In the field of ecology, camera traps are important tools to collect information on the wildlife of certain areas. The problem that arises with many camera traps is that they can collect more images than a human can realistically go trough all by themselves. To help classify these images computer vision is proposed as an alternative to manual classification. Many modern computer vision applications use neural networks. A hard part for the neural networks is that to train them well a large data set is needed, and sometimes it is almost impossible to build this dataset. This is where synthetic samples can be used instead of real samples. These samples are created by using computer graphics software to create realistic looking images to enlarge the dataset, or even be the whole dataset. This work evaluates how well a segmentation network was trained on only synthetic samples could perform on the real data. For this multiple segmentation networks were used like: U-Net and SegNet and the networks were trained on different datasets all derived from the synthetic data. The results show that while the networks can work real images that look similar to the synthetic samples, they fail to segment images that are captured in locations that look different from the synthetic samples.

Horizontal gene transfer (HGT) trough plasmids is one of the main contributors to the rapid increase of antimicrobial resistance (AMR). Studying wastewater from wastewater treatment plants (WWTPs) allows us new insights into HGT as bacteria from different sources come together. Currently the analysis of HGT is limited, as plasmids cannot be linked to their host species with only metagenomic samples, however when combined with Hi-C sequencing data, sequences from the same cell can be linked together. We developed a method that uses metagenomic Hi-C data to link bacterial genera together with detected plasmid consensus clusters and resistance genes. Using this method, we analysed datasets from two sources: activated sludge put into a reactor with an antibiotic pressure and a WWTP entrance. The activated sludge dataset was sequenced at two timepoints with an increasing antibiotic concentration. This allowed us to compare degrees of antibiotic resistance in different antibiotic pressures as well as detect broad host-range resistant plasmids. We detected an increase in acquired resistance in environments with a higher antibiotic pressure and detected a resistant plasmid in both locations, linked to both pathogenic as well as bacteria found in active sludge.