David Waroquiers

Matgenix proposes solutions to boost the research and development of innovative materials, compounds and processes by combining the three pillars of materials science simulation: Machine-Learning (ML), data consolidation, and high-throughput simulations. Matgenix supports its customers throughout the entire innovation process, starting from the idea to the concrete realization, production and commercialization of new materials and compounds. Matgenix helps in the definition of clear and precise specifications and proposes tailored work plans matching its customer’s business goals and schedule. Matgenix identifies the best candidates by executing this work plan and continues to support the implementation and up-scaling of its customer’s new materials, compounds and processes. Core competencies: Machine-Learning: Matgenix uses state-of-the art ML algorithms tailored to materials science and chemistry to provide guidance to their collaborators and customers. Data consolidation: By combining data stemming from different sources (e.g. open and commercial databases, experimental and computed databases, customer data, …), Matgenix consolidates the industry knowledge and leverages it to get new insights. High-throughput simulations: Matgenix performs atomistic simulations of materials to virtually test new compounds before they are synthesized. Expertise offered :   Matgenix has a very good expertise in developing automatized procedures (workflows) to apply ML, data consolidation and high-throughput simulations on a large scale (tens of thousands of compounds). Matgenix is also involved in open science projects, developing and maintaining their own software tools as open-source (e.g. turbomoleio[i], jobflow-remote[ii], atomate2-turbomole[iii]) or contributing to other open-source codes (e.g. pymatgen[iv], jobflow[v], atomate2[vi], matminer[vii], ...). Matgenix also has a strong expertise in the open-source datalab data management system[viii] with the main developer (Matthew Evans) being part of the Matgenix team. The main aim of datalab is to provide a platform for capturing the significant amounts of long-tail experimental data and metadata produced in a typical lab, and enable storage, filtering and future data re-use by humans and machines. The platform provides researchers with a way to record sample- and cell-specific metadata, attach and sync raw data from instruments, and perform analysis and visualisation of many characterisation techniques in the browser (XRD, NMR, electrochemical cycling, TEM, TGA, Mass Spec, Raman). Importantly, datalab stores all interconnections, provenance and metadata such that individual pieces of data are stored with the context needed to make them scientifically useful. [i] https://github.com/Matgenix/turbomoleio [ii] https://github.com/Matgenix/jobflow-remote [iii] https://github.com/Matgenix/atomate2-turbomole [iv] https://github.com/materialsproject/pymatgen [v] https://github.com/materialsproject/jobflow [vi] https://github.com/materialsproject/atomate2 [vii] https://github.com/hackingmaterials/matminer [viii] https://github.com/the-grey-group/datalab