Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Quantitative Biology Biomolecules

q-bio.BM Watch Biomolecules

Monday 12 October

Biomolecules

Calibrating AlphaFold confidence scores for interface quality

Sagyndyk Sagadinov, Vsevolod Viliuga and Arne Elofsson

AlphaFold confidence scores are widely used to rank protein complex predictions and to select subsets of models for downstream applications. Although these scores provide strong discriminatory power for distinguishing prediction quality, their numerical values were never intended to represent the probability that a prediction satisfies a given structural quality criterion. In this work, we calibrate commonly used confidence scores to estimate the probability that a predicted complex exceeds a chosen threshold of DockQ, an established measure of interface quality. On antibody-antigen and general multimer datasets, post-hoc isotonic calibration consistently improves agreement between predicted probabilities and observed DockQ success rates while preserving the underlying score ordering. The calibrated probabilities also provide more accurate estimates of the fraction of selected models expected to pass a given structural quality threshold. Although the mapping is fitted within a given prediction distribution and therefore transfers imperfectly across prediction domains, we show that reliable estimates are recovered from a small number of labeled target-domain samples. Because the calibration is entirely post hoc and requires no underlying AlphaFold model fine-tuning, it provides a straightforward and customizable way to convert existing model quality rankings into calibrated probabilities of passing a chosen structural quality threshold.
Read the full abstract

Friday 9 October

Biomolecules · Cross-listed from cs.LG

Designing Protein Structures from Natural Language

Joseph Lee, Yanjing Li, Bo Qiang et al. (+7 more)

A central challenge in de novo protein design is generating proteins with desired structural and functional properties. Existing design models typically require a dedicated input representation for each property, limiting the design objectives they support. We develop Prompteina, the first all-atom structure generation model that supports new and broader design objectives specified in natural language, analogous to text-to-image generation. To train Prompteina, we construct Prompteina-Data, a paired text–protein structure dataset of 1.8M structures and 50M+ captions describing global and residue-specific structural and functional properties. We adapt Proteina-Complexa, a pretrained structure generation model, through text-conditioned pretraining and finetuning that aligns residues with their corresponding text. Prompteina outperforms baselines on 15 of 18 structural properties and generates proteins that more closely match descriptions of their intended functions. In binder design, it leads baselines on at least 13 of 20 targets and improves interface confidence by 14% over the strongest baseline. With iterative in silico feedback, Prompteina's gain over non-iterative generation is 57% larger than the next-best baseline on the hardest targets. Finally, we experimentally validate Prompteina designs against GM2A, a target with no reported de novo binders. We identify nine binders, with the strongest at an apparent $K_{\mathrm{D}}$ of 107 nM. These results establish natural language as an effective and powerful conditioning interface for protein structure generation.
Read the full abstract

All authors Joseph Lee, Yanjing Li, Bo Qiang, Gregory Lau, Allyson Ettinger, Noah A. Smith, Rory Donovan-Maiye, David Baker, Hanna Hajishirzi, Pang Wei Koh

Biomolecules · Cross-listed from cs.LG

MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design

Jixin Tang, Ji Guo and Jun Zhao

We introduce MORAD, an online reinforcement learning framework for backbone-conditioned RNA diffusion models that trains a single shared policy across diverse target backbones. Structure-conditioned RNA inverse design seeks nucleotide sequences compatible with a target three-dimensional backbone, yet existing reinforcement learning approaches either optimize a separate policy for each target backbone or rely on offline preference optimization, leaving online post-training of a reusable backbone-conditioned model largely unexplored. MORAD combines backbone-conditioned group sampling, group-relative reward normalization, and a forward-process diffusion objective. Beyond existing RL rewards that primarily target tertiary structural quality, MORAD jointly optimizes six measurements spanning tertiary geometry, base pairing, ensemble behavior, and sequence composition. To aggregate these heterogeneous objectives despite differences in scale and optimization direction, MORAD maps each measurement to a bounded desirability score and combines them with a weighted geometric mean. Compared with a tertiary-structure-only reward, this multi-objective formulation improves 10 of the 11 evaluation metrics that have a preferred direction. Applied to pretrained RIDE, MORAD improves GDT-TS by 16.0% (from 0.3300 to 0.3827) and pairing MCC by 19.4% (from 0.6110 to 0.7295), while reducing normalized ensemble defect by 27.5% (from 0.3906 to 0.2830). On the test set, MORAD outperforms RiboDiffusion, gRNAde, and RDesign across tertiary structural accuracy, secondary-structure pairing, and thermodynamic quality, establishing a new state of the art in structure-conditioned RNA inverse design.
Read the full abstract

Biomolecules

TopoLIA: Topology-Inspired Latent Interaction Attention for Drug Discovery

Xiang Liu, Yiming Ren, Mustafa Hajij et al. (+2 more)

The growing sophistication of drug discovery calls for new advances in artificial intelligence (AI). Transformers have underpinned recent breakthroughs in AI, yet their conventional source-target attention mechanism can become a bottleneck for modeling complex interactions. Here, we introduce TopoLIA, a topology-inspired latent interaction attention mechanism that learns not only how much information should be exchanged between interaction partners, but also how that information should be transformed. Source-target-dependent attention is mediated through a compact latent interaction space, providing a structured representation of complex interactions. We further incorporate topological spectral representations to capture multiscale data geometry and extract algebraic relationships. TopoLIA thus incorporates topological principles into both data representation and neural network architecture. We demonstrate TopoLIA on protein-ligand binding, where persistent spectra encode multiscale topological and geometric patterns in 3D protein-ligand complexes, while latent interaction attention (LIA) enables structured, source-target-dependent information exchange. We pretrain TopoLIA by reconstructing masked multiscale spectral tokens from unlabeled molecular structures, yielding transferable structural representations without task-specific annotations. Across multiple scoring and docking benchmarks, TopoLIA achieves state-of-the-art performance and consistently outperforms its standard-attention counterpart. Rank analyses show that compact latent dimensions yield the best performance, supporting compact interaction spaces as an effective inductive bias for biomolecular learning. More broadly, LIA provides a general framework for structured, source-target-dependent information exchange that is applicable to diverse scientific and AI problems involving complex heterogeneous interactions.
Read the full abstract

