Papers

Protein-conditioned 3D molecule generation is a central challenge in structure-based drug design, requiring a balance between pocket compatibility, molecular properties, and physical geometry. We propose PocketVE, a protein-pocket-conditioned variance-exploding (VE) diffusion framework that couples stable coordinate denoising with inference-time property guidance. Specifically, PocketVE combines an EDM-style training and sampling setup for 3D denoising, classifier-free guidance for multi-property steering, and adaptive protein perturbation as a training-time pocket regularizer.On the CrossDocked2020 benchmark under GenBench3D, PocketVE improves Valid$_{3\text{D}}$ from 58.6 to 80.6 and reduces strain energy from 457.4 to 127.9 relative to its guided TAGMol architectural parent; relative to TargetDiff, it attains comparable Valid$_{3\text{D}}$ with lower strain energy (127.9 vs.\ 306.0), while retaining competitive docking and molecular-property scores under moderate guidance. A guidance-scale study shows that moderate guidance gives a favorable balance between target-related objectives and geometric quality, whereas stronger guidance can degrade geometry and distributional fidelity. Pocket-permutation and PoseCheck diagnostics further support pocket-specific spatial compatibility with reduced steric conflicts. Overall, the results suggest that geometric stability and inference-time property guidance should be considered as coupled design objectives.

Physical equations in protein modeling appear to have been replaced by generative models trained directly on structure data. By learning a mapping from noise to data, sampling de novo protein structures has become much more efficient. However, such models can also learn non-physical features and break down with out-of-distribution settings which are typical in protein design campaigns. In this review, we highlight where the physics persists in protein generative modeling pipelines and the issues that linger when physically relevant components of a macromolecular system are left unmodeled. We present a perspective that respecting the underlying physics of macromolecular systems, increasingly through learned representations that are physically grounded and updating generative models with experimental data, is foundational to generative modeling for functional protein design.

Alzheimer's disease is a progressive neurodegenerative disorder characterized by memory loss, cognitive decline, and behavioral changes, primarily affecting the elderly. Current treatments focus on symptom management as no therapies effectively halt or reverse disease progression. Newer therapies targeting BACE1, a key enzyme in amyloid plaque formation, have shown promise in clinical trials, though they have been limited by side effects and insufficient efficacy in slowing cognitive decline. This is the first study where multi-ligand simultaneous docking (MLSD) was employed to identify potential synergistic inhibitor combinations from among thousands of small molecules that could yield better results than the current phase-III inhibitors of BACE1. The recent phase III drugs such as Atabecestat, Elenbecestat, Lanabecestat, and Verubecestat were considered to be standards for comparison in this study. A library of small molecules with known IC50 values against BACE1 was filtered for flagging Pan-Assay Interference (PAINS) and "Brenk" compounds. Single-ligand docking revealed individual ligand interactions with the protein, forming the basis for creating ligand pairs tested in MLSD. Among these combinations, CHEMBL4078427 and CHEMBL3656158, CHEMBL4078427 and CHEMBL3695732, Verubecestat and CHEMBL3656158, and CHEMBL4078427 and Lanabecestat demonstrated excellent binding affinity of -19.90 kcal/mol, -18.45 kcal/mol, -18.07 kcal/mol, and -17.67 kcal/mol with the protein, which is significantly greater than those of phase-III inhibitors, along with inter-ligand interactions indicative of a synergistic effect. These findings underscore the transformative potential of MLSD in identifying synergistic compound interactions, paving the way for novel combination therapies in the treatment of Alzheimer's disease.

Isotopic fractionation factors for oxygen and silicon in selected silicates (quartz, enstatite, forsterite, lizardite, kaolinite) have been calculated using first-principles methods. Good agreement between theory and experiment is obtained in the case of oxygen. In the case of silicon, agreement and differences with existing estimates of equilibrium fractionation factors are discussed. The relationships between silicon fractionation factors and oxygen fractionation factors, silicate polymerization degree and chemical composition is studied. The previously stated relationship with the polymerization degree of the mineral is not confirmed. Nevertheless, our calculation suggests that silicon fractionation depends on the cationic content of the mineral, in a way similar to oxygen. Oxygen fractionation properties could thus provide some insights on silicon fractionation behavior.

