This work Represents a new method to Integrate Multi-Omic Data in a way that corresponds to the Biological Relevance between Single Cell RNAseq and Proteomic Data. Most Integration Techniques diminish the Chemical Dynamics, Physical Interations and Kinetic Movement between the Experiments, preparing a Correlation Score that may not Represent the data as Accurately as it should. scPEA, scPC, scScreen and PRna, recreate some of the Dynamics Between Genes, Cells and Proteins, determining a more accurate Mechanism for Biomarker Prediction. The techniques Described in scPEA, scPC, scScreen and PRna aim to Appropriately produce Proteomic Analytic directly related to the target Disease, producing much more Sensitive results for Biomarker Discovery and Prediction. The model Describe different techniques to produce results pertaining to the Dynamics between Genes in scRNAseq and Protein within Single Cell Proteomic Data. The aim is to incorporate layers and depth in a Neural Network to Correlate the Biological Process between Omic data.