7HC conceives, designs and develops personalized decision-making tools to support and link three main decision-making pillars:


Problem Identification

Identification of the problem
Tools to depict the health patient status as function of specific real world-features.


Prediction of the evolution

Tools to predict evolution dynamics health condition depending on patient state (diagnosis), and environment conditions.


Solution strategies

Tools to characterize the therapeutic support as a force influencing the evolution dynamics of the health condition.


Related to the clinical practice, 7HC designs Explainable Machine Learning tools to predict pathological events such the 7HC cardiovascular risk predictors.

In this field 7HC develop ready-to—se machine learning driven algorithms to improve Cardiovascular (CV) risk prediction with respect to traditional statistics.
In a greater detail, solution have been developed in the field of CV risk prediction also as a comorbity for patients affected by inflammatory Arthritis and other disease.

7HC supporting decision tools allow clinicians to investigate and capture high-dimensional, non-linear relationships among clinical features, and allow a personalized analysis of the patient clinical condition still keeping comparative knowledge of the the overall data collection for model training and validation.


Related to Pharmaceutical research field 7HC designed automated tools for computational affinity and pharmacokinetics estimation for lead selection. Those supporting tools are designed to help and speed up the Drug Design/Discovery research by equipping pharma companies with virtual funnels to reduce the in vitro testing activity and thus reducing costs and human resources.

7HC Develops comprehensive and easy-to-use computational platform for drug property prediction, target identification, drug-target affinity and efficacy prediction.

  • Automated tools for computational affinity and pharmacokinetics estimation for lead selection.
  • Interface dressed on the custumer needs.

The 7HC PHARMA solution takes the a compound’s simplified molecular-input line-entry system (SMILES) string and protein amino acid sequence pair as input.
The computational intelligent algorithm automatically select the best Machine learning model to specifically address the user’s query in term of drug physical properties(water solubility, hydration free energy, logp, and logd) drug-protein interaction (kd, and ic50), and small molecule physiology (blood brain barrier penetration, drug likeness, and toxicity)


It proposes customised open innovation approaches also based on artificial intelligence for rational understanding and innovation in the field of precision nutrition.

Solutions include:

  • strategies for the development of customised nutrition plans
  • support for the design of functional foods and/or defined organoleptic properties
  • support for predicting the effect on the final product of mixing products and processes in order to maximise the efficiency of crops or food production processes