Proteins are fundamental to biological processes, with their function determined by the complex interplay between the amino acid sequence and the three-dimensional structure. Developing generative models capable of understanding this intrinsically multi-modal relationship is crucial for fields like drug discovery and protein engineering. Existing models often rely on a multi-stage training process where autoencoders that tokenize data into latent representations are trained in a first stage. Secondly, a generative model is trained on the latent representation of the autoencoder(s), i.e., generative modeling in a latent space. We hypothesize that this multi-stage training is not necessary to obtain performant co-design models and thus present SimpleDesign, an effective multi-modal protein design model trained directly in the data space. SimpleDesign leverages a single-stage end-to-end objective that combines discrete cross-entropy for sequences and a regression objective for structures. In order to effectively model the difference in sequence and structure modalities, we develop a Mixture-of-Transformer architecture that allows modality-specific processing while keeping global self-attention over both modalities. We train SimpleDesign on over 2M sequence-structure pairs achieving strong performance across co-design and unconditional sequence/structure generation benchmarks.

Predicting drug–target binding affinity (DTA) requires models to distinguish subtle chemical and structural determinants underlying molecular recognition. Although recent approaches increasingly incorporate richer drug and protein information, such information may be compressed, homogenized or discretized during representation construction, causing affinity-relevant distinctions to be lost before interaction modelling. We hypothesized that this representation-stage information loss constitutes an upstream bottleneck that cannot be reliably overcome by increasingly complex interaction predictors. To test this hypothesis, we developed ReGeoDTA, a representation-preserving framework that maintains affinity-relevant chemical heterogeneity in molecular representations and continuous geometric relationships in protein structures. Across three benchmark datasets, ReGeoDTA consistently improved affinity prediction, and the proposed representation-preserving strategies retained their benefits across diverse DTA architectures. Controlled representation degradation progressively reduced predictive performance, whereas increasing downstream predictor complexity failed to recover information lost during representation construction. These findings identify representation fidelity as an upstream design principle for accurate and generalizable drug–target affinity prediction, with potential implications for computational compound prioritization.

T-cell immunity acts as a major defense system against controlling viral infections in vertebrates. During viral entry, innate immune cells degrade the viral proteins (antigens) and present them on their surface via Major Histocompatibility (MHC) proteins. T-cell receptors (TCRs) recognize these antigens/peptides presented by MHC (pMHC), initiating a T-cell mediated immune response. Despite its significance, the mechanism by which pMHC-TCR binding triggers T-cell activation remains unclear. In this study, we employed an integrative computational approach combining Bioinformatics, Molecular Dynamics (MD) simulations, and Machine Learning (ML) to identify viral epitopes as potential vaccine candidates. We performed large-scale all-atom and coarse-grained MD simulations on MHC-peptide-TCR complexes embedded into dendritic and T-cells, for which experimental immunogenicity data is available. One hundred fifty such systems are simulated for 1 {\mu}s each to capture the conformational and dynamical changes that underlie T-cell activation. Our ML model (DynamiT), trained on simulation-derived structural and dynamical features extracted from 2500 time points, revealed key determinants responsible for T-cell activation with an accuracy of 73.3%. Notably, we have identified the bending of the TCR transmembrane region, major dynamic motions of the TCR{\alpha} constant region and the buried surface area at the pMHC and TCR interface as critical factors influencing immune response initiation. Our approach unravels the mechanism of T-cell mediated immune response and helps ML-guided screening of viral epitopes for vaccine development.

How 3D genome architecture contributes to transcriptional specificity across neuronal cell types remains unclear. Here, we used multiplexed chromatin tracing to map chromatin architecture and cell identity at single-cell resolution in the adult Drosophila brain. We found that enhancer-promoter (E-P) proximity was increased in transcriptionally active compared with inactive neurons. Analysis of single traces revealed the existence of distinct proximal and distal E-P states, with active neurons enriched in the proximal state. However, this relationship broke down across active neuronal subtypes, where neither E-P proximity nor chromatin accessibility predicted transcriptional output. Thus, 3D genome organization distinguishes transcriptionally competent from inactive neuronal states without quantitatively specifying transcriptional output. Our findings support a model in which E-P proximity establishes a permissive structural state, while additional cell-type-specific regulatory mechanisms tune transcriptional output.

