Molecular Modeling Services
molecular modeling services
Scientific Software Development Services
Scientific Software Development Services
Corporate Alliances & Partnerships
Corporate Alliances & Partnerships

Intelligent Pharma offers a broad range of computationally aided drug discovery services to assist you along the drug design and development pipeline. We have gained extensive experience over the last 10 years by performing over 200 molecular modeling projects.

Our cutting-edge technologies are amongst the best in the computational chemistry field and we are constantly developing new technology to meet the ever-changing needs of the market. By combining our technologies with a team of highly skilled, experienced scientists, we can assure the highest quality of our services.

  • We customize projects according to your needs.
  • Multi-disciplinary team of experts (chemists, biologists, mathematicians, computer scientists …) working together to address every characteristic of your project.
  • In order to provide you with the highest quality results, we use our own in-house technologies in combination with the industry gold standard software.
  • We work as your external molecular modeling department or we can work together with yours.
Identification of compounds with specific activity against your target of interest.

We screen large databases of molecules in order to predict which molecules have the best possible activity against your target. The only required input is the name of your target of interest; the protein structure of your target doesn’t have to be available.

Ligand- and receptor-based approaches are combined in a virtual screening workflow that is tailored and validated for your project. We use our technologies PEGASUS (2D ligand comparison), HERCULES (3D ligand molecular field comparison), MEDEA (QSAR and filters), SELENE (receptor-based docking screening) and Pharmacophore models (ligand- or receptor-based) in combination with a customized database of molecules to screen for new hits (up to 16 million of compounds). We have many databases at our disposal, including those consisting of natural compounds, commercial compounds, drug-like compounds, small molecules, peptides and others.

A hit can be further optimized in order to improve its properties and/or to circumvent patent protection. We apply MOBIUS, an artificial intelligence approach for the optimization of structures according to multiple objectives (activity, selectivity, solubility, ADME …) based on genetic algorithms.

Some of the most common tasks include determining the bioactive conformation of active molecules, the determination of ligand-protein 3D structures and the construction and validation of predictive models. Analysis of the protein surface in order to find drugable sites as well as the study of known protein-protein complexes can be are included. All workflows are always validated with known active and inactive ligands.

Competitive Advantages
  • Projects can be customized to several scenarios: the structure of the target is not known, no active ligands or protein-protein interactions known.
  • Several set-ups are used to modulate the exhaustiveness and speed of the process.
  • The incorporation of steps which favor scaffold hopping compared to known ligands.
  • Our large databases of compounds are readily available and can be used to create project-specific databases.
  • The combination of ligand- and receptor-based approaches.
Linking ligand structure to its activity.
Understanding the activity of molecules based on their structure is key for optimization and validation of potential ligands in the drug development process. With high precision SELENE docking, we are able to determine the most reliable binding poses and link protein-ligand interactions with structure activity relationship (SAR). We can complement the docking studies with alternative ligand-based studies: predictive pharmacophore- and/or molecular-field-based models which are suitable for SAR interpretation.
Competitive Advantages
  • We can perform SAR even when the protein structure information of the target is unknown.
  • Molecular fields are used for ligand-based models.
  • Peptidomimetics: from peptides to small molecules. Case study
The determination of the mechanism of action of your molecule of interest.
Departing from the molecule’s structure, we perform a two-step protocol to predict targets. First, a list of molecular targets is determined using our proprietary software PYTHIA, combining molecular similarity searches with the bioactivities of known target-ligand interactions. In the second step, specific targets can be further analyzed by a combination of two different approaches. Our SELENE technology, based on docking, simulates the interaction of your molecule with the target protein. A second approach is building a pharmacophore model based on known ligands.
Competitive Advantages
  • This process uses both experimental data and structural information about the targets and molecular binders.
  • Only the 2D structural information of the molecule of interest is required as input.
  • The first list of predicted targets can be provided in days.
  • Manual intervention allows for the inclusion of your own findings.
  • We collaborate with established synthesis partners to include molecular synthesis tasks in your project.
Design of new small molecules using tailored predictive models.
We have developed several technologies specialized for designing small molecules. The input for these technologies depends on the information available: known active ligands or receptor conformation structures. Structure-based technologies include SELENE docking and pharmacophore models. Ligand-based technologies include molecular-field-based models and pharmacophore. MEDEA incorporates other methodologies which allow QSAR model building and activity prediction. We use a combination of different technologies (developed in-house and/or by third parties) in order to find the optimal molecules within the designed library. The technology MOBIUS allows the search for optimal molecules according to a simultaneous multi-parameter evaluation within a large chemical library. This is possible due to the machine learning process of MOBIUS's algorithm on the different fragments which define the library.
Competitive Advantages
  • Generation of new chemical space based on machine learning techniques.
  • Combination of ligand- and receptor-based approaches.
  • Use of molecular fields for ligand-based models.
  • Multi-objective optimization with large chemical libraries.
  • To find new therapeutic indications for your drug of interest.
  • To determine which already approved drugs can be of importance in your indication of interest.

In order to find new therapeutic indications for your drug, our proprietary software PYTHIA is used to compare the target profile of your drug of interest with the target profile of approved drugs within our database. While we list the most interesting new therapeutic indications for your drug, we also provide you with the most important targets of your drug, an essential step which provides crucial information for designing experiments to reposition your drug. We can also include a second step in the workflow to refine the predictions for a specific target using our docking technology SELENE or pharmacophore models.

