Cancer is one of the leading causes of death worldwide, making it a major concern in modern society. Therefore, the proposal of strategies against this illness is of major importance and has been widely studied by the scientific community in the past decades. In this sense, these strategies mainly focus on achieving improved therapy and diagnosis, with some proposals focusing on developing chemical agents capable of both treating and diagnosing cancer through targeting a cancer-related biomarker. In the role of cancer-related targets, MALT1 shows great potential as a cancer biomarker, being related to the nuclear factor-κB (NF-κB) signaling activation, an important biochemical process that regulates immune responses and inflammatory events in the human body, and its malfunction is related to the development and survival of several types of cancer. Despite MALT1's importance as a cancer target, to the best of our knowledge, there is a lack of literature proposing chemical agents capable of treating and diagnosing cancer through this biomarker. Hence, the present work's main goal was to propose a theranostic agent for this task, for which a combination of biased MD simulations, convolutional variational autoencoders (CVAEs), and quantum calculations was used. From this, it was possible to propose and optimize a compound to achieve a good MALT1 allosteric inhibition ratio while also presenting different fluorescence in different environments, crucial for signaling purposes. From this, both compounds 1 and 2 showed a cyan enol emission to blue enol emission when compared between the water-only environment and the protein environment, a feature that may serve as a molecular signature of the signaling process induced by the compound. In addition, this result also sheds light on the major relevance of enol emission of ESIPT-based probes, a few explored characteristics in the literature, which mainly focus solely on keto emission. Now, regarding inhibition, compound 1 indicated that the use of a phenothiazine derivative was a good choice, and by making a simple modification in its phenothiazine portion to generate compound 2, the inhibition ratio more than doubled, from 29% for compound 1 to 71% for compound 2, with compound 2 being an optimized chemical agent that has promising action suitable for theranostics purposes. Hence, the presented results show a promising direction toward the development of cancer theranostics drugs targeting the MALT1 allosteric pocket and provide a powerful theoretical framework that can be extended to other biological systems.

Chemical analog design in the hit-to-lead and lead optimization stages of drug discovery relies on systematic structural modifications, often guided by medicinal chemistry intuition. Although a matched molecular pair (MMP) provides an interpretable framework to capture intuition, models trained on individual MMP instances face significant limitations, such as bias toward frequent transformations in historical data. This work introduces a novel approach to transform the concept of "how to design chemical analogs like a medicinal chemist" into a primary training objective for generative models by focusing on matched molecular pair transformations (MMPTs) as the fundamental unit of chemical modifications. This allows for a more generalizable and context-independent representation of medicinal chemistry intuition, enabling the application of the same transformation priors across different projects, regardless of the target or indication. Using a consistently curated ChEMBL-derived data set, we compared a transformation-centric foundation model (MMPT-FM) with multiple MMP-based generative formulations trained on the same underlying data. Furthermore, performance is assessed through challenging within-patent and cross-patent real-world test cases derived from drug discovery patents. The MMPT-FM model achieves comparable or improved recall metrics across all test cases, demonstrating particularly strong performance for low-frequency and previously unseen transformations. This work not only shifts the paradigm of learning and utilizes medicinal chemistry intuition in an efficient and scalable manner in the AI for drug discovery era but also establishes a significant competitive advantage by enabling the drug discovery industry to encode decades of collective medicinal chemistry knowledge─both public and proprietary─into a scalable foundation generative model that could help researchers design chemical analogs.