The last five-plus years have seen many protein engineering disciplines transformed by advances in machine learning (ML), but the same cannot be said for directed evolution. Reflecting on a previously co-authored perspective, I discuss why I believe this to be the case, arguing that a disconnect between the goals of machine-learning-assisted directed evolution (MLDE) researchers–"identify an optimal protein"–and the goals of directed evolution more broadly–"identify a sufficient protein given time and resource constraints"–is a principal culprit. As an example, I highlight how nearly all current MLDE methods neglect to account for the cost of DNA synthesis, resulting in strategies that have limited practical applicability regardless of the underlying models' capabilities. I close by discussing recent works that are exceptions to this overarching trend, and emphasize that the last five years of efforts in ML-assisted protein engineering and the prescribed reframe of MLDE objectives need not be mutually exclusive.

Activity-cliff ranking remains difficult because local structural changes can cause large activity differences, while high-quality data that resolve the underlying mechanisms remain limited. To use available activity labels more effectively, we combine absolute-activity regression with ranking-consistency learning. CliffRank trains two parallel predictors with mean squared error, a thresholded listwise loss, and Pairwise Preference Consistency (PPC), which aligns relative ordering in the preference-probability space. On three antimicrobial peptide datasets, CliffRank with ESM2-t12 achieved the highest mean Spearman correlation of 0.5393 and mean Recall@50 of 21.4, although the leading method varied across individual datasets. On three small-molecule datasets, CliffRank with PNA, where PPC was activated after 120 epochs, achieved the highest mean Spearman correlation of 0.6890, while its mean Recall@50 of 30.4 matched that of ACANet-PNA. The PPC results also define its practical limits. Asymmetric initialization improved the MolCLR-GIN averages but did not improve every target. For PNA without pretrained weights, delayed PPC improved selected metrics, but no schedule was best for both mean Spearman correlation and mean Recall@50. Future work should evaluate more targets and antimicrobial peptide systems, develop adaptive PPC schedules, and incorporate protein or membrane context when available.

RNA molecules perform diverse biological functions by dynamically exploring multiple conformational states rather than adopting a single static structure. Capturing these ensembles is a challenge in molecular biology. Recent advances in cryoEM are now transforming this landscape by enabling the visualization of RNA molecules across a broad spectrum of functionally relevant conformations at near atomic resolution. Here, we examine how cryoEM is reshaping RNA structural biology changing focus from the analysis of static structures to dynamic conformational landscapes. Through 8 representative case studies we illustrate how cryoEM has revealed previously inaccessible mechanisms of RNA motion, including folding processes, ligand-dependent switching, and cooperative assembly. We specifically discuss emerging experimental and computational approaches that address and overcome the challenges associated with studying dynamic RNAs, particularly in construct design, sample preparation, vitrification, and data analysis. These novel methods resolve conformational variability and enable the reconstruction of discrete and continuous RNA conformational landscapes from cryoEM data, highlighting how structural heterogeneity can be harnessed to extract functional insights. Looking forward, the integration of cryoEM with complementary biophysical techniques and time resolved methodologies promises to bridge structural and temporal resolution, to routinely derive experimental molecular movies of RNA in action. These advances will not only deepen our understanding of RNA biology but also provide new opportunities for RNA targeted therapeutics and the rational design of dynamic RNA-based nanodevices. By connecting structural snapshots into coherent dynamic models, cryoEM is establishing a framework for quantitative descriptions of RNA energy landscapes and their functional roles.

