A force field as accurate as quantum mechanics (QMs) and as fast as molecular mechanics (MMs), with which one can simulate a biomolecular system efficiently enough and meaningfully enough to get quantitative insights, is among the most ardent dreams of biophysicists—a dream, nevertheless, not to be fulfilled any time soon. Machine learning force fields (MLFFs) represent a meaningful endeavor in this direction, where differentiable neural functions are parametrized to fit ab initio energies and forces through automatic differentiation. We argue that, as of now, the utility of the MLFF models is no longer bottlenecked by accuracy but primarily by their speed, as well as stability and generalizability—many recent variants, on limited chemical spaces, have long surpassed the chemical accuracy of 1 kcal/mol—the empirical threshold beyond which realistic chemical predictions are possible—though still magnitudes slower than MM. Hoping to kindle exploration and design of faster, albeit perhaps slightly less accurate MLFFs, in this review, we focus our attention on the technical design space (the speed-accuracy trade-off) between MM and ML force fields. After a brief review of the building blocks (from a machine learning-centric point of view) of force fields of either kind, we discuss the desired properties and challenges now faced by the force field development community, survey the efforts to make MM force fields more accurate and ML force fields faster, and envision what the next generation of MLFF might look like.

Two-headed biomotor myosin V autonomously coordinates its two identical heads in fuel consumption and mechanical stepping, so that the dimerized motor as a whole gains the capability of processive, unidirectional movement along cytoskeletal filament. How the dimer-level functions like sustained direction rectification and autonomous coordination emerge out of physical principles poses an outstanding question pertinent to motor protein biology as well as the nascent field of bioinspired nanomotors. Here the comprehensive physical mechanism for myosin V motor is identified by a dimer-level free-energy analysis that is methodologically calibrated against experimental data. A hallmark of the identified mechanism is a mechanically mediated symmetry breaking that occurs at the dimer level and prevails against ubiquitous thermal fluctuations. Another character is the onset of substantial free-energy gaps between major dimer-track binding configurations. The symmetry breaking is the basis for myosin V’s directional rectification, and the energy gaps facilitate autonomous head-head coordination. The mechanism explains the experimental finding that myosin V makes ATP-independent consecutive steps under high opposing loads but not under pushing loads. Interestingly, myosin V and another major biomotor kinesin 1 are found to share essentially the same core mechanism but for distinctly different working regimes.

The rapid progression of machine learning, especially deep learning (DL), has catalyzed a new era in drug discovery, introducing innovative approaches for predicting molecular properties. Despite the many methods available for feature representation, efficiently utilizing rich, high-dimensional information remains a significant challenge. Our work introduces ChemXTree, a novel graph-based model that integrates a Gate Modulation Feature Unit (GMFU) and neural decision tree (NDT) in the output layer to address this challenge. Extensive evaluations on benchmark data sets, including MoleculeNet and eight additional drug databases, have demonstrated ChemXTree's superior performance, surpassing or matching the current state-of-the-art models. Visualization techniques clearly demonstrate that ChemXTree significantly improves the separation between substrates and nonsubstrates in the latent space. In summary, ChemXTree demonstrates a promising approach for integrating advanced feature extraction with neural decision trees, offering significant improvements in predictive accuracy for drug discovery tasks and opening new avenues for optimizing molecular properties.

The origin of life on Earth remains one of the most perplexing challenges in biochemistry. While numerous bottom-up experiments under prebiotic conditions have provided valuable insights into the spontaneous chemical genesis of life, there remains a significant gap in the theoretical understanding of the complex reaction processes involved. In this study, we propose a novel approach using a roto-translationally invariant potential (RTIP) formulated with pristine Cartesian coordinates to facilitate the simulation of chemical reactions. By employing RTIP pathway sampling to explore the reactivity of primitive molecules, we identified several low-energy reaction mechanisms, such as two-hydrogen-transfer hydrogenation and HCOOH-catalyzed hydration and amination. This led to the construction of a comprehensive reaction network, illustrating the synthesis pathways for glycine, serine, and alanine. Further thermodynamic analysis highlights the pivotal role of formaldimine as a key precursor in amino acid synthesis, owing to its more favorable reactivity in coupling reactions compared to the traditionally recognized hydrogen cyanide. Our study demonstrates that the RTIP methodology, coupled with a divide-and-conquer strategy, provides new insights into the simulation of complex reaction processes, offering promising applications for advancing organic design and synthesis.

Designing organic fluorescent molecules with tailored optical properties has been a long-standing challenge. Recently, statistical models have opened new avenues for tackling this problem. Inverse design has attracted considerable attention in organic materials science; however, most existing approaches focus on arbitrary design or theoretical properties. Here, we introduce a strategy that enables the direct optimization of specific experimental properties during the inverse design process. Our method employs an adaptive β-variational autoencoder (adaptive β-VAE) combined with a latent vector-based prediction model. By dynamically tuning the Kullback–Leibler divergence scaling factor (β) and employing a separate training strategy, we enhance both the robustness of the generator and the diversity of the generated molecules. We demonstrate that latent vectors from the adaptive β-VAE serve as powerful inputs for downstream prediction models of experimental properties, such as fluorescence energy and quantum yield. Our optimized search framework for organic fluorescent materialsguided by gradients in latent space and validated by newly synthesized molecules sampled from optimal regions in the high-dimensional spaceshows strong potential for broader applications in the design of diverse organic materials.

Computational molecular design—the endeavor to design molecules, with various missions, aided by machine learning and molecular dynamics approaches—has been widely applied to create valuable new molecular entities, from small molecule therapeutics to protein biologics. In the small data regime, physics-based approaches model the interaction between the molecule being designed and proteins of key physiological functions, providing structural insights into the mechanism. When abundant data have been collected, a quantitative structure–activity relationship can be more directly constructed from experimental data, from which machine learning can distill key insights to guide the design of the next round of experiment design. Machine learning methodologies can also facilitate physical modeling, from improving the accuracy of force fields and extending them to unseen chemical spaces to more directly enhancing the sampling on the conformational spaces. We argue that these techniques are mature enough to be applied to not just extend the longevity of life but the beauty it manifests. In this Perspective, we review the current frontiers in the research and development of skincare products, as well as the statistical and physical toolbox applicable to addressing the challenges in this industry. Feasible interdisciplinary research projects are proposed to harness the power of machine learning tools to design innovative, effective, and inexpensive skincare products.