Title: Compositional Autoencoder for Disentangling G x E
Abstract: This study introduces a novel compositional autoencoder (CAE) framework designed to disentangle the complex interplay between genotypic and environmental factors in high-dimensional phenotype data to improve trait prediction in plant breeding and genetics programs. Traditional predictive methods, which use compact representations of high-dimensional data through handcrafted features or latent features like PCA or more recently autoencoders, do not separate genotype-specific and environment-specific factors. We hypothesize that disentangling these features into genotype-specific and environment-specific components can enhance predictive models. To test this, we developed a novel compositional autoencoder (CAE) that decomposes high-dimensional data into distinct genotype-specific and environment-specific latent features. Our CAE framework employs a hierarchical architecture within an autoencoder to effectively separate these entangled latent features. Applied to a maize diversity panel dataset, the CAE demonstrates superior modeling of environmental influences and improved predictive performance for key traits like Days to Pollen and Yield, surpassing traditional methods, including standard autoencoders, PCA with regression, and Partial Least Squares Regression (PLSR). By disentangling latent features, the CAE provides powerful tool for precision breeding and genetic research. This work significantly enhances trait prediction models, advancing agricultural and biological sciences.
Bio:
– Ph.D. student at Iowa State University specializing in hierarchical latent space disentanglement from high-dimensional multispectral data (Autoencoders).
– Industry experience at Corteva Agriscience using AI and geospatial data (Sentinel-1, Sentinel-2, SkySat) for classification and segmentation problems.
– Published two peer-reviewed papers in “Frontiers” and “Plants People Planet” on the above research. Google Scholar
– Proficient in PyTorch Lightning, geospatial tools (ArcPy, GeoPandas, Rasterio), and advanced ML models like Transformers and autoencoders.
– Currently working on time-series multimodal foundational model. (multiple satellites’, weather, and soil data)
Please click this URL to start or join. https://iastate.zoom.us/j/96810972944?pwd=SVVLWlY2cVdZYXhxWWg4ZHF1cVdSZz09
Or, go to https://iastate.zoom.us/join and enter meeting ID: 968 1097 2944 and password: 334840
Join from dial-in phone line:
Dial: +1 309 205 3325 or +1 312 626 6799
Meeting ID: 968 1097 2944
Participant ID: Shown after joining the meeting
International numbers available: https://iastate.zoom.us/u/aqUgrVklM