20.500.12556/RUL-186337 Strojni pospeševalnik za analizo booleovih modelov gensko regulatornih omrežij Hardware accelerator for the analysis of Boolean models of gene regulatory networks Diplomsko delo obravnava razvoj strojnega pospeševalnika za analizo booleovih modelov, ki se uporabljajo pri modeliranju gensko regulatornih omrežij. Analiza takšnih modelov je zaradi eksponentne rasti prostora možnih stanj pri večjih omrežjih računsko zahtevna, zato smo raziskali možnost uporabe programirljivega vezja FPGA za pospešitev iskanja atraktorjev. Razvili smo avtomatiziran sistem, ki sprejme model v formatu .bnet, iz njega generira specializirano kodo strojnega opisa v jeziku Verilog ter jo s pomočjo orodja Vivado sintetizira in implementira na razvojni plošči Nexys A7-100T. Za zaznavanje cikličnih in fiksnih atraktorjev smo v strojni opremi uporabili Floydov algoritem tortoise and hare, najdene atraktorje pa kanonizirali in agregirali glede na njihove bazene. Rezultati analize se prek serijskega vmesnika UART prenesejo na gostiteljski računalnik. Pravilnost strojne izvedbe smo preverili z lastno referenčno implementacijo v jeziku Python ter neodvisno z orodjem BoolNet. Sistem smo ovrednotili na dveh bioloških modelih različnih velikosti. Pri modelu ErbB je bila FPGA izvedba približno 100-krat hitrejša od lastne programske implementacije, pri zahtevnejšem modelu apoptoze pa približno 133-krat hitrejša. Pri slednjem je bila FPGA izvedba tudi približno 3,2-krat hitrejša od orodja BoolNet ter je uspešno identificirala vseh 97 atraktorjev. Rezultati kažejo, da je uporaba FPGA učinkovita za pospeševanje analize sinhronih Booleovih omrežij srednje velikosti. Razvita rešitev hkrati predstavlja osnovo za nadaljnje izboljšave, kot so paralelizacija več analizatorjev, optimizacija pomnilniške organizacije in podpora večjim modelom. This thesis presents the development of a hardware accelerator for the analysis of Boolean models used in the modelling of gene regulatory networks. The analysis of such models becomes computationally demanding for larger networks due to the exponential growth of the state space. Therefore, we investigated the use of a field-programmable gate array (FPGA) to accelerate attractor identification. We developed an automated system that accepts a model in the .bnet format, generates specialised hardware description code in Verilog, and uses the Vivado tool to synthesise and implement it on a Nexys A7-100T development board. Floyd's tortoise and hare algorithm was implemented in hardware to detect cyclic and fixed-point attractors. The identified attractors are canonicalised and aggregated according to their basins of attraction. The analysis results are transferred to the host computer through UART serial interface. The correctness of the hardware implementation was verified using our own reference implementation in Python and independently using the BoolNet tool. The system was evaluated on two biological models of different sizes. For the ErbB model, the FPGA implementation was approximately 100 times faster than our software implementation, while for the more demanding apoptosis model it was approximately 133 times faster. For the latter, the FPGA implementation was also approximately 3.2 times faster than BoolNet and successfully identified all 97 attractors. The results demonstrate that FPGA-based acceleration is an effective approach for analysing medium-sized synchronous Boolean networks. The developed system also provides a basis for further improvements, including the parallelisation of multiple analysers, optimisation of memory organisation, and support for larger models. Booleovi modeli gensko regulatorna omrežja FPGA strojni pospeševalnik atraktorji Verilog Boolean models gene regulatory networks FPGA hardware accelerator attractors Verilog true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2026-08-31 11:20:55 2026-08-31 11:21:07 2026-09-03 04:37:23 0000-00-00 00:00:00 2026 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 38694 289668355 Ahacic_Matej_-_Strojni_pospesevalnik_za_analizo_booleovih_modelov_gensko_regulatornih_omrezij.pdf Ahacic_Matej_-_Strojni_pospesevalnik_za_analizo_booleovih_modelov_gensko_regulatornih_omrezij.pdf 1 F877FA837867928D1C32AB4B6E65F8B8 1fe0e8a27fac2be2a64057bee9de56fcd6dafea07fc470bbedc1f2cfdf4fcdc7 e106287d-a51c-11f1-9b0d-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=245507 Fakulteta za računalništvo in informatiko 0 0 0