scholarly journals Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron

Molecules ◽  
2021 ◽  
Vol 26 (21) ◽  
pp. 6669
Author(s):  
Mohammed Khaldoon Altalib ◽  
Naomie Salim
Keyword(s):  
Signal To Noise Ratio ◽  
Computational Procedure ◽  
New Drugs ◽  
Multi Layer Perceptron ◽  
Virtual Screen ◽  
Traditional Drug ◽  
Benchmark Datasets ◽  
Biological Similarity ◽  
Mdl Drug Data Report ◽  
Similarity Distance

Traditional drug development is a slow and costly process that leads to the production of new drugs. Virtual screening (VS) is a computational procedure that measures the similarity of molecules as one of its primary tasks. Many techniques for capturing the biological similarity between a test compound and a known target ligand have been established in ligand-based virtual screens (LBVSs). However, despite the good performances of the above methods compared to their predecessors, especially when dealing with molecules that have structurally homogenous active elements, they are not satisfied when dealing with molecules that are structurally heterogeneous. The main aim of this study is to improve the performance of similarity searching, especially with molecules that are structurally heterogeneous. The Siamese network will be used due to its capability to deal with complicated data samples in many fields. The Siamese multi-layer perceptron architecture will be enhanced by using two similarity distance layers with one fused layer, then multiple layers will be added after the fusion layer, and then the nodes of the model that contribute less or nothing during inference according to their signal-to-noise ratio values will be pruned. Several benchmark datasets will be used, which are: the MDL Drug Data Report (MDDR-DS1, MDDR-DS2, and MDDR-DS3), the Maximum Unbiased Validation (MUV), and the Directory of Useful Decoys (DUD). The results show the outperformance of the proposed method on standard Tanimoto coefficient (TAN) and other methods. Additionally, it is possible to reduce the number of nodes in the Siamese multilayer perceptron model while still keeping the effectiveness of recall on the same level.

scholarly journals A Hybrid Deep Learning Model for Predicting Protein Hydroxylation Sites

2018 ◽  
Vol 19 (9) ◽  
pp. 2817 ◽  
Author(s):  
Haixia Long ◽  
Bo Liao ◽  
Xingyu Xu ◽  
Jialiang Yang
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Learning Model ◽  
New Drugs ◽  
Post Translational Modifications ◽  
Novel Approach ◽  
Benchmark Datasets ◽  
Memory Network ◽  
Scoring Matrix ◽  
Deep Learning Model

Protein hydroxylation is one type of post-translational modifications (PTMs) playing critical roles in human diseases. It is known that protein sequence contains many uncharacterized residues of proline and lysine. The question that needs to be answered is: which residue can be hydroxylated, and which one cannot. The answer will not only help understand the mechanism of hydroxylation but can also benefit the development of new drugs. In this paper, we proposed a novel approach for predicting hydroxylation using a hybrid deep learning model integrating the convolutional neural network (CNN) and long short-term memory network (LSTM). We employed a pseudo amino acid composition (PseAAC) method to construct valid benchmark datasets based on a sliding window strategy and used the position-specific scoring matrix (PSSM) to represent samples as inputs to the deep learning model. In addition, we compared our method with popular predictors including CNN, iHyd-PseAAC, and iHyd-PseCp. The results for 5-fold cross-validations all demonstrated that our method significantly outperforms the other methods in prediction accuracy.

scholarly journals Predicting drug-target interactions from drug structure and protein sequence using novel convolutional neural networks

2019 ◽  
Vol 20 (S25) ◽  
Author(s):  
ShanShan Hu ◽  
Chenglin Zhang ◽  
Peng Chen ◽  
Pengying Gu ◽  
Jun Zhang ◽  
...  
Keyword(s):  
Drug Target ◽  
Large Scale ◽  
New Drugs ◽  
Accurate Identification ◽  
Protein Targets ◽  
Benchmark Datasets ◽  
Practical Tool ◽  
Auc Value ◽  
Improved Performance ◽  
Potential Interactions

