Volume 3 Issue 9, September 2023

Rapid urban expansion presents a major challenge to delivering the United Nations Sustainable Development Goals. Urban populations are forecast to increase by 2.2 billion by 2050, and business as usual will condemn many of these new citizens to lives dominated by disaster risk. This need not be the case. Computational science can help urban planners and decision-makers to turn this threat into a time-limited opportunity to reduce disaster risk for hundreds of millions of people.

Progress towards universal access to safe drinking water and nutritious food has been moving forward at a slower than desired rate. Computational tools can help accelerate progress towards these goals, but solutions need to be open source, and designed, developed and implemented in a participatory manner.

Dr Cristina Villalobos — Myles and Sylvia Aaronson endowed professor in the School of Mathematical and Statistical Sciences at The University of Texas Rio Grande Valley (UTRGV), Director of the Center of Excellence in STEM Education, and Fellow of the American Mathematical Society — talks to Nature Computational Science about her work on empowering underrepresented groups in STEM education and gives her insights into the United Nations Sustainable Development Goals (UN SDGs) related to equitable education and gender equality.

Dr Perrine Hamel — Assistant Professor at Nanyang Technological University’s Asian School of the Environment and Principal Investigator at the Earth Observatory of Singapore — talks to Nature Computational Science about making cities more sustainable and resilient by incorporating green infrastructure into urban environments, as well as about our current progress with the United Nations’ Sustainable Development Goals (SDGs) related to sustainable cities and climate action.

A reinforcement-learning-based framework is proposed for assisting urban planners in the complex task of optimizing the spatial design of urban communities.

A recent work provides a mathematical framework for studying how changes in network structure over time can influence cooperative behavior.

Deep learning approaches have potential to substantially reduce the astronomical costs and long timescales involved in drug discovery. KarmaDock proposes a deep learning workflow for ligand docking that shows improved performance against both benchmark cases and in a real-world virtual screening experiment.

SAHMI performs in silico denoising of microbial signals from existing host genomic sequencing data to select for present microbes, as well as filter out contaminants and false-positive misclassifications.

A graph-based artificial intelligence model for urban planning outperforms human-designed plans in objective metrics, offering an efficient and adaptable collaborative workflow for future sustainable cities.

Real-world social networks are often ephemeral and subject to exogenous restructuring. Q. Su et al. show that dynamic networks can foster cooperative behavior.

The computational platform u-signal3D defines a shape-invariant representation of the spatial scales of molecular organization at the cell surface to enable comparison and machine learning of signaling across morphologically diverse cell populations.

KarmaDock, a deep learning approach, is proposed to improve the speed, accuracy and pose quality of molecular docking and is validated on multiple datasets and a real-world virtual screening.