All authors Xiang Liu, Yiming Ren, Mustafa Hajij, Pietro Liò, Guo-Wei Wei

Thursday 8 October

Biomolecules

La-Ribo: RNA Co-Design via Geometry-Latent Flow Matching

Runze Ma, Will Hua and Shuangjia Zheng

RNA function arises from the coupling of nucleotide sequence and three-dimensional structure, motivating their joint design. Coordinating global folding with nucleotide-level detail remains challenging under limited structural supervision. We introduce La-Ribo, a generative framework for RNA sequence-structure co-design via geometry-latent flow matching. La-Ribo retains a sparse phosphate-sugar–base scaffold and encodes nucleotide identity and local conformation in residue-wise latents. A shared flow network generates both jointly, and an RNA-specific decoder then reconstructs all heavy atoms. To expand supervision, we construct a quality-controlled corpus of 168,561 RNA structures, integrating experimental data with predictions from three folding models, including 10,631 MSA-supported structures generated in this work. La-Ribo improves designability and codesignability over the evaluated baselines across sampling budgets and two refolding models, and the same prior supports scaffold-conditioned inverse folding without additional training.
Read the full abstract

Biomolecules · Cross-listed from physics.bio-ph

Three-dimensional imaging of isolated membrane-protein complexes in vacuo with an X-ray laser

Kartik Ayyer, Tej Varma Yenupuri, Johan Bielecki et al. (+51 more)

The prospect of imaging single biomolecules, viruses and cells with intense, ultrashort X-ray pulses has driven the development of X-ray free-electron lasers (XFELs). However, the weak scattering from small particles is easily swamped by background from residual gas, which has so far limited applications to strongly scattering targets such as viruses, cell organelles and cells. Here we report a three-dimensional (3D) reconstruction of an isolated 1-MDa membrane-protein complex, photosystem I (PS I), from single-particle diffraction data. PS I trimers were aerosolised by charge-reduction electrospray ionisation and injected into the European XFEL beam, with partial helium gas exchange reducing background scattering by 80%. From 32 788 diffraction patterns of single trimers in random orientations, we reconstructed the 3D electron density to a resolution of 3.8 nm, limited by the detector geometry. The disc-shaped density, about 22 nm across and 10 nm thick, matches the size of a PS I trimer in a detergent micelle and is consistent with the compaction predicted by molecular dynamics simulations of the complex in vacuo and observed in native mass spectrometry. These results show that membrane-protein complexes can be imaged in vacuo with X-ray lasers, an important step towards ultrafast diffractive imaging of single macromolecules.
Read the full abstract

All authors Kartik Ayyer, Tej Varma Yenupuri, Johan Bielecki, Lutz A. Eichacker, J. Domingo Meza-Aguilar, Louise J. Persson, Lena Worbs, Patrick Adams, Roberto Alvarez, Adil Ansari, Alfredo Bellisario, Rebecca Boll, Carl Caleman, Sebastian Cardoch, Andrea Castoldi, Joe P. J. Chen, Cyril Danilevski, Merle Dechering, Simon Dold, Armando D. Estillore, Alberto De Fanis, Lukas V. Haas, Patrick Konold, David Lomitze, Abhishek Mall, Dimitra Manatou, Iñaki de Diego Martinez, Parichita Mazumder, Andrew J. Morgan, Anna Munke, Yevheniy Ovcharenko, Matteo Porro, Safi Rafie-Zinedine, Amit K. Samanta, Christina Schmidt, Arezu Sehati, Jonas A. Sellberg, Björn Senfftleben, Carolin Seuring, Zhou Shen, Nicusor Timneanu, Sergey Usenko, Daniel Westphal, August Wollter, Tamme Wollweber, Paul Lourdu Xavier, Henry N. Chapman, Janos Hajdu, Richard A. Kirian, Jochen Küpper, Erik G. Marklund, Petra Fromme, Michael Meyer, Filipe R. N. C. Maia

Wednesday 7 October

Biomolecules

MD-LLM-2: A Transferable Language Model of Molecular Dynamics with Physical Conditioning and Explicit Path Probabilities

Mhd Hussein Murtada, Z. Faidon Brotzakis and Michele Vendruscolo

Molecular dynamics (MD) simulations model the motion of proteins between conformational states, but crossing free energy barriers and sampling multiple thermodynamic conditions remain computationally costly. We recently introduced MD-LLM-1, which showed that language models can generate conformational trajectories at lower cost, but required a separate model for each protein and did not explicitly model thermodynamics or kinetics. Here we introduce MD-LLM-2, a transferable language model that generates trajectories conditioned on sequence, temperature and molecular history. Because each step defines a normalized distribution over structural tokens, the model assigns an explicit likelihood to every generated or simulated trajectory. Trained across mdCATH domains, MD-LLM-2 reproduces the median radius of gyration of MD within 1 Angstrom in 10 of 12 unseen domains, predicts reduced Trp-cage compaction at higher temperature, and generates L99A T4 lysozyme trajectories that reach published transition-region backbone structures. In alanine dipeptide simulations, conditioning on a torsional scaling parameter $\lambda$ predicts basin populations at unseen couplings with a mean absolute error of 0.09 versus 0.35 for MBAR, and first-passage probabilities with an error of 0.08 versus 0.16 for a reversible Markov state model. Frame-isoentropic sampling further limits the accumulation of errors during autoregressive trajectory generation. Together, these results extend MD-LLM from protein-specific trajectory generation to transferable, physically conditioned modelling with explicit path likelihoods, and show that the framework can predict equilibrium populations for force-field parameters not seen during training, with an initial indication that first-passage kinetics can also be captured.
Read the full abstract