Token aggregation converts token-level representations into fixed-dimensional sample representations, but most pooling methods operate only in the original token space. We introduce Frequency-Domain Latent-attention Gated Pooling (FLaG), a plug-in aggregation module that re-expresses encoder outputs in the Fourier domain before final pooling. FLaG represents the nonredundant rFFT spectrum through concatenated real and imaginary components, summarizes spectral tokens with learnable latent queries, derives a sample-conditioned channel gate, and reconstructs modulated token representations for downstream aggregation. We evaluate the same architecture across ESM2-based antimicrobial peptide (AMP) activity prediction, ResNet18 image classification on CIFAR-10 and CIFAR-100, and three RoBERTa-based language tasks. FLaG achieves the best macro-averaged Spearman correlation coefficient, RMSE, and Recall@50 across four AMP backbone-species settings and the highest top-1 accuracy on CIFAR 10. It also achieves the best mean results on five of seven language metrics, although mean pooling remains strongest on STSBenchmark. AMP-side mechanistic analyses reveal low-frequency prediction sensitivity across most encoder layers, with increased relative high-frequency sensitivity in the final layer, and pronounced peptide-specific positional responses. The residual gate broadly amplifies spectral channels while preserving the low-frequency-dominated energy profile, whereas latent cross-attention exhibits sample- and species-specific spectral allocation. Overall, FLaG provides a transferable frequency-domain aggregation bias across protein, visual, and textual representations, with benefits that depend on the backbone and downstream task. Supplementary materials, source code, and data are available at https://www.healthinformaticslab.org/supp/ and https://github.com/Kewei2023/AMPCliff/tree/FLaG.

Antibody-specific language models pretrained via masked language modeling (MLM) learn representations that are critical for downstream sequence design and property prediction tasks. Yet, the corruption process itself is rarely leveraged as a source of inductive bias during pretraining. While preferentially masking complementarity-determining regions (CDRs) improves binding-related predictions, antibodies possess diverse biological priors over a variety of functions. Herein, we introduce function-aware masking, a family of pretraining algorithms that align mask placement with specific functional priors (e.g., from IMGT annotations or structure predictions) to shape the learned representation space. We show that these specialist masking strategies significantly improve performance on their respective objectives, yielding up to a 14% gain on structure-related tasks and up to a 5.9x improvement on CDR-related tasks. To further improve performance across multiple functional axes, we develop hybrid masking strategies that integrate multiple priors, balancing reconstruction over binding, structural, and biophysical objectives. Our results demonstrate that informed mask placement provides a parameter-free mechanism for imposing functional inductive biases in antibody language model training.

Antimicrobial peptides (AMPs) often act against multiple pathogen classes, making multi-label activity prediction a more realistic screening target than binary antimicrobial classification. The ESCAPE benchmark formalizes this setting, but leading approaches typically rely on multimodal, structure-conditioned deep models that are costly to train and tune. We show that a simple, sequence-only pipeline can match and surpass these methods by combining 330 interpretable sequence descriptors with TabPFN, a tabular foundation model that performs in-context prediction in a single forward pass without gradient-based training or hyperparameter search. On ESCAPE (82,359 peptides; five labels), a label-powerset TabPFN model achieves mAP-5 = 77.8%, improving on the previously best reported 72.1%. A probabilistic classifier chain is the first method to match or exceed the best published average precision on each of the five labels simultaneously. The gains persist under the prior state-of-the-art single-fold training protocol, indicating they are not a training-set-size artefact, and are largest for remote homologues (+11.2 points below 30% sequence identity). Ablations further show that predicted structure is unnecessary at inference and that performance is not driven by any single descriptor family: ten global physicochemical scalars recover 91% of full-feature performance. Finally, explicitly modelling label dependence yields targeted benefits for scarce activities and supports ranking which activity to assay next from partial positive evidence.

Molecular self-supervised learning uses chemical structures to guide which molecular embeddings should be similar. We study whether explicitly encoding a molecule's Bemis-Murcko scaffold and using it to supervise the molecular embedding changes what the model learns. We further test whether this effect depends on the embedding geometry by comparing Euclidean and Lorentz contrastive objectives. Across two augmentation strengths, scaffold-supervised models consistently organize molecules according to both identical and structurally related scaffolds. The resulting embeddings also improve molecular property prediction on several tasks, while the exact gains depend on the predicted property. The effect of scaffold supervision on molecular organization is stronger under Lorentz objectives, but neither geometry provides a consistent overall advantage. These results show that explicitly teaching the relation between a molecule and its structural core can reliably shape the organization of molecular embedding space, while the extent of usefulness of this organization remains task dependent.

