| dc.rights.license | CC-BY-NC-ND | |
| dc.contributor.advisor | Externe beoordelaar - External assesor, | |
| dc.contributor.author | Elst, Maarten van | |
| dc.date.accessioned | 2023-12-22T00:01:26Z | |
| dc.date.available | 2023-12-22T00:01:26Z | |
| dc.date.issued | 2023 | |
| dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/45665 | |
| dc.description.abstract | We present results of two attempts to improve irregularity (epigenetic modifications or damage) recognition in nanopore sequenced DNA signals. This was done on a limited dataset for proof of concept purposes. The first approach uses bayesian optimization to improve current algorithms used, the second approach uses a random forest with curated features to recognize irregularities in the sequencing signal. Only the random forest approach showed some promise, with positive results for in silico generated mutations of the sequencing data for a limited genetic context. | |
| dc.description.sponsorship | Utrecht University | |
| dc.language.iso | EN | |
| dc.subject | We present results of two attempts to improve irregularity (epigenetic modifications or damage) recognition in nanopore sequenced DNA signals. The first approach uses bayesian optimization to improve current algorithms used, the second approach uses a random forest. Only the random forest approach showed some promise on in silico generated DNA mutations. | |
| dc.title | RECOGNIZING IRREGULARITIES IN STACKED NANOPORE SIGNALS FROM IN SILICO PERMUTED SEQUENCING DATA | |
| dc.type.content | Master Thesis | |
| dc.rights.accessrights | Open Access | |
| dc.subject.keywords | nanopore sequencing, random forest, bayesian optimization, machine learning | |
| dc.subject.courseuu | Bioinformatics and Biocomplexity | |
| dc.thesis.id | 26792 | |
