MULocDeep: A deep-learning framework for protein subcellular and suborganellar localization prediction with residue-level interpretation.

Prediction of protein localization plays an important role in understanding protein function and mechanisms. In this paper, we propose a general deep learning-based localization prediction framework, MULocDeep, which can predict multiple localizations of a protein at both subcellular and suborganellar levels. We collected a dataset with 44 suborganellar localization annotations in 10 major subcellular compartments-the most comprehensive suborganelle localization dataset to date.

Anatomy of an urban waterbody: a case study of Boston's Muddy River.

The objective of this study was to characterize and understand the water quality of Boston's Muddy River prior to restoration, to help guide those activities and evaluate their success. We use a combination of monitoring, data analysis and mathematical modeling. The seasonal pattern of temperature, pollutant signatures (identified using a principal component analysis), correlations with precipitation and spatial patterns all point to a significant wastewater input at one of the outfalls and suggest significant receiving water impact.