In order to find approved drugs that may have activity in your indication of interest, we perform a hit identification protocol using our database of about 9,000 approved drugs. Our various technologies such as PEGASUS (2D ligand comparison), HERCULES (3D ligand molecular field comparison), MEDEA (QSAR and filters), SELENE (receptor-based docking screening) and/or pharmacophore models (ligand- or receptor-based) are used depending on the nature of the project ranging from having only one active molecule to the availability of multiple compounds and a known receptor structure.

Competitive Advantages
  • The combination of ligand- and receptor-based approaches.
  • Our repositioning work has been validated by multiple collaborators which have taken the repositioned molecules into clinical trials.
  • To build the three-dimensional (3D) structure of your protein(s) of interest.
  • Study the dynamic structure of your biomolecule of interest.
We apply comparative modeling to build three-dimensional protein structures in the desired conformation. Many protein structures haven’t been resolved, and even when they have, they may not be available in the desired conformation (related to protein activity or type of bound ligand). The modeling of protein-protein complexes/peptides, also known as protein-protein/peptide docking, can also be tackled, opening the door to new disruptive strategies in drug design. The dynamic structure of proteins can be studied by Molecular Dynamics (MD). We can carry out molecular dynamic studies of biomolecules and their complexes with ligands, parameterizing atoms/molecules if necessary. We can study the stability of your molecules and estimate variations of free energy of multiple processes such as ligand-protein binding and mutations. We have excellent hybrid computational resources available (our own CPU cluster, the cloud or a combination of both) in order to execute your project in the best possible price quality range.
Case study GPCR modeling
Competitive Advantages
  • Parameterization of small molecules with quantum chemistry.
  • Hybrid computational system in order to control time and pricing.
  • Protein-protein/peptide docking.
Prediction of ADME/Tox (absorption, distribution, metabolism, excretion and toxicology) properties of your small molecules of interest.

In order to develop molecules with the most favorable characteristics, we can predict ADME/Tox properties for a large group of molecules. We have developed models to predict properties early on in the drug discovery process, such as cardiovascular toxicity (hERG), solubility (logS) and Blood Brain Barrier (BBB) penetration.

Using MEDEA, our QSAR and data mining technology, we can optimize our models for your molecules. This allows us to accurately select a small number of molecules for synthesis and experimental testing. In addition, MEDEA incorporates several machine learning methodologies to build your own model for your specific molecular family. MEDEA includes PLS, SVM, and other methodologies, as well as a varied set of descriptors, ranging from 2D fingerprints to 3D molecular fields. State of the art data distribution, validation protocols, and applicability domain definition are incorporated to provide you with most reliable model possible within your data.

Competitive Advantages
  • The possibility of the incorporation of new methodologies into MEDEA (including learning algorithms and validation protocols).
  • Parallelization of calculations to allow large sets of training data in a short period of time.
  • Methodologies that allow the interpretation of models for molecular design.
  • MEDEA can be coupled with SELENE and other ligand pose-determining technologies.
Organization of your data for fast and easy access
We can build relational and non-relational databases of biochemical data in order to organize your it, enable searches on it and generate prediction models with your data. We have experience in merging heterogeneous databases, creating special tools for fast cross-searching and the use of natural language when retrieving equivalent information from different source databases.
Competitive Advantages
  • Merging heterogeneous databases.
  • Natural language processing.
To speed up the discovery of new compounds and materials with specific properties for the Chemical and Oil & Gas industry
With the use of our cutting-edge computational technologies we help Chemical and Oil & Gas companies during the process of design and discovery of new compounds and materials with specific properties, to tackle challenges faced by the industry.
With our services you will make your R&D team more productive and, most importantly, you will discover new chemicals with a significant reduction of time and expenses.
For more information, check our detailed list of services.
Competitive Advantages
  • Our experts in QSAR, Molecular Dynamics, Metadynamics and Quantum Chemistry make our team unique to deliver complete results.
  • Our cutting-edge technologies will allow us to obtain results in record time (average time: 6 weeks, max time: 6 months).
  • Our clients are the owners of the Intellectual Properties resulting from our projects.
  • Clients can claim expenses through SRED tax credits.
Our computer science department develops computational chemistry technologies and artificial intelligence to be used by our molecular modeling department to carry out clients´ research. Our technologies are designed to accelerate research in drug discovery and to meet the needs of the market. Some clients are interested in using our technologies directly in addition to working with our computational department. If you would like to use our technologies, please contact our Sales and Business Development department.
PYTHIA is a standalone computational technology that predicts targets and indications for molecules and mixtures.
2D Ligand-based virtual screening solution
PEGASUS is a computational tool that identifies active molecules hat are structurally similar to a molecule with a specific function.
3D Ligand-based virtual screening solution
HERCULES is a computational tool that identifies non-structural analogues of a reference compound with similar biological activity but different chemical structure.
SELENE is a computational tool that identifies active molecules with the ability to bind to a receptor.
A data mining solution for medicinal chemistry
MEDEA is a data mining solution for the identification of biological pattern and the prediction of biological properties.
MOBIUS fosters interactions between computational and medicinal chemistry to produce a new approach to address the challenges of Lead Optimization and enables faster identification of potential drug candidates.
HYPERION is a computational tool for detecting allosteric sites on a protein.
Computer-aided hit to lead optimization
CHIRON is a technology used for accelerating molecular optimization. It determines compounds by processing the desired properties with a faster, less rigorous experimentation and synthesis processes.