The tumor cell population in a cancer tissue has distinct molecular characteristics and exhibits different phenotypes, thus, resulting in different subpopulations. This phenomenon is known as Intratumor Heterogeneity (ITH), which is a major contributor in drug resistance, poor prognosis, etc. Therefore, quantifying the levels of ITH in cancer patients is essential and there are many algorithms which do so in different ways, using different types of omics data. DEPTH (Deviating gene Expression Profiling Tumor Heterogeneity) is the latest algorithm that uses transcriptomic data to evaluate the ITH score. It shows promising performance, has strong similarity with six other algorithms, and has advantage over two algorithms that uses same type of data (tITH, sITH). However, it has a major drawback that it uses expression values of all the genes (~20K genes) in quantifying ITH levels. We hypothesize that a subset of key genes is sufficient to quantify the ITH level for a tumor. To prove our hypothesis, we developed a deep learning-based computational framework using unsupervised Concrete Autoencoder (CAE) to select a set of cancer-specific key genes that can be used to evaluate the ITH score. For experiment, we used gene expression profile data of tumor cohorts of breast, kidney and lung cancer from TCGA repository. We selected three sets of key genes, each set related to breast, kidney, and lung tumor cohorts, using multi-run CAE. For the three cancers stated and three molecular subtypes of lung cancer, we calculated ITH level using all genes and key genes selected by CAE and performed a side-by-side comparison. It was found that similar conclusions can be reached for survival and prognostic outcomes based on ITH scores derived from all genes and the sets of key genes. Additionally, for subtypes of lung cancer, the comparative distribution of ITH scores derived from all genes and key genes remains similar. Based on these observations, it can be stated that, a subset of key genes, instead of all genes, is sufficient for ITH quantification. Our results also showed that many of the key genes are prognostically significant, which can be used as possible therapeutic targets.