URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment

Synthesis planning aiming to find pathways of reactions for a target molecule is one of the most important and challenging tasks in drug discovery. Recent progress has produced both specialized deep-learning retrosynthesis systems and general-purpose large language models, but objective comparison remains difficult due to the lack of flexible, chemically interpretable benchmarking protocols. In the current study, we are introducing the URSA (Utilitarian RetroSynthesis Assessment) evaluation framework that provides the opportunity to benchmark the synthetic routes not only from a formal perspective, such as convergence to commercially available starting materials, but also from a chemical plausibility perspective, mimicking the way expert chemists evaluate the reactions and routes. The study covers a comprehensive evaluation of both conventional end-to-end retrosynthesis solutions and LLMs for the synthesis planning task on a set of novel, diverse target molecules with undisclosed synthetic routes, which represent realistic tasks in the daily drug design routine. We find that while LLMs can support high-level strategic planning, they currently underperform specialized retrosynthesis models in reliably solving synthesis planning tasks.

Project Ariadne: Prompt-Conditioned Route Generation for Synthesis Planning

Retrosynthetic planning seeks to connect a target molecule to commercially available starting materials through a multistep route. Classical planners construct such routes by iteratively applying single-step reaction models within a search procedure; constrained variants often require specialized algorithms or architectural changes. Direct route generation reframes retrosynthesis as sequence generation, but existing direct-generation methods still train separate models for different planning specifications. We introduce Ariadne, a decoder-only route generator that represents the target, optional constraints, and route in one prompt-completion sequence. On the RetroCast/PaRoutes mkt-cnv-160 benchmark family, one 24-layer checkpoint follows route-depth and required-starting-material prompts: adding the corresponding prompt fields raises Solv-0 by 13.7 points for depth constraints and 31.2 points for required-leaf constraints. Ariadne also improves over DESP, a bidirectional search planner, on required-leaf Top-10 and Solv-0 in 24 GPU-minutes versus 6.8 GPU-hours. On standard reconstruction, Ariadne is comparable to DMS Explorer XL at about half the reported inference time. Across additional target-only benchmarks, Ariadne's clearest gains are on route-holdout reconstruction, whereas AiZynthFinder MCTS remains stronger on several Solv-0 comparisons. These results extend sequence generation from specialist retrosynthesis models to prompt-conditioned structural route generation. We release the codebase and training scripts to support further work, but do not introduce Tier-1--3 route checkers; those remain the main bottleneck before models of this kind can become useful to experimental chemists.

FragmentRetro: A Quadratic Retrosynthetic Method Based on Fragmentation Algorithms

Retrosynthesis, the process of deconstructing a target molecule into simpler precursors, is crucial for computer-aided synthesis planning (CASP). Widely adopted tree-search methods often suffer from exponential computational complexity. In this work, we introduce FragmentRetro, a novel retrosynthetic method that leverages fragmentation algorithms, specifically BRICS and r-BRICS, combined with stock-aware exploration and pattern fingerprint screening to achieve quadratic complexity. FragmentRetro recursively combines molecular fragments and verifies their presence in a building block set, providing sets of fragment combinations as retrosynthetic solutions. We present the first formal computational analysis of retrosynthetic methods, showing that tree search exhibits exponential complexity $O(b^h)$, DirectMultiStep scales as $O(h^6)$, and FragmentRetro achieves $O(h^2)$, where $h$ represents the number of heavy atoms in the target molecule and $b$ is the branching factor for tree search. Evaluations on PaRoutes, USPTO-190, and natural products demonstrate that FragmentRetro achieves high solved rates with competitive runtime, including cases where tree search fails. The method benefits from fingerprint screening, which significantly reduces substructure matching complexity. While FragmentRetro focuses on efficiently identifying fragment-based solutions rather than full reaction pathways, its computational advantages and ability to generate strategic starting candidates establish it as a powerful foundational component for scalable and automated synthesis planning.

DirectMultiStep: Direct Route Generation for Multi-Step Retrosynthesis

Traditional computer-aided synthesis planning (CASP) methods rely on iterative single-step predictions, leading to exponential search space growth that limits efficiency and scalability. We introduce a transformer-based model that directly generates multi-step synthetic routes as a single string by conditionally predicting each molecule based on all preceding ones. The model accommodates specific conditions such as the desired number of steps and starting materials, outperforming state-of-the-art methods on the PaRoutes dataset with a 2.2x improvement in Top-1 accuracy on the n$_1$ test set and a 3.3x improvement on the n$_5$ test set. It also successfully predicts routes for FDA-approved drugs not included in the training data, showcasing its generalization capabilities. While the current suboptimal diversity of the training set may impact performance on less common reaction types, our approach presents a promising direction towards fully automated retrosynthetic planning.

ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generation

The incredible capabilities of generative artificial intelligence models have inevitably led to their application in the domain of drug discovery. It is therefore of tremendous interest to develop methodologies that enhance the abilities and applicability of these powerful tools. In this work, we present a novel and efficient semi-supervised active learning methodology that allows for the fine-tuning of a generative model with respect to an objective function by strategically operating within a constructed representation of the sample space. In the context of targeted molecular generation, we demonstrate the ability to fine-tune a GPT-based molecular generator with respect to an attractive interaction-based scoring function by strategically operating within a chemical space proxy, thereby maximizing attractive interactions between the generated molecules and a protein target. Importantly, our approach does not require the individual evaluation of all data points that are used for fine-tuning, enabling the incorporation of computationally expensive metrics. We are hopeful that the inherent generality of this methodology ensures that it will remain applicable as this exciting field evolves. To facilitate implementation and reproducibility, we have made all of our software available through the open-source ChemSpaceAL Python package.