Artificial Intelligence for new drug design

Iktos Home

Drug discovery needs improvement!

New drug design is a long (5 years), costly (50-100M$) and unproductive process (1% success rate from hit to pre-clinical candidate)… Iktos aims to leverage big data and AI to bring radical improvement to this process.

Artificial intelligence for new drug design

Iktos has invented and is developing a truly innovative and disruptive artificial intelligence technology for ligand-based de novo drug design, focusing on multi parametric optimization (MPO).

Deep learning generative algorithms

Our proprietary technology is built upon the latest developments in deep learning algorithms. In a few hours, our technology can design new, druggable and synthesizable molecules, that are optimized to match all your selection criteria.

A virtual designing technology

Virtual screening has many well-known limitations that limit its usefulness in practice: time consuming, strong expertise, dependence upon fragments libraries, constrained by a priori scaffold definitions, limitation to a small number of targets...

In contrast, Iktos technology is a “virtual designing” algorithm that is able to create novel molecular structures which are optimized to match a given multi-objective blueprint.

Iktos is a virtual designing technology
vs Virtual screening.

Iktos has no a priori on the scaffold, it identifies what is important for the activity
vs Need to define a fixed scaffold and allowed structural modifications to the chosen places.

Iktos does not depend on databases of molecular fragments, its diversity is almost infinite
vs Conventional combinatorial approaches, that are dependent upon availability of fragment databases

The number of parameters to optimize does not modify the performance of Iktos
vs With traditional approaches, the size of the database must increase exponentially with the number of constraints

In average, Iktos identifies promising molecules for your project in 48 hours
vs Need a high amount of  data preparation, computation time and expertise

Big data and Deep learning "boosted" prediction

Iktos has developed a unique "computer generated molecular fingerprint" that we have incorporated in the building of high performance bioactivity predictors that outrank traditional approaches.

We put our predictors at your service on your data sets to optimize the success rate of in silico to in vitro translation

Our value proposition

Solving the Rubik’s cube!

In a matter of days, Iktos provides you with optimal virtual compounds that match your expectations. With Iktos, inverse-QSAR becomes a child’s play.

Hit generation

You have a collection of diverse molecules measured on one or several objectives. Iktos is able to virtually design a series of new structures based on new scaffolds, for any given blueprint.

Lead generation

After several months of effort, you are struggling to find a molecule which makes the consensus. Iktos will help you to design new structures, close to your chemical series, that optimize your targets.

Lead optimization

You have a promising lead but you miss one or two objectives. Iktos will help you to design a molecule very similar to your best lead, with optimal characteristics fulfilling your remaining objectives.


  • Yann Gaston-Mathé

    Pharma R&D executive

    Experienced pharma R&D executive consultant in data science and strategy for pharma/healthcare.

  • Nicolas Do-Huu

    Artificial intelligence

    PhD in artificial intelligence, expert in Deep Learning and Big data infrastructure

  • Quentin Perron


    PhD in organometallic chemistry, expert in chemoinformatics.



March 2018:

Iktos wins the French "Worldwide Innovation Challenge Phase 2" and will benefit from non-dilutive funding from Bpifrance for 900k€

Dec 2017:

Iktos initiates a research collaboration with Laboratoires Servier

Dec 2017:

Iktos initiates a research collaboration with Laboratoires Pierre Fabre

Nov 2017:

Iktos successfully closes its initial fundraising round for 680k€ with private investors and business angels.

Oct 2017:

Iktos wins the Innov'Up Proto challenge sponsored by the Paris region and will get a 100k€ to help develop our SaaS AI-powered de novo drug design software

May 2017:

Iktos is selected by Paris region start-up incubator Scientipole Initiative.

March 2017:

Iktos application to Concours Mondial de l'Innovation (CMI) phase 2 is selected for oral presentation

Iktos application to Concours de l'Innovation Numérique (CIN) is selected for oral presentation

Iktos is labelled by Cap Digital for its application to CMI and CIN challenges.

Contact Us



© 2017 IKTOS. All rights reserved