Structure-based drug design (SBDD) aims to design small-molecule ligands that bind with high affinity and specificity to pre-determined protein targets. Generative SBDD methods leverage structural data of drugs with their protein targets to propose new drug candidates. However, most existing methods focus exclusively on bottom-up de novo design of compounds or tackle other drug development challenges with task-specific models. The latter requires curation of suitable datasets, careful engineering of the models and retraining from scratch for each task. Here we show how a single pretrained diffusion model can be applied to a broader range of problems, such as off-the-shelf property optimization, explicit negative design and partial molecular design with inpainting. We formulate SBDD as a three-dimensional conditional generation problem and present DiffSBDD, an SE(3)-equivariant diffusion model that generates novel ligands conditioned on protein pockets. Furthermore, we show how additional constraints can be used to improve the generated drug candidates according to a variety of computational metrics.

Transition states (TSs) are transient structures that are key to understanding reaction mechanisms and designing catalysts but challenging to capture in experiments. Many optimization algorithms have been developed to search for TSs computationally. Yet, the cost of these algorithms driven by quantum chemistry methods (usually density functional theory) is still high, posing challenges for their applications in building large reaction networks for reaction exploration. Here we developed React-OT, an optimal transport approach for generating unique TS structures from reactants and products. React-OT generates highly accurate TS structures with a median structural root mean square deviation of 0.053 Å and median barrier height error of 1.06 kcal mol⁻¹ requiring only 0.4 s per reaction. The root mean square deviation and barrier height error are further improved by roughly 25% through pretraining React-OT on a large reaction dataset obtained with a lower level of theory, GFN2-xTB. We envision that the remarkable accuracy and rapid inference of React-OT will be highly useful when integrated with the current high-throughput TS search workflow. This integration will facilitate the exploration of chemical reactions with unknown mechanisms.

Designing and generating new data under targeted properties has been attracting various critical applications such as molecule design, image editing and speech synthesis. Traditional hand-crafted approaches heavily rely on expertise experience and intensive human efforts, yet still suffer from the insufficiency of scientific knowledge and low throughput to support effective and efficient data generation. Recently, the advancement of deep learning has created the opportunity for expressive methods to learn the underlying representation and properties of data. Such capability provides new ways of determining the mutual relationship between the structural patterns and functional properties of the data and leveraging such relationships to generate structural data, given the desired properties. This article is a systematic review that explains this promising research area, commonly known as controllable deep data generation. First, the article raises the potential challenges and provides preliminaries. Then the article formally defines controllable deep data generation, proposes a taxonomy on various techniques and summarizes the evaluation metrics in this specific domain. After that, the article introduces exciting applications of controllable deep data generation, experimentally analyzes and compares existing works. Finally, this article highlights the promising future directions of controllable deep data generation and identifies five potential challenges.

Protein molecules are inherently dynamic and modulate their interactions with different molecular partners by accessing different tertiary structures under physiological conditions. Elucidating such structures remains challenging. Current momentum in deep learning and the powerful performance of generative adversarial networks (GANs) in complex domains, such as computer vision, inspires us to investigate GANs on their ability to generate physically-realistic protein tertiary structures. The analysis presented here shows that several GAN models fail to capture complex, distal structural patterns present in protein tertiary structures. The study additionally reveals that mechanisms touted as effective in stabilizing the training of a GAN model are not all effective, and that performance based on loss alone may be orthogonal to performance based on the quality of generated datasets. A novel contribution in this study is the demonstration that Wasserstein GAN strikes a good balance and manages to capture both local and distal patterns, thus presenting a first step towards more powerful deep generative models for exploring a possibly very diverse set of structures supporting diverse activities of a protein molecule in the cell.

Large language models (LLMs) have demonstrated outstanding capabilities in general problem-solving and been shown to improve productivity in certain domains. Thanks to their flexibility, recent work has leveraged them for diverse scientific applications, ranging from predictive modeling, scientific Q&A, and even as autonomous agents towards automation in chemistry. The democratization of high-quality chemistry education faces several challenges, including heterogeneity among sub-fields, limited access to personalized guidance, and an uneven distribution of resources. Additionally, hands-on laboratory experiments, a crucial component of chemistry education, are difficult to scale due to inherent safety risks that necessitate close supervision. We propose that LLMs can help overcome these obstacles by providing scalable solutions that tailor educational content to individual needs, enhancing the overall learning experience. In this perspective, we discuss how LLMs can catalyze chemistry education across multiple dimensions, from preparing and delivering lectures and tackling guidance in both wet lab and computational experiments, to re-thinking evaluation methodologies in the classroom. We also discuss some potential risks of this technology, such as the possibility of generating inaccurate or biased content, and emphasize the need for further development to ensure the successful integration of LLMs in the chemistry classroom.

Discovering meaningful molecules in the vast combinatorial chemical space has been a long-standing challenge in many fields from materials science to drug discovery. Recent advances in machine learning, especially generative models, have made remarkable progress and demonstrate considerable promise for automated molecule design. Nevertheless, most molecule generative models remain black-box systems, whose utility is limited by a lack of interpretability and human participation in the generation process. In this work we propose Chemical Space Explorer (ChemSpacE), a simple yet effective method for exploring the chemical space with pre-trained deep generative models. It enables users to interact with existing generative models and inform the molecule generation process. We demonstrate the efficacy of ChemSpacE on the molecule optimization task and the molecule manipulation task in single property and multi-property settings. On the molecule optimization task, the performance of ChemSpacE is on par with previous black-box optimization methods yet is considerably faster and more sample efficient. Furthermore, the interface from ChemSpacE facilitates human-in-the-loop chemical space exploration and interactive molecule design.