Automatic construction of molecular similarity networks for visual graph mining in chemical space of bioactive peptides: an unsupervised learning approach

Aguilera‐Mendoza, Longendri; Marrero-Ponce, Yovani; García-Jacas, César R.; Chávez, Edgar; Beltran, Jesus A.; Guillén-Ramírez, Hugo A.; Brizuela, Carlos A.

doi:10.1038/s41598-020-75029-1

Cited by 46 publications

(95 citation statements)

References 86 publications

(138 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The starPepDB was processed using the starPep toolbox, a software designed to perform network analysis of data contained in this resource. 29 Thus, we filtered the database by metadata function using the "Antiparasitic" query and retrieved 550 APPs (see SI1-A, a FASTA file).…”

Section: Data Collectionmentioning

confidence: 99%

“…The starPep toolbox allowed us to create three types of networks: CSNs, HSPNs, and METNs. CSNs and HSPNs are similarity or correlation networks, 29 defined as G = (V, E) where V is a set of nodes and E is a set of edges. In these networks, nodes in V represent AMPs, characterized by multi-dimensional molecular descriptors vectors, and edges linking nodes in E are pairwise similarity relationships between sequence-based descriptors of the peptides.…”

Section: Creation Of Networkmentioning

confidence: 99%

“…Thus, nodes of CSNs and HSPNs are connected because they are similar to each other, instead of direct interactions among these compounds. 29 METNs are multilayer networks, defined as G = (V, E, L), where V and E are the sets of nodes and edges, same as in CSNs and HSPNs, and L is the set of layers, which represent different edge types or labels. 33 METNs have two layers: metadata and AMPs.…”

Section: Creation Of Networkmentioning

confidence: 99%

“…Some centrality measures were applied to identify the most important nodes, and these sequences were taken as queries against the graph database starPepDB to discover new potential APPs with similarity searching by group fusion (MAX-SIM rule) models, using the starPep toolbox (http://mobiosd-hub.com/starpep). 29 It is worth mentioning this is the first time we are exploring the chemical space from starPepDB to retrieve valuable information derived from AMPs. In addition, we evaluated the multi-query similarity searching models (mQSSMs) performance with five benchmarking data sets of APP/non-APPs, and we compared these results with performance metrics of ML APPs prediction servers AMPDiscover (https://biocom-ampdiscover.cicese.mx) 30 and AMPFun (http://fdblab.csie.ncu.edu.tw/AMPfun/index.html).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Exploring the Chemical Space of Antiparasitic Peptides and Discovery of New Promising Leads through a Novel Approach based on Network Science and Similarity Searching

Ayala-Ruano

Marrero-Ponce

Aguilera‐Mendoza

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Antimicrobial peptides (AMPs) are small bioactive chemicals that have appeared as promising compounds to treat a wide range of diseases. The effectiveness of AMPs resides in the wide range of mechanisms they can use for both killing microbes and modulating immune responses. However, the AMPs’ chemical space (AMPCS) is huge, it is estimated that there exist more than 1065 unique sequences of peptides with 50 residues or fewer, which represent a big challenge for the discovery of new promising sequences and the identification of common features, motifs, or relevant biological functions shared by these peptides. Therefore, we present a new approach based on network science and similarity searching to discover new potential AMPs, specifically antiparasitic peptides (APPs). We have taken advantage of network-based representation of APPs’ chemical space (APPCS) to retrieve valuable information, using three types of networks: chemical space (CSN), half-space proximal (HSPN), and metadata (METN). Some centrality measures were applied to identify the most important and non-redundant nodes, and these peptides were taken as queries (Qs) against the graph database starPepDB to discover new potential APPs with similarity searching by group fusion (MAX-SIM rule) models. We evaluated the multi-query similarity searching models (mQSSMs) performance with five benchmarking data sets of APP/non-APPs. It can be stated that the predictions performed by the best mQSSMs present a strong-to-very strong predictive agreement since their external Matthews correlation coefficient (MCC) values ranged from 0.834 to 0.965. Outstanding outcomes were attained by the mQSSM with 219 Qs from both networks CSN and HSPN (219Q_0.5_HB-HC-Singletons_CSN-HSPN) and by using 0.5 as similarity threshold, with MCC values greater than 0.85 in external datasets. Then, we compared the performance metrics of our mQSSMs with APPs prediction servers AMPDiscover and AMPFun. The model proposed in this report outperformed the machine learning approaches with statistically significant differences, showing the enormous potential of this method. After applying our method and additional filters, we proposed 95 repurposed leads as potential APPs, which have not been associated with this activity until now. In addition, we explored sequence similarities and motifs shared by these peptides, which can serve as templates for searching and designing new promising APPs. The analyses show that the similarity models proposed in this study could contribute to identifying APPs with high effectivity and reliability. Our models and pipeline are freely available through the starPep toolbox software at http://mobiosd-hub.com/starpep.