Biomolecules

De novo design of monoclonal and bispecific antibodies with OFAntibody

Valhalla Team

Recent advances in generative protein design have enabled de novo antibody generation with explicit target and epitope conditioning. However, most existing approaches remain formulated around a single antigen-antibody interface, whereas bispecific antibody design requires modeling multi-component complexes in which multiple target-recognition interfaces must coexist and interact within a shared antibody structure. Here we present OFAntibody, an all-atom generative framework for de novo design of monoclonal and bispecific antibodies. OFAntibody expands CDR-epitope interaction learning with large-scale distilled antigen-antibody complexes, and introduces multi-component structural supervision and arm-aware multi-hotspot routing to learn compatible multi-interface geometries and couple each antibody paratope to its designated epitope. OFAntibody supports epitope-conditioned generation across monoclonal antibodies and diverse bispecific formats, including tandem VHH, diabody and CODV. In nanobody design benchmarks, OFAntibody achieves a Top-5 enrichment rate of 41.5%, representing a 5.39-fold improvement over RFantibody in competitive candidate ranking. In bispecific antibody design tasks, OFAntibody achieves hotspot pass rates of 94-100% across the three evaluated tasks and achieves energy pass rates of 60%, 13% and 8% for diabody, tandem VHH and CODV formats, respectively. OFAntibody further enables the same target combination to be explored across different antibody formats, while joint multi-interface generation reduces geometric incompatibilities arising from independent design and post hoc assembly. Together, these results extend de novo antibody design from binary antigen-antibody complexes to programmable multi-component complexes, providing a foundation for designing single molecules that combine recognition of distinct targets and their associated biological functions.
Read the full abstract

Tuesday 6 October

Biomolecules

A Shortcut to Structure in AlphaFold 3

Jonathan Feldman and Jeffrey Skolnick

AlphaFold 3 predicts protein structures with remarkable accuracy, yet how structural information emerges within the model remains poorly understood. Here, through causal interventions on internal representations and direct probing of every Pairformer block, we trace the formation of global protein geometry and identify the multiple sequence alignment (MSA) as a structural shortcut to the fold. Removing the MSA largely preserves local secondary structure while disrupting the long-range relationships that define global topology. Restoring the MSA-enriched pair representation at only forty residues recovers most of this lost organization, including at pairs never directly modified. This contribution depends on the detailed direction of the MSA module's output rather than its magnitude. The Pairformer rapidly converts this signal into global geometry: the final fold becomes recoverable by approximately block 9 of 48 for a majority of proteins, roughly twenty-seven blocks before the model's decoder can render it, whereas without the MSA it remains inaccessible for most proteins throughout the pass. Which homologs are supplied shapes this trajectory more strongly than which query is supplied; it persists for a designed query that never evolved but collapses for a shuffled sequence. Most importantly, an alignment built for a different protein that shares the fold, supplied only at the structurally corresponding columns, raises the median TM-score against experiment from 0.44 to 0.72, while the same alignment shifted a few residues along the chain performs worse than supplying no alignment at all. What AlphaFold 3 reads from an alignment is therefore a description of the fold itself, transferable between proteins that share one, rather than the query's own evolutionary history. This explains both its accuracy and the limits of what it has solved.
Read the full abstract

Biomolecules · Cross-listed from stat.ML

Information-Dense Synthesis for Molecular Discovery

Kasper K. Jakobsen and Eli N. Weinstein

Machine learning can accelerate molecular discovery by designing molecules and planning experiments. However, many scientific challenges demand molecules with very rare properties, and in this sparse setting, existing algorithms offer little gain over random guessing. We propose a method to efficiently search large regions of molecular space using algorithmically controlled stochastic synthesis. Rather than design, make and test individual molecules, we design and make complex mixtures, test them as a pool, then deconvolute the molecule-activity map. We optimize synthesis to encode maximal information. Theoretically, this approach can reduce the number of experiments required to find the optimal molecule among $d$ candidates from $\mathcal{O}(d)$ to $\mathcal{O}(\log d)$ or $\mathcal{O}(1)$. In simulation, on estimated protein fitness landscapes, it finds active molecules with an order of magnitude fewer experiments than existing Bayesian optimization methods.
Read the full abstract

Biomolecules

Mathematical Invariant-Enabled Topological Neural Networks for Molecular and Materials Property Prediction

Yiming Ren, Xiang Liu, Mustafa Hajij et al. (+2 more)

Existing molecular and materials learning approaches often rely on a limited set of structural representations, which may capture only selected aspects of complex three-dimensional structure. Here, we introduce mathematical invariant-enabled topological neural networks (MITNNs), a framework that represents complex structures through multiple complementary mathematical views and integrates them with topological neural architectures. MITNNs combine multiscale invariants from topology, spectral theory, commutative algebra, differential geometry, and discrete curvature, capturing complementary structural information from the same system. Systematic invariant-subset, architecture-subset, and ensemble analyses show that predictive performance depends on how mathematical representations and neural architectures are paired, with selected combinations outperforming individual models and the aggregation of all available components. Across protein-ligand binding, metal-organic framework properties, mutation-induced protein solubility, and molecular toxicity prediction, MITNN consistently outperforms existing methods. These results establish MITNN as a mathematically multimodal framework for scientific machine learning.
Read the full abstract

All authors Yiming Ren, Xiang Liu, Mustafa Hajij, Pietro Liò, Guo-Wei Wei

Monday 5 October

Biomolecules · Cross-listed from q-bio.MN

IMPPAT 3.0: An updated FAIR database of phytochemicals and formulations of Indian Medicinal plants

