Highlights of Model Quality Assessment in CASP16.

Model quality assessment (MQA) remains a critical component of structural bioinformatics for both structure predictors and experimentalists seeking to use predictions for downstream applications. In CASP16, the Evaluation of Model Accuracy (EMA) category featured both global and local quality estimation for multimeric assemblies (QMODE1 and QMODE2), as well as a novel QMODE3 challenge-requiring predictors to identify the best five models from thousands generated by MassiveFold. This paper presents detailed results from several leading CASP16 EMA methods, highlighting the strengths and limitations of the approaches.

Estimating protein complex model accuracy using graph transformers and pairwise similarity graphs.

Motivation: Estimation of protein complex structure accuracy is essential for effective structural model selection in structural biology applications such as protein function analysis and drug design. Despite the success of structure prediction methods such as AlphaFold2 and AlphaFold3, selecting top-quality structural models from large model pools remains challenging.

Results: We present GATE, a novel method that uses graph transformers on pairwise model similarity graphs to predict the quality (accuracy) of complex structural models.

A Survey of Deep Learning Methods and Tools for Protein Binding Site Prediction.

Proteins are essential to various cellular functions by interacting with various ligands, including peptides, small molecules, ions, and nucleic acids. Accurate prediction of protein binding sites is essential for understanding these interactions and their biological significance. Recent advancements in deep learning (DL) have greatly enhanced the accuracy of protein binding site prediction.

Atomistic Modeling of Bio-Nano Hybrids: Interactions between Iron Oxide Nanoparticles and the Outer Membrane of .

Dissimilatory metal-reducing bacteria transfer electrons to the external surface of metal oxides during their anaerobic respiration. Combining these bacteria with iron oxide nanoparticles (NPs) supports continuous redox processes for bioremediation and bioenergy, yet their molecular interactions between iron oxide NPs and the extracellular membrane, which regulate extracellular electron transfer, remain unexplored. This work investigates the adsorption of an iron oxide (α-FeO) NP with a 3.

A labeled dataset for AI-based cryo-EM map enhancement.

Cryogenic electron microscopy (cryo-EM) has transformed structural biology by enabling near atomic resolution imaging of macromolecular complexes. However, cryo-EM density maps suffer from intrinsic noise arising from structural sources, shot noise, and digital recording, which complicates accurate model building. While various methods for denoising cryo-EM density maps exist, there is a lack of standardized datasets for benchmarking artificial intelligence (AI) approaches.

Unavailability of experimental 3D structural data on protein folding dynamics and necessity for a new generation of structure prediction methods in this context.

Motivation: Protein folding is a dynamic process during which a protein's amino acid sequence undergoes a series of 3-dimensional (3D) conformational changes en route to reaching a native 3D structure; the resulting 3D structural conformations are called folding intermediates. While data on native 3D structures are abundant, data on 3D structures of non-native intermediates remain sparse, due to limitations of current technologies for experimental determination of 3D structures. Yet, analyzing folding intermediates is crucial for understanding folding dynamics and misfolding-related diseases.

FlowDock: Geometric flow matching for generative protein-ligand docking and affinity prediction.

Motivation: Powerful generative AI models of protein-ligand structure have recently been proposed, but few of these methods support both flexible protein-ligand docking and affinity estimation. Of those that do, none can directly model multiple binding ligands concurrently or have been rigorously benchmarked on pharmacologically relevant drug targets, hindering their widespread adoption in drug discovery efforts.

Results: In this work, we propose FlowDock, the first deep geometric generative model based on conditional flow matching (CFM) that learns to directly map unbound (apo) structures to their bound (holo) counterparts for an arbitrary number of binding ligands.

Boosting AlphaFold Protein Tertiary Structure Prediction through MSA Engineering and Extensive Model Sampling and Ranking in CASP16.

AlphaFold2 and AlphaFold3 have revolutionized protein structure prediction by enabling high-accuracy tertiary structure predictions for most single-chain proteins. However, obtaining high-quality predictions for some hard protein targets with shallow or noisy multiple sequence alignments (MSAs) and complicated multi-domain architectures remains challenging. Here, we present MULTICOM4, an integrative protein structure prediction system that uses diverse MSA generation, large-scale model sampling, and an ensemble model quality assessment (QA) strategy of combining individual QA methods to improve model generation and ranking of AlphaFold2 and AlphaFold3.

Multimodal deep learning integration of cryo-EM and AlphaFold3 for high-accuracy protein structure determination.

