Research On Trend Analysis Algorithm Of Single Cell Related Technology

Multicellular organisms rely on a variety of differentiated cells to work closely together to complete complex life activities.By analyzing the interaction between single cells and cells to reveal the activities in the organism,the goal of discovering differences between cells and accurately treating diseases can be achieved.When researching the information contained in cells,different techniques are used for research and analysis.With the increase of investment in single cell research,a large number of single cell related technologies have emerged,and a large amount of relevant data has been accumulated.However,it is difficult for researchers to obtain effective information from massive amounts of data.Proposing fast and efficient machine learning algorithms to automatically extract and intelligently analyze the research hotspots of single cell related technologies has become one of the urgent problems in the field of bioinformatics.Based on the machine learning method,this paper realizes the automatic extraction of research hotspots of single cell technology research papers from 2009 to2019.Through the analysis of the hotspots after extraction,the research trend and development direction of single cell related technologies are predicted.Provide decision support for single cell research scholars.This research first extracted the full text and abstract data sets of papers related to single cell technology from Pub Med,and constructed a research hotspot extraction model based on natural language processing methods,and used this model to extract the full text and abstract data of the papers.Then,the extracted hotspots are combined with the Me SH database to perform entity filtering,and the research hotspots of single-cell technology are analyzed from the three perspectives of Anatomy,Chemicals and drugs,and Diseases.Finally,based on the DAVID tool to perform genetic analysis on the extracted hot spots,analyze the data of the full text and abstract of the paper from the two aspects of disease and genetic Pathway.The analysis results are visually displayed with the help of drawing tools.The results of this work can provide data support and theoretical basis for biomedical researchers.