2025 Makya self-service demos

Novel molecules

Makya's Generative AI goes beyond the patented chemical space, to provide novel scaffolds for first and best in class therapies.

Optimized to meet your target product profile

Makya simultaneously optimizes all key properties to generate potent, safe, and selective compounds in every iteration.

Synthesizable by design

Makya generates new molecules through virtual chemical reactions—just like a chemist would. This ensures the compounds are synthetically feasible and ready for validation in the wet lab.

Hit Identification

Design novel chemical compounds from minimal input — no protein structure needed. Unlock novel scaffolds, grow from fragments, design macrocycles, and steer generations with powerful medicinal chemistry constraints.

Hit Expansion

Accelerate SAR exploration using 2D or 3D insights. Expand chemical diversity, fine-tune binding profiles, and iterate faster on promising hits.

Lead Optimization

Turn promising leads into pre-clinical candidates with multi-parameter optimization — balancing potency, ADMET, and synthetic feasibility in a single generative loop.

GenAI and Makya, what to expect?

What to expect from GenAI in Drug Discovery and what makes Makya unique!

Watch now - 9 min

Chemistry experiments in Makya

Makya thinks like a chemist! Learn how to ideate design experiments.

Watch now - 9 min

Reward functions & design strategies

GenAI + traditional computational methods work together for optimal results.

Watch now - 8 min

Small Molecule GLP1-R agonists

Use case introduction discussing binding pocket interactions determining the fragment growing strategy

Watch now - 4 min

In-silico experimentation with Makya

Guide experiments with structural information, rewards, exit vectors and building blocks.

Watch now - 1 min

Exploring generated compounds

Prioritizing compounds based on key pocket interactions and retrosynthetic feasibility

Watch now - 2 min

Webinar --> Generative AI Under Pressure: Tackling the constraints of Pharma R&D

How well does Generative AI perform under the real-world pressures of drug discovery?

In this webinar, we explore how to rethink GenAI through a chemistry-driven lens—empowering medicinal chemists to take control of generative design with multi-parametric reward functions and real-time synthesis awareness. Learn how to elevate virtual experimentation by prioritizing only synthesizable, low-risk, high-potential hits.

Watch the webinar in YouTube and share with colleagues!

Check our publications!

Overcoming DMTA Cycle Challenges: A Unified AI-Driven System for Efficient Drug Design

Integrating synthetic accessibility with AI-based generative drug design.

Growing and Linking Optimizers: Synthesis-driven Molecule Design.

GenAI vs Virtual Screening

Traditional virtual screening methods operate by searching through existing libraries to identify compounds that may bind a target of interest—essentially selecting the best match from what already exists. However, this approach comes with key limitations: there is no guarantee of identifying a hit at all, and if one is found, it may not exhibit high enough activity, optimal properties, or novelty - impacting patentability.

In contrast, Makya, Iktos’ generative AI platform, performs de novo molecular design, generating novel chemical structures optimized to fit a target profile. By leveraging AI-driven multi-objective optimization and synthetic feasibility prediction, Makya explores a vastly broader chemical space, enabling the identification of novel, high-quality, synthetically accessible hits that go beyond the limitations of library-based approaches. This results in more innovative starting points and accelerated hit discovery.

Drug hunters use Makya’s Generative AI to design novel, potent, and synthesizable compounds, fast-tracking DMTA cycles

Makya's Virtual DMTA cycles deliver:

Novel molecules

Optimized to meet your target product profile

Synthesizable by design

Makya Use Cases — From Hit ID to Lead Optimization

Hit Identification

Hit Expansion

Lead Optimization

What makes Makya GenAI unique?

Benchmark vs REINVENT 4

DMTAs with Makya: what you must know

GenAI and Makya, what to expect?

Chemistry experiments in Makya

Reward functions & design strategies

Multi-parametric optimization for Lead Opt

GLP1R - Hit finding use case

Small Molecule GLP1-R agonists

In-silico experimentation with Makya

Exploring generated compounds

Results in Makya

Makya's Roadmap

Get a preview of our next release!

✉️ Contact us to discuss how Makya help you drive breakthroughs, fast!