ACP-CapsPred: an explainable computational framework for identification and functional prediction of anticancer peptides based on capsule network.

Cancer is a severe illness that significantly threatens human life and health. Anticancer peptides (ACPs) represent a promising therapeutic strategy for combating cancer. In silico methods enable rapid and accurate identification of ACPs without extensive human and material resources. This study proposes a two-stage computational framework called ACP-CapsPred, which can accurately identify ACPs and characterize their functional activities across different cancer types. ACP-CapsPred integrates a protein language model with evolutionary information and physicochemical properties of peptides, constructing a comprehensive profile of peptides. ACP-CapsPred employs a next-generation neural network, specifically capsule networks, to construct predictive models. Experimental results demonstrate that ACP-CapsPred exhibits satisfactory predictive capabilities in both stages, reaching state-of-the-art performance. In the first stage, ACP-CapsPred achieves accuracies of 80.25% and 95.71%, as well as F1-scores of 79.86% and 95.90%, on benchmark datasets Set 1 and Set 2, respectively. In the second stage, tasked with characterizing the functional activities of ACPs across five selected cancer types, ACP-CapsPred attains an average accuracy of 90.75% and an F1-score of 91.38%. Furthermore, ACP-CapsPred demonstrates excellent interpretability, revealing regions and residues associated with anticancer activity. Consequently, ACP-CapsPred presents a promising solution to expedite the development of ACPs and offers a novel perspective for other biological sequence analyses.

Enhanced Recognition of a Herbal Compound Epiberberine by a DNA Quadruplex-Duplex Structure.

The small molecule epiberberine (EPI) is a natural alkaloid with versatile bioactivities against several diseases including cancer and bacterial infection. EPI can induce the formation of a unique binding pocket at the 5' side of a human telomeric G-quadruplex (HTG) sequence with four telomeric repeats (Q4), resulting in a nanomolar binding affinity (KD approximately 26 nM) with significant fluorescence enhancement upon binding. It is important to understand (1) how EPI binding affects HTG structural stability and (2) how enhanced EPI binding may be achieved through the engineering of the DNA binding pocket. In this work, the EPI-binding-induced HTG structure stabilization effect was probed by a peptide nucleic acid (PNA) invasion assay in combination with a series of biophysical techniques. We show that the PNA invasion-based method may be useful for the characterization of compounds binding to DNA (and RNA) structures under physiological conditions without the need to vary the solution temperature or buffer components, which are typically needed for structural stability characterization. Importantly, the combination of theoretical modeling and experimental quantification allows us to successfully engineer Q4 derivative Q4-ds-A by a simple extension of a duplex structure to Q4 at the 5' end. Q4-ds-A is an excellent EPI binder with a KD of 8 nM, with the binding enhancement achieved through the preformation of a binding pocket and a reduced dissociation rate. The tight binding of Q4 and Q4-ds-A with EPI allows us to develop a novel magnetic bead-based affinity purification system to effectively extract EPI from Rhizoma coptidis (Huang Lian) extracts.

CapsEnhancer: An Effective Computational Framework for Identifying Enhancers Based on Chaos Game Representation and Capsule Network.

Enhancers are a class of noncoding DNA, serving as crucial regulatory elements in governing gene expression by binding to transcription factors. The identification of enhancers holds paramount importance in the field of biology. However, traditional experimental methods for enhancer identification demand substantial human and material resources. Consequently, there is a growing interest in employing computational methods for enhancer prediction. In this study, we propose a two-stage framework based on deep learning, termed CapsEnhancer, for the identification of enhancers and their strengths. CapsEnhancer utilizes chaos game representation to encode DNA sequences into unique images and employs a capsule network to extract local and global features from sequence "images". Experimental results demonstrate that CapsEnhancer achieves state-of-the-art performance in both stages. In the first and second stages, the accuracy surpasses the previous best methods by 8 and 3.5%, reaching accuracies of 94.5 and 95%, respectively. Notably, this study represents the pioneering application of computer vision methods to enhancer identification tasks. Our work not only contributes novel insights to enhancer identification but also provides a fresh perspective for other biological sequence analysis tasks.

Discovery and substrate specificity engineering of nucleotide halogenases.

