Active Learning-Guided Seq2Seq Variational Autoencoder for Multi-target Inhibitor Generation

Simultaneously optimizing molecules against multiple therapeutic targets remains a profound challenge in drug discovery, particularly due to sparse rewards and conflicting design constraints. We propose a structured active learning (AL) paradigm integrating a sequence-to-sequence (Seq2Seq) variational autoencoder (VAE) into iterative loops designed to balance chemical diversity, molecular quality, and multi-target affinity. Our method alternates between expanding chemically feasible regions of latent space and progressively constraining molecules based on increasingly stringent multi-target docking thresholds. In a proof-of-concept study targeting three related coronavirus main proteases (SARS-CoV-2, SARS-CoV, MERS-CoV), our approach efficiently generated a structurally diverse set of pan-inhibitor candidates. We demonstrate that careful timing and strategic placement of chemical filters within this active learning pipeline markedly enhance exploration of beneficial chemical space, transforming the sparse-reward, multi-objective drug design problem into an accessible computational task. Our framework thus provides a generalizable roadmap for efficiently navigating complex polypharmacological landscapes.

sHGCN: Simplified hyperbolic graph convolutional neural networks

Hyperbolic geometry has emerged as a powerful tool for modeling complex, structured data, particularly where hierarchical or tree-like relationships are present. By enabling embeddings with lower distortion, hyperbolic neural networks offer promising alternatives to Euclidean-based models for capturing intricate data structures. Despite these advantages, they often face performance challenges, particularly in computational efficiency and tasks requiring high precision. In this work, we address these limitations by simplifying key operations within hyperbolic neural networks, achieving notable improvements in both runtime and performance. Our findings demonstrate that streamlined hyperbolic operations can lead to substantial gains in computational speed and predictive accuracy, making hyperbolic neural networks a more viable choice for a broader range of applications.

Addressing Model Overcomplexity in Drug-Drug Interaction Prediction With Molecular Fingerprints

Accurately predicting drug-drug interactions (DDIs) is crucial for pharmaceutical research and clinical safety. Recent deep learning models often suffer from high computational costs and limited generalization across datasets. In this study, we investigate a simpler yet effective approach using molecular representations such as Morgan fingerprints (MFPS), graph-based embeddings from graph convolutional networks (GCNs), and transformer-derived embeddings from MoLFormer integrated into a straightforward neural network. We benchmark our implementation on DrugBank DDI splits and a drug-drug affinity (DDA) dataset from the Food and Drug Administration. MFPS along with MoLFormer and GCN representations achieve competitive performance across tasks, even in the more challenging leak-proof split, highlighting the sufficiency of simple molecular representations. Moreover, we are able to identify key molecular motifs and structural patterns relevant to drug interactions via gradient-based analyses using the representations under study. Despite these results, dataset limitations such as insufficient chemical diversity, limited dataset size, and inconsistent labeling impact robust evaluation and challenge the need for more complex approaches. Our work provides a meaningful baseline and emphasizes the need for better dataset curation and progressive complexity scaling.

ICML Topological Deep Learning Challenge 2024: Beyond the Graph Domain

This paper describes the 2nd edition of the ICML Topological Deep Learning Challenge that was hosted within the ICML 2024 ELLIS Workshop on Geometry-grounded Representation Learning and Generative Modeling (GRaM). The challenge focused on the problem of representing data in different discrete topological domains in order to bridge the gap between Topological Deep Learning (TDL) and other types of structured datasets (e.g. point clouds, graphs). Specifically, participants were asked to design and implement topological liftings, i.e. mappings between different data structures and topological domains --like hypergraphs, or simplicial/cell/combinatorial complexes. The challenge received 52 submissions satisfying all the requirements. This paper introduces the main scope of the challenge, and summarizes the main results and findings.

Scoreformer: A Surrogate Model For Large-Scale Prediction of Docking Scores

In this study, we present ScoreFormer, a novel graph transformer model designed to accurately predict molecular docking scores, thereby optimizing high-throughput virtual screening (HTVS) in drug discovery. The architecture integrates Principal Neighborhood Aggregation (PNA) and Learnable Random Walk Positional Encodings (LRWPE), enhancing the model's ability to understand complex molecular structures and their relationship with their respective docking scores. This approach significantly surpasses traditional HTVS methods and recent Graph Neural Network (GNN) models in both recovery and efficiency due to a wider coverage of the chemical space and enhanced performance. Our results demonstrate that ScoreFormer achieves competitive performance in docking score prediction and offers a substantial 1.65-fold reduction in inference time compared to existing models. We evaluated ScoreFormer across multiple datasets under various conditions, confirming its robustness and reliability in identifying potential drug candidates rapidly.

Are Protein Language Models Compute Optimal?

While protein language models (pLMs) have transformed biological research, the scaling laws governing their improvement remain underexplored. By adapting methodologies from NLP scaling laws, we investigated the optimal ratio between model parameters and training tokens within a fixed compute budget. Our study reveals that pLM sizes scale sublinearly with compute budget, showing diminishing returns in performance as model size increases, and we identify a performance plateau in training loss comparable to the one found in relevant works in the field. Our findings suggest that widely-used pLMs might not be compute-optimal, indicating that larger models could achieve convergence more efficiently. Training a 35M model on a reduced token set, we attained perplexity results comparable to larger models like ESM-2 (15B) and xTrimoPGLM (100B) with a single dataset pass. This work paves the way towards more compute-efficient pLMs, democratizing their training and practical application in computational biology.

GeoDirDock: Guiding Docking Along Geodesic Paths

This work introduces GeoDirDock (GDD), a novel approach to molecular docking that enhances the accuracy and physical plausibility of ligand docking predictions. GDD guides the denoising process of a diffusion model along geodesic paths within multiple spaces representing translational, rotational, and torsional degrees of freedom. Our method leverages expert knowledge to direct the generative modeling process, specifically targeting desired protein-ligand interaction regions. We demonstrate that GDD significantly outperforms existing blind docking methods in terms of RMSD accuracy and physicochemical pose realism. Our results indicate that incorporating domain expertise into the diffusion process leads to more biologically relevant docking predictions. Additionally, we explore the potential of GDD for lead optimization in drug discovery through angle transfer in maximal common substructure (MCS) docking, showcasing its capability to predict ligand orientations for chemically similar compounds accurately.

Optimizing Drug Design by Merging Generative AI With Active Learning Frameworks

Traditional drug discovery programs are being transformed by the advent of machine learning methods. Among these, Generative AI methods (GM) have gained attention due to their ability to design new molecules and enhance specific properties of existing ones. However, current GM methods have limitations, such as low affinity towards the target, unknown ADME/PK properties, or the lack of synthetic tractability. To improve the applicability domain of GM methods, we have developed a workflow based on a variational autoencoder coupled with active learning steps. The designed GM workflow iteratively learns from molecular metrics, including drug likeliness, synthesizability, similarity, and docking scores. In addition, we also included a hierarchical set of criteria based on advanced molecular modeling simulations during a final selection step. We tested our GM workflow on two model systems, CDK2 and KRAS. In both cases, our model generated chemically viable molecules with a high predicted affinity toward the targets. Particularly, the proportion of high-affinity molecules inferred by our GM workflow was significantly greater than that in the training data. Notably, we also uncovered novel scaffolds significantly dissimilar to those known for each target. These results highlight the potential of our GM workflow to explore novel chemical space for specific targets, thereby opening up new possibilities for drug discovery endeavors.