1. Deep GONet : Self-explainable deep neural network based on Gene Ontology for phenotype prediction from gene expression data
Link to Paper
GitHub Repository
Paper accepted at the 19th Asia Pacific Bioinformatics Conference (APBC 2021), my memoir on that subject is available in the next project
Deep GONet provides an explanation to its predictions by identifying the most important neurons and associating them with biological functions, making the model understandable for biologists and physicians.
2. Biological interpretation of deep neural networks learned from transcriptomic data
Link to Memoir
GitHub Repository
Redaction of a memoir and development of a new method called Deep GONet.
Deep GONet, the purpose of this internship was to develop a neural network able to learn and evolve the weights of the following layers by biological information introduced with a knowledge base outside.
3. Twitter Sentiment Analysis
Link to Publication
GitHub Repository
Twitter archive data and real stream tweets for sentiment and emotion analysis.
Our primary purpose is to build a robust platform system for real-time data analysis of tweets on twitter trends. We also want to analyse all the tweets of 2017 based on a downloaded sample of data (average of 6 To). All this data analysis will be accessible via a web interface.