Generating molecules that jointly fit heterogeneous protein binding environments while retaining medicinal-chemistry plausibility remains challenging in computational dual-target design. We present PSGS-Drug, a generation-time dual-pocket framework that fuses localized token priors from the mitogen-activated protein kinase kinase 1 (MEK1) adenosine triphosphate (ATP)-site context in Protein Data Bank (PDB) entry 7PQV and the FK506-binding protein 12 (FKBP12)-FKBP12-rapamycin-binding (FRB) composite context of mechanistic target of rapamycin (mTOR) in PDB entry 3FAP, and uses contact-guided prefix initialization for rank-head exploration. The selected pair represents pathway-linked but structurally nonsymmetric intervention contexts: the druggable MEK1 ATP site and the mTOR-associated FKBP12-FRB composite interface. Their joint consideration is motivated by documented MEK/ERK-PI3K/AKT/mTOR cross-talk, compensatory resistance, and disease-specific preclinical evidence in NRAS mutant melanoma. [ Mendoza, M. C.; et al.Trends Biochem. Sci.2011, 36, 320-328.Kakadia, S.; et al.Onco Targets Ther.2018, 11, 7095-7107.Posch, C.; et al.Proc. Natl. Acad. Sci. U.S.A.2013, 110, 4015-4020.Mita, M.; et al.Invest. New Drugs2017, 35, 616-626, and.Wang, B.; et al.Oncogene2021, 40, 5590-5599]. Across five independent contact-guided runs standardized to 1889 unique valid molecules, PSGS-Drug achieved a mean summed two-context docking score (docksum) of -17.700 ± 0.242 and 29.00 ± 2.98% coverage of the stated operational dual-hit ≤-9.0 criterion; relative to independently repeated Pocket2Mol and PCMol comparators under the shared downstream protocol, it showed lower full-set docksum and higher operational dual-hit coverage after six-test Holm adjustment, and a five-seed matched A0 to A1 validation on the additional 5L2I-3ERT kinase-nuclear-receptor pair supported transfer of the fused-prior population-level effect. Docking scores, operational dual-hit labels, and residue-level contact analyses are interpreted as fixed-protocol computational prioritization signals that support candidate selection for this pathway-linked dual-context hypothesis. The biochemical and cellular activities of individual candidates remain to be tested; PSGS-Drug is therefore presented as an early stage, limitation-aware computational prioritization framework.

Designing protein sequences with favorable predicted energetic properties is an important challenge in protein inverse folding, because many existing deep learning methods are primarily trained by maximizing sequence recovery and do not explicitly incorporate energy-related preferences during generation. In this work, we propose EnerBridge-DPO, an energy-aware inverse folding framework that integrates Markov bridge sequence generation with preference optimization for protein complex design. The framework builds on the Markov bridge inverse-folding process to generate structure-compatible sequences from an informative prior sequence. It then introduces a Bridge-DPO objective that uses energy-related winner-loser preference pairs to bias the generator toward sequences favored by computational or experimental energy-related signals. In addition, we incorporate a quantitative energy-constrained loss based on mutation-induced binding free-energy changes to provide continuous ΔΔG supervision. Evaluations show that EnerBridge-DPO maintains competitive inverse-folding performance while obtaining lower predicted energy scores under selected computational scoring functions for protein complexes. On SKEMPI, EnerBridge-DPO achieves competitive ΔΔG prediction performance, with small numerical gains in several overall metrics that are not statistically conclusive under paired bootstrap analysis. These results suggest that incorporating energy-related preferences into Markov bridge inverse folding can improve computationally predicted energetic profiles, although experimental validation is required to confirm thermodynamic stability.

Accurate prediction of antibody-antigen (Ab-Ag) complexation is crucial for understanding immune responses, diagnostics, and the development of therapeutic antibodies. While molecular docking generates conformations, current scoring functions struggle to identify near-native poses, particularly for Ab-Ag interactions. We present ARID-sf (Antibody-antigen Residue Interface Docking scoring function), which combines classical force fields with structural features and protein language model embeddings through a self-attention-based neural network architecture. ARID-sf was trained on >1.5 million docking models and evaluated across four independent test sets comprising 806 cases and 700,000+ docking models. ARID-sf consistently outperforms other functions on increasingly challenging docking scenarios. Critically, ARID-sf maintains performance across diverse sequence identities and increasing conformational change required to reach the bound state, starting with unbound components, demonstrating robust generalization. ARID-sf is parallelizable and can process thousands of docking models per minute, enabling practical application in computational Ab engineering pipelines. The code, trained network, and complete pipeline are freely available at https://github.com/DSIMB/ARID-sf.git.