Abstract Background Accurate identification of potential interactions between drugs and protein targets is a critical step to accelerate drug discovery. Despite many relative experimental researches have been done in the past decades, detecting drug-target interactions (DTIs) remains to be extremely resource-intensive and time-consuming. Therefore, many computational approaches have been developed for predicting drug-target associations on a large scale. Results In this paper, we proposed an deep learning-based method to predict DTIs only using the information of drug structures and protein sequences. The final results showed that our method can achieve good performance with the accuracies up to 92.0%, 90.0%, 92.0% and 90.7% for the target families of enzymes, ion channels, GPCRs and nuclear receptors of our created dataset, respectively. Another dataset derived from DrugBank was used to further assess the generalization of the model, which yielded an accuracy of 0.9015 and an AUC value of 0.9557. Conclusion It was elucidated that our model shows improved performance in comparison with other state-of-the-art computational methods on the common benchmark datasets. Experimental results demonstrated that our model successfully extracted more nuanced yet useful features, and therefore can be used as a practical tool to discover new drugs. Availability http://deeplearner.ahu.edu.cn/web/CnnDTI.htm.

scholarly journals Biomarker-Based Targeting of the Androgen-Androgen Receptor Axis in Advanced Prostate Cancer

2012 ◽  
Vol 2012 ◽  
pp. 1-14 ◽  
Author(s):  
Manish Kohli ◽  
Rui Qin ◽  
Rafael Jimenez ◽  
Scott M. Dehm
Keyword(s):  
Prostate Cancer ◽  
Advanced Prostate Cancer ◽  
Predictive Biomarkers ◽  
Cancer Therapeutics ◽  
Predictive Biomarker ◽  
Abiraterone Acetate ◽  
New Drugs ◽  
Traditional Drug ◽  
Castrate Resistant Prostate Cancer ◽  
Castrate Resistant

Recent therapeutic advances for managing advanced prostate cancer include the successful targeting of the androgen-AR axis with several new drugs in castrate resistant prostate cancer including abiraterone acetate and enzalutamide (MDV3100). This translational progress from “bench to bed-side” has resulted in an enlarging repertoire of novel and traditional drug choices now available for use in advanced prostate cancer therapeutics, which has had a positive clinical impact in prolonging longevity and quality of life of advanced prostate cancer patients. In order to further the clinical utility of these drugs, development of predictive biomarkers guiding individual therapeutic choices remains an ongoing challenge. This paper will summarize the potential in developing predictive biomarkers based on the pathophysiology of the androgen-AR axis in tumor tissue from patients with advanced prostate cancer as well as inherited variation in the patient’s genome. Specific examples of rational clinical trial designs incorporating potential predictive biomarkers from these pathways will illustrate several aspects of pharmacogenetic and pharmacogenomic predictive biomarker development in advanced prostate cancer therapeutics.

scholarly journals Deep Learning-Based Ultrasonic Testing to Evaluate the Porosity of Additively Manufactured Parts with Rough Surfaces

Metals ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. 290
Author(s):  
Seong-Hyun Park ◽  
Jung-Yean Hong ◽  
Taeho Ha ◽  
Sungho Choi ◽  
Kyung-Young Jhang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Ultrasonic Testing ◽  
Signal To Noise Ratio ◽  
Rough Surfaces ◽  
Acoustic Microscopy ◽  
Processing Conditions ◽  
Multi Layer Perceptron ◽  
Ultrasonic Signals ◽  
Low Snr

Ultrasonic testing (UT) has been actively studied to evaluate the porosity of additively manufactured parts. Currently, ultrasonic measurements of as-deposited parts with a rough surface remain problematic because the surface lowers the signal-to-noise ratio (SNR) of ultrasonic signals, which degrades the UT performance. In this study, various deep learning (DL) techniques that can effectively extract the features of defects, even from signals with a low SNR, were applied to UT, and their performance in terms of the porosity evaluation of additively manufactured parts with rough surfaces was investigated. Experimentally, the effects of the processing conditions of additive manufacturing on the resulting porosity were first analyzed using both optical and scanning acoustic microscopy. Second, convolutional neural network (CNN), deep neural network, and multi-layer perceptron models were trained using time-domain ultrasonic signals obtained from additively manufactured specimens with various levels of porosity and surface roughness. The experimental results showed that all the models could evaluate porosity accurately, even that of the as-deposited specimens. In particular, the CNN delivered the best performance at 94.5%. However, conventional UT could not be applied because of the low SNR. The generalization performance when using newly manufactured as-deposited specimens was high at 90%.

scholarly journals In silico drug repositioning using deep learning and comprehensive similarity measures

