Predicting epitopes Based on TCR sequence using an embedding deep neural network artificial intelligence approach

AI has gained a large momentum in the field of T cell receptor (TCR) immunology. TCR is a complex that is expressed on CD4+ T cells and CD8+ T cells. Its main function is to it recognize antigens presented to T cells either through MHCI or MHCII. However, there are various knowledge gaps about classifying antigen affinity to MHC, epitope interactions with TCRs, and antigens immunogenicity. Deep learning is a type of machine learning that uses various layers of neural networks to increase prediction accuracy. There are different types of deep learning approaches, including autoencoders and recursive neural networks. There has been an exponential growth of using these two deep learning techniques in investigating TCR function. In this review, we discuss the main aspects of using these networks in elucidating TCR function. We also compare various platforms that are capable of performing deep learning studies. Taken together, our review sheds lighter on AI's ability to expand our knowledge of TCR interactions. It highlights types, implementation techniques, and various advantages and disadvantages of using these techniques.

Predicting Customer Turnover Using Recursive Neural Networks

The most valuable asset for a company is its customers’ base. As a result, customer relationship management (CRM) is an important task that drives companies. By identifying and understanding the valuable customer segments, appropriate marketing strategies can be used to enhance customer satisfaction and maintain loyalty, as well as increase company retention. Predicting customer turnover is an important tool for companies to stay competitive in a fast-growing market. In this paper, we use the recurrent nerve sketch to predict rejection based on the time series of the lifetime of the customer. In anticipation, a key aspect of identifying key triggers is to turn off. To overcome the weakness of recurrent neural networks, the research model of the combination of LRFMP with the neural network has been used. In this paper, it was found that clustering by LRFMP can be used to perform a more comprehensive analysis of customers’ turnover. In this solution, LRFMP is used to execute customer segregation. The objective is to provide a new framework for LRFMP for macrodata and macrodata analysis in order to increase the problem of business problem solving and customer depreciation. The results of the research show that the neural networks are capable of predicting the LRFMP precursors of the customers in an effective way. This model can be used in advocacy systems for advertising and loyalty programs management. In the previous research, the LRFM and RFM algorithms along with the neural network and the machine learning algorithm, etc., have been used, and in the proposed solution, the use of the LRFMP algorithm increases the accuracy of the desired.

STOCK MARKET PREDICTION: USING ECONOMETRIC MODELS AND NEURAL NETWORKS

Stock market trading involves buying and selling of shares or stocks, which represents ownership of business. This research paper will focus on capturing the algorithmic trading based on historical data and compare present day algorithms to nd the best t model to understand the underlying patterns in stock market trading. A comparative analysis of closing stock price for 12 companies from three different sectors has been considered to understand the efcacy of the models in order to predict the future stock prices with minimal errors. Stock market was earlier predicted using traditional econometric models like the ARIMA and SARIMA, however, in this paper, Machine Learning, a part of Articial Intelligence will be incorporated in the stock data collected from Yahoo Finance to train models and provide predictions/decisions without being explicitly programmed to do so. Models such as OLS, SARIMA, Convolutional Neural Networks and Recursive Neural Networks (LSTM) will also be used to analyze the historical stock data and will be compared for accuracy using testing parameters like Mean Squared Error (MSE).

Cardinality Estimation of an SQL Query Using Recursive Neural Networks

To learn complex interactions between predicates and accurately estimate the cardinality of an SQL query, we develop a novel framework based on recursive tree-structured neural networks, which take into account the natural properties of logical expressions: compositionality and n-ary associativity. The proposed architecture is an extension of MSCN (multi-set convolutional network) for queries containing both conjunction and disjunction operators. The goal is to represent an arbitrary logical expression in a continuous vector space by combining sub-expression vectors according to the operator type. We compared the proposed approach with the histogram-based approach on the real-world dataset and showed that our approach significantly outperforms histograms with a large margin.