This project was about creating a database of herbarium records from tropical forest species of the Americas and the development of machine learning classifiers to predict the phenological stages of these species using the herbarium records.
I created machine learning classifiers to predict the antimicrobial activity of peptides. It was an end-to-end project in which I did the data pre-processing, feature engineering, training, hyperparameter tuning, and deployment of the best model as a web application with Streamlit.
Oral presentation in English about The molecular basis of JAZ-MYC coupling, a key component of plant immunity project. This presentation was awarded as the best oral presentation of the symposium.
In this project, we identified binding specificity between repressor proteins and a transcriptional factor associated with the Jasmonic Acid pathway in Arabidopsis thaliana through Molecular Dynamics simulations and Machine Learning algorithms.
In this project, we captured sentiments of replies to tweets from two Ecuadorian presidential candidates in the 2021 elections (@LassoGuillermo and @ecuarauz). A model of artificial neural networks was used to classify tweets considering their sentiment as positive, negative, or neutral.
In this project, I created machine learning classifiers (Logistic Regression, Random Forest, and XGBoost) to evaluate the activity of molecules that have been experimentally tested to bind or not bind to Beta-Lactamases. Also, I implemented a web service with the best model.
In this project, we created a plant disease detector based on convolutional neural networks, trained to recognize two types of maize infectious diseases - Common rust of corn and Northern corn leaf blight.