C2'-halogenation has been recognized as an essential modification to enhance the drug-like properties of nucleotide analogs. The direct C2'-halogenation of the nucleotide 2'-deoxyadenosine-5'-monophosphate (dAMP) has recently been achieved using the Fe(II)/α-ketoglutarate-dependent nucleotide halogenase AdaV. However, the limited substrate scope of this enzyme hampers its broader applications. In this study, we report two halogenases capable of halogenating 2'-deoxyguanosine monophosphate (dGMP), thereby expanding the family of nucleotide halogenases. Computational studies reveal that nucleotide specificity is regulated by the binding pose of the phosphate group. Based on these findings, we successfully engineered the substrate specificity of these halogenases by mutating second-sphere residues. This work expands the toolbox of nucleotide halogenases and provides insights into the regulation mechanism of nucleotide specificity.

A two-stage computational framework for identifying antiviral peptides and their functional types based on contrastive learning and multi-feature fusion strategy.

Antiviral peptides (AVPs) have shown potential in inhibiting viral attachment, preventing viral fusion with host cells and disrupting viral replication due to their unique action mechanisms. They have now become a broad-spectrum, promising antiviral therapy. However, identifying effective AVPs is traditionally slow and costly. This study proposed a new two-stage computational framework for AVP identification. The first stage identifies AVPs from a wide range of peptides, and the second stage recognizes AVPs targeting specific families or viruses. This method integrates contrastive learning and multi-feature fusion strategy, focusing on sequence information and peptide characteristics, significantly enhancing predictive ability and interpretability. The evaluation results of the model show excellent performance, with accuracy of 0.9240 and Matthews correlation coefficient (MCC) score of 0.8482 on the non-AVP independent dataset, and accuracy of 0.9934 and MCC score of 0.9869 on the non-AMP independent dataset. Furthermore, our model can predict antiviral activities of AVPs against six key viral families (Coronaviridae, Retroviridae, Herpesviridae, Paramyxoviridae, Orthomyxoviridae, Flaviviridae) and eight viruses (FIV, HCV, HIV, HPIV3, HSV1, INFVA, RSV, SARS-CoV). Finally, to facilitate user accessibility, we built a user-friendly web interface deployed at https://awi.cuhk.edu.cn/∼dbAMP/AVP/.

AMPActiPred: A three-stage framework for predicting antibacterial peptides and activity levels with deep forest.

The emergence and spread of antibiotic-resistant bacteria pose a significant public health threat, necessitating the exploration of alternative antibacterial strategies. Antibacterial peptide (ABP) is a kind of antimicrobial peptide (AMP) that has the potential ability to fight against bacteria infection, offering a promising avenue for developing novel therapeutic interventions. This study introduces AMPActiPred, a three-stage computational framework designed to identify ABPs, characterize their activity against diverse bacterial species, and predict their activity levels. AMPActiPred employed multiple effective peptide descriptors to effectively capture the compositional features and physicochemical properties of peptides. AMPActiPred utilized deep forest architecture, a cascading architecture similar to deep neural networks, capable of effectively processing and exploring original features to enhance predictive performance. In the first stage, AMPActiPred focuses on ABP identification, achieving an Accuracy of 87.6% and an MCC of 0.742 on an elaborate dataset, demonstrating state-of-the-art performance. In the second stage, AMPActiPred achieved an average GMean at 82.8% in identifying ABPs targeting 10 bacterial species, indicating AMPActiPred can achieve balanced predictions regarding the functional activity of ABP across this set of species. In the third stage, AMPActiPred demonstrates robust predictive capabilities for ABP activity levels with an average PCC of 0.722. Furthermore, AMPActiPred exhibits excellent interpretability, elucidating crucial features associated with antibacterial activity. AMPActiPred is the first computational framework capable of predicting targets and activity levels of ABPs. Finally, to facilitate the utilization of AMPActiPred, we have established a user-friendly web interface deployed at https://awi.cuhk.edu.cn/∼AMPActiPred/.

Identifying Residues for Substrate Recognition in Human GPAT4 by Molecular Dynamics Simulations.

Glycerol-3-phosphate acyltransferase (GPAT) catalyzes the first step in triacylglycerol synthesis. Understanding its substrate recognition mechanism may help to design drugs to regulate the production of glycerol lipids in cells. In this work, we investigate how the native substrate, glycerol-3-phosphate (G3P), and palmitoyl-coenzyme A (CoA) bind to the human GPAT isoform GPAT4 via molecular dynamics simulations (MD). As no experimentally resolved GPAT4 structure is available, the AlphaFold model is employed to construct the GPAT4-substrate complex model. Using another isoform, GPAT1, we demonstrate that once the ligand binding is properly addressed, the AlphaFold complex model can deliver similar results to the experimentally resolved structure in MD simulations. Following the validated protocol of complex construction, we perform MD simulations using the GPAT4-substrate complex. Our simulations reveal that R427 is an important residue in recognizing G3P via a stable salt bridge, but its motion can bring the ligand to different binding hotspots on GPAT4. Such high flexibility can be attributed to the flexible region that exists only on GPAT4 and not on GPAT1. Our study reveals the substrate recognition mechanism of GPAT4 and hence paves the way towards designing GPAT4 inhibitors.

