Molecular property prediction is a crucial task that guides the design of new compounds, including drugs and materials. While explainable artificial intelligence methods aim to scrutinize model predictions by identifying influential molecular substructures, many existing approaches rely on masking strategies that remove either atoms or atom-level features to assess importance via fidelity metrics. These methods, however, often fail to adhere to the underlying molecular distribution and thus yield unintuitive explanations. In this work, we propose counterfactual masking, a novel framework that replaces masked substructures with chemically reasonable fragments sampled from generative models trained to complete molecular graphs. Rather than evaluating masked predictions against implausible zeroed-out baselines, we assess them relative to counterfactual molecules drawn from the data distribution. Our method offers two key benefits: (1) molecular realism that underpins robust and distribution-consistent explanations, and (2) meaningful counterfactuals that directly indicate how structural modifications may affect predicted properties. We demonstrate that counterfactual masking is well-suited for benchmarking model explainers and yields more actionable insights across multiple datasets and property prediction tasks. Our approach bridges the gap between explainability and molecular design, offering a principled and generative path toward explainable machine learning in chemistry.

DNA-Encoded Libraries (DELs) represent a transformative technology in drug discovery, facilitating the high-throughput exploration of vast chemical spaces. Despite their potential, the scarcity of publicly available DEL datasets presents a bottleneck for the advancement of machine learning methodologies in this domain. To address this gap, we introduce KinDEL, one of the largest publicly accessible DEL datasets and the first one that includes binding poses from molecular docking experiments. Focused on two kinases, Mitogen-Activated Protein Kinase 14 (MAPK14) and Discoidin Domain Receptor Tyrosine Kinase 1 (DDR1), KinDEL includes 81 million compounds, offering a rich resource for computational exploration. Additionally, we provide comprehensive biophysical assay validation data, encompassing both on-DNA and off-DNA measurements, which we use to evaluate a suite of machine learning techniques, including novel structure-based probabilistic models. We hope that our benchmark, encompassing both 2D and 3D structures, will help advance the development of machine learning models for data-driven hit identification using DELs.

Interpolating between points is a problem connected simultaneously with finding geodesics and study of generative models. In the case of geodesics, we search for the curves with the shortest length, while in the case of generative models, we typically apply linear interpolation in the latent space. However, this interpolation uses implicitly the fact that Gaussian is unimodal. Thus, the problem of interpolating in the case when the latent density is non-Gaussian is an open problem. In this article, we present a general and unified approach to interpolation, which simultaneously allows us to search for geodesics and interpolating curves in latent space in the case of arbitrary density. Our results have a strong theoretical background based on the introduced quality measure of an interpolating curve. In particular, we show that maximizing the quality measure of the curve can be equivalently understood as a search of geodesic for a certain redefinition of the Riemannian metric on the space. We provide examples in three important cases. First, we show that our approach can be easily applied to finding geodesics on manifolds. Next, we focus our attention in finding interpolations in pretrained generative models. We show that our model effectively works in the case of arbitrary density. Moreover, we can interpolate in the subset of the space consisting of data possessing a given feature. The last case is focused on finding interpolation in the space of chemical compounds.

In this work, we propose the novel Prototypical Graph Regression Self-explainable Trees (ProGReST) model, which combines prototype learning, soft decision trees, and Graph Neural Networks. In contrast to other works, our model can be used to address various challenging tasks, including compound property prediction. In ProGReST, the rationale is obtained along with prediction due to the model's built-in interpretability. Additionally, we introduce a new graph prototype projection to accelerate model training. Finally, we evaluate PRoGReST on a wide range of chemical datasets for molecular property prediction and perform in-depth analysis with chemical experts to evaluate obtained interpretations. Our method achieves competitive results against state-of- the-art methods.

Recent years have seen a surge in research on combining deep neural networks with other methods, including decision trees and graphs. There are at least three advantages of incorporating decision trees and graphs: they are easy to interpret since they are based on sequential decisions, they can make decisions faster, and they provide a hierarchy of classes. However, one of the well-known drawbacks of decision trees, as compared to decision graphs, is that decision trees cannot reuse the decision nodes. Nevertheless, decision graphs were not commonly used in deep learning due to the lack of efficient gradient-based training techniques. In this paper, we fill this gap and provide a general paradigm based on Markov processes, which allows for efficient training of the special type of decision graphs, which we call Self-Organizing Neural Graphs (SONG). We provide a theoretical study on SONG, complemented by experiments conducted on Letter, Connect4, MNIST, CIFAR, and TinyImageNet datasets, showing that our method performs on par or better than existing decision models.

Large-scale transformer-based methods are gaining popularity as a tool for predicting the properties of chemical compounds, which is of central importance to the drug discovery process. To accelerate their development and dissemination among the community, we are releasing HuggingMolecules -- an open-source library, with a simple and unified API, that provides the implementation of several state-of-the-art transformers for molecular property prediction. In addition, we add a comparison of these methods on several regression and classification datasets. HuggingMolecules package is available at: github.com/gmum/huggingmolecules.

Multitask learning helps to obtain a meaningful representation of the data, retaining a small number of parameters needed to train the model. In natural language processing, models often reach as many as a few hundred million trainable parameters, which makes adaptations to new tasks computationally infeasible. Creating shareable layers for multiple tasks allows to spare resources and often leads to better data representation. In this work, we propose a new approach to train a BERT model in a multitask setup, which we call EmBERT. To introduce information about the task, we inject task-specific embeddings to the multi-head attention layers. Our modified architecture requires a minimal number of additional parameters relative to the original BERT model (+0.025% per task) while achieving state-of-the-art results in the GLUE benchmark.

Graph neural networks have recently become a standard method for analysing chemical compounds. In the field of molecular property prediction, the emphasis is now put on designing new model architectures, and the importance of atom featurisation is oftentimes belittled. When contrasting two graph neural networks, the use of different atom features possibly leads to the incorrect attribution of the results to the network architecture. To provide a better understanding of this issue, we compare multiple atom representations for graph models and evaluate them on the prediction of free energy, solubility, and metabolic stability. To the best of our knowledge, this is the first methodological study that focuses on the relevance of atom representation to the predictive performance of graph neural networks.