Machine Learning for Prediction of Drug Targets in Microbe Associated Cardiovascular Diseases by Incorporating Host‐pathogen Interaction Network Parameters

2021 ◽  
pp. 2100115
Author(s):  
Nirupma Singh ◽  
Sonika Bhatnagar
Keyword(s):  
Machine Learning ◽  
Cardiovascular Diseases ◽  
Drug Targets ◽  
Interaction Network ◽  
Host Pathogen Interaction ◽  
Network Parameters ◽  
Host Pathogen

scholarly journals In silico drug design for Staphylococcus aureus and development of host-pathogen interaction network

2018 ◽  
Vol 10 ◽  
pp. 58-70 ◽  
Author(s):  
Rucha M. Wadapurkar ◽  
M.D. Shilpa ◽  
Anil Kumar S. Katti ◽  
M.B. Sulochana
Keyword(s):  
Staphylococcus Aureus ◽  
Drug Design ◽  
In Silico ◽  
Interaction Network ◽  
Host Pathogen Interaction ◽  
In Silico Drug Design ◽  
Host Pathogen

scholarly journals Plant-Necrotroph Co-transcriptome Networks Illuminate a Metabolic Battlefield

2018 ◽  
Author(s):  
Wei Zhang ◽  
Jason A. Corwin ◽  
Daniel Copeland ◽  
Julie Feusier ◽  
Robert Eshbaugh ◽  
...  
Keyword(s):  
Interaction Network ◽  
In Planta ◽  
Systematic Map ◽  
Plant Host ◽  
Host Pathogen Interaction ◽  
Host Pathogen ◽  
Species Dynamics ◽  
Transcriptomic Level ◽  
The Impact ◽  
Interaction Research

AbstractA central goal of studying host-pathogen interaction research is to understand how the host and pathogen manipulate each other to promote their own fitness in a pathosystem. Co-transcriptomic approaches can simultaneously analyze dual transcriptomes during infection and provide a systematic map of the cross-kingdom communication between two species. Here we used the Arabidopsis-B. cinerea pathosystem to test how plant host and fungal pathogen interaction at the transcriptomic level during infection. We assessed the impact of natural genetic diversity in the pathogen and plant host by utilization of a collection of 96 isolates of B. cinerea infection on Arabidopsis wild-type and two mutants with jasmonate or salicylic acid compromised immunities. We identified ten B. cinerea gene co-expression networks (GCNs) that encode known or novel virulence mechanisms. We constructed a dual interaction network by combining four host-and ten pathogen-GCNs into a single network, which revealed potential connections between the fungal and plant GCNs involving both novel and conserved mechanisms. These co-transcriptome data shed lights on the potential mechanisms underlying host-pathogen interaction and illustrate the continued need for advancements of in planta analysis of dual-species dynamics.

scholarly journals Identification of Infection- and Defense-Related Genes via a Dynamic Host-Pathogen Interaction Network Using a Candida Albicans-Zebrafish Infection Model

2013 ◽  
Vol 5 (2) ◽  
pp. 137-152 ◽  
Author(s):  
Zong-Yu Kuo ◽  
Yung-Jen Chuang ◽  
Chun-Cheih Chao ◽  
Fu-Chen Liu ◽  
Chung-Yu Lan ◽  
...  
Keyword(s):  
Candida Albicans ◽  
Interaction Network ◽  
Infection Model ◽  
Host Pathogen Interaction ◽  
Host Pathogen ◽  
Zebrafish Infection

scholarly journals Plant–necrotroph co-transcriptome networks illuminate a metabolic battlefield

eLife ◽  
2019 ◽  
Vol 8 ◽  
Author(s):  
Wei Zhang ◽  
Jason A Corwin ◽  
Daniel Harrison Copeland ◽  
Julie Feusier ◽  
Robert Eshbaugh ◽  
...  
Keyword(s):  
Fungal Pathogen ◽  
Interaction Network ◽  
Transcriptome Data ◽  
Wild Type ◽  
Systematic Map ◽  
Plant Host ◽  
Host Pathogen Interaction ◽  
Host Pathogen ◽  
Transcriptomic Level ◽  
The Impact

A central goal of studying host-pathogen interaction is to understand how host and pathogen manipulate each other to promote their own fitness in a pathosystem. Co-transcriptomic approaches can simultaneously analyze dual transcriptomes during infection and provide a systematic map of the cross-kingdom communication between two species. Here we used the Arabidopsis-B. cinerea pathosystem to test how plant host and fungal pathogen interact at the transcriptomic level. We assessed the impact of genetic diversity in pathogen and host by utilization of a collection of 96 isolates infection on Arabidopsis wild-type and two mutants with jasmonate or salicylic acid compromised immunities. We identified ten B. cinereagene co-expression networks (GCNs) that encode known or novel virulence mechanisms. Construction of a dual interaction network by combining four host- and ten pathogen-GCNs revealed potential connections between the fungal and plant GCNs. These co-transcriptome data shed lights on the potential mechanisms underlying host-pathogen interaction.

scholarly journals Harnessing machine learning to unravel protein degradation in Escherichia coli

2020 ◽  
Author(s):  
Natan Nagar ◽  
Noa Ecker ◽  
Gil Loewenthal ◽  
Oren Avram ◽  
Daniella Ben-Meir ◽  
...  
Keyword(s):  
Machine Learning ◽  
Escherichia Coli ◽  
Drug Targets ◽  
Isotope Labeling ◽  
Interaction Network ◽  
Culture Method ◽  
Mass Spectrometry Analysis ◽  
Antibacterial Drug ◽  
Spectrometry Analysis ◽  
Quality Control Mechanism

