A Multithreaded Model for Cancer Tissue Heterogeneity: An Application
Choudhury, S.
Show abstract
Studying the heterogeneity in cancerous tissue is challenging in cancer research. It is vital to process the real-world data efficiently to understand the heterogeneous nature of cancer tissue. GPU compatible models, which can estimate the subpopulation of cancerous tissue, are fast if the size of input data, i.e., the number of qPCR (quantitative polymerase chain reaction) gene expression reading is extensive. In the real world, we rarely get that much data to reap the benefits of a GPUs parallelism. Real experimental data from fibroblasts are much less, and models using those data on a GPU are slower than the CPU multithreaded application. This paper will show a method to run GPU-compatible models for cancer tissue heterogeneity on a multithreaded CPU. Further, we also show that the model running on a multithreaded CPU is faster than the model running on a GPU with real experimental data.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.