Structural predictions of protein-DNA binding: MELD-DNA

PDNAPred: Interpretable prediction of protein-DNA binding sites based on pre-trained protein language models

Protein-DNA interactions play critical roles in various biological processes and are essential for drug discovery. However, traditional experimental methods are labor-intensive and unable to keep pace with the increasing volume of protein sequences, leading to a substantial number of proteins lacking DNA-binding annotations. Therefore, developing an efficient computational method to identify protein-DNA binding sites is crucial. Unfortunately, most existing computational methods rely on manually selected features or protein structure information, making these methods inapplicable to large-scale prediction tasks. In this study, we introduced PDNAPred, a sequence-based method that combines two pre-trained protein language models with a designed CNN-GRU network to identify DNA-binding sites. Additionally, to tackle the issue of imbalanced dataset samples, we employed focal loss. Our comprehensive experiments demonstrated that PDNAPred significantly improved the accuracy of DNA-binding site prediction, outperforming existing state-of-the-art sequence-based methods. Remarkably, PDNAPred also achieved results comparable to advanced structure-based methods. The designed CNN-GRU network enhances its capability to detect DNA-binding sites accurately. Furthermore, we validated the versatility of PDNAPred by training it on RNA-binding site datasets, showing its potential as a general framework for amino acid binding site prediction. Finally, we conducted model interpretability analysis to elucidate the reasons behind PDNAPred's outstanding performance.

Improving prediction performance of general protein language model by domain-adaptive pretraining on DNA-binding protein

DNA-protein interactions exert the fundamental structure of many pivotal biological processes, such as DNA replication, transcription, and gene regulation. However, accurate and efficient computational methods for identifying these interactions are still lacking. In this study, we propose a method ESM-DBP through refining the DNA-binding protein sequence repertory and domain-adaptive pretraining based the general protein language model. Our method considers the lacking exploration of general language model for DNA-binding protein domain-specific knowledge, so we screen out 170,264 DNA-binding protein sequences to construct the domain-adaptive language model. Experimental results on four downstream tasks show that ESM-DBP provides a better feature representation of DNA-binding protein compared to the original language model, resulting in improved prediction performance and outperforming the state-of-the-art methods. Moreover, ESM-DBP can still perform well even for those sequences with only a few homologous sequences. ChIP-seq on two predicted cases further support the validity of the proposed method.

Geometric deep learning of protein-DNA binding specificity

Predicting protein-DNA binding specificity is a challenging yet essential task for understanding gene regulation. Protein-DNA complexes usually exhibit binding to a selected DNA target site, whereas a protein binds, with varying degrees of binding specificity, to a wide range of DNA sequences. This information is not directly accessible in a single structure. Here, to access this information, we present Deep Predictor of Binding Specificity (DeepPBS), a geometric deep-learning model designed to predict binding specificity from protein-DNA structure. DeepPBS can be applied to experimental or predicted structures. Interpretable protein heavy atom importance scores for interface residues can be extracted. When aggregated at the protein residue level, these scores are validated through mutagenesis experiments. Applied to designed proteins targeting specific DNA sequences, DeepPBS was demonstrated to predict experimentally measured binding specificity. DeepPBS offers a foundation for machine-aided studies that advance our understanding of molecular interactions and guide experimental designs and synthetic biology.

Discovering New Metallo-Deubiquitinase CSN5 Inhibitors by a Non-Catalytic Activity Assay Platform

COP9 signalosome catalytic subunit CSN5 plays a key role in tumorigenesis and tumor immunity, showing potential as an anticancer target. Currently, only a few CSN5 inhibitors have been reported, at least partially, due to the challenges in establishing assays for CSN5 deubiquitinase activity. Here, we present the establishment and validation of a simple and reliable non-catalytic activity assay platform for identifying CSN5 inhibitors utilizing a new fluorescent probe, CFP-1, that exhibits enhanced fluorescence and fluorescence polarization features upon binding to CSN5. By using this platform, we identified 2-aminothiazole-4-carboxylic acids as new CSN5 inhibitors, which inhibited CSN5 but slightly downregulated PD-L1 in cancer cells. Furthermore, through the integration of deep learning-enabled virtual screening, we discovered that shikonins are nanomolar CSN5 inhibitors, which can upregulate PD-L1 in HCT116 cells. The binding modes of these structurally distinct inhibitors with CSN5 were explored by using microsecond-scale molecular dynamics simulations and tryptophan quenching assays.

