The shape of a molecule determines its physicochemical and biological properties. However, it is often underrepresented in standard molecular representation learning approaches. Here, we propose using the Euler Characteristic Transform (ECT) as a geometrical-topological descriptor. Computed directly on a molecular graph derived from handcrafted atomic features, the ECT enables the extraction of multiscale structural features, offering a novel way to represent and encode molecular shape in the feature space. We assess the predictive performance of this representation across nine benchmark regression datasets, all centered around predicting the inhibition constant $K_i$. In addition, we compare our proposed ECT-based representation against traditional molecular representations and methods, such as molecular fingerprints/descriptors and graph neural networks (GNNs). Our results show that our ECT-based representation achieves competitive performance, ranking among the best-performing methods on several datasets. More importantly, its combination with traditional representations, particularly with the AVALON fingerprint, significantly \emph{enhances predictive performance}, outperforming other methods on most datasets. These findings highlight the complementary value of multiscale topological information and its potential for being combined with established techniques. Our study suggests that hybrid approaches incorporating explicit shape information can lead to more informative and robust molecular representations, enhancing and opening new avenues in molecular machine learning tasks. To support reproducibility and foster open biomedical research, we provide open access to all experiments and code used in this work.

Proteins are complex and dynamic molecules, encoded by our genes, that are responsible for many of the varied and fundamental processes of life. They have an astounding range of roles in biology. The rods and cones in our eyes that sense light and make it possible for us to see, the molecular sensors that underlie hearing and our sense of touch, the complex molecular machines that convert sunlight into chemical energy in plants, the motors that drive motion in microbes and our muscles, enzymes that break down plastic, antibodies that protect us from disease, and molecular circuits that cause disease when they fail -- are all proteins. Metagenomics, one of the new frontiers in the natural sciences, uses gene sequencing to discover proteins in samples from environments across the earth, from microbes living in the soil, deep in the ocean, in extreme environments like hydrothermal vents, and even in our guts and on our skin. The natural world contains a vast number of proteins beyond the ones that have been cataloged and annotated in well-studied organisms.

A tiny turbine made from DNA looks like a windmill and is hundreds of times smaller than most bacteria. It rotates when immersed in salty water and could be used as a molecular machine for speeding up chemical reactions or transporting particles inside cells. Cees Dekker at Delft University of Technology in the Netherlands and his colleagues created the turbine after being inspired by a rotating enzyme that helps catalyse energy-storing molecules in our cells.

Molecular engines were created inside E. coli bacteria The first components of a molecular engine – self-assembling axles and rotors made of specially designed proteins – have been created entirely from scratch. "We are starting very simply," says Alexis Courbet at the University of Washington in Seattle. But as he and his team create more parts, it will become possible to combine them into ever more sophisticated nanomachines, he says. "There could really be an incredible number of applications," says David Baker, a team member also at the University of Washington. For instance, nanomachines might one day be used to unclog arteries or to repair damaged cells, he says.

Molecular engines were created inside E. coli The first components of a molecular engine – self-assembling axles and rotors made of specially designed proteins – have been created entirely from scratch. "We are starting very simply," says Alexis Courbet at the University of Washington. But as he and his team create more basic parts, it will become possible to combine them into ever more sophisticated nanomachines, he says. "There could really be an incredible number of applications," says David Baker, a team member also at the University of Washington. For instance, nanomachines might one day be used to unclog arteries or to repair damaged cells, he says.

An example: when cells live out their usual lifespan, they go through a process called apoptosis--in Greek, the falling of the leaves--in which the cell gently falls apart without disturbing its neighbors by leaking toxic chemicals. The entire process is a cascade of protein-protein interactions. One protein grabs onto another protein to activate it. The now-activated protein is subsequently released to stir up the next protein in the chain, and so on, eventually causing the aging or diseased cell to sacrifice itself. Another example: in neurons during learning, synapses (the hubs that connect brain cells) call upon a myriad of proteins that form a complex together.

MIT's Hockfield Court is bordered on the west by the ultramodern Stata Center, with its reflective, silver alcoves that jut off at odd angles, and on the east by Building 68, which is a simple, window-lined, cement rectangle. At first glance, Bonnie Berger's mathematics lab in the Stata Center and Joey Davis's biology lab in Building 68 are as different as the buildings that house them. And yet, a recent collaboration between these two labs shows how their disciplines complement each other. The partnership started when Ellen Zhong, a graduate student from the Computational and Systems Biology (CSB) Program, decided to use a computational pattern-recognition tool called a neural network to study the shapes of molecular machines. Three years later, Zhong's project is letting scientists see patterns that run beneath the surface of their data, and deepening their understanding of the molecules that shape life.

The space of synthesizable molecules is greater than $10^{60}$, meaning only a vanishingly small fraction of these molecules have ever been realized in the lab. In order to prioritize which regions of this space to explore next, synthetic chemists need access to accurate molecular property predictions. While great advances in molecular machine learning have been made, there is a dearth of benchmarks featuring properties that are useful for the synthetic chemist. Focussing directly on the needs of the synthetic chemist, we introduce the Photoswitch Dataset, a new benchmark for molecular machine learning where improvements in model performance can be immediately observed in the throughput of promising molecules synthesized in the lab. Photoswitches are a versatile class of molecule for medical and renewable energy applications where a molecule's efficacy is governed by its electronic transition wavelengths. We demonstrate superior performance in predicting these wavelengths compared to both time-dependent density functional theory (TD-DFT), the incumbent first principles quantum mechanical approach, as well as a panel of human experts. Our baseline models are currently being deployed in the lab as part of the decision process for candidate synthesis. It is our hope that this benchmark can drive real discoveries in photoswitch chemistry and that future benchmarks can be introduced to pivot learning algorithm development to benefit more expansive areas of synthetic chemistry.

In what is a biological breakthrough, researchers from the California Institute of Technology have constructed a test tube artificial neural network that can recognize'molecular handwriting'. The development overcomes a major problem with machine learning; that is the ability of a machine to correctly identify handwritten numbers. Artificial neural networks are computing systems based on the biological neural networks that constitute animal brains. These systems can "learn" to perform tasks by examining examples and instead of being programmed with any task-specific rules. Neural networks consist of input and output layers together with a layer made up of units that can transform the input into something that the output layer can use.

Caltech scientists have recently developed an AI made out of DNA that can tackle a classic machine learning problem by precisely recognizing written by hand numbers. The work is a critical advance in showing the ability to program AI into engineered biomolecular circuits. Lulu Qian, assistant professor of bioengineering at Caltech said, "Though scientists have only just begun to explore creating artificial intelligence in molecular machines, its potential is already undeniable. Similar to how electronic computers and smartphones have made humans more capable than a hundred years ago, artificial molecular machines could make all things made of molecules, perhaps including even paint and bandages, more capable and more responsive to the environment in the hundred years to come." Scientists' goal behind this study is to program intelligent behaviors (the ability to compute, make choices, and more) with artificial neural networks made out of DNA.