IRB Barcelona is a self-standing, non-profit institution devoted to basic and applied biomedical research. It was set up in 2005 jointly by the Government of Catalonia and the University of Barcelona and is located at the Barcelona Science Park. The institute currently has more than 430 members (scientific, technical and administrative staff) from all over the world, who work across disciplines to advance research in the biomedical sciences.
Applications for the above opening should include a CV and a letter of interest and should be sent by e-mail to: firstname.lastname@example.org with the Reference: PD/20/07
If no suitable candidate is found, the deadline will be extended.
IRB Barcelona is seeking a talented and highly motivated Postdoctoral Researcher to join the Structural Bioinformatics and Network Biology group (https://sbnb.irbbarcelona.org), led by Dr. Patrick Aloy, to work on Generative Models to create Precision Drugs. The candidate will work on the project “Valorización de EGA para la Industria y la Sociedad” (VEIS) funded by the Secretariat of Universities and Research of the Ministry of Business and Knowledge (Government of Catalonia) and by the European Regional Development Fund (FEDER) with reference number 001-P-001647.
Biological data is accumulating at an unprecedented rate, escalating the role of data-driven methods in computational drug discovery. The urge to couple biological data to cutting-edge machine learning has spurred developments in data integration and knowledge representation, especially in the form of heterogeneous, multiplex and semantically-rich biological networks. Today, thanks to the propitious rise in knowledge embedding techniques, these large and complex biological networks can be converted to a vector format that suits the majority of machine learning implementations. Indeed, we have generated biological embeddings (i.e. bioactivity signatures) that capture complex relationships between small molecules and other biological entities such as targets or diseases (Duran-Frigola et al. 2020 Nat Biotechnol in press, available at bioRxiv). However, only a tiny fraction of the possible chemical space has been so far explored, meaning that most compounds able to modulate biological activities (i.e. drugs) are yet to be discovered. Accordingly, the main objective of this project is to couple our bioactivity signatures to inverse design algorithms to generate new chemical entities with a desired functionality. In particular, we aim at generating new chemical entities (NCEs) to modulate the activity of a specific set of targets, selected from a combination of perturbagen profiles, to revert the pathological state induced by Alzheimer´s disease (AD) and other complex disorders. All in all, the incorporation of machine learning methods to the drug discovery process will trigger the development of thousands of novel compounds, finally enabling precision medicine.
The successful candidate shall be responsible for the implementation of ML-based Generative Models (i.e. cVAEs or GANs) to create new small molecules that fulfill the required polypharmacological properties to revert AD pathological signatures.
Must Have – Required