1,4-Dioxane is a widespread groundwater contaminant frequently co-occurring with chlorinated solvents. The group-6 propane monooxygenase (PRM) from Mycobacterium dioxanotrophicus PH-06 degrades dioxane efficiently, yet the molecular determinants underlying its broad substrate spectrum and inhibition behavior remain unresolved. Here, we combined AlphaFold2-based structure prediction, molecular docking, and alchemical free energy calculations to systematically characterize ligand binding in PH-06 PRM. The catalytic center (residues 87-265), coordinated by two histidines and four glutamates, exhibited calculated binding free energies for five substrates (C2-C4 alkanes and cyclic ethers) that significantly correlated with experimentally determined degradation rates (p < 0.05), supporting the ability of ligand binding thermodynamics to capture major substrate-recognition trends in PH-06 PRM. In addition, we identified a remote binding site (residues 329-446) approximately 30 Å from the catalytic center. Thermodynamic analysis indicates that this remote site can attract methane and ethane, potentially limiting their access to the catalytic center. Comparative binding analyses of three common chlorinated solvent inhibitors (i.e., trichloroethylene [TCE], 1,1-dichloroethylene [DCE], and 1,1,1-trichloroethane [TCA]) revealed distinct site preferences consistent with their experimentally observed inhibition modes. Noncompetitive inhibitors (DCE and TCA) displayed stronger affinity for the remote site, whereas the competitive inhibitor TCE exhibited comparable affinity for both binding regions. Sequence conservation, contact probability analysis, and Gene Ontology enrichment further suggest the structural relevance of the remote site and its possible role in ligand recognition and inhibitor selectivity. These findings demonstrate that the AlphaFold-guided free energy calculations can capture experimentally observed substrate and inhibitor trends in PH-06 PRM, while identifying a remote ligand-binding pocket that warrants further mechanistic investigation.

The rapid proliferation of per- and polyfluoroalkyl substances (PFASs) necessitates high-throughput tools to assess safety and prevent regrettable substitution. However, conventional toxicological testing is resource-intensive, while standard computational methods often lack the mechanistic transparency required for rational molecular design. This study presents a deep learning framework coupling graph neural networks (GNNs) with transfer learning to predict acute oral rat LD50 toxicity in data-scarce environments. Among the architectures evaluated, GIN with stratified transfer learning (GIN-TL-Strat) achieved the highest predictive correlation (test R2 = 0.7426). By leveraging knowledge transferred from a broad chemical space, the model demonstrates promising generalization potential to structurally diverse fluorinated compounds. GNNExplainer was integrated as an interpretability mechanism to map prediction logic back to specific atomic substructures, enabling quantitative disentanglement of the contributions of chain length, functional group composition, and structural isomerism to acute toxicity. The results demonstrate that the fluorinated carbon chain length is the primary structural determinant of toxicity in continuous-chain alkyl PFAS. Crucially, attribution magnitude does not linearly dictate toxicity impact: while fluorinated backbones and specific nitrogenous/polar functionalities drive positive toxicity shifts, heavy halogens (I, Br, and Cl) exhibit the lowest mean attribution scores and correlate with reduced predicted toxicity, highlighting a decoupling between model attention and net toxicological outcomes. Structural isomerism between straight-chain and branched PFAS was found to have no statistically meaningful effect on predicted toxicity. This work transitions computational toxicology from a passive screening tool to an active platform for the safety-by-design of next-generation fluorinated alternatives.

Accurate prediction of variants within intrinsically disordered regions (IDRs) is crucial for advancing disease diagnosis and biomedical interpretation. However, the intrinsic lack of stable structural conformations and the high sequence variability of IDRs make it challenging for existing predictors to achieve robust performance in these regions. Here, we introduce DisoPatho, a deep learning framework specifically tailored for predicting disease-associated variants in IDRs. DisoPatho features a novel mutation-centric architecture that utilizes the variant site as an anchor for feature construction and interaction. The core innovation lies in a cross-view adaptive-feature interaction mechanism, which synergistically integrates IDR-specific energy representations with embeddings from protein language models, including xTrimoPGLM and Evolutionary Scale Modeling. This strategy enables the comprehensive capture of evolutionary constraints and physicochemical patterns without requiring explicit structural descriptors, multiple-sequence alignments, or hand-crafted conservation scores. Consequently, DisoPatho exhibits enhanced discriminative power better adapted to the highly flexible nature of IDRs. Comprehensive evaluations across multiple IDR data sets demonstrate that DisoPatho substantially outperforms existing methods. In 5-fold cross-validation, it achieves average AUCs of 0.899 and 0.840, with ACCs of 0.862 and 0.860 on two data sets. Notably, on a highly confounded independent test set where phylogenetic constraints offer limited discriminative signals, DisoPatho yields a 50.2% relative improvement in MCC over AlphaMissense on their respective predictable variants, while achieving broader prediction coverage. In-depth analyses of the prediction results further confirm the effectiveness and stability of the framework in IDR-specific scenarios. The code, data sets, and predictions for DisoPatho are available for academic use at https://github.com/IBHFLab/DisoPatho.

