DNA-encoded library (DEL) screening has revolutionized protein-ligand binding detection, enabling rapid exploration of vast chemical spaces through read count analysis. However, two critical challenges limit its effectiveness: distribution noise in low copy number regimes and systematic shifts between read counts and true binding affinities. We present DEL-Ranking, a comprehensive framework that simultaneously addresses both challenges through innovative rankingbased denoising and activity-referenced correction. Our approach introduces a dual-perspective ranking strategy combining Pair-wise Soft Rank (PSR) and Listwise Global Rank (LGR) constraints to preserve both local and global count relationships. Additionally, we develop an Activity-Referenced Correction (ARC) module that bridges the gap between read counts and binding affinities through iterative refinement and biological consistency enforcement. Another key contribution of this work is the curation and release of three comprehensive DEL datasets that uniquely combine ligand 2D sequences, 3D conformational information, and experimentally validated activity labels. We validate our framework on five diverse DEL datasets and introduce three new comprehensive datasets featuring 2D sequences, 3D structures, and activity labels. DEL-Ranking achieves state-of-the-art performance across multiple correlation metrics and demonstrates strong generalization ability across different protein targets. Importantly, our approach successfully identifies key functional groups associated with binding affinity, providing actionable insights for drug discovery.

The idea of using deep-learning-based molecular generation to accelerate discovery of drug candidates has attracted extraordinary attention, and many deep generative models have been developed for automated drug design, termed molecular generation. In general, molecular generation encompasses two main strategies: de novo design, which generates novel molecular structures from scratch, and lead optimization, which refines existing molecules into drug candidates. Among them, lead optimization plays an important role in real-world drug design. For example, it can enable the development of me-better drugs that are chemically distinct yet more effective than the original drugs. It can also facilitate fragment-based drug design, transforming virtual-screened small ligands with low affinity into first-in-class medicines. Despite its importance, automated lead optimization remains underexplored compared to the well-established de novo generative models, due to its reliance on complex biological and chemical knowledge. To bridge this gap, we conduct a systematic review of traditional computational methods for lead optimization, organizing these strategies into four principal sub-tasks with defined inputs and outputs. This review delves into the basic concepts, goals, conventional CADD techniques, and recent advancements in AIDD. Additionally, we introduce a unified perspective based on constrained subgraph generation to harmonize the methodologies of de novo design and lead optimization. Through this lens, de novo design can incorporate strategies from lead optimization to address the challenge of generating hard-to-synthesize molecules; inversely, lead optimization can benefit from the innovations in de novo design by approaching it as a task of generating molecules conditioned on certain substructures.

Recombinant adeno-associated virus (rAAV) vectors have revolutionized gene therapy, but their broad tropism and suboptimal transduction efficiency limit their clinical applications. To overcome these limitations, researchers have focused on designing and screening capsid libraries to identify improved vectors. However, the large sequence space and limited resources present challenges in identifying viable capsid variants. In this study, we propose an end-to-end diffusion model to generate capsid sequences with enhanced viability. Using publicly available AAV2 data, we generated 38,000 diverse AAV2 viral protein (VP) sequences, and evaluated 8,000 for viral selection. The results attested the superiority of our model compared to traditional methods. Additionally, in the absence of AAV9 capsid data, apart from one wild-type sequence, we used the same model to directly generate a number of viable sequences with up to 9 mutations. we transferred the remaining 30,000 samples to the AAV9 domain. Furthermore, we conducted mutagenesis on AAV9 VP hypervariable regions VI and V, contributing to the continuous improvement of the AAV9 VP sequence. This research represents a significant advancement in the design and functional validation of rAAV vectors, offering innovative solutions to enhance specificity and transduction efficiency in gene therapy applications.