SKM 2023 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
DS: Fachverband Dünne Schichten
DS 12: Poster
DS 12.43: Poster
Wednesday, March 29, 2023, 17:00–19:00, P3
Optimizing two-dimensional materials for biomolecule detection using machine learning techniques — •Calin-Andrei Pantis-Simut1,2,3, Amanda Teodora Preda1,2,3, Nicolae Filipoiu1,2, and George Alexandru Nemnes1,2,3 — 1Horia Hulubei National Institute of Physics and Nuclear Engineering (IFIN-HH), Str. Reactorului no.30, P.O.BOX MG-6, Magurele, Romania — 2University of Bucharest, Faculty of Physics, 077125 Magurele-Ilfov, Romania — 3Research Institute of the University of Bucharest (ICUB), Sos. Panduri 90, Bucharest Romania.
The problem of correctly identifying the biomarkers associated with specific pathologies is of great interest nowadays for rapid diagnoses. The transport properties of different active layers like beta-arsenate, phosphorene, graphene, or Al-doped MoSe2 were investigated in the presence of certain biomolecules. Additionally, predictions of biomolecular compounds with tunable gaps were reported as well as carbon nanotube-based. Our study brings a detailed analysis of 2D semiconductor heterostructures in contact with biomarkers of respiratory diseases, which exhibit large tunabilities in transport properties. As a first step, by using DFT simulations, the electronic properties of the systems are analyzed under different doping conditions and nanostructuring. In a second step, a large number of systems will be considered for transport calculations and the results will define the input for machine learning procedures. This involves the mapping between structural information and transport properties. In the end, an analysis of the sensor's limit of detection and regeneration is performed.