2021 ◽  
Vol 22 (S3) ◽  
Author(s):  
Hai-Cheng Yi ◽  
Zhu-Hong You ◽  
Lei Wang ◽  
Xiao-Rui Su ◽  
Xi Zhou ◽  
...  
Keyword(s):  
Drug Repositioning ◽  
Similarity Measures ◽  
Predictive Ability ◽  
New Drugs ◽  
Potential Drug ◽  
Proposed Model ◽  
Disease Associations ◽  
Benchmark Datasets ◽  
Gated Recurrent Units ◽  
New Treatments

Abstract Background Drug repositioning, meanings finding new uses for existing drugs, which can accelerate the processing of new drugs research and development. Various computational methods have been presented to predict novel drug–disease associations for drug repositioning based on similarity measures among drugs and diseases. However, there are some known associations between drugs and diseases that previous studies not utilized. Methods In this work, we develop a deep gated recurrent units model to predict potential drug–disease interactions using comprehensive similarity measures and Gaussian interaction profile kernel. More specifically, the similarity measure is used to exploit discriminative feature for drugs based on their chemical fingerprints. Meanwhile, the Gaussian interactions profile kernel is employed to obtain efficient feature of diseases based on known disease-disease associations. Then, a deep gated recurrent units model is developed to predict potential drug–disease interactions. Results The performance of the proposed model is evaluated on two benchmark datasets under tenfold cross-validation. And to further verify the predictive ability, case studies for predicting new potential indications of drugs were carried out. Conclusion The experimental results proved the proposed model is a useful tool for predicting new indications for drugs or new treatments for diseases, and can accelerate drug repositioning and related drug research and discovery.

scholarly journals Drug Repurposing: A Paradigm Shift in Drug Discovery

2020 ◽  
Vol 5 (04) ◽  
pp. 60-68
Author(s):  
Saravanan Jayaram ◽  
Emdormi Rymbai ◽  
Deepa Sugumar ◽  
Divakar Selvaraj
Keyword(s):  
Drug Discovery ◽  
Success Rate ◽  
Chemical Structure ◽  
Target Identification ◽  
Drug Repurposing ◽  
New Drugs ◽  
Attractive Option ◽  
Traditional Drug ◽  
Repurposed Drugs

The traditional methods of drug discovery and drug development are a tedious, complex, and costly process. Target identification, target validation; lead identification; and lead optimization are a lengthy and unreliable process that further complicates the discovery of new drugs. A study of more than 15 years reports that the success rate in the discovery of new drugs in the fields of ophthalmology, cardiovascular, infectious disease, and oncology to be 32.6%, 25.5%, 25.2% and 3.4%, respectively. A tedious and costly process coupled with a very low success rate makes the traditional drug discovery a less attractive option. Therefore, an alternative to traditional drug discovery is drug repurposing, a process in which already existing drugs are repurposed for conditions other than which were originally intended. Typical examples of repurposed drugs are thalidomide, sildenafil, memantine, mirtazapine, mifepristone, etc. In recent times, several databases have been developed to hasten drug repurposing based on the side effect profile, the similarity of chemical structure, and target site. This work reviews the pivotal role of drug repurposing in drug discovery and the databases currently available for drug repurposing.

scholarly journals A global water resources ensemble of hydrological models: the eartH2Observe Tier-1 dataset

2016 ◽  
Author(s):  
Jaap Schellekens ◽  
Emanuel Dutra ◽  
Alberto Martínez-de la Torre ◽  
Gianpaolo Balsamo ◽  
Albert van Dijk ◽  
...  
Keyword(s):  
Land Surface ◽  
Snow Water Equivalent ◽  
Water Cycle ◽  
Signal To Noise Ratio ◽  
Model Performance ◽  
Meteorological Forcing ◽  
Unconstrained Model ◽  
Total Runoff ◽  
Ensemble Mean ◽  
Benchmark Datasets

