Periodic Reporting for period 1 - MolPredict (Neural-based solution to boost drug preclinical research success )
Période du rapport: 2018-06-01 au 2018-11-30
Every year, the pharmaceutical industry invests €31.5 billion in R&D just in Europe, generating over 118,000 direct jobs. However, the competitiveness of the R&D process in this industry has been steadily declining during the past two decades, increasing the costs of new drug development from €1 billion in 2000 to €2.58 billion in 2015. The increase is due to several factors, including a stricter regulatory landscape, a lower investment in public R&D and the difficulty to find original molecules (New Molecular Entities – NME) subject to be patented.
Early drug discovery stages (where computers are employed) have a deep impact on deciding which molecules are fed into a drug discovery pipeline and on the overall drug development costs in consequence. Pharmacelera aims at creating a new computing standard for Computer-Aided Drug Design (CADD) through a machine learning platform that enables accurate prediction of molecular properties of candidate molecules and enables a holistic view of all relevant molecular interactions.
Early drug discovery stages (where computers are employed) have a deep impact on deciding which molecules are fed into a drug discovery pipeline and on the overall drug development costs in consequence. Pharmacelera aims at creating a new computing standard for Computer-Aided Drug Design (CADD) through a machine learning platform that enables accurate prediction of molecular properties of candidate molecules and enables a holistic view of all relevant molecular interactions.
During the execution of the SME Instrument Phase I project, Pharmacelera has conducted the necessary market research, opportunity checking and technical exploration in order to assess the feasibility of the proposed project. All this work has included conversations with key stakeholders of the proposed technology: key opinion leaders, current customers, potential partners and senior employees from the pharmaceutical industry. The conclusion of the study is that there are big opportunities in the sector for companies owning disruptive technology to overcome the declining ROI of pharmaceutical R+D and machine learning, High-Performance Computing and multi-disciplinary research are observed as key driving pillars to accelerate drug discovery.
Pharmacelera has developed accurate molecular descriptors that outperform current methodologies when identifying new candidate molecules. A collaborative computational platform for drug discovery that uses these descriptors and machine learning in a holistic manner will increase the chances to find molecules with higher chances to become a drug. The goal of the proposed project is to reduce the overall costs of drug development project by up to 25% and increase the success rate by 3X. This translates into $500 million savings per new approved drug.
The current lack of productivity of pharmaceutical R+D is especially relevant in Europe considering the health consequences of an aging population, leading to a higher incidence of age-related diseases such as cancer, Alzheimer’s, Parkinson’s and cardiovascular diseases.
The current lack of productivity of pharmaceutical R+D is especially relevant in Europe considering the health consequences of an aging population, leading to a higher incidence of age-related diseases such as cancer, Alzheimer’s, Parkinson’s and cardiovascular diseases.