arXiv subjects

Alexander Tropsha

Publications and source records attributed to Alexander Tropsha.

18 recordsLinked to original sources

arXiv2026

A Modular Agentic Framework for Synthetically Constrained Multi-Objective Hit-to-Lead Optimization

Hit-to-lead optimization requires iterative design of hit analogs across competing potency, selectivity, physicochemical, pharmacokinetic, safety, and synthetic constraints. We present SABLE (Synthetically-accessible Agentic Bayesian Ligand Exploration), an open-source framework that employs natural-language orchestration to guide chemical structure optimization. SABLE uses an LLM to interpret user-defined goals and route tasks, while specialized tools perform reaction-templated analog enumeration, physicochemical and ADMET property prediction, structure-based affinity scoring, and Bayesian optimization. The resulting workflow is a computational twin of the analytical and prioritization stages of the design-make-test-analyze cycle, providing provenance of each numerical output. Across single, and multi-objective optimization studies, SABLE enriches candidate sets for user-defined computational objectives while evaluating only a subset of the enumerated search space. Its modular architecture allows tools and characterization backends to be replaced by editing a simple config file, without modifying operational logic. SABLE provides an extensible decision-support framework for prioritizing synthetically constrained analogs in early-stage drug discovery.

cs.AI↗

arXiv2026

BASIL: Bayesian Application for Scientific Iteration and Learning

We introduce BASIL, a user-friendly desktop application for process optimization. BASIL employs a Bayesian approach, incorporating special acquisition functions that can be used to solve both single and multi-objective optimization problems. It provides a graphical interface that enables users to input their experimental parameters, optimization objectives, and legacy data. This is then used to build surrogate models, which are coupled with acquisition functions to guide and optimize a process towards a desired objective. To facilitate model building, BASIL provides a variety of predefined surrogate model templates. BASIL can be used to optimize any arbitrary experiment or process with known, user-defined input variables, optimization objectives, and defined output.

cs.LG↗

arXiv2026

Extending machine learning model for implicit solvation to free energy calculations

The implicit solvent approach offers a computationally efficient framework to model solvation effects in molecular simulations. However, its accuracy often falls short compared to explicit solvent models, limiting its use in precise thermodynamic calculations. Recent advancements in machine learning (ML) present an opportunity to overcome these limitations by leveraging neural networks to develop more precise implicit solvent potentials for diverse applications. A major drawback of current ML-based methods is their reliance on force-matching alone, which can lead to energy predictions that differ by an arbitrary constant and are therefore unsuitable for absolute free energy comparisons. Here, we introduce a novel methodology with a graph neural network (GNN)-based implicit solvent model, dubbed Lambda Solvation Neural Network (LSNN). In addition to force-matching, this network was trained to match the derivatives of alchemical variables, ensuring that solvation free energies can be meaningfully compared across chemical species. Trained on a dataset of approximately 300,000 small molecules, LSNN achieves free energy predictions with accuracy comparable to explicit-solvent alchemical simulations, while offering a computational speedup and establishing a foundational framework for future applications in drug discovery.

physics.chem-ph↗

arXiv2026

KANEL: Kolmogorov-Arnold Network Ensemble Learning Enables Early Hit Enrichment in High-Throughput Virtual Screening

Machine learning models of chemical bioactivity are increasingly used for prioritizing a small number of compounds in virtual screening libraries for experimental follow-up. In these applications, assessing model accuracy by early hit enrichment such as Positive Predicted Value (PPV) calculated for top N hits (PPV@N) is more appropriate and actionable than traditional global metrics such as AUC. We present KANEL, an ensemble workflow that combines interpretable Kolmogorov-Arnold Networks (KANs) with XGBoost, random forest, and multilayer perceptron models trained on complementary molecular representations (LillyMol descriptors, RDKit-derived descriptors, and Morgan fingerprints).

physics.chem-ph↗

arXiv2026

Reliable OOD Virtual Screening with Extrapolatory Pseudo-Label Matching

Machine learning (ML) models are increasingly deployed for virtual screening in drug discovery, where the goal is to identify novel, chemically diverse scaffolds while minimizing experimental costs. This creates a fundamental challenge: the most valuable discoveries lie in out-of-distribution (OOD) regions beyond the training data, yet ML models often degrade under distribution shift. Standard novelty-rejection strategies ensure reliability within the training domain but limit discovery by rejecting precisely the novel scaffolds most worth finding. Moreover, experimental budgets permit testing only a small fraction of nominated candidates, demanding models that produce reliable confidence estimates. We introduce EXPLOR (Extrapolatory Pseudo-Label Matching for OOD Uncertainty-Based Rejection), a framework that addresses both challenges through extrapolatory pseudo-labeling on latent-space augmentations, requiring only a single labeled training set and no access to unlabeled test compounds, mirroring the realistic conditions of prospective screening campaigns. Through a multi-headed architecture with a novel per-head matching loss, EXPLOR learns to extrapolate to OOD chemical space while producing reliable confidence estimates, with particularly strong performance in high-confidence regions, which is critical for virtual screening where only top-ranked candidates advance to experimental validation. We demonstrate state-of-the-art performance across chemical and tabular benchmarks using different molecular embeddings.