Shanmuga Priya Baskaran, Ajaya Kumar Sahoo, Priyotosh Sil et al. (+6 more)

Ayurvedic formulations represent a rich source of traditional knowledge, encompassing distinct therapeutic approaches, medicinal ingredients, and underlying principles of drug action. However, systematic integration of this knowledge with standardized modern biomedical terminology and resources remains limited. Here, we present IMPPAT 3.0, an updated version of the Indian Medicinal Plants, Phytochemistry And Therapeutics (IMPPAT: https://cb.imsc.res.in/imppat/) database that extends its scope by incorporating curated and harmonized information on Ayurvedic formulations from authoritative sources, while expanding its coverage of medicinal plants, phytochemicals, and therapeutic use terms. IMPPAT 3.0 further enriches plant and phytochemical information with annotations on clinical trials, patents, bioactivity, protein targets, spectral data, plant image links, and AyuCaRe reports. The compiled data is also organized as IMPPAT-KG, a knowledge graph that enables exploration of relationships among IMPPAT entities. We demonstrate the utility of the resource through a network medicine analysis of single herbal drugs (SHDs) reported for rheumatoid arthritis (RA), revealing significant proximity of their protein targets to RA-associated genes, and pinpointing of phytochemical pairs with potentially complementary effects on RA pathogenesis. In conclusion, by integrating traditional medicinal knowledge, IMPPAT provides a FAIR-compliant ethnopharmacological platform for systematic investigation of Indian medicinal plants and Ayurvedic formulations for drug discovery applications.
Read the full abstract

All authors Shanmuga Priya Baskaran, Ajaya Kumar Sahoo, Priyotosh Sil, Rahul Tiwari, Nikhil Chivukula, Sabrina Elsa Eapen, Geetha Ranganathan, Preeti Semwal, Areejit Samal

Biomolecules · Cross-listed from cond-mat.soft

Self-assembly Monte Carlo reveals localized entanglement in giant polymer melts

Enrico Fornasa, Francesco Slongo and Cristian Micheletti

Topological entanglements are central to understanding and predicting the properties of polymer melts. Yet, they make equilibrium sampling computationally challenging, as decorrelation times grow rapidly with chain length. Here, we introduce a Monte Carlo scheme that bypasses typical computational bottlenecks by working in a self-assembly ensemble rather than at fixed composition. Strictly local moves efficiently propagate backbone reconnections across scales while conserving the number of linear chains, achieving near-linear scaling of decorrelation time with system size, $\tau_{\rm eq}\sim V^{1.0}$. With this method, formulated for a fully-packed lattice, we equilibrate periodic systems totalling up to $\simeq 1.1\times 10^9$ monomers, accessing a universal melt regime insensitive to lattice details. We analyze intra- and inter-chain entanglements for chains of up to $N\simeq 5 \times 10^5$ monomers, revealing that they manifest as localized knots and links rather than as global tangles. Finally, we show that the magnitude of the Gauss linking integral between neighbouring chains grows only as $N^{1/4}$.
Read the full abstract

Friday 2 October

Biomolecules

MathAgent: Multi-Agent Optimization of Mathematical Invariants for Molecular Property Prediction

Yiming Ren, Josh V. Vermaas and Guo-Wei Wei

Mathematical invariants provide complementary representations of molecular structure, but their predictive utility can vary across datasets and prediction tasks. For a new dataset, appropriate construction of invariant representations from algebraic topology, differential geometry, topological spectral theory, and commutative algebra is a challenging task, particularly when evaluating multiple representations is computationally expensive. We develop a Mathematical Agentic Model (MathAgent) to automatically optimize invariant representations in molecular property prediction. The framework combines dataset-aware representation design, low-cost candidate screening, and progressive evaluation. Language-model reasoning supports task interpretation, strategy proposal, and workflow coordination, while scientific computations and numerical decisions are carried out by deterministic tools. We evaluate MathAgent on protein–ligand binding-affinity and quantitative toxicity prediction tasks. Different datasets favor different combinations of mathematical invariants, demonstrating the need for dataset-adaptive representation selection rather than a fixed universal representation. Objective-conditioned executions further show that the framework can adjust its evaluation strategy according to user-specified goals. MathAgent therefore provides a systematic, evidence-driven, and traceable approach for optimizing mathematical invariant representations and reducing reliance on manual configuration and/or experimentation in molecular property prediction.
Read the full abstract

Biomolecules · Cross-listed from cs.LG

Learning Latent Protein Languages for Autoregressive Generation

Mahdi Pourmirzaei, Farzaneh Esmaili, Amir Ziashahabi et al. (+2 more)

Autoregressive transformers remain comparatively weak for protein sequence and structure generation. We study the role of target representation: amino acid tokens encode residue identities without explicit contextual semantics, while backbone coordinates require a discrete representation in our framework. We introduce two learned latent protein languages. Protein Latent Language (PLL) maps sequences to a 4,096-state contextual alphabet built on a frozen ESM-2 encoder, with one token per residue. Structure Latent Language (SLL) adapts GCP-VQVAE Lite with auxiliary sequence and confidence supervision while retaining decoding to backbone coordinates. We separately pretrain autoregressive transformer models on PLL and SLL tokens using next-token prediction, yielding PLLM and SLLM. Under matched downstream sequence training, PLLM has a fitted compute-scaling exponent of 0.038 versus 0.020 for the amino acid autoregressive model. In unconditional sequence generation, PLLM reduces the fraction of samples below a heuristic 1.5-bit residue-composition entropy threshold by 54% relative to the amino acid model across sampling temperatures. For sequence-to-structure prediction, replacing the original GCP-VQVAE Lite tokenizer with SLL reduces best validation perplexity by 34% under matched training. For long proteins, latent-token sampling is approximately 1,000 times faster than MSA-based AlphaFold2 in our measurements. In backbone generation, SLLM compares favorably with other generative models on diversity and novelty. We also observe early signs that using SLLM's internal token confidence for inference-time sampling can improve sequence-to-structure prediction quality beyond a single decoded sample. These results position learned latent protein languages as a promising substrate for autoregressive transformer scaling and inference-time sampling in protein generation.
Read the full abstract