show abstract

Section: Data Collectionmentioning

confidence: 99%

Section: Creation Of Networkmentioning

confidence: 99%

Section: Creation Of Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exploring the Chemical Space of Antiparasitic Peptides and Discovery of New Promising Leads through a Novel Approach based on Network Science and Similarity Searching

Ayala-Ruano

Marrero-Ponce

Aguilera‐Mendoza

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The first of these peptides have been discovered decades ago and have been investigated ever since (4,(10)(11)(12). The list of amino acid sequences with antimicrobial activities is continuously increasing and they are accessible through various data bases (13)(14)(15)(16). To understand their mechanisms of action several of them have been investigated by a variety of biological, biochemical, and biophysical approaches (17,18).…”

Section: Introductionmentioning

confidence: 99%

Revealing the Mechanisms of Synergistic Action of Two Magainin Antimicrobial Peptides

Bechinger

Juhl

Glattard

et al. 2020

Front. Med. Technol.

View full text Add to dashboard Cite

The study of peptide-lipid and peptide-peptide interactions as well as their topology and dynamics using biophysical and structural approaches have changed our view how antimicrobial peptides work and function. It has become obvious that both the peptides and the lipids arrange in soft supramolecular arrangements which are highly dynamic and able to change and mutually adapt their conformation, membrane penetration, and detailed morphology. This can occur on a local and a global level. This review focuses on cationic amphipathic peptides of the magainin family which were studied extensively by biophysical approaches. They are found intercalated at the membrane interface where they cause membrane thinning and ultimately lysis. Interestingly, mixtures of two of those peptides namely magainin 2 and PGLa which occur naturally as a cocktail in the frog skin exhibit synergistic enhancement of antimicrobial activities when investigated together in antimicrobial assays but also in biophysical experiments with model membranes. Detailed dose-response curves, presented here for the first time, show a cooperative behavior for the individual peptides which is much increased when PGLa and magainin are added as equimolar mixture. This has important consequences for their bacterial killing activities and resistance development. In membranes that carry unsaturations both peptides align parallel to the membrane surface where they have been shown to arrange into mesophases involving the peptides and the lipids. This supramolecular structuration comes along with much-increased membrane affinities for the peptide mixture. Because this synergism is most pronounced in membranes representing the bacterial lipid composition it can potentially be used to increase the therapeutic window of pharmaceutical formulations.

show abstract

An efficient hybrid deep learning architecture for predicting short antimicrobial peptides

Nguyen,

Nguyen‐Vo,

et al. 2024

Proteomics

View full text Add to dashboard Cite

Short‐length antimicrobial peptides (AMPs) have been demonstrated to have intensified antimicrobial activities against a wide spectrum of microbes. Therefore, exploration of novel and promising short AMPs is highly essential in developing various types of antimicrobial drugs or treatments. In addition to experimental approaches, computational methods have been developed to improve screening efficiency. Although existing computational methods have achieved satisfactory performance, there is still much room for model improvement. In this study, we proposed iAMP‐DL, an efficient hybrid deep learning architecture, for predicting short AMPs. The model was constructed using two well‐known deep learning architectures: the long short‐term memory architecture and convolutional neural networks. To fairly assess the performance of the model, we compared our model with existing state‐of‐the‐art methods using the same independent test set. Our comparative analysis shows that iAMP‐DL outperformed other methods. Furthermore, to assess the robustness and stability of our model, the experiments were repeated 10 times to observe the variation in prediction efficiency. The results demonstrate that iAMP‐DL is an effective, robust, and stable framework for detecting promising short AMPs. Another comparative study of different negative data sampling methods also confirms the effectiveness of our method and demonstrates that it can also be used to develop a robust model for predicting AMPs in general. The proposed framework was also deployed as an online web server with a user‐friendly interface to support the research community in identifying short AMPs.

show abstract

Automatic construction of molecular similarity networks for visual graph mining in chemical space of bioactive peptides: an unsupervised learning approach

Cited by 46 publications

References 86 publications

Exploring the Chemical Space of Antiparasitic Peptides and Discovery of New Promising Leads through a Novel Approach based on Network Science and Similarity Searching

Exploring the Chemical Space of Antiparasitic Peptides and Discovery of New Promising Leads through a Novel Approach based on Network Science and Similarity Searching

Revealing the Mechanisms of Synergistic Action of Two Magainin Antimicrobial Peptides

An efficient hybrid deep learning architecture for predicting short antimicrobial peptides

Contact Info

Product

Resources

About