cs.LG↗

arXiv2026

Binding Free Energies without Alchemy

Absolute Binding Free Energy (ABFE) methods are among the most accurate computational techniques for predicting protein-ligand binding affinities, but their utility is limited by the need for many simulations of alchemically modified intermediate states. We propose Direct Binding Free Energy (DBFE), an end-state ABFE method in implicit solvent that requires no alchemical intermediates. DBFE outperforms OBC2 double decoupling on a host-guest benchmark and performs comparably to OBC2 MM/GBSA on a protein-ligand benchmark. Since receptor and ligand simulations can be precomputed and amortized across compounds, DBFE requires only one complex simulation per ligand compared to the many lambda windows needed for double decoupling, making it a promising candidate for virtual screening workflows. We publicly release the code for this method at https://github.com/molecularmodelinglab/dbfe.

q-bio.QM↗

arXiv2025

Look mom, no experimental data! Learning to score protein-ligand interactions from simulations

Despite recent advances in protein-ligand structure prediction, deep learning methods remain limited in their ability to accurately predict binding affinities, particularly for novel protein targets dissimilar from the training set. In contrast, physics-based binding free energy calculations offer high accuracy across chemical space but are computationally prohibitive for large-scale screening. We propose a hybrid approach that approximates the accuracy of physics-based methods by training target-specific neural networks on molecular dynamics simulations of the protein in complex with random small molecules. Our method uses force matching to learn an implicit free energy landscape of ligand binding for each target. Evaluated on six proteins, our approach achieves competitive virtual screening performance using 100-500 $μ$s of MD simulations per target. Notably, this approach achieves state-of-the-art early enrichment when using the true pose for active compounds. These results highlight the potential of physics-informed learning for virtual screening on novel targets. We publicly release the code for this paper at https://github.com/molecularmodelinglab/lfm under the MIT license.

q-bio.QM↗

arXiv2024

Explainable Enrichment-Driven GrAph Reasoner (EDGAR) for Large Knowledge Graphs with Applications in Drug Repurposing

Knowledge graphs (KGs) represent connections and relationships between real-world entities. We propose a link prediction framework for KGs named Enrichment-Driven GrAph Reasoner (EDGAR), which infers new edges by mining entity-local rules. This approach leverages enrichment analysis, a well-established statistical method used to identify mechanisms common to sets of differentially expressed genes. EDGAR's inference results are inherently explainable and rankable, with p-values indicating the statistical significance of each enrichment-based rule. We demonstrate the framework's effectiveness on a large-scale biomedical KG, ROBOKOP, focusing on drug repurposing for Alzheimer disease (AD) as a case study. Initially, we extracted 14 known drugs from the KG and identified 20 contextual biomarkers through enrichment analysis, revealing functional pathways relevant to shared drug efficacy for AD. Subsequently, using the top 1000 enrichment results, our system identified 1246 additional drug candidates for AD treatment. The top 10 candidates were validated using evidence from medical literature. EDGAR is deployed within ROBOKOP, complete with a web user interface. This is the first study to apply enrichment analysis to large graph completion and drug repurposing.

cs.IT↗

arXiv2024

An Improved Metric and Benchmark for Assessing the Performance of Virtual Screening Models

Structure-based virtual screening (SBVS) is a key workflow in computational drug discovery. SBVS models are assessed by measuring the enrichment of known active molecules over decoys in retrospective screens. However, the standard formula for enrichment cannot estimate model performance on very large libraries. Additionally, current screening benchmarks cannot easily be used with machine learning (ML) models due to data leakage. We propose an improved formula for calculating VS enrichment and introduce the BayesBind benchmarking set composed of protein targets that are structurally dissimilar to those in the BigBind training set. We assess current models on this benchmark and find that none perform appreciably better than a KNN baseline.

q-bio.QM↗

arXiv2024

Utilizing Low-Dimensional Molecular Embeddings for Rapid Chemical Similarity Search

