Introduction

The "AI & Drug Discovery" mode has accelerated the research and development of drugs and made outstanding contributions to safeguarding human health. In general, drug discovery is considered to be the process of identifying chemical entities with potential druggability in response to imminent and unsatisfied medical needs [1\cite{bib1}]. However, the complex experimental verification and low success rate results make this process extremely time and cost-consuming, which now takes about 10–15 years with an average cost of $2.5 billion [2\cite{bib3}]. With the rapid development of artificial intelligence, especially deep learning, huge breakthroughs have already occurred in the drug discovery process, including drug design, drug screening, and chemical synthesis, reducing overall attrition rate and significantly improving discovery efficiency. Recently, AlphaFold2 [3\cite{bib9}] was used to directly predict the 3D structure of the protein from the amino acid sequence of the protein and achieved atomic-level accuracy, which deciphered the entire human proteome (98.5% of human protein). Deep models [4, 5, 6\cite{bib10,bib11,bib12}] were also used to improve the prediction accuracy of retrosynthesis pathways. As a critical step to be approved for a candidate drug, deep models [7, 8, 9, 10, 11\cite{bib4,bib5,bib6,bib7,bib8}] assisted in the prediction of toxicity, physiological activity, and other properties, which carried out molecular screening more efficiently.
However, although deep learning greatly accelerates and promotes the process of drug discovery, the "black box" characteristic [12\cite{bib13}] of deep models seriously hinders the in-depth research and application of existing methods. The "black box" characteristic is mainly reflected in two aspects, namely the unexplainable decision route and the unexplainable prediction result of deep models. Developing an explainable deep learning method for drug discovery has significant meaning, such as providing transparent property prediction results of drugs for review (model results can directly determine the life and death of patients); explaining the decision logic of deep models in property prediction, molecular synthesis, and other tasks, to help experts understand the predicted results and find important factors for specified tasks.
Recently, a few works have attempted to explain the relationship between the predicted results and original molecules. Xu et al. (2017) [13\cite{bib14}] proposed a framework for acute oral toxicity (AOT) prediction based on convolutional neural networks and attempted to use the deep molecular fingerprints for mining vital substructures related to AOT. Wu et al. (2021) [14\cite{bib15}] proposed a multi-task graph attention (MGA) framework for the task of predicting toxicity and also tried to use the attention mechanism to explore the most critical structural information. These two methods provide only a few examples of one or two specific tasks for verifying interpretability, which was inevitably subjective. Meanwhile, the main drawback is that the two methods essentially revolve around the relationship between atoms, which is inconsistent with existing scientific discoveries [15, 16, 17, 18, 19, 20\cite{bib16,bib17,bib18,bib19,bib20,bib21}].
In fact, those researches [15, 16, 17, 18, 19, 20\cite{bib16,bib17,bib18,bib19,bib20,bib21}] reveal that molecular properties are directly affected by specific fragments. Smith et al. (2011) [20\cite{bib21}] mentioned the molecular mechanism of carcinogenesis, such as electrophilic fragments or fragments that can trigger electrophilic intermediates. Typical genotoxins, such as aromatic amines, are believed to cause mutations because they are highly nucleophilic and form strong DNA covalent bonds that lead to the formation of aromatic amine-DNA adducts, preventing accurate replication. Therefore, common electrophiles should be avoided unless a specific drug-protein covalent interaction is the intended target.
Based on the above fact, we propose a novel fragment-based molecular property attribution method (Fig. 2) to explore the relevance between the molecular property and the specific fragments. A total of 365 specific molecular fragments were obtained from 42 property tasks with the devised gradient attribution technique ("Step I" in Fig. 2). Mathematical statistics and scientific mechanisms demonstrated the reliability of these attribution results: about 90% of all the attribution fragments obtained by our method show potential relevance to specific properties, and the attribution fragments for randomly selected positive molecules are pretty identical to the structures in the literature on the six classical side effect tasks. Meanwhile, based on the above-constructed property-fragment relation map, we also demonstrated that the attribution fragments can measure the relationships between property tasks ("Step IV" and "Step V"),  which have about 80% coincidence degree with the inherent relationships through quantitative calculations.