direct sequence-based retrosynthesis

Existing template-free, single-step retrosynthesis models suffer from slow convergence and limited generation quality and diversity due to the difficulty of explicitly modeling chemical semantics. To address this, this work proposes a Graph Representation Guidance (GRG) framework that integrates molecular representations from a pretrained encoder into a denoising diffusion Transformer. During generation, multi-granularity alignment strategies provide deep guidance, while a representation similarity–based reranking mechanism enhances both diversity and accuracy without requiring an additional verifier. Evaluated on USPTO-50k, the model achieves top-1/3/5/10 accuracies of 58.6/77.2/83.4/87.1, respectively, with diversity improved to 15.5, training epochs reduced by 35%, and inference time shortened by 30%.

This study addresses the challenge that large language models (LLMs) struggle to generate Planning Domain Definition Language (PDDL) specifications end-to-end for chemical retrosynthetic planning due to the absence of intermediate abstractions. To overcome this limitation, this work proposes a structured design paradigm based on intermediate representations, decomposing the task into three sequential sub-steps: molecule mapping, reaction mapping, and PDDL generation. Our investigation reveals that representation alignment, rather than model capacity, constitutes the primary bottleneck constraining performance. The proposed approach significantly improves the success rate of retrosynthetic planning, empirically validating the critical role of intermediate representations in complex symbolic reasoning. Ultimately, this research establishes a novel paradigm for integrating LLMs with symbolic planning frameworks.

Traditional retrosynthetic planning struggles to flexibly accommodate constraints such as pathway depth and specified starting materials. This work proposes a prompt-conditioned, end-to-end method for retrosynthetic route generation, introducing for the first time a prompting mechanism into this domain. The approach unifies the target molecule, user-defined constraints, and the complete synthetic route into a single prompt-completion sequence, which is directly decoded by a 24-layer decoder-only architecture to produce structured pathways. Notably, the model supports diverse planning constraints without requiring task-specific retraining. Experimental results demonstrate significant improvements under depth and specified starting material constraints, with Solv-0 scores increasing by 13.7 and 31.2 points, respectively. Moreover, compared to the DESP planner, the proposed method achieves superior Top-10 and Solv-0 performance while using less GPU time.

Traditional retrosynthetic planning suffers from exponential search-space explosion and poor generalizability due to its reliance on single-step iterative decomposition. To address this, we propose an end-to-end multi-step synthesis pathway generation paradigm, formulating multi-step retrosynthesis for the first time as a controllable conditional sequence generation task—enabling hard constraints such as prescribed step count and specified starting materials. Methodologically, we design a Transformer-based seq2seq model that jointly encodes molecular graphs and SMILES sequences, enabling molecule-level conditional pathway prediction. On the PaRoutes benchmark, our approach achieves a Top-1 accuracy 2.2–3.3× higher than state-of-the-art baselines. Moreover, it successfully generates chemically feasible, multi-step routes for numerous unseen FDA-approved drugs, demonstrating substantial improvements in both planning efficiency and cross-molecule generalization.

This work addresses the misalignment between local reaction prediction and global synthetic objectives in retrosynthetic planning by introducing the first end-to-end chain-of-thought reasoning framework that directly embeds strategic foresight into chemical reasoning. The approach employs path-consistent molecular representations and a progressive training strategy, coupled with a smooth transition from reasoning distillation to verifiable reward-based reinforcement learning, ensuring that each step aligns with the utility of actual synthetic pathways. Evaluated on the RetroBench benchmark, the method achieves state-of-the-art performance, significantly outperforming existing hybrid approaches—particularly in long-horizon planning tasks—while demonstrating enhanced robustness and consistency.

This study addresses the modeling challenge of dynamically changing molecular graph connectivity and size in retrosynthesis, where existing methods are constrained by fixed-size graph canvases. We propose RetroGEF, a flow-based generative model that leverages dynamic graph neural networks within a flow-matching framework to directly simulate atom additions and bond transformations via dynamic graph editing flows, thereby unifying the modeling of structural transitions and graph size variations. By eliminating the need for predefined editing orders and removing reliance on fixed canvases, our approach enables end-to-end, single-step retrosynthesis prediction. Experimental results demonstrate that RetroGEF achieves state-of-the-art performance across multiple representative retrosynthesis benchmarks.

This study addresses the challenge of balancing reaction pathway coverage and instruction controllability in retrosynthesis models by proposing the RIGS framework. Introducing a novel "coverage-before-control" paradigm, RIGS achieves instruction-guided retrosynthesis through a two-stage training procedure. First, a language projector learns preference projections to construct nested multi-support sets. Subsequently, with the generator frozen, lightweight instruction tuning is performed via residual adapters, effectively decoupling coverage capacity from control logic. Experimental results demonstrate that this approach significantly enhances both pathway diversity and instruction-following accuracy. Furthermore, the study reveals a non-monotonic relationship between model scale and coverage-control performance.

This study addresses the practical unsynthesizability of generated molecules in goal-directed molecular design, alongside the low search efficiency and goal deviation inherent in existing discrete-space methods. To overcome these limitations, this work proposes RouteFlow, a novel framework that reformulates synthesizable molecular design as a search problem within a continuous route latent space. The method introduces a cycle-consistency mechanism to prevent optimization from drifting off the true synthetic manifold and employs a reward-guided flow matching sampler for efficient directed optimization. Experimental evaluations across 16 tasks demonstrate that RouteFlow achieves state-of-the-art sample efficiency, synthetic accessibility, and retrosynthetic success rates, enabling efficient and intrinsically synthesizable molecular discovery.

研究解决了逆合成路线规划问题，通过开发名为Rachel的环境，利用通用大型语言模型GPT-5.5直接指导和修正化学合成路径。

研究通过基于规则的逆生物合成方法，使用Qwen2.5-7B策略选择扩展分子，提高了在给定扩展次数下的解题率。