Cocrystal formation is a widely used strategy in solid-state chemistry and pharmaceutical development to improve the solubility, stability, and bioavailability of molecules with otherwise poor physicochemical properties. Identifying viable coformer combinations remains laborious and uncertain. A key but underappreciated challenge is that experimental databases overwhelmingly report successful cocrystals, while unsuccessful attempts are rarely documented, creating biased data sets that cause many machine-learning models to make overly optimistic and unreliable predictions when applied to new chemical systems. Here, we address this limitation by reframing cocrystal prediction as a learning problem with missing negative information and by adopting a conservative strategy that focuses on identifying molecular pairs that are very unlikely to form cocrystals. We leverage multiple, independent molecular descriptions─including structural, electronic, and physicochemical characteristics─that provide complementary views for identifying reliable negatives, and use their agreement to exclude implausible combinations from large sets of untested pairs. These highly confident pseudonegative examples are then used to mitigate data imbalance and to fine-tune a pretrained graph attention network for cocrystal prediction. Across large and chemically diverse data sets, this data-centric strategy significantly improves the reliability and generalization of cocrystal prediction models compared with existing deep-learning approaches, demonstrating that carefully correcting for missing negative information is critical for making computational screening more realistic and more useful for guiding future experimental discovery.

Identifying cryptic binding sites in proteins remains a challenge in structure-based drug discovery because these sites are often not apparent in apo structures. Here, we developed and validated a novel "induce-and-identify" workflow that integrates mixed solvent molecular dynamics (MxMD) simulations with SiteMap. This approach leverages MxMD to sample protein conformations to expose hidden pockets, which are then effectively identified and ranked by SiteMap. Using a challenging data set of 65 cryptic binding sites, the developed workflow identified the cryptic binding site within the top 5 predictions in 78.5% of cases. These results suggest that the proposed MxMD + SiteMap workflow provides a robust and valuable tool for early phase drug discovery, enabling the exploration of a broader range of druggable targets by effectively inducing and identifying cryptic binding sites.

The recent discovery that inverse agonists bind to a secondary orthosteric site in PPARγ reveals unexpected structural complexity in this nuclear receptor. To differentiate between full and partial agonists, we hypothesize that partial agonists exhibit dynamic positional behavior, moving among alternative binding sites at equilibrium when saturated, while full agonists bind directly and consistently to the primary orthosteric site. Using a two-state model derived from the Boltzmann distribution and molecular docking (MODO) sampling, we developed a computational metric called the Ligand Drift Rate (LDR) Descriptor to differentiate full agonists (Emax ≥ 90%) from partial agonists (Emax ≤ 45%) of PPARγ by simulating ligand positional instability within the primary orthosteric binding pocket. We combined molecular docking and hydrogen bond fluctuation analysis across 28 PPARγ-ligand complexes (18 full agonists and 10 partial agonists). MODO sampling was performed with several algorithms, each tested on five carefully selected receptor-binding pockets from 356 crystal complexes. Hydrogen bonds between ligands and key residues (His323, His449, Tyr473) were analyzed at various hydrogen-bond displacement (HBD) thresholds (6-12 Å). The LDR was calculated as the percentage of the top 20-scoring poses that lacked hydrogen bonds. We found that adding constraints on pose diversity and allowing receptor flexibility can improve LDR's ability to distinguish full from partial agonists. Finally, MODO-sampling-based LDR calculations were conducted on 1079 ChEMBL ligands (393 full agonists and 686 partial agonists). In this validation set, LDR successfully differentiated partial from full agonists (t-test, p = 0.00043) using the genetic algorithm with the 3B1M-KRC binding pocket and a 10 Å hydrogen-bond threshold. In QSAR applications for drug discovery, we have developed a dynamics-aware molecular descriptor, LDR, that can be a key factor in quantifying partial agonism arising from small-molecule ligand drift away from the primary orthosteric site.

