Transfer learning has gained importance in areas where there is a labeled data shortage. However, it is still controversial as to what extent natural image datasets as pre-training sources contribute scientifically to success in different fields, such as medical imaging. In this study, the effect of transfer learning for medical object detection was quantitatively compared using natural and medical image datasets. Within the scope of this study, transfer learning strategies based on five different weight initialization methods were discussed. A natural image dataset MS COCO and brain tumor dataset BraTS 2020 were used as the transfer learning source, and Gazi Brains 2020 was used for the target. Mask R-CNN was adopted as a deep learning architecture for its capability to effectively handle both object detection and segmentation tasks. The experimental results show that transfer learning from the medical image dataset was found to be 10% more successful and showed 24% better convergence performance than the MS COCO pre-trained model, although it contains fewer data. While the effect of data augmentation on the natural image pre-trained model was 5%, the same domain pre-trained model was measured as 2%. According to the most widely used object detection metric, transfer learning strategies using MS COCO weights and random weights showed the same object detection performance as data augmentation. The performance of the most effective strategies identified in the Mask R-CNN model was also tested with YOLOv8. Results showed that even if the amount of data is less than the natural dataset, in-domain transfer learning is more efficient than cross-domain transfer learning. Moreover, this study demonstrates the first use of the Gazi Brains 2020 dataset, which was generated to address the lack of labeled and qualified brain MRI data in the medical field for in-domain transfer learning. Thus, knowledge transfer was carried out from the deep neural network, which was trained with brain tumor data and tested on a different brain tumor dataset.

Predicting secondary structure and solvent accessibility of proteins are among the essential steps that preclude more elaborate 3D structure prediction tasks. Incorporating class label information contained in templates with known structures has the potential to improve the accuracy of prediction methods. Building a structural profile matrix is one such technique that provides a distribution for class labels at each amino acid position of the target. In this paper, a new structural profiling technique is proposed that is based on deriving PFAM families and is combined with an existing approach. Cross-validation experiments on two benchmark datasets and at various similarity intervals demonstrate that the proposed profiling strategy performs significantly better than Homolpro, a state-of-the-art method for incorporating template information, as assessed by statistical hypothesis tests. The DSPRED method can be accessed by visiting the PSP server at http://psp.agu.edu.tr. Source code and binaries are freely available at https://github.com/yusufzaferaydin/dspred. Supplementary data are available at Bioinformatics online.

Periodic spatio-temporal co-occurrence patterns (PECOPs) represent subsets of object-types that are often periodically located together in space and time. Discovering PECOPs is an important problem with many applications such as discovering interactions between animals and identifying tactics in games. However, mining PECOPs is computationally very expensive because the interest measures are computationally complex, databases are larger due to the archival history, and the set of candidate patterns is exponential in the number of object-types. In this paper, we define the problem of mining PECOPs, and propose a novel PECOP mining algorithm. The experimental results show that the proposed algorithm is computationally more efficient than the naïve alternatives.

Cluster computing combines the resources of multiple computers as they act like a single high-performance computer. In this study, a computer cluster consisting of Lustre distributed file system with one cluster server based on Slurm resource management system and thirteen calculation nodes were built by using available and inert computers that have different processors. Different bioinformatics algorithms were run using different data sets in the cluster, and the performance of the clusters was evaluated with the amount of time the computing cluster spent to finish the jobs.