AbstractDegradation of intracellular proteins in Gram-negative bacteria regulates various cellular processes and serves as a quality control mechanism by eliminating damaged proteins. To understand what causes the proteolytic machinery of the cell to degrade some proteins while sparing others, we employed a quantitative pulsed-SILAC (Stable Isotope Labeling with Amino acids in Cell culture) method followed by mass spectrometry analysis to determine the half-lives for the proteome of exponentially growing Escherichia coli, under standard conditions. We developed a likelihood-based statistical test to find actively degraded proteins, and identified dozens of novel proteins that are fast-degrading. Finally, we used structural, physicochemical and protein-protein interaction network descriptors to train a machine-learning classifier to discriminate fast-degrading proteins from the rest of the proteome. Our combined computational-experimental approach provides means for proteomic-based discovery of fast degrading proteins in bacteria and the elucidation of the factors determining protein half-lives and have implications for protein engineering. Moreover, as rapidly degraded proteins may play an important role in pathogenesis, our findings could identify new potential antibacterial drug targets.

scholarly journals QPowered Compound2DeNovoDrugPropMax –A Novel Programmatic Tool Incorporating Deep Learning and In Silico Methods for Automated In Silico Bio- Activity Discovery for any Compound of Interest

2021 ◽  
Author(s):  
Ben Geoffrey A S ◽  
Rafal Madaj ◽  
Akhil Sanker ◽  
Pavan Preetham Valluri
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
In Silico ◽  
Drug Target ◽  
Drug Targets ◽  
Learning Algorithms ◽  
Interaction Network ◽  
Network Data ◽  
Data Set ◽  
Target Interaction

Network data is composed of nodes and edges. Successful application of machine learning/deep<br>learning algorithms on network data to make node classification and link prediction have been shown<br>in the area of social networks through which highly customized suggestions are offered to social<br>network users. Similarly one can attempt the use of machine learning/deep learning algorithms on<br>biological network data to generate predictions of scientific usefulness. In the presented work,<br>compound-drug target interaction network data set from bindingDB has been used to train deep<br>learning neural network and a multi class classification has been implemented to classify PubChem<br>compound queried by the user into class labels of PBD IDs. This way target interaction prediction for<br>PubChem compounds is carried out using deep learning. The user is required to input the PubChem<br>Compound ID (CID) of the compound the user wishes to gain information about its predicted<br>biological activity and the tool outputs the RCSB PDB IDs of the predicted drug target interaction for<br>the input CID. Further the tool also optimizes the compound of interest of the user toward drug<br>likeness properties through a deep learning based structure optimization with a deep learning based<br>drug likeness optimization protocol. The tool also incorporates a feature to perform automated In<br>Silico modelling for the compounds and the predicted drug targets to uncover their protein-ligand<br>interaction profiles. The program is hosted, supported and maintained at the following GitHub<br><div>repository</div><div><br></div><div>https://github.com/bengeof/Compound2DeNovoDrugPropMax</div><div><br></div>Anticipating the rise in the use of quantum computing and quantum machine learning in drug discovery we use<br>the Penny-lane interface to quantum hardware to turn classical Keras layers used in our machine/deep<br>learning models into a quantum layer and introduce quantum layers into classical models to produce a<br>quantum-classical machine/deep learning hybrid model of our tool and the code corresponding to the<br><div>same is provided below</div><div><br></div>https://github.com/bengeof/QPoweredCompound2DeNovoDrugPropMax<br>

scholarly journals Network Analyses Based on Machine Learning Methods to Quantify Effects of Peptide–Protein Complexes as Drug Targets Using Cinnamon in Cardiovascular Diseases and Metabolic Syndrome as a Case Study

2021 ◽  
Vol 12 ◽  
Author(s):  
Yingying Wang ◽  
Lili Wang ◽  
Yinhe Liu ◽  
Keshen Li ◽  
Honglei Zhao
Keyword(s):  
Machine Learning ◽  
Metabolic Syndrome ◽  
Cardiovascular Diseases ◽  
Drug Targets ◽  
Protein Complexes ◽  
Deep Understanding ◽  
Learning Methods ◽  
Network Analyses ◽  
Machine Learning Methods

Peptide–protein complexes play important roles in multiple diseases such as cardiovascular diseases (CVDs) and metabolic syndrome (MetS). The peptides may be the key molecules in the designing of inhibitors or drug targets. Many Chinese traditional drugs are shown to play various roles in different diseases, and comprehensive analyses should be performed using networks which could offer more information than results generated from a single level. In this study, a network analysis pipeline was designed based on machine learning methods to quantify the effects of peptide–protein complexes as drug targets. Three steps, namely, pathway filter, combined network construction, and biomarker prediction and validation based on peptides, were performed using cinnamon (CA) in CVDs and MetS as a case. Results showed that 17 peptide–protein complexes including six peptides and four proteins were identified as CA targets. The expressions of AKT1, AKT2, and ENOS were tested using qRT-PCR in a mouse model that was constructed. AKT2 was shown to be a CA-indicating biomarker, while E2F1 and ENOS were CA treatment targets. AKT1 was considered a diabetic responsive biomarker because it was down-regulated in diabetic but not related to CA. Taken together, the pipeline could identify new drug targets based on biological function analyses. This may provide a deep understanding of the drugs’ roles in different diseases which may foster the development of peptide–protein complex–based therapeutic approaches.

Sign in / Sign up

Export Citation Format

Share Document