Skip to main content
Interface with all APEX models

ApexSuite

Led by our core foundational model APEX, our specialized suite of AI engines is revolutionizing antibiotic discovery and biological computation.

Models

6 Models

APEX

Antimicrobial prediction

Our activity predictor reads whole proteomes and finds the encrypted peptides that act as antibiotics.

ApexImmuno

Anti-inflammatory prediction

Generates peptides scored for both antimicrobial potency and immune modulation.

ApexFold

Secondary structure prediction

Predicts how a peptide folds in the environment it will actually meet, water, membrane or organic solvent, and scores how much its structure shifts between them.

ApexCPP

Cell penetration prediction

Predicts cell-penetrating activity across biological membranes to guide intracellular peptide delivery.

ApexHemo

Hemolysis prediction

Evaluates hemolytic activity against red blood cells to screen for non-toxic peptide candidates.

ApexTox

Cytolysis prediction

Predicts mammalian cytotoxicity and cytolytic activity to prioritize safe therapeutic sequences.

Applications

7 Applications

ApexGPT

Sequence generation from a target profile

A generative language model that writes new peptides from a target profile.

ApexGO

Template-guided optimization

Optimizes a known peptide instead of starting over, searching a generative latent space under a similarity constraint.

ApexOracle

Antibiotics for pathogens never seen

Pairs a molecular diffusion model with genome and literature profiles of each strain, predicting activity and generating new molecules for pathogens it has never seen.

ApexDuo

Dual-function peptide design

Designs peptides that enter mammalian cells and kill the bacteria hiding inside them.

Amphion

Reward-guided peptide design

Fine-tunes a 6.4-billion-parameter protein language model with reinforcement learning against predicted MIC.

AMPSpace

Design for druggability

Makes druggability a design goal, one loop generates, recognizes and ranks peptides for potency, safety, stability and structure at once.

Key-Cutting Machine

Sequences cut to fit a fold

Cuts sequences to fit a target backbone, optimizing shape, energy and residue properties with no retraining.

Other Models

3 Models

panCleave

Protease cleavage site prediction

Trained on MEROPS, it predicts where proteases cut a sequence.

OmegAMP

Conditional diffusion, three ways to design

Designs peptides de novo, as analogs of a known lead, or around a required motif.

Termini

Terminal modifications chemistry by design

Designs antimicrobial and safe peptides together with their terminal chemistry, N-terminal acetylation and C-terminal amidation.

Collaborate with the APEX AI ecosystem

Interested in deploying our APEX suite to your institution's pathogen research or benchmarking clinical screening pipelines?