{"id":359,"date":"2018-12-16T13:39:00","date_gmt":"2018-12-16T05:39:00","guid":{"rendered":"https:\/\/www.next-bioinfo.tw\/?p=359"},"modified":"2024-10-01T15:32:36","modified_gmt":"2024-10-01T07:32:36","slug":"%e3%80%903d-genome%e3%80%91-%e6%87%89%e7%94%a8%e9%9b%bb%e8%85%a6%e8%a6%96%e8%a6%ba%e6%96%bctad%e6%8b%93%e6%92%b2%e7%b5%90%e6%a7%8b%e5%9f%9f%e4%b9%8b%e9%a0%90%e6%b8%ac%e5%89%b5%e6%84%8f%e7%99%bc","status":"publish","type":"post","link":"https:\/\/www.next-bioinfo.tw\/en\/2018\/12\/%e3%80%903d-genome%e3%80%91-%e6%87%89%e7%94%a8%e9%9b%bb%e8%85%a6%e8%a6%96%e8%a6%ba%e6%96%bctad%e6%8b%93%e6%92%b2%e7%b5%90%e6%a7%8b%e5%9f%9f%e4%b9%8b%e9%a0%90%e6%b8%ac%e5%89%b5%e6%84%8f%e7%99%bc\/","title":{"rendered":"\u30103D Genome\u3011Computer vision-based methods to predict Hi-C Topologically associating domains (TAD) - A proof of concept."},"content":{"rendered":"
A Hi-C contact map can be represented as a 2d array (matrix) and visualized as a gray-scale image. Topologically associating domains (TAD) were identified as a high interaction region inside a submatrix. Therefore, we can transfer the Hi-C contact map into image space and then use the common computer vision technique to filter the TAD just like how we find ROI.<\/p>\n\n\n\n