Molecular Modeling of Self-Assembling Peptides

Peptide epitopes mediate as many as 40% of protein-protein interactions and fulfill signaling, inhibition, and activation roles within the cell. Beyond protein recognition, some peptides can self- or coassemble into stable hydrogels, making them a readily available source of biomaterials. While these 3D assemblies are routinely characterized at the fiber level, there are missing atomistic details about the assembly scaffold. Such atomistic detail can be useful in the rational design of more stable scaffold structures and with improved accessibility to functional motifs. Computational approaches can in principle reduce the experimental cost of such an endeavor by predicting the assembly scaffold and identifying novel sequences that adopt said structure. Yet, inaccuracies in physical models and inefficient sampling have limited atomistic studies to short (two or three amino acid) peptides. Given recent developments in machine learning and advances in sampling strategies, we revisit the suitability of physical models for this task. We use the MELD (Modeling Employing Limited Data) approach to drive self-assembly in combination with generic data in cases where conventional MD is unsuccessful. Finally, despite recent developments in machine learning algorithms for protein structure and sequence predictions, we find the algorithms are not yet suited for studying the assembly of short peptides.

ULDNA: integrating unsupervised multi-source language models with LSTM-attention network for high-accuracy protein-DNA binding site prediction

Efficient and accurate recognition of protein-DNA interactions is vital for understanding the molecular mechanisms of related biological processes and further guiding drug discovery. Although the current experimental protocols are the most precise way to determine protein-DNA binding sites, they tend to be labor-intensive and time-consuming. There is an immediate need to design efficient computational approaches for predicting DNA-binding sites. Here, we proposed ULDNA, a new deep-learning model, to deduce DNA-binding sites from protein sequences. This model leverages an LSTM-attention architecture, embedded with three unsupervised language models that are pre-trained on large-scale sequences from multiple database sources. To prove its effectiveness, ULDNA was tested on 229 protein chains with experimental annotation of DNA-binding sites. Results from computational experiments revealed that ULDNA significantly improves the accuracy of DNA-binding site prediction in comparison with 17 state-of-the-art methods. In-depth data analyses showed that the major strength of ULDNA stems from employing three transformer language models. Specifically, these language models capture complementary feature embeddings with evolution diversity, in which the complex DNA-binding patterns are buried. Meanwhile, the specially crafted LSTM-attention network effectively decodes evolution diversity-based embeddings as DNA-binding results at the residue level. Our findings demonstrated a new pipeline for predicting DNA-binding sites on a large scale with high accuracy from protein sequence alone.

Probing the role of the protonation state of a minor groove-linker histidine in Exd-Hox-DNA binding

DNA recognition and targeting by transcription factors (TFs) through specific binding are fundamental in biological processes. Furthermore, the histidine protonation state at the TF-DNA binding interface can significantly influence the binding mechanism of TF-DNA complexes. Nevertheless, the role of histidine in TF-DNA complexes remains underexplored. Here, we employed all-atom molecular dynamics simulations using AlphaFold2-modeled complexes based on previously solved co-crystal structures to probe the role of the His-12 residue in the Extradenticle (Exd)-Sex combs reduced (Scr)-DNA complex when binding to Scr and Ultrabithorax (Ubx) target sites. Our results demonstrate that the protonation state of histidine notably affected the DNA minor-groove width profile and binding free energy. Examining flanking sequences of various binding affinities derived from SELEX-seq experiments, we analyzed the relationship between binding affinity and specificity. We uncovered how histidine protonation leads to increased binding affinity but can lower specificity. Our findings provide new mechanistic insights into the role of histidine in modulating TF-DNA binding.

DeepPBS: Geometric deep learning for interpretable prediction of protein-DNA binding specificity

Predicting specificity in protein-DNA interactions is a challenging yet essential task for understanding gene regulation. Here, we present Deep Predictor of Binding Specificity (DeepPBS), a geometric deep-learning model designed to predict binding specificity across protein families based on protein-DNA structures. The DeepPBS architecture allows investigation of different family-specific recognition patterns. DeepPBS can be applied to predicted structures, and can aid in the modeling of protein-DNA complexes. DeepPBS is interpretable and can be used to calculate protein heavy atom-level importance scores, demonstrated as a case-study on p53-DNA interface. When aggregated at the protein residue level, these scores conform well with alanine scanning mutagenesis experimental data. The inference time for DeepPBS is sufficiently fast for analyzing simulation trajectories, as demonstrated on a molecular-dynamics simulation of a Drosophila Hox-DNA tertiary complex with its cofactor. DeepPBS and its corresponding data resources offer a foundation for machine-aided protein-DNA interaction studies, guiding experimental choices and complex design, as well as advancing our understanding of molecular interactions.