Cryo-electron microscopy (cryo-EM) is a key technology for determining the structures of proteins, particularly large protein complexes. However, automatically building high-accuracy protein structures from cryo-EM density maps remains a crucial challenge. In this work, we introduce MICA, a fully automatic and multimodal deep learning approach combining cryo-EM density maps with AlphaFold3-predicted structures at both input and output levels to improve cryo-EM protein structure modeling.

TransFun: A Tool of Integrating Large Language Models, Transformers, and Equivariant Graph Neural Networks to Predict Protein Function.

Experimentally determining the functions of proteins is a complex and time-consuming process. This challenge contributes to a gap, where many proteins have known sequences, predicted structures, and other crucial information, yet lack functional annotations. This gap underscores the critical importance of automated function prediction (AFP) methods, which aim to develop computational techniques dedicated to predicting protein functions.

Boosting AlphaFold Protein Tertiary Structure Prediction through MSA Engineering and Extensive Model Sampling and Ranking in CASP16.

AlphaFold2 and AlphaFold3 have revolutionized protein structure prediction by enabling high-accuracy tertiary structure predictions for most single-chain proteins (monomers). However, obtaining high-quality predictions for some hard protein targets with shallow or noisy multiple sequence alignments (MSAs) and complicated multi-domain architectures remains challenging. Here, we present MULTICOM4, an integrative protein structure prediction system that uses diverse MSA generation, large-scale model sampling, and an ensemble model quality assessment (QA) strategy of combining individual QA methods to improve model generation and ranking of AlphaFold2 and AlphaFold3.

Improving AlphaFold2- and AlphaFold3-Based Protein Complex Structure Prediction With MULTICOM4 in CASP16.

With AlphaFold achieving high-accuracy tertiary structure prediction for most single-chain proteins (monomers), the next major challenge in protein structure prediction is to accurately model multichain protein complexes (multimers). We developed MULTICOM4, the latest version of the MULTICOM system, to improve protein complex structure prediction by integrating transformer-based AlphaFold2, diffusion model-based AlphaFold3, and our in-house techniques. These include protein complex stoichiometry prediction, diverse multiple sequence alignment (MSA) generation leveraging both sequence and structure comparison, modeling exception handling, and deep learning-based protein model quality assessment.

Global modulation of gene expression and transcriptome size in aneuploid combinations of maize.

Genomic imbalance refers to the more severe phenotypic consequences of changing a single chromosome compared to changing the whole genomic set. Previous genomic imbalance studies in maize have identified gene expression modulation in aneuploids of single chromosome arms. Here, the modulation of gene expression in more complex aneuploids, e.

Protein-Ligand Structure and Affinity Prediction in CASP16 Using a Geometric Deep Learning Ensemble and Flow Matching.

Predicting the structure of ligands bound to proteins is a foundational problem in modern biotechnology and drug discovery, yet little is known about how to combine the predictions of protein-ligand structure (poses) produced by the latest deep learning methods to identify the best poses and how to accurately estimate the binding affinity between a protein target and a list of ligand candidates. Further, a blind benchmarking and assessment of protein-ligand structure and binding affinity prediction is necessary to ensure it generalizes well to new settings. Towards this end, we introduce MULTICOM_ligand, a deep learning-based protein-ligand structure and binding affinity prediction ensemble featuring structural consensus ranking for unsupervised pose ranking and a new deep generative flow matching model for joint structure and binding affinity prediction.

Starfish-inspired wearable bioelectronic systems for physiological signal monitoring during motion and real-time heart disease diagnosis.

Soft bioelectronics enable noninvasive, continuous monitoring of physiological signals, essential for precision health care. However, capturing biosignals during physical activity, particularly biomechanical signals like cardiac mechanics, remains challenging due to motion-induced interference. Inspired by starfish's pentaradial symmetry, we introduce a starfish-like wearable bioelectronic system designed for high-fidelity signal monitoring during movement.

A Labeled Dataset for AI-based Cryo-EM Map Enhancement.

Cryo-electron microscopy (cryo-EM) has transformed structural biology by enabling near-atomic resolution imaging of macromolecular complexes. However, cryo-EM density maps suffer from intrinsic noise arising from structural sources, shot noise, and digital recording, which complicates accurate atomic structure building. While various methods for denoising cryo-EM density maps exist, there is a lack of standardized datasets for benchmarking artificial intelligence (AI) approaches.

Rapamycin enhances neurovascular, peripheral metabolic, and immune function in cognitively normal, middle-aged APOE4 Carriers: genotype-dependent effects compared to non-carriers.