All authors Mahdi Pourmirzaei, Farzaneh Esmaili, Amir Ziashahabi, Mohammadreza Pourmirzaei, Dong Xu

Biomolecules · Cross-listed from cs.LG

RNADyn: A Benchmark for Generating and Understanding RNA Dynamics

Yiming Huang, Lennart Bastian, Hanqun Cao et al. (+2 more)

Ribonucleic acid (RNA) functions through conformational changes that are not fully captured by static structures. However, large-scale standardized RNA dynamics data remain limited, and existing approaches typically treat trajectory generation and dynamics understanding as separate objectives. Here, we introduce RNADynBench, a standardized RNA molecular dynamics (MD) benchmark with 2585 quality-controlled 100-ns all-atom trajectories and leakage-controlled splits. Building on RNADynBench, we develop RNADynNet, a unified model for RNA dynamics learning that uses a shared backbone for both trajectory generation and dynamics fingerprint extraction from a single conformer. It combines coordinate denoising, single-frame-to-trajectory alignment, and physical grounding to connect all-atom trajectory generation with dynamics representation learning. Physical grounding improves both generated dynamics and the physical information recoverable from these fingerprints. Across both test sets, including the high-flexibility challenge set, the generated trajectories achieve RMSF correlations of 0.875 and 0.766, while single-conformer predictions show comparable agreement with MD-derived dynamics. RNADynBench and RNADynNet together establish a benchmark and unified modeling framework for generating and understanding RNA dynamics.
Read the full abstract

All authors Yiming Huang, Lennart Bastian, Hanqun Cao, Luis Vollmers, Tolga Birdal

Thursday 1 October

Biomolecules · Cross-listed from cs.CE

RipplePLM: Structural and Property Decoupling for Protein Mutation Effect Generation

Liuzhenghao Lv, Yuyang Liu, Yuyang Gao et al. (+2 more)

Protein mutation effect generation asks a model to describe the functional consequence of a point mutation in natural language. Existing protein-to-text systems typically encode mutation information into undifferentiated representations, overlooking the organization of mutation-induced evidence across structural and biochemical factors. We propose RipplePLM, a mutation-aware generation framework centered on Direct-Distal Cross-Attention (DDCA). By constructing a residue-level Mutation Perturbation Field from pre-trained protein language models, DDCA leverages predicted contact maps to organize mutation representations into two pathways: the mutation site's immediate contact neighborhood and its multi-hop distal context. To complement this structural decomposition, we further introduce the Property Latent Chain (PLChain), which injects expert-guided supervision of biochemical property changes (e.g., thermostability and optimal pH) into the LLM hidden-state pathway through latent property tokens. On MutaDescribe, RipplePLM improves over mutation-specific baselines on temporal and structural splits; under a matched-backbone comparison, average structural-split ROUGE-L increases from 22.23 to 35.65. Expert evaluation further shows a higher proportion of biologically accurate or relevant descriptions than the mutation-specific baseline. Additional ablations, representation diagnostics, and low-$N$ fitness regression experiments further support the effectiveness of the learned mutation-aware representations. Code: https://github.com/Lyu6PosHao/RipplePLM.
Read the full abstract

All authors Liuzhenghao Lv, Yuyang Liu, Yuyang Gao, Li Yuan, Yonghong Tian

Biomolecules · Cross-listed from cs.LG

pCoMole: Pareto-Constrained Molecule Editing with Discrete Flows

Tong Chen, Maximilian Holsman, Lin Zhao et al. (+1 more)

Biomolecular therapeutics often start from known sequences and require targeted editing to improve multiple properties while satisfying hard biochemical and manufacturability constraints. However, existing generative methods do not jointly support multi-objective optimization, hard feasibility, and sequence editing in discrete, variable-length biological spaces. In this work, we introduce Pareto-Constrained Molecule Editing (pCoMole), a framework built on discrete flow matching that steers a pre-trained Edit Flow toward user-specified preferences while enforcing terminal feasibility. pCoMole defines a feasibility-gated terminal distribution using an augmented Tchebycheff utility and realizes the resulting preference tilt through a Doob-h transform of the underlying edit process. To make this construction practical, we approximate the required harmonic function using short Monte Carlo rollouts over candidate edits, yielding an efficient guided editor with provable preference consistency. We validate pCoMole by shrinking GFP while retaining fluorescence-related properties, shortening diverse Cas9 orthologs while preserving PAM specificity, and compressing peptide binders into short peptidomimetics that optimize seven drug-related properties under hard constraints. In wet lab testing, two 229-residue pCoMole-designed eGFP variants retained clear green fluorescence in BL21 cells after 10 deletions, with either one or two substitutions. Together, pCoMole enables constraint-aware, Pareto-aligned editing of biomolecular sequences in discrete, variable-length spaces.
Read the full abstract

All authors Tong Chen, Maximilian Holsman, Lin Zhao, Pranam Chatterjee

Biomolecules

Fold'EM: Direct atomic structure inference from Cryo-EM particles

Advaith Maddipatla, Märt-Erik Mäeots, Marco Pegoraro et al. (+5 more)