When MELD Meets GaMD: Accelerating Biomolecular Landscape Exploration

We introduce Gaussian accelerated MELD (GaMELD) as a new method for exploring the energy landscape of biomolecules. GaMELD combines the strengths of Gaussian accelerated molecular dynamics (GaMD) and modeling employing limited data (MELD) to navigate complex energy landscapes. MELD uses replica-exchange molecular simulations to integrate limited and uncertain data into simulations via Bayesian inference. MELD has been successfully applied to problems of structure prediction like protein folding and complex structure prediction. However, the computational cost for MELD simulations has limited its broader applicability. The synergy of GaMD and MELD surmounts this limitation efficiently sampling the energy landscape at a lower computational cost (reducing the computational cost by a factor of 2 to six). Effectively, GaMD is used to shift energy distributions along replicas to increase the overlap in energy distributions across replicas, facilitating a random walk in replica space. We tested GaMELD on a benchmark set of 12 small proteins that have been previously studied through MELD and conventional MD. GaMELD consistently achieves accurate predictions with fewer replicas. By increasing the efficacy of replica exchange, GaMELD effectively accelerates convergence in the conformational space, enabling improved sampling across a diverse set of systems.

Structural Insights into Protein-Aptamer Recognitions Emerged from Experimental and Computational Studies

Aptamers are synthetic nucleic acids that are developed to target with high affinity and specificity chemical entities ranging from single ions to macromolecules and present a wide range of chemical and physical properties. Their ability to selectively bind proteins has made these compounds very attractive and versatile tools, in both basic and applied sciences, to such an extent that they are considered an appealing alternative to antibodies. Here, by exhaustively surveying the content of the Protein Data Bank (PDB), we review the structural aspects of the protein-aptamer recognition process. As a result of three decades of structural studies, we identified 144 PDB entries containing atomic-level information on protein-aptamer complexes. Interestingly, we found a remarkable increase in the number of determined structures in the last two years as a consequence of the effective application of the cryo-electron microscopy technique to these systems. In the present paper, particular attention is devoted to the articulated architectures that protein-aptamer complexes may exhibit. Moreover, the molecular mechanism of the binding process was analyzed by collecting all available information on the structural transitions that aptamers undergo, from their protein-unbound to the protein-bound state. The contribution of computational approaches in this area is also highlighted.

Computing Free Energies of Fold-Switching Proteins Using MELD x MD

Some proteins are conformational switches, able to transition between relatively different conformations. To understand what drives them requires computing the free-energy difference ΔGAB between their stable states, A and B. Molecular dynamics (MD) simulations alone are often slow because they require a reaction coordinate and must sample many transitions in between. Here, we show that modeling employing limited data (MELD) x MD on known endstates A and B is accurate and efficient because it does not require passing over barriers or knowing reaction coordinates. We validate this method on two problems: (1) it gives correct relative populations of α and β conformers for small designed chameleon sequences of protein G; and (2) it correctly predicts the conformations of the C-terminal domain (CTD) of RfaH. Free-energy methods like MELD x MD can often resolve structures that confuse machine-learning (ML) methods.

Proteomic applications in identifying protein-protein interactions

There are many things that can be used to characterize a protein. Size, isoelectric point, hydrophobicity, structure (primary to quaternary), and subcellular location are just a few parameters that are used. The most important feature of a protein, however, is its function. While there are many experiments that can indicate a protein's role, identifying the molecules it interacts with is probably the most definitive way of determining its function. Owing to technology limitations, protein interactions have historically been identified on a one molecule per experiment basis. The advent of high throughput multiplexed proteomic technologies in the 1990s, however, made identifying hundreds and thousands of proteins interactions within single experiments feasible. These proteomic technologies have dramatically increased the rate at which protein-protein interactions (PPIs) are discovered. While the improvement in mass spectrometry technology was an early driving force in the rapid pace of identifying PPIs, advances in sample preparation and chromatography have recently been propelling the field. In this chapter, we will discuss the importance of identifying PPIs and describe current state-of-the-art technologies that demonstrate what is currently possible in this important area of biological research.