Early on in the emergence of virtual high-throughput screening (VHTS), it was recognized that, for validation to be robust and reliable, decoys should match actives as closely as possible in as many aspects as possible. This has given rise to several generations of validation sets that address previously reported shortcomings of earlier collections. This is an iterative and expensive method of curating validation sets that leaves ample scope for discrepancies between actives and decoys to creep in. It has previously been conjectured that in silico isomerization offers an attractive alternative for generating decoys for drug-like compounds that naturally mitigates many of these discrepancies. Here, we explore this proposition and prove the conjecture. We show that isomerization can produce molecules that have hydrogen bond acceptor, donor, rotatable bonds counts, charge, and surface area distributions that match experimental actives more closely than experimental decoys. While these are properties that receive a lot of attention in drug design, we also show that isomerization can effectively produce decoys that are positioned more closely to actives in property hyperspace than current experimental decoys, which tend to be highly dissimilar from the actives. The latter is a significant shortcoming that has thus far remained unreported and unaddressed. Additionally, we introduce the concept of pseudoisomers - decoys that have nearly identical atomic compositions to the actives - and show how they too can be used in VHTS validation at practically no cost. Herein, we build upon the methods, tools, and work of others to facilitate the generation of new and better validation sets more cheaply and efficiently, in the hope of moving the field of VHTS forward toward maturity. To that end, we make our code fully and freely available on GitHub (https://github.com/sivanovMU-Sofia/isomerization).

Equilibrist is a free, open-source platform for the quantitative analysis of chemical equilibria and kinetics. It runs in a local web browser, requires no installation, and uses a plain-text scripting language to specify reversible and irreversible reactions, polyprotic acid-base networks, and thermodynamic-cycle constraints. Five fitting modes cover species concentration, NMR shifts (fast exchange), NMR integrations (slow exchange), a mixed mode, and UV-vis/emission spectrophotometry, optimized by the L-BFGS-B and Nelder-Mead methods. A comprehensive statistical layer adds information criteria (AIC, AICc, BIC) with Akaike weights and a Fisher F-test for model selection, residual diagnostics (Durbin-Watson and Shapiro-Wilk statistics, Q-Q plot), and three uncertainty quantification families (bootstrap, jackknife, and Monte Carlo input propagation). Parameter identifiability is mapped by 1D and 2D RMSE profiles, sloppy-spectrum eigen decomposition, correlation heatmaps, t-tests, and a novel local sensitivity coefficient ξ. The combined diagnostics let the user move past R2 coefficients and Hessian standard errors to assess parameter estimates and the chemical model itself.

Balancing target-specific biological affinity with drug-likeness remains a central challenge in de novo molecular design, where existing generative models often exhibit limited controllability or reduced structural diversity. Here, we present DF-S4, a conditional molecular generation framework based on Structured State Space Models (S4), which addresses this limitation through a disentangled latent representation and hierarchical feature-wise linear modulation (FiLM). By decoupling structural and property variables and injecting conditional signals across multiple representation levels, DF-S4 enables fine-grained and stable multi-objective control beyond conventional input-level conditioning. Evaluated via a rigorous progressive multi-denominator auditing framework across three kinase targets (EGFR, BRAF, and FGFR1), DF-S4 exhibits robust target-steering performance, yielding favorable intradomain active ratios (74.2-83.9%) while maintaining high novelty (>95%) and competitive internal diversity (∼0.85). Furthermore, DF-S4 shifts the multi-objective Pareto Frontier toward regions of simultaneous high apparent affinity and drug-likeness, mitigating the distributional-trapping trade-offs commonly observed in prior approaches. Molecular docking analyses confirm the physical plausibility of generated candidates, yielding stronger binding affinities than reference inhibitors. Finally, comprehensive ablation studies and latent space dependence analyses mathematically validate that both explicit latent disentanglement and hierarchical FiLM modulation are critical for robust feature isolation, tighter property alignment, and generative stability.