Unraveling the morphological complexity of two-dimensional macromolecules

Physical scientist or a data scientist? A journey between disciplines

“…With the rapid advances in structural and functional materials and the ever-increasing demands from the industry, more powerful methods and tools have to be developed to address the spatial and temporal complexities. We turn to data science for inspiration only very recently, and the work published in this issue of Patterns 3 marks our first effort.…”

“…We expect the combination of morphology and free energy to provide a route to the full free energy landscapes and a picture of the phase transitions. We mentioned it briefly in the current work, 3 but further discussion on this topic will need a richer set of data that covers the channels of transitions.…”

A statistical learning protocol to resolve the morphological complexity of two-dimensional macromolecules

“…A statistical learning model combining unsupervised and supervised learning which embeds the geometrical, topological, and physical features was proposed to unravel the morphological complexity of 2D macromolecules ( Zhao et al., 2022 ) and extended to 3D model brain ( Razavi et al., 2015 ). This protocol provides detailed guidance for generating the data, extracting the features, and implementing the model.…”

“…We further describe model implementation and evaluation via unsupervised and supervised learning and discuss a theoretical description of morphological complexity including topological features. For complete details on the use and execution of this protocol, please refer to Zhao et al. (2022) .…”

“…For complete details on the use and execution of this protocol, please refer to Zhao et al. (2022) .…”