Single-particle cryo-electron microscopy (cryo-EM) has become a widely adopted technique for biomolecular structure determination. The conventional cryo-EM computational pipeline first combines many particle images to reconstruct an electrostatic potential (ESP) map and then fits an atomic model to the recovered map. Density reconstruction has high sample complexity, requiring large numbers of particle images and making structure determination high-cost and low-throughput, particularly for heterogeneous samples. Downstream atomic model building, in turn, becomes increasingly difficult as the resolution of the reconstructed map deteriorates. Protein structure prediction models provide strong sequence-derived priors on atomic structure, and experiment-guided approaches can use these priors to recover structures consistent with experimental measurements. Yet, in cryo-EM, such priors are typically integrated only after density reconstruction during atomic model fitting. We introduce Fold'EM, an inference-time framework that combines priors from protein generative models directly with cryo-EM particle images to determine atomic models from a small number of single particle images, bypassing both intermediate density reconstruction and downstream model building against the reconstructed map. Across synthetic and experimental cryo-EM datasets, Fold'EM recovers accurate atomic structures both with known particle orientations and in an ab-initio setting where orientations are inferred jointly with structure. In heterogeneous datasets, Fold'EM further resolves distinct conformational states from mixed particle populations without separately reconstructing a density map and building an atomic model for each state. We believe these results open new avenues for structure determination in the low-sample regime and for characterizing low-population conformational states directly from cryo-EM particles.
Read the full abstract

All authors Advaith Maddipatla, Märt-Erik Mäeots, Marco Pegoraro, Nikolaus Dräger, Roberto Covino, Sanketh Vedula, Martin Pacesa, Alex M. Bronstein

Biomolecules

Multi-Scale Temporal Flows for Peptide Trajectory Generation

Xichen Sun, Wentao Wei, Xiaoxi Zhang et al. (+2 more)

Peptides occupy a particularly challenging regime of biomolecular dynamics. Short peptides lack a stable folded core and populate broad conformational ensembles, while cyclization adds ring closure, non-local residue coupling, and stereochemical diversity. Deep generative models have made remarkable progress in emulating molecular-dynamics trajectories directly, yet each is trained on windows cut at a fixed interval and therefore observes the process at a fixed temporal resolution. More fundamentally, none takes that interval as an input, so the physical time a window spans is never represented, leaving the sparse frames on which a peptide crosses between metastable states difficult to learn. Here, we introduce PepTIDE, a multi-scale temporal framework for peptide trajectory generation. The stride of each training window is drawn from a continuous range, so one model observes the same dynamics at many temporal resolutions, and an Adaptive Physical-Time Embedding encodes the relative interval of a window together with the absolute time of each frame, making the shared velocity field interval-aware. All frames are generated jointly through a stochastic-interpolant flow, and pair-aware invariant point attention captures the geometry and topology of both linear and cyclic peptides. On PepMD and a 50-system cyclic-peptide benchmark, PepTIDE reaches state-of-the-art distribution agreement and structural validity. Read in temporal order, its trajectories recover these sparse transition frames and reproduce inter-state fluxes more faithfully, confirming that modeling multiple temporal scales is what makes these rare events accessible.
Read the full abstract

All authors Xichen Sun, Wentao Wei, Xiaoxi Zhang, Yuedong Yang, Jiahua Rao

Biomolecules

Molecular architecture of TE-seeded chromosome-naive initiation networks of protein-protein interactions delineates the Human Protein Map of the assembly of multiprotein complexes

Gennadi Glinsky

Upon binding to transposable elements seeded DNA, initiator transcription factors are poised to activate the hybrid assembly pathways (HAP) of endogenous multiprotein complexes (EMC) by iteratively engaging protein-protein interaction (PPI) cascade and creating cell type-specific pools of protein dimers. Here, molecular features and inferred biological functions of PPI cascade constituents were elucidated within the context of cell type-specific intracellular protein monomer pools documented in the Human Protein Atlas (HPA) of 154 human cell types. The following key features of the molecular architecture and functional performance of the 4 families of PPI cascade constituents were documented within the HPA contexts of intracellular proteomes: a) the ubiquitous expression and balanced representation; c) the universal availability and engagements; d) constitutive {invariant) and cell type-specific assembly profiles of EMCs. The biological relevance of the PPI cascades is demonstrated by cell-type-resolved multiprotein complex-engagement analysis across the HPA of human body, which faithfully recovers without supervision the intrinsic lineage structures of EMCs and lineage-specific master-regulator multiprotein assemblies. PPI cascade constituents have the capacity to generate 51,830 protein dimers within the proteome availability contexts of 154 types of human cells. Present analyses revealed critical impacts of the persistence of proteinopathy proteins that may cause the damage to the PPI cascade performance by sequestering 44 synaptic proteins. The sequestration of synaptic proteins withdraws structural-functional components of synapses suggesting a mechanism contributing to the pathogenesis of neurodegeneration. Conversely, reconstitution of availability of defined synaptic structural proteins appears to restore stoichiometry and recovers the lost assembly of synaptic protein dimers.
Read the full abstract

Biomolecules · Cross-listed from cs.LG

Auditable Algebraic Counting Field for Cryptic-Pocket Detection from Apo Structures

Shan Yu and Xuening Wu

Cryptic ligand-binding pockets are not apparent in experimentally determined apo structures, making them difficult to identify from unbound receptor geometry. A complementary challenge is to make the structural measurements and learned evidence behind each prediction directly inspectable. We introduce a supervised algebraic counting field (ACF) for predicting cryptic-pocket residues from apo structures. ACF compiles explicit geometric, physicochemical, and topological features into compact, integer-weighted lookup tables. Each prediction score can be reconstructed from feature values, training counts, table weights, and spatial aggregation, without sequence search, structural-template transfer, or a protein language model at inference. We evaluate ACF on CryptoBench and two locked external collections, separating ranking performance from the effects of residue-calling budgets. On an external set of 57 post-CryptoBench apo-holo units, ACF exceeded P2Rank by +0.044 in mean paired ROC-AUC (multiplicity-adjusted 95% CI [+0.010, +0.079]). The advantage was dataset-dependent: official-fold ROC-AUC and matched-budget F1 differences against P2Rank remained unresolved, and a second external evaluation did not confirm gains from added structural features. ACF thus provides a compact predictor with externally validated signal and an inspectable path from structural measurements and training counts to residue scores.
Read the full abstract