Rapamycin, known for its anti-aging properties, shows promise as a preventive strategy for Alzheimer's disease (AD) in APOE4 carriers-the highest-risk group for late-onset AD. Here we show that a 4-week open-label trial of low-dose Rapamycin (Sirolimus; 1mg/day) significantly improved cerebral blood flow (CBF) relative to baseline in cognitively normal APOE4 carriers (E4(+)) aged 45-65. It also reduced inflammatory cytokines, enhanced lipid metabolism, increased short-chain fatty acids (SCFA) and enriched gut microbiome composition linked to SCFA production.

Improving AlphaFold2 and 3-based protein complex structure prediction with MULTICOM4 in CASP16.

With AlphaFold achieving high-accuracy tertiary structure prediction for most single-chain proteins (monomers), the next major challenge in protein structure prediction is accurately modeling multi-chain protein complexes (multimers). We developed MULTICOM4, the latest version of the MULTICOM system, to improve protein complex structure prediction by integrating transformer-based AlphaFold2, diffusion model-based AlphaFold3, and our in-house techniques. These include protein complex stoichiometry prediction, diverse multiple sequence alignment (MSA) generation leveraging both sequence and structure comparison, modeling exception handling, and deep learning-based model quality assessment.

Reconstructing 3D chromosome structures from single-cell Hi-C data with SO(3)-equivariant graph neural networks.

The spatial conformation of chromosomes and genomes of single cells is relevant to cellular function and useful for elucidating the mechanism underlying gene expression and genome methylation. The chromosomal contacts (i.e.

CryoTEN: efficiently enhancing cryo-EM density maps using transformers.

Motivation: Cryogenic electron microscopy (cryo-EM) is a core experimental technique used to determine the structure of macromolecules such as proteins. However, the effectiveness of cryo-EM is often hindered by the noise and missing density values in cryo-EM density maps caused by experimental conditions such as low contrast and conformational heterogeneity. Although various global and local map-sharpening techniques are widely employed to improve cryo-EM density maps, it is still challenging to efficiently improve their quality for building better protein structures from them.

Assessing the predicted impact of single amino acid substitutions in MAPK proteins for CAGI6 challenges.

New thermodynamic and functional studies have been recently conducted to evaluate the impact of amino acid substitutions on the Mitogen Activated Protein Kinases 1 and 3 (MAPK1/3). The Critical Assessment of Genome Interpretation (CAGI) data provider, at Sapienza University of Rome, measured the unfolding free energy and the enzymatic activity of a set of variants (MAPK challenge dataset). Thermodynamic measurements for the denaturant-induced equilibrium unfolding of the phosphorylated and unphosphorylated forms of the MAPKs were obtained by monitoring the far-UV circular dichroism and intrinsic fluorescence changes as a function of denaturant concentration.

Accurate Prediction of Protein Complex Stoichiometry by Integrating AlphaFold3 and Template Information.

Protein structure prediction methods require stoichiometry information (i.e., subunit counts) to predict the quaternary structure of protein complexes.

Estimating Protein Complex Model Accuracy Using Graph Transformers and Pairwise Similarity Graphs.

Motivation: Estimation of protein complex structure accuracy is an essential step in protein complex structure prediction and is also important for users to select good structural models for various applications, such as protein function analysis and drug design. Despite the success of structure prediction methods such as AlphaFold2 and AlphaFold3, predicting the quality of predicted complex structures (structural models) and selecting top ones from large model pools remains challenging.

Results: We present GATE, a novel method that uses graph transformers on pairwise model similarity graphs to predict the quality (accuracy) of complex structural models.

The SEPALLATA-like gene in regulates flower development by interacting with other MADS-box subfamily genes.

MADS-box genes are classified into five categories: ABCDE, including , , , , and other homologous genes, which play important roles in floral organ development. In this study, the cDNA sequence of the gene was cloned by RT-PCR and confirmed that this gene belongs to the MADS-box gene family. In addition, subcellular localization experiments showed that the protein was localized in the nucleus.

FlowDock: Geometric Flow Matching for Generative Protein-Ligand Docking and Affinity Prediction.

Motivation: Powerful generative AI models of protein-ligand structure have recently been proposed, but few of these methods support both flexible protein-ligand docking and affinity estimation. Of those that do, none can directly model multiple binding ligands concurrently or have been rigorously benchmarked on pharmacologically relevant drug targets, hindering their widespread adoption in drug discovery efforts.

Results: In this work, we propose FlowDock, the first deep geometric generative model based on conditional flow matching that learns to directly map unbound (apo) structures to their bound (holo) counterparts for an arbitrary number of binding ligands.