The enumeration of chemical structures traditionally relies on graph- and group-theoretic techniques, including Pólya theory, in order to account for stereochemical symmetries. These methods require bespoke derivations and methods for each molecular family of interest, and quickly become very intricate for nontrivial classes. In this work, we demonstrate that analytic combinatorics provides a unifying, highly extensible, and relatively simple framework for enumeration problems. Using the symbolic method, we show that classical counting problems, such as the enumeration of acyclic alkanes and other hydrocarbon families, can be naturally solved via concise combinatorial specifications of the class of interest. We first demonstrate the simplicity of this approach by replicating existing results in this framework, requiring significantly less work than previously necessary, and then extend these ideas to more complex problems, counting broader classes of molecules accounting for both tetrahedral and E/Z stereoisomerism, counting the distribution of stereogenic units, and enumerating achiral and meso compounds. All results are made reproducible through CombOL, our open-source software package which automates the translation of combinatorial specifications into generating functions using the symbolic method, and performs both univariate and multivariate enumeration.

Cryo-electron microscopy (cryo-EM) determines the structures of proteins and macromolecular assemblies at near-atomic resolution, and the final 3D reconstruction depends on extracting a clean particle stack from noisy micrographs. This extraction decomposes into three sub-tasks, namely particle picking, contamination removal, and 2D class selection. Each of them, however, is trained and evaluated in isolation, and none is optimized for the reconstruction. We instead integrate the three sub-tasks into a single pipeline posed against downstream reconstruction quality. We instantiate the pipeline with a state-of-the-art component for each sub-task, CryoTransformer picking permissively, MicrographCleaner masking contamination, and CryoSift selecting 2D classes by a continuous quality score, and close the loop with a fine-tuning step that returns the surviving particles to the picker. The pipeline achieves a better 3D resolution than every picker we compare. We also show that the best 2D F1 is not the best resolution, so particle selection is better treated as one reconstruction-aware pipeline judged by the map it delivers.

Polymer-functionalised mesopores are an emerging technology for colloid separation, sensing and delivery. Their potential is strikingly illustrated in living cells, where nuclear pore complexes (NPCs) control biocolloid transport between the nucleus and the cytosol. Even colloids much smaller than the biopolymer-filled NPC channel are effectively blocked, but some larger colloids with distinct surface features rapidly permeate. Simplistically, one may expect any polymer filling to obstruct and slow down colloid transport. We demonstrate how a polymer filling that attracts colloids and extends beyond the mesopore, thus maximizing colloid capture, can instead increase permeation compared to a bare pore. We also define how polymer-filled mesopores can effectively gate colloids according to their size and surface features. Our findings provide a basic physical explanation for the exquisite permselectivity of NPCs, and a rational design strategy for novel mesopore-based separation, sensing, catalysis and drug delivery devices with enhanced performance features.

The evolutionary fate of proteins is driven by both folding stability and biological function, dual constraints that often conflict, creating frustration and imposing functional costs beyond stability. These costs can be captured by a "dark energy": the difference between the evolutionary energy of protein sequences and their physical folding energy. Recent advances in deep mutational scanning, protein language models, and inverse-folding models have enabled the quantification of dark energy across the protein universe. We review the computational and experimental approaches that disentangle folding and function at scale, revealing a dark energy component and providing new insights into how biological information flows from sequence to structure to function and back to sequence.