Nearest neighbor-based similarity searching is a common task in chemistry, with notable use cases in drug discovery. Yet, some of the most commonly used approaches for this task still leverage a brute-force approach. In practice this can be computationally costly and overly time-consuming, due in part to the sheer size of modern chemical databases. Previous computational advancements for this task have generally relied on improvements to hardware or dataset-specific tricks that lack generalizability. Approaches that leverage lower-complexity searching algorithms remain relatively underexplored. However, many of these algorithms are approximate solutions and/or struggle with typical high-dimensional chemical embeddings. Here we evaluate whether a combination of low-dimensional chemical embeddings and a k-d tree data structure can achieve fast nearest neighbor queries while maintaining performance on standard chemical similarity search benchmarks. We examine different dimensionality reductions of standard chemical embeddings as well as a learned, structurally-aware embedding -- SmallSA -- for this task. With this framework, searches on over one billion chemicals execute in less than a second on a single CPU core, five orders of magnitude faster than the brute-force approach. We also demonstrate that SmallSA achieves competitive performance on chemical similarity benchmarks.

cs.IR↗

arXiv2023

SALSA: Semantically-Aware Latent Space Autoencoder

In deep learning for drug discovery, chemical data are often represented as simplified molecular-input line-entry system (SMILES) sequences which allow for straightforward implementation of natural language processing methodologies, one being the sequence-to-sequence autoencoder. However, we observe that training an autoencoder solely on SMILES is insufficient to learn molecular representations that are semantically meaningful, where semantics are defined by the structural (graph-to-graph) similarities between molecules. We demonstrate by example that autoencoders may map structurally similar molecules to distant codes, resulting in an incoherent latent space that does not respect the structural similarities between molecules. To address this shortcoming we propose Semantically-Aware Latent Space Autoencoder (SALSA), a transformer-autoencoder modified with a contrastive task, tailored specifically to learn graph-to-graph similarity between molecules. Formally, the contrastive objective is to map structurally similar molecules (separated by a single graph edit) to nearby codes in the latent space. To accomplish this, we generate a novel dataset comprised of sets of structurally similar molecules and opt for a supervised contrastive loss that is able to incorporate full sets of positive samples. We compare SALSA to its ablated counterparts, and show empirically that the composed training objective (reconstruction and contrastive task) leads to a higher quality latent space that is more 1) structurally-aware, 2) semantically continuous, and 3) property-aware.

cs.LG↗

arXiv2023

PLANTAIN: Diffusion-inspired Pose Score Minimization for Fast and Accurate Molecular Docking

Molecular docking aims to predict the 3D pose of a small molecule in a protein binding site. Traditional docking methods predict ligand poses by minimizing a physics-inspired scoring function. Recently, a diffusion model has been proposed that iteratively refines a ligand pose. We combine these two approaches by training a pose scoring function in a diffusion-inspired manner. In our method, PLANTAIN, a neural network is used to develop a very fast pose scoring function. We parameterize a simple scoring function on the fly and use L-BFGS minimization to optimize an initially random ligand pose. Using rigorous benchmarking practices, we demonstrate that our method achieves state-of-the-art performance while running ten times faster than the next-best method. We release PLANTAIN publicly and hope that it improves the utility of virtual screening workflows.

q-bio.QM↗

arXiv2020

Text Mining to Identify and Extract Novel Disease Treatments From Unstructured Datasets

Objective: We aim to learn potential novel cures for diseases from unstructured text sources. More specifically, we seek to extract drug-disease pairs of potential cures to diseases by a simple reasoning over the structure of spoken text. Materials and Methods: We use Google Cloud to transcribe podcast episodes of an NPR radio show. We then build a pipeline for systematically pre-processing the text to ensure quality input to the core classification model, which feeds to a series of post-processing steps for obtaining filtered results. Our classification model itself uses a language model pre-trained on PubMed text. The modular nature of our pipeline allows for ease of future developments in this area by substituting higher quality components at each stage of the pipeline. As a validation measure, we use ROBOKOP, an engine over a medical knowledge graph with only validated pathways, as a ground truth source for checking the existence of the proposed pairs. For the proposed pairs not found in ROBOKOP, we provide further verification using Chemotext. Results: We found 30.4% of our proposed pairs in the ROBOKOP database. For example, our model successfully identified that Omeprazole can help treat heartburn.We discuss the significance of this result, showing some examples of the proposed pairs. Discussion and Conclusion: The agreement of our results with the existing knowledge source indicates a step in the right direction. Given the plug-and-play nature of our framework, it is easy to add, remove, or modify parts to improve the model as necessary. We discuss the results showing some examples, and note that this is a potentially new line of research that has further scope to be explored. Although our approach was originally oriented on radio podcast transcripts, it is input-agnostic and could be applied to any source of textual data and to any problem of interest.

