20.500.12556/RUL-174324 Kontroliranje orientacije proteina s strižnim tokom z uporabo spodbujevalnega učenja Controlling protein orientation with shear flow using reinforcementlearning Proteini so naravni polimeri, ki imajo ključno vlogo tako v živih organizmih kot tudi v biotehnoloških aplikacijah. Pri bioloških in industrijskih procesih so lahko izpostavljeni mehanskim vplivom, na primer strižnemu toku. V tem delu želimo vpliv strižnega toka na protein izkoristiti za kontroliranje njegove orientacije. Pri tem za simuliranje v vodi solvatiranega proteina uporabimo simulacijo molekulske dinamike v kombinaciji s poljem sil Martini. Kontroliranje orientacije proteina izvajamo s spodbujevalnim učenjem z metodo Q-učenja. Celoten postopek sestavlja cikel iz krajše simulacije, določitve nove smeri proteina ter izbire nove strižne napetosti za simulacijo v naslednji iteraciji cikla. Rezultate spodbujevalnega učenja, kot je npr.~trajektorija orientacije proteina, primerjamo z referenčno fizikalno napovedjo, ki temelji na predpostavki, da strižni tok lahko povzroča rotacijo le okoli dveh fiksnih osi v prostoru. Proteins are natural polymers that play a crucial role both in living organisms and in biotechnological applications. In biological and industrial processes, they can be exposed to mechanical influences, such as shear flow. In this work, we aim to exploit the effect of shear flow on a protein to control its orientation. To simulate a protein solvated in water, we employ molecular dynamics simulations in combination with the Martini force field. Control of the protein orientation is carried out using reinforcement learning with the Q-learning method. The procedure consists of a cycle of a short simulation, determination of the new protein orientation, and selection of new shear stress parameters for the simulation in the next iteration of the cycle. The results of reinforcement learning, such as the trajectory of protein orientation, are compared with a reference physical prediction, which is based on the assumption that shear flow can induce rotation only around two fixed axes in space. simulacija molekulske dinamike protein kontroliranje orientacije spodbujevalno učenje strižni tok molecular dynamics protein control of orientation reinforcement learning shear flow true false false Slovenski jezik Angleški jezik Magistrsko delo/naloga 2025-10-01 08:16:08 2025-10-01 08:16:12 2025-11-20 03:52:32 0000-00-00 00:00:00 2025 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 155103 251677955 20260.pdf 20260.pdf 1 7E164B1DE7A417FFE528D97204CD6274 1bdc6c7b81f30055cf4e43ba5be3a44de89649c9ed1249c372563b6741c45b8c ec3f0106-9e8d-11f0-9328-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=219113 Fakulteta za matematiko in fiziko 0 0 0