High-throughput drug screening relies on low-cost primary assays to prioritize compounds for more expensive dose-response profiling, where potency is ultimately quantified. Current screening strategies largely focus on identifying compounds that will confirm biological activity on follow-up, implicitly assuming that confirmed activity will also yield a usable potency estimate. However, confirmed biological activity in screening does not necessarily translate into a quantifiable potency, because active compounds can still fail to produce a reportable dose-response estimate. We therefore present a framework for modeling quantifiability, whether follow-up testing will yield a usable potency estimate, as a distinct triage objective from biological activity. Quantifiability was strongly predictable from the preceding low-cost screen, with most predictive information arising from the observed screening features rather than molecular structure. Response-based predictors remained robust on previously unseen chemical scaffolds and generalized across held-out assay-mechanism families, while the probability of successful quantification varied strongly with response amplitude and assay context. These findings establish experimental measurability, distinct from biological activity, as a predictable property of screening outcomes and show that quantifiability-aware triage can improve the allocation of costly dose-response profiling capacity.

We describe a systematic approach for spawning and aggregating multi-class cryo-EM reconstruction jobs. This approach formalizes standard ad hoc strategies of iterative classification and filtering typically used by practitioners to sort impure, heterogeneous samples. To our knowledge, this is the first method that can successfully perform ab initio reconstruction on datasets containing dozens of distinct species. We obtain 97% accuracy on ab initio reconstruction of a 45-class subset of Tomotwin-100, 75% accuracy on the full Tomotwin-100 dataset, and demonstrate recovery of ribosomal assembly states from an unfiltered experimental cryo-EM dataset. Our approach's capability scales with compute and lays the foundation for automated cryo-EM workflows in modern experimental settings.

RNA inverse folding asks for an RNA sequence whose prescribed secondary structure is the unique maximum-base-pair compatible fold. In the four-letter Watson-Crick model (A-U and C-G pairs only, no pseudoknots, and zero minimum base-pair span), Hales et al. introduced a separated-coloring certificate and an even-odd device, while Boury et al. generalized this to modulo-$m$ separability, gave an $O(n 2^m)$ decision algorithm, and guaranteed designability when every helix has length at least 3. We prove that the guarantee still holds when a motif-free target has at most two maximal helices of length 2, no maximal helix of length 1, and all remaining helices of length at least 3. The proof builds on Boury et al.'s local helix-coloring transfers and adds a global counting argument showing that the demands created by at most two short helices can always be coordinated. This is a structural success guarantee for the existing modulo-2 algorithm, not a new general decision capability. The resulting coloring yields an explicit sequence whose every distinct compatible noncrossing fold has fewer pairs. No claim is made for nearest-neighbor thermodynamic energy models. The theorem and supporting lemmas are formalized in Lean 4 against pinned Mathlib and reproduced from a frozen public artifact; the kernel-reported axiom set is $\{\mathrm{propext},\mathrm{Classical.choice},\mathrm{Quot.sound}\}$. The work was developed with foundational generative-AI assistance under the author's direction and has not yet received independent human expert review.

Messenger RNA (mRNA)-based therapeutics have emerged as a powerful platform for vaccines, protein replacement therapies, and cancer immunotherapy. A critical bottleneck in mRNA development is manufacturing large quantities of RNA economically, as measured by RNA yield emerging from an in vitro transcription (IVT) reaction. However, how promoter-adjacent DNA sequences influence RNA yield remains poorly characterized. Here, we present an integrated deep learning framework that leverages massively parallel next-generation sequencing (NGS) assays to measure RNA yield across large sequence spaces. A library of 10^5 randomized oligonucleotide sequences was designed to systematically explore sequence diversity within a defined structural context. DNA and RNA abundances were quantified in parallel using Illumina sequencing, enabling high-resolution measurement of sequence-to-yield relationships at scale. Sequences were one-hot encoded and used to train deep learning models, using a convolutional neural network architecture. The model achieved a Pearson correlation of 0.94 between predicted and experimentally measured RNA yield on a held-out test set, demonstrating strong generalization across diverse sequence contexts. Importantly, the trained model can be deployed in a production environment to score and rank novel RNA sequence designs by predicted IVT yield, enabling cost-effective, pre-experimental prioritization of the most manufacturable candidates. This framework establishes a scalable, data-driven approach to DNA and RNA sequence optimization, with broad applicability to vaccine antigen design, therapeutic protein delivery, and synthetic biology. By integrating high-throughput experimentation with advanced deep learning modeling, it significantly reduces screening costs and accelerates RNA engineering cycle times.

