Technology

THE ARCHITECTURE OF DISCOVERY.

Five layers of differentiation that competitors cannot replicate overnight. Full methodology →

Layer 01

Generative Chemistry — MolForge-Gen Engine

Proprietary 25.4M-parameter Transformer (GPT-2 architecture) trained on 1.6M drug-like molecules, then fine-tuned per target with property-conditioned generation. Specify a pre-trained, data-rich kinase target (TYK2/CDK4/CDK6/EGFR) + desired QED/hERG/pIC50 range → generates structurally diverse molecules matching those constraints. Generation quality tracks the availability of prior medicinal-chemistry data for the target — strong on data-rich kinases, an open research problem for sparse/novel targets. FTO-aware: outputs screened for IP whitespace.

01

Layer 02

Uncertainty Quantification

Every prediction ships with a conformal prediction interval instead of a bare point estimate. We report the current intervals honestly as provisional / uncalibrated (small-n, out-of-distribution) rather than a guaranteed 90% CI — so you know how much to trust each number before spending a dollar on synthesis.

02

Layer 03

Failure Boundary Mapping

ROBOGATE adaptive sampling + Multi-Objective Pareto optimization. We don't just find good molecules — we map the parameter space where candidates fail. hERG toxicity, mutagenicity, bioavailability — every failure mode is charted.

03

Layer 04

Certified Compound Tiers

Tier 1: AI Screened (ADMET + QSAR). Tier 2: Structure Verified (Boltz-2 ligand_ptm ≥ 0.85). Tier 3: Experimentally Validated (CRO assay in progress). Pharmaceutical R&D teams know exactly what level of evidence they're working with.

04

Layer 05

Continuous Feedback Loop

Every CRO assay result — hit or miss — is ingested (idempotent, hash-verified) as a first-class negative-data asset. Automated retraining and reranking of the conformal calibration and Pareto boundary maps from those verdicts is in development — not yet closed-loop end-to-end. This is the moat that takes time to build.

05

Validated Benchmark

0.903

AUC-ROC

PASS

0.838

BEDROC

PASS

0.503

Pearson R

PASS

ExtDesc

Descriptor

Morgan2048MACCS166TopTorsion256PhysChem201201 features

Split: Bemis-Murcko scaffold + Tanimoto<0.4 cap between train and test. Leak-proof external benchmarks (LP-PDBBind, PLINDER-ECOD, PLINDER-TIME) scheduled 2026-Q2 and 2026-Q3 — split-integrity report →

Pipeline

From Target to Dossier in Hours

1

Target Selection

Auto

2

Seed Collection

~30min

3

Generative Design

~1h

4

Structure Prediction

~2h

5

ADMET Filtering

~15min

6

QSAR Scoring

~10min

7

Failure Boundary

~2min

8

Compound Dossier

~30min

Validated Results

TYK2 — A Phase III Clinical Target

108,220+

Total Compounds

71,651

ADMET Passed (5 targets)

0.5+

External Benchmark R

2,403

Pareto Top (5 targets)

Publications & Methods

TitleTypeStatus
MolForge: Failure Boundary Mapping with Conformal Prediction for Drug DiscoveryPreprintIn preparation
ROBOGATE: Adaptive Sampling for Multi-Objective Pareto Optimization in ADMET SpacePreprintIn preparation
Uncertainty-Aware Compound Tiering: A 3-Gate Framework for AI Drug DiscoveryConferenceSubmitted
TNIK Inhibitors for Obesity: A Computational Repurposing StudyResearch ArticleIn preparation
MolForge-Gen: A Property-Conditioned Transformer for FTO-Aware Multi-Target Drug DesignTechnical ReportData collected
TNIK Binding Affinity Prediction: A GNN Approach with Conformal CalibrationPreprintIn preparation