Wednesday 30 September

Biomolecules

StabilityArc: Decoding Protein Sequence Embeddings into Generalizable Stability Landscapes

Aaron L. Feller, Andrew D. Ellington and Claus O. Wilke

Every protein has a unique stability landscape, but the physical consequences of mutation are governed by recurring biochemical constraints. We test whether a shared decoder, trained on measurements from diverse proteins, can interpret these constraints in an unseen target, enabling cross-protein transfer for initial experimental round prescreening. We present StabilityArc , which maps frozen ESMC-600M residue representations through a shared RoPE transformer to an Lx20 matrix of substitution effects; a symmetric, contact-aware residual aids in predicting epistasis in simultaneous substitutions. In 66 strict leave-one-protein-out evaluations covering 134,794 ProteinGym variants, StabilityArc achieves 0.7134 Spearman correlation, exceeding the strongest zero-shot baseline, ProSST-2048 (0.6526), by 0.0608. We further explore the utility of this method by providing the score as a prior for Kermut, achieving Spearman correlation of 0.8280 across three supervised split schemes, improving on Kermut's reported 0.8167.
Read the full abstract

Biomolecules · Cross-listed from physics.bio-ph

Computational Insights into Mechanostability and Dissociation Dynamics of the Dengue Virus Envelope Protein Ectodomain Dimer Across pH and Temperature Gradients

Georcki Ropón-Palacios, Luís G. F. Crespi, Jakub Rydzewski et al. (+2 more)

Dengue virus (DENV) is an enveloped flavivirus of major public health importance. Its envelope (E) protein mediates viral entry through homodimer dissociation and subsequent membrane fusion, making it one of the principal targets for antiviral strategies. To investigate the molecular determinants of this process, we performed steered molecular dynamics (SMD) simulations of the E protein ectodomain (ecE) dimer from DENV-2 and DENV-3 under variable pH and temperature conditions. Force-extension analyses revealed a highly stable interface for both serotypes, with rupture forces exceeding 1000 pN. pH and temperature had modest effects on overall mechanical resistance. However, DENV-3 displayed a distinct sensitivity to thermal stress compared to DENV-2. We identified a robust, asymmetric dissociation pathway across all conditions, characterized by a metastable intermediate state involving partial dimer opening and exposure of the fusion loop (FL). This intermediate exposes an immunodominant epitope and persists under physiological conditions, suggesting it as a viable target for therapeutic intervention. The primary contributions to the interfacial interaction network were found to arise from van der Waals interactions, followed by hydrogen bonds, salt bridges, and pi-cation interactions. DENV-3 exhibited a slightly greater contribution from polar interactions involving domains EDI, EDII, and EDIII. Furthermore, pairwise occupancy analysis identified pH-sensitive contacts that are disrupted under acidic conditions, particularly in DENV-3, providing mechanistic insight into the early stages of ecE dissociation. Together, these findings provide structural insights into the dissociation mechanism, identifying key metastable states and pH-sensitive interactions that could be exploited to develop antivirals that stabilize the dimer and prevent viral fusion.
Read the full abstract

All authors Georcki Ropón-Palacios, Luís G. F. Crespi, Jakub Rydzewski, Walter Rocchia, Alexandre S. de Araujo

Tuesday 29 September

Biomolecules

Ca$^{2+}$-tunable mechanics and recoil in reconstituted Tcb2 networks

Xiangting Lei, K. R. Prathyusha, Carlos Floyd et al. (+2 more)

Tetrahymena calcium-binding protein (Tcb2) forms Ca$^{2+}$-responsive networks that exhibit contractile behavior, yet how Ca$^{2+}$ concentration controls their local mechanical response remains poorly understood. Here, we use optical tweezers to perform active microrheology on reconstituted Tcb2 networks inside a microfluidic device that enables precise control of Ca$^{2+}$ concentration, allowing systematic tuning of network structure and mechanics. We find that increasing Ca$^{2+}$ from 1 to 100~mM enhances the effective stiffness by nearly two orders of magnitude, from $\sim$1$\times$10$^{-3}$ to $\sim$7$\times$10$^{-2}$~pN/nm, corresponding to a transition from a viscosity-dominated to a more elastic and mechanically robust network. Recoil assays further reveal rapid release of stored elastic energy following deformation. After two orthogonal pulls, the bead recoils along the diagonal rather than retracing the loading path, indicating that stresses from different directions combine to produce a resultant restoring response. These results establish Tcb2 networks as a minimal, tunable system for probing chemomechanical coupling and viscoelasticity in Ca$^{2+}$-regulated protein networks.
Read the full abstract

All authors Xiangting Lei, K. R. Prathyusha, Carlos Floyd, Jerry Honts, Saad Bhamla

Biomolecules · Cross-listed from cs.LG

LEMON-ZEST: Evolution-Informed Tokenization for Efficient Protein Language Modeling

Biswajit Banerjee, Claudia Alvarez Carreno and Anton S. Petrov

Protein Language Models (PLMs) have made remarkable progress following scaling laws established in natural language processing across sequence- and structure-based tasks, yet the potential of tokenization remains underexploited. Unlike human language, proteins preserve structure despite extensive sequence variation a property standard tokenization strategies fundamentally fail to capture. We introduce ZEST (Zoned Encoding of Sequence Traits), an evolution-informed vocabulary derived from conserved regions of multiple sequence alignments. ZEST allows embedding domain-level biological priors directly at the tokenization stage rather than learning them implicitly through scale. ZEST natively compresses sequences to an average token length of 4 residues, enabling our model to process 4,000 residues within a standard 1024-token context window. Building on this, we present LEMON (Layered Extraction of Molecular Ordering from Nature), a compact 200M-parameter sequence-based model for detection of remote homology between protein sequences trained on a single H100 GPU for one week. Despite its modest size, LEMON outperforms state-of-the-art models ranging from 600M to 3B parameters. Our results demonstrate that evolution-informed tokenization can substitute for massive parameter scaling, opening a new direction for efficient, biologically-grounded protein representation learning. All code, model weights, and results are publicly available under the MIT license.
Read the full abstract