Protein function is governed by conformational ensembles, which can be viewed as high-dimensional probability distributions over molecular conformations. Yet the statistical organization of these distributions is often represented only implicitly, either through collections of simulation trajectories or within high-capacity generative models. Here, we introduce PHASE (Protein Hamiltonians for Sampling of Ensembles), a system-specific framework that converts atomistic conformational ensembles into an explicit and interpretable statistical model. Applied to ten conformational ensembles derived from approximately 37$\mu$s of atomistic simulations of the adenosine A2A receptor, Hamiltonians containing only local residue couplings within 6$\mathring{A}$ reproduce residue-wise and pairwise microstate statistics, including correlations between residues that are not directly coupled in the model. Moreover, independently fitted inactive and active reference Hamiltonians define an endpoint preference coordinate that organizes newly sampled ligand-, effector- and conformation-dependent ensembles along the A2A activation landscape without receiving these biochemical labels as model inputs. Finally, a cluster-conditioned all-atom reconstruction model preserves the prescribed residue microstate patterns of newly sampled configurations, closing the coarse-graining-sampling-backmapping cycle. The resulting discrete representation additionally admits direct QUBO encoding, enabling classical annealing and providing a route toward future quantum-annealing implementations. PHASE therefore provides a protein-general procedure for constructing compact, interpretable and atomistically realizable statistical models of protein conformational ensembles.

Temperature-sensitive transient receptor potential (TRP) channels play a significant role in intercellular signalling in response to membrane depolarisation and caclium influx. TRPM8 ion channels have been investigated as the main cold receptors (neurosensors), but they can also be activated by voltage, $Ca^{2+}$ store depletion, and certain lipids and other ligands that induce cold sensation (such as menthol and icilin). Despite recent progress in studying these channels at the single-channel level, the mechanisms and time course of their activation remain underexplored. We propose an approach to single-ion channel analysis that elucidates the presence of correlations between dwell-times of adjacent open and closed states. One of the major benefits of this approach is that it can serve as an express test of channel activity properties owing to its simplicity and fast numerical realization. The idea of our analysis is to study the difference between the distribution function derived from the given trace (simulated or experimentally recorded) and the predicted distributions of simple models without correlation. In this way, we compared the distribution function of the difference between the durations of the adjacent open and closed states of the channel, as well as that of a similar sequence of open-closed-open-closed states.

Vibrational spectroscopy reports on molecular structure with chemical-bond specificity, but in biological systems the vibrational signals of a target chromophore are typically buried under contributions from the surrounding matrix. Resonance Raman (RR) spectroscopy addresses this problem by matching the excitation wavelength to an electronic transition of the chromophore of interest, which increases Raman cross sections by up to six orders of magnitude and restricts the enhanced modes to those coupled to the resonant electronic state. This chapter introduces the physical basis of resonance enhancement and shows how RR isolates chromophore-specific vibrational markers in complex biological systems. We then extend the same principle into the time domain with femtosecond stimulated resonance Raman spectroscopy (FSRRS). In FSRRS, the Raman pump is tuned across the visible range and can be placed in resonance with the transient absorption of a chosen excited-state species, which makes the Raman pump wavelength an additional experimental variable. Sampling this variable across the excited-state absorption manifold provides a selection criterion that separates coexisting transient species sharing a common vibrational window.

Accurate prediction of protein-ligand binding affinity remains a central challenge in computational drug discovery due to the complex interplay among molecular geometry, physicochemical interactions, and atom-specific charge information. In this work, we introduce a Persistent Sheaf Laplacian learning (PSLL) framework for protein-ligand binding affinity prediction. The proposed approach constructs multiscale topological representations from three-dimensional protein-ligand complexes by incorporating atomic partial charges into sheaf restriction maps over Vietoris-Rips and alpha complex filtrations. To capture chemically diverse protein-ligand interactions, we introduce element-specific and category-specific atom-pair representations within the PSLL framework. Harmonic and non-harmonic spectra extracted from the resulting persistent sheaf Laplacians are used as molecular descriptors. To complement the PSLL-derived molecular representation, we incorporate transformer-based protein embeddings and SMILES-derived ligand descriptors for binding affinity prediction. The scoring power of the proposed multiscale PSLL model is validated against existing state-of-the-art methods on three widely used PDBbind benchmark datasets, including PDBbind-v2007, PDBbind-v2013, and PDBbind-v2016. The computational results indicate that the proposed PSLL model achieves strong predictive performance across benchmark datasets, highlighting its potential as an interpretable and mathematically grounded framework with promising generalizability for molecular machine learning and drug discovery.

