GitHub

TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.

Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluation. We also release a list of papers about transfer-based attacks here. If our paper or this code is ...
C&EN

XGBMUT: Predicting the Functional Impact of Missense Mutations Using an Extreme Gradient Boost Classifier

Laboratory of Molecular Modeling and QSAR, Faculty of Pharmacy, Federal University of Rio de Janeiro, 373 Carlos Chagas Filho Avenue, Rio de Janeiro, Rio de Janeiro 21941-170, Brazil Laboratory of ...
PNAS

Epistatic hotspots organize antibody fitness landscape and boost evolvability

Epistatic interactions between mutations are thought to constrain evolution since they make an adaptive landscape in sequence space very rugged. However, an increasing variety of empirical fitness ...
PNAS

Breakthrough-induced loop formation in evolving transport networks

Loops are ubiquitous in animate and inanimate transport networks, from leaf venation to river deltas. Yet, current physical models fail to reproduce them accurately. We report a way of loop formation ...
Frontiers

Interaction Analysis Based on Shapley Values and Extreme Gradient Boosting: A Realistic Simulation and Application to a Large Epidemiological Prospective Study

SHapley Additive exPlanations (SHAP) based on tree-based machine learning methods have been proposed to interpret interactions between exposures in observational studies, but their performance in ...
Frontiers

Predicting Ischemic Stroke Outcome Using Deep Learning Approaches

Predicting functional outcomes after an Ischemic Stroke (IS) is highly valuable for patients and desirable for physicians. This facilitates physicians to set reasonable goals for patients and ...
C&EN

An Adaptive Machine Learning Strategy for Accelerating Discovery of Perovskite Electrocatalysts

The Supporting Information is available free of charge at https://pubs.acs.org/doi/10.1021/acscatal.9b05248. Python code to generate features and raw data of ...