Tanzila Islam

ConvCGP: A Convolutional Neural Network to Predict Genotypic Values of Rice Traits from Compressed Genome-Wide Polymorphisms

The paper introduces ConvCGP, a deep learning framework combining CNNs and autoencoders to predict rice trait genotypic values from compressed genome-wide polymorphism data, outperforming existing methods.

Comprehensive non-black box classification of highly correlated ecological time series pairs containing many zeros: the case of gut microbiome of mice

This paper introduces a non-black-box method to classify ecological time series pairs in mouse gut microbiota, revealing significant correlations despite many zeros and non-stationarity.