Biomolecules · Cross-listed from cs.LG

Benchmarking graph-based models for in-silico toxicity prediction in drug discovery

Noel Suarez-Barro, Manuel Lama and Juan C. Vidal

Drug discovery is a costly and high-risk process, where toxicity-related failures remain a major cause of attrition in both preclinical and clinical stages. As a result, accurate early prediction of chemical toxicity is essential to reduce downstream costs and improve compound prioritization. In this context, graph deep learning (GDL) has emerged as a powerful paradigm for toxicity prediction, leveraging molecular graph representations to learn directly from chemical structure with improved expressivity over traditional approaches. Despite the growing number of proposed models, current literature-based comparisons are often difficult to interpret due to inconsistencies in datasets, preprocessing pipelines, and evaluation protocols. To address this limitation, we introduce a unified and standardized benchmarking framework for GDL-based toxicity prediction. We systematically evaluate more than 20 representative approaches under consistent experimental conditions and across multiple datasets and partitioning strategies, enabling a fair and reproducible comparison of model performance. In addition, we complement this empirical study with a structured literature analysis to contextualize existing methodological trends and performance claims. Our results provide a clearer and more reliable assessment of the current state of the field, highlighting both the strengths and limitations of existing graph-based approaches. To support transparency and reproducibility, we release our benchmarking framework as open-source software https://gitlab.citius.gal/noel.suarez/benchtox, allowing the community to evaluate and compare models under consistent conditions.
Read the full abstract

Biomolecules

How 'Foundational' Are Current Molecular Foundation Models?

Francesca Grisoni

Large-scale models have permeated the molecular sciences, yet what makes a model 'foundational' in this domain remains poorly defined. This paper proposes three testable criteria for assessing the foundational nature of molecular models: (i) generality across molecular entities, properties, and tasks; (ii) transferability to new applications with no or minimal task-specific retraining; and (iii) generalization beyond the training distribution. Applying these criteria to the state of the art reveals promising progress, particularly visible in biomolecular structure prediction and machine-learned interatomic potentials, although none of the approaches examined fully satisfies all three. Success is concentrated in domains where target properties are consistently defined and training data are abundant, with low label noise relative to physically meaningful variation. More broadly, progress in the molecular sciences appears to depend less on model scale alone than on the quality and structure of available data, as well as the incorporation of prior knowledge into models, prediction tasks, or downstream applications. This work shifts the notion of a molecular foundation model from a descriptive label to a testable hypothesis, offering a framework for assessing current models and guiding future developments.
Read the full abstract

Biomolecules

Leveraging secondary-structure information for accurate nucleic acid structure prediction with OFoldNA

Valhalla Team

Recent advances in biomolecular structure prediction have enabled accurate modelling of increasingly complex molecular systems. However, nucleic acid structure prediction remains challenging because of conformational flexibility and the limited availability of high-quality 3D structural data. Secondary structure (SS) provides a more readily available layer of structural information that captures base-pairing relationships and folding topology. Here we present OFoldNA, an all-atom diffusion model that incorporates SS information into nucleic acid folding and protein–nucleic acid co-folding. Without external SS information, OFoldNA achieved leading performance on FoldBench for both nucleic acid monomer folding and protein–nucleic acid co-folding, with particularly strong performance on DNA monomers and protein–DNA interfaces involving longer nucleic acid chains. When accurate base-pairing information was provided, OFoldNA-SS2TS further improved both folding and co-folding accuracy, while partial SS information also yielded consistent gains. The same auxiliary branch can also be used for RNA SS prediction as OFoldNA-SS, which achieved the best out-of-distribution performance on CHANRG. Together, these results show that intermediate structural information such as nucleic acid SS can be leveraged to improve all-atom 3D modelling, providing a general direction for incorporating complementary structural modalities into molecular structure prediction and design.
Read the full abstract

Biomolecules · Cross-listed from cs.AI

AssayRouter: Historical Utility Priors for Frozen Molecular Predictor Routing

Dong Xu, Zhangfan Yang, Jiantao Wu et al. (+5 more)

Laboratories often face a new molecular assay with 16-64 labels and a bank of predictors whose training data and parameters are unavailable. The practical question is which frozen outputs to include in a small local model. AssayRouter treats completed assays as pseudo-targets and labels each candidate by its post-fit utility: the reduction in held-out discovery loss when the candidate is added to the local target predictor. A shared regressor learns to predict this utility from candidate behavior on the support set, without source identity; on a new assay, one frozen ranking selects four sources and separate labels fit a convex combiner. We train only on completed ChEMBL-MT assays and evaluate 24 external regression assays across six frozen interface families. AssayRouter-C lowers strict four-call negative log-likelihood (NLL) by 0.0409 relative to Support-CV@4. Frozen candidate-label permutations confirm that candidate-utility correspondence carries the transferred information, and leave-one-interface-out training shows that the mapping generalizes to unseen predictor families. Completed assays therefore provide transferable supervision for scarce-label routing through frozen prediction interfaces.
Read the full abstract

All authors Dong Xu, Zhangfan Yang, Jiantao Wu, Shipeng Zhang, Zexuan Zhu, Jiangqiang Li, Jun Zhang, Junkai Ji