Identifying Antitubercular Peptides via Deep Forest Architecture with Effective Feature Representation.

Tuberculosis (TB) is a severe disease caused by Mycobacterium tuberculosis that poses a significant threat to human health. The emergence of drug-resistant strains has made the global fight against TB even more challenging. Antituberculosis peptides (ATPs) have shown promising results as a potential treatment for TB. However, conventional wet lab-based approaches to ATP discovery are time-consuming and costly and often fail to discover peptides with desired properties. To address these challenges, we propose a novel machine learning-based framework called ATPfinder that can significantly accelerate the discovery of ATP. Our approach integrates various efficient peptide descriptors and utilizes the deep forest algorithm to construct the model. This neural network-like cascading structure can effectively process and mine features without complex hyperparameter tuning. Our experimental results show that ATPfinder outperforms existing ATP prediction tools, achieving state-of-the-art performance with an accuracy of 89.3% and an MCC of 0.70. Moreover, our framework exhibits better robustness than baseline algorithms commonly used for other sequence analysis tasks. Additionally, the excellent interpretability of our model can assist researchers in understanding the critical features of ATP. Finally, we developed a downloadable desktop application to simplify the use of our framework for researchers. Therefore, ATPfinder can facilitate the discovery of peptide drugs and provide potential solutions for TB treatment. Our framework is freely available at https://github.com/lantianyao/ATPfinder/ (data sets and code) and https://awi.cuhk.edu.cn/dbAMP/ATPfinder.html (software).

Structural insights into the activation and inhibition of CXC chemokine receptor 3.

The chemotaxis of CD4+ type 1 helper cells and CD8+ cytotoxic lymphocytes, guided by interferon-inducible CXC chemokine 9-11 (CXCL9-11) and CXC chemokine receptor 3 (CXCR3), plays a critical role in type 1 immunity. Here we determined the structures of human CXCR3-DNGi complexes activated by chemokine CXCL11, peptidomimetic agonist PS372424 and biaryl-type agonist VUF11222, and the structure of inactive CXCR3 bound to noncompetitive antagonist SCH546738. Structural analysis revealed that PS372424 shares a similar orthosteric binding pocket to the N terminus of CXCL11, while VUF11222 buries deeper and activates the receptor in a distinct manner. We showed an allosteric binding site between TM5 and TM6, accommodating SCH546738 in the inactive CXCR3. SCH546738 may restrain the receptor at an inactive state by preventing the repacking of TM5 and TM6. By revealing the binding patterns and the pharmacological properties of the four modulators, we present the activation mechanisms of CXCR3 and provide insights for future drug development.

Predicting Anti-inflammatory Peptides by Ensemble Machine Learning and Deep Learning.

Inflammation is a biological response to harmful stimuli, aiding in the maintenance of tissue homeostasis. However, excessive or persistent inflammation can precipitate a myriad of pathological conditions. Although current treatments such as NSAIDs, corticosteroids, and immunosuppressants are effective, they can have side effects and resistance issues. In this backdrop, anti-inflammatory peptides (AIPs) have emerged as a promising therapeutic approach against inflammation. Leveraging machine learning methods, we have the opportunity to accelerate the discovery and investigation of these AIPs more effectively. In this study, we proposed an advanced framework by ensemble machine learning and deep learning for AIP prediction. Initially, we constructed three individual models with extremely randomized trees (ET), gated recurrent unit (GRU), and convolutional neural networks (CNNs) with attention mechanism and then used stacking architecture to build the final predictor. By utilizing various sequence encodings and combining the strengths of different algorithms, our predictor demonstrated exemplary performance. On our independent test set, our model achieved an accuracy, MCC, and F1-score of 0.757, 0.500, and 0.707, respectively, clearly outperforming other contemporary AIP prediction methods. Additionally, our model offers profound insights into the feature interpretation of AIPs, establishing a valuable knowledge foundation for the design and development of future anti-inflammatory strategies.