Single-particle cryo-electron microscopy (cryo-EM) pose estimation is traditionally solved anew for each dataset, where iterative refinement is done from scratch while the estimator learns to store the molecule in its weights. In this work, we show that pose inference is a generalizable, specimen-agnostic operation when conditioned explicitly on a reference volume. We introduce ARCHER, an amortized contrastive classifier that models the pose posterior over a discrete rotation grid. Trained across a variety of protein structures, it operates zero-shot without retraining per structure. This transferability is grounded in Fourier-space information mechanics, where all specimen dependence is captured by the reference structure's power spectrum and spatial extent. ARCHER achieves a median angular error of 5.0{\deg} on 100 held-out test structures and 2.5{\deg} on experimental particles, matching dedicated estimators within 0.16 Å in 3D reconstruction. Crucially, downstream conformational signal is preserved. The leading conformational coordinate correlates at 0.97 with deposited benchmarks, faithfully reconstructing free-energy basins and mobile domains. These results overall demonstrate that cryo-EM pose estimation can be generalized across different structures.

Molecular docking is a vital computational task in drug discovery, wherein the objective is to efficiently identify optimal binding poses between a ligand and a target receptor protein. Due to the combinatorial explosion of possible binding configurations, docking of large and flexible molecules remains a computationally intensive problem, especially at scale. Early studies have revealed that the molecular docking can be re-cast as a maximum vertex-weighted clique problem (MVWCP) problem on a compatibility graph to be solved classically. In this work, we proposed a hybrid quantum-classical approach for molecular docking leveraging the MVWCP formalism with a variational full-basis encoding (FBE) strategy, which enables efficient encoding of classical binary variables with Bloch sphere vectors. We further prove that a global minimizer of the FBE objective can always be chosen to be a pure product state, thereby providing a rigorous justification for its optimization using a unitary variational circuit. The molecular docking problem is first mapped to a cost Hamiltonian that is minimized within a variational framework, optimized via a randomized imaginary time evolution (ITE)-inspired warm start, and gradient-based techniques. Finally, we also executed the circuit on an IBM quantum computer, underlying the feasibility and of quantum-assisted optimization for structure-based drug design and point towards the broader utility of advanced encoding techniques in quantum optimization for computational biology.

Bioassay activity prediction is often data-limited because drug-discovery datasets rely on time-consuming and expensive wet-lab experiments for data generation and evaluation. This challenge has inspired recent research into molecular foundation models (MFMs), which aim to encode general-purpose chemical knowledge into molecular representations that generalize well in data-constrained scenarios. This paper presents Monroe, a new MFM with several innovations over the existing state of the art: increased scale allowing pre-training on over 81 million molecules from the PM6 quantum chemistry dataset; improved graph representation of stereochemistry; improved training losses including conformer denoising and embedding decorrelation; improved multi-task learning; and the use of a prior-data-fitted model (TabPFN) for downstream in-context prediction. Our evaluations use a principled pairwise comparison framework that measures statistically significant performance differences. Across established Polaris benchmarks, Monroe matches or exceeds existing MFMs, while on activity cliff benchmarks, designed to assess utility for molecular discovery, it achieves significant improvements over prior methods. Finally, ablation and transfer experiments show that PFN-based downstream predictors also substantially improve two leading existing models, MiniMol and CheMeleon, yielding new state-of-the-art variants we call MiniMol_PFN and CheMeleon_PFN, suggesting that our downstream adaptation strategy generalizes beyond Monroe. Source code is at github.com/blazejba/monroe.