the cross-frame ranker: on the 7-target benchmark, it lifts rank-1 recovery from 0/7 strict (single-frame detection) to 3/7 strict, and from 2/7 near to 6/7 near.
04Pre-pilot MSA tractability screening
Before running the full pipeline we estimate whether your target’s evolutionary profile carries the diversity needed for MSA-driven prediction to help. Empirical screen — at least one homolog at <77% identity, or a non-trivial fraction in the 70-80% identity band. Calibrated on the v0.2 benchmark; refined as more targets accumulate.
05Customer-facing PDF reports + downloadable bundle
Each run produces a downloadable bundle: ensemble PDB, JSON pocket data, residue lists, residues.csv, and a branded PDF report with full per-cluster metadata. Designed to drop into existing medicinal-chemistry workflows — we hand you the geometry; you bring the chemistry.

// How it works

From sequence to ranked shortlist

A single deterministic pipeline. Input a sequence (or a PDB upload); pick up a top-3 ranked shortlist of candidate pockets with full geometric metadata.

01

Predict and ensemble

AI structure prediction generates the 3D tertiary structure from sequence. A five-frame conformational ensemble is sampled around the prediction. MSA-driven prediction available where the pre-pilot screen indicates.

02

Detect and cluster

Cavities are detected on each frame and clustered across the ensemble at 4 Å. Persistent cavities — those that survive the conformational sampling — are kept; transient or single-frame artefacts are filtered out.

03

Rank and return

Persistent cavities are ranked by our RNA-applicable scoring function. You receive a top-3 shortlist with residue lists, geometric metadata, the ensemble PDB and a branded PDF report.

// Why work with RNAfold

Honest scope, transparent methodology, EU jurisdiction

The differentiators that matter once the science is right.

[scope]

Pre-pilot screening with explicit scope

Cleft-shaped binding pockets are in scope. Groove binders, surface interfaces and large complex folds are flagged out-of-scope upfront via the pre-pilot screen. We tell you whether v0.2 should help on your specific target before you commit to a pilot — not after.

See pricing & screen →
[EU]

EU-based, GDPR-compliant

Incorporated in Malta. All compute and storage on EU infrastructure. No sequence data leaves European jurisdiction. Zero-retention option available on the Enterprise tier.

Privacy policy →
[docs]

Transparent methodology

Full pipeline, third-party attribution and licences, validation methodology — all on /methodology. Customer pilots get the same disclosure in the PDF report. We don’t hide what we integrate; we name it where it belongs.

Read methodology →
[bench]

Reproducible benchmark

Seven cleft-binder targets, locked methodology, deterministic re-runs. The numbers below are what the pipeline actually produces, including the one neither case we don’t recover. No survivorship; no cherry-picking.

See benchmark →

// v0.2.0 benchmark

What the pipeline actually recovers

Seven cleft-binder targets with deposited co-crystal structures — six riboswitch families plus one group I intron. As-shipped configuration: single-sequence prediction by default; MSA mode where the pre-pilot screen indicates. Numbers are exact, deterministic, and reproducible.

TargetArmResult

2GDI

TPP RF00059 · 78 nt

single-seqStrict @1

4GXY

B12 RF00174 · 161 nt

MSANear @1

2GIS

SAM-I RF00162 · 94 nt

single-seqNear @1

5C45

FMN RF00050 · 54 nt

single-seqNear @1

3DIL

Group I intron · 174 nt

MSANeither

2HOJ

TPP (thi-box) · 83 nt

single-seqStrict @1

4LVV

THF RF01831 · 89 nt

MSAStrict @1

Strict @1 = at least one cluster in the rank-1 position with ≥ 50 % binding-site residue overlap.Near @1 = ≥ 30 %. RMSD = backbone C3′ RMSD vs experimental chain. Top-cluster overlap is shown after the result.

3DIL (group I intron) is a known out-of-scope fold class for v0.2 — we surface it in the table rather than hide it. Reproducer + per-cell records described on the methodology page.

// Worked examples

See the pipeline output

Three live worked examples spanning the v0.2 outcome classes — strict@1 (2GDI, single-seq), strict@1 via the opt-in MSA path (4LVV) and near@1 with global RMSD honestly reported (5C45).

78 nt · single-seqlive

TPP riboswitch (2GDI)

Live worked example. The pipeline recovers the TPP binding-site cluster at rank 1 with 71% binding-site residue overlap. Top-3 with full per-cluster metadata + interactive 3D viewer.

live demorank-1 strictoverlap 71%
Open worked example
89 nt · MSAlive

THF riboswitch (4LVV)

Live worked example. The pre-pilot screen flags 4LVV’s diverse-tail homologs; MSA mode lifts rank-1 recovery from neither (19% overlap, single-seq) to strict (50% overlap, MSA). Same pipeline a Discovery-tier customer runs.

msa opt-inrank-1 strictoverlap 50%
Open worked example
54 nt · single-seqlive

FMN riboswitch (5C45)

Live worked example. Smallest target in the benchmark (54 nt). Backbone RMSD 10 Å but the rank-1 cluster picks up 40% of the FMN binding-site residues — near@1, not strict. The case for reporting both global and local quality metrics.

near @1overlap 40%small RNA
Open worked example

// Roadmap

What's next

Public roadmap for v0.2.1 and v0.3, with honest status labels. We do not commit to dates; items move when the work is done.

v0.2.1In development
  • →Comparative pocket analysis across sequence variants
  • →ChEMBL annotation overlay on detected pockets
  • →Per-pocket sequence conservation analysis
v0.3Planned
  • →Batch submission API for screening campaigns
  • →Energy-aware ensemble via molecular dynamics (research)
  • →Groove-binding pocket detection (research)

// Get started

Ready to assess your RNA target for cleft pockets?

We are onboarding pilot customers now. Send a sequence and we will run the pre-pilot screen and schedule a 30-minute walk-through of the output.

Request AccessTalk to the Team

Pre-pilot screen · Pilot pricing · Malta-based · EU data residency