cs.IR↗

arXiv2018

Deep Reinforcement Learning for De-Novo Drug Design

We propose a novel computational strategy for de novo design of molecules with desired properties termed ReLeaSE (Reinforcement Learning for Structural Evolution). Based on deep and reinforcement learning approaches, ReLeaSE integrates two deep neural networks - generative and predictive - that are trained separately but employed jointly to generate novel targeted chemical libraries. ReLeaSE employs simple representation of molecules by their SMILES strings only. Generative models are trained with stack-augmented memory network to produce chemically feasible SMILES strings, and predictive models are derived to forecast the desired properties of the de novo generated compounds. In the first phase of the method, generative and predictive models are trained separately with a supervised learning algorithm. In the second phase, both models are trained jointly with the reinforcement learning approach to bias the generation of new chemical structures towards those with the desired physical and/or biological properties. In the proof-of-concept study, we have employed the ReLeaSE method to design chemical libraries with a bias toward structural complexity or biased toward compounds with either maximal, minimal, or specific range of physical properties such as melting point or hydrophobicity, as well as to develop novel putative inhibitors of JAK2. The approach proposed herein can find a general use for generating targeted chemical libraries of novel compounds optimized for either a single desired property or multiple properties.

cs.AI↗

arXiv2017

The AFLOW Fleet for Materials Discovery

The traditional paradigm for materials discovery has been recently expanded to incorporate substantial data driven research. With the intent to accelerate the development and the deployment of new technologies, the AFLOW Fleet for computational materials design automates high-throughput first principles calculations, and provides tools for data verification and dissemination for a broad community of users. AFLOW incorporates different computational modules to robustly determine thermodynamic stability, electronic band structures, vibrational dispersions, thermo-mechanical properties and more. The AFLOW data repository is publicly accessible online at aflow.org, with more than 1.7 million materials entries and a panoply of queryable computed properties. Tools to programmatically search and process the data, as well as to perform online machine learning predictions, are also available.

cond-mat.mtrl-sci↗

arXiv2017

AFLOW-ML: A RESTful API for machine-learning predictions of materials properties

Machine learning approaches, enabled by the emergence of comprehensive databases of materials properties, are becoming a fruitful direction for materials analysis. As a result, a plethora of models have been constructed and trained on existing data to predict properties of new systems. These powerful methods allow researchers to target studies only at interesting materials $\unicode{x2014}$ neglecting the non-synthesizable systems and those without the desired properties $\unicode{x2014}$ thus reducing the amount of resources spent on expensive computations and/or time-consuming experimental synthesis. However, using these predictive models is not always straightforward. Often, they require a panoply of technical expertise, creating barriers for general users. AFLOW-ML (AFLOW $\underline{\mathrm{M}}$achine $\underline{\mathrm{L}}$earning) overcomes the problem by streamlining the use of the machine learning methods developed within the AFLOW consortium. The framework provides an open RESTful API to directly access the continuously updated algorithms, which can be transparently integrated into any workflow to retrieve predictions of electronic, thermal and mechanical properties. These types of interconnected cloud-based applications are envisioned to be capable of further accelerating the adoption of machine learning methods into materials development.

cond-mat.mtrl-sci↗

arXiv2017

Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals

Historically, materials discovery has been driven by a laborious trial-and-error process. The growth of materials databases and emerging informatics approaches finally offer the opportunity to transform this practice into data- and knowledge-driven rational design. By using data from the AFLOW repository for high-throughput ab-initio calculations, we have generated Quantitative Materials Structure-Property Relationship (QMSPR) models to predict eight critical electronic and thermomechanical materials properties, such as the metal/insulator classification, band gap energy, bulk and shear moduli, Debye temperature, and heat capacity. The prediction accuracy obtained with these QMSPR models approaches training data for virtually any stoichiometric inorganic crystalline material. The success and universality of these models is attributed to the construction of new materials descriptors---referred to as the universal Property-Labeled Materials Fragments (PLMF). The representation requires only minimal structural input and affords straightforward model interpretation in terms of simple heuristic design rules that guide rational materials design. This study demonstrates the power of materials informatics to dramatically accelerate the search for new materials.

cond-mat.mtrl-sci↗

arXiv2012

Local kernel canonical correlation analysis with application to virtual drug screening

Drug discovery is the process of identifying compounds which have potentially meaningful biological activity. A major challenge that arises is that the number of compounds to search over can be quite large, sometimes numbering in the millions, making experimental testing intractable. For this reason computational methods are employed to filter out those compounds which do not exhibit strong biological activity. This filtering step, also called virtual screening reduces the search space, allowing for the remaining compounds to be experimentally tested. In this paper we propose several novel approaches to the problem of virtual screening based on Canonical Correlation Analysis (CCA) and on a kernel-based extension. Spectral learning ideas motivate our proposed new method called Indefinite Kernel CCA (IKCCA). We show the strong performance of this approach both for a toy problem as well as using real world data with dramatic improvements in predictive accuracy of virtual screening over an existing methodology.

stat.AP↗