Abstract. The dataset presented here consists of an ensemble of ten global hydrological and land surface models for the period 1979–2012 using a reanalysis-based meteorological forcing dataset (0.5° resolution). The current dataset serves as a state-of-the-art in current global hydrological modelling and as a benchmark for further improvements in the coming years. A signal-to-noise ratio analysis revealed low inter-model agreement over (i) snow-dominate regions and (ii) tropical rainforest and monsoon areas. The large uncertainty of precipitation in the tropics is not being reflected in the ensemble runoff. Verification of the results against benchmark datasets for evapotranspiration, snow cover, snow water equivalent, soil moisture anomaly and total water storage anomaly using the tools from The International Land Model Benchmarking Project (ILAMB) showed overall useful model performance, while the ensemble mean generally outperformed the single model estimates. The results also show that there is currently no single best model for all variables and that model performance is spatially variable. In our unconstrained model runs the ensemble mean of total runoff into the ocean was 46 268 km3/yr (334 kg/m2/yr) while the ensemble mean of total evaporation was 537 kg/m2/yr. All data are made available openly through a Water Cycle Integrator portal (WCI, wci.earth2observe.eu), and via a direct http and ftp download. The portal follows the protocols of the open geospatial consortium such as OPeNDAP, WCS and WMS. The doi for the data is: doi:10.5281/zenodo.167070

Adaptive One-Class gaussian processes allow accurate prioritization of oncology drug targets

2020 ◽  
Author(s):  
Antonio de Falco ◽  
Zoltan Dezso ◽  
Francesco Ceccarelli ◽  
Luigi Cerulo ◽  
Angelo Ciaramella ◽  
...  
Keyword(s):  
Gaussian Processes ◽  
Drug Targets ◽  
Process Model ◽  
New Drugs ◽  
Supplementary Information ◽  
Novel Approach ◽  
Benchmark Datasets ◽  
Hyperparameter Selection ◽  
The Cost ◽  
Selection Of

Abstract Motivation The cost of drug development has dramatically increased in the last decades, with the number new drugs approved per billion US dollars spent on R&D halving every year or less. The selection and prioritization of targets is one the the most influential decisions in drug discovery. Here we present a Gaussian Process model for the prioritization of drug targets cast as a problem of learning with only positive and unlabeled examples. Results Since the absence of negative samples does not allow standard methods for automatic selection of hyperparameters, we propose a novel approach for hyperparameter selection of the kernel in One Class Gaussian Processes. We compare our methods with state-of-the-art approaches on benchmark datasets and then show its application to druggability prediction of oncology drugs. Our score reaches an AUC 0.90 on a set of clinical trial targets starting from a small training set of 102 validated oncology targets. Our score recovers the majority of known drug targets and can be used to identify novel set of proteins as drug target candidates. Availability Source code implemented in Python is freely available for download at https://github.com/AntonioDeFalco/Adaptive-OCGP. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Drug Repurposing (DR): An Emerging Approach in Drug Discovery

2020 ◽  
Author(s):  
Mithun Rudrapal ◽  
Shubham J. Khairnar ◽  
Anil G. Jadhav
Keyword(s):  
Drug Discovery ◽  
De Novo ◽  
Drug Repositioning ◽  
Development Program ◽  
Drug Repurposing ◽  
New Drugs ◽  
Time Saving ◽  
Biological Targets ◽  
Drug Molecules ◽  
Traditional Drug

Drug repurposing (DR) (also known as drug repositioning) is a process of identifying new therapeutic use(s) for old/existing/available drugs. It is an effective strategy in discovering or developing drug molecules with new pharmacological/therapeutic indications. In recent years, many pharmaceutical companies are developing new drugs with the discovery of novel biological targets by applying the drug repositioning strategy in drug discovery and development program. This strategy is highly efficient, time saving, low-cost and minimum risk of failure. It maximizes the therapeutic value of a drug and consequently increases the success rate. Thus, drug repositioning is an effective alternative approach to traditional drug discovery process. Finding new molecular entities (NME) by traditional or de novo approach of drug discovery is a lengthy, time consuming and expensive venture. Drug repositioning utilizes the combined efforts of activity-based or experimental and in silico-based or computational approaches to develop/identify the new uses of drug molecules on a rational basis. It is, therefore, believed to be an emerging strategy where existing medicines, having already been tested safe in humans, are redirected based on a valid target molecule to combat particularly, rare, difficult-to-treat diseases and neglected diseases.

scholarly journals Drug Repurposing in Neurological Diseases: Opportunities and Challenges

2020 ◽  
Author(s):  
Xiao-Yuan Mao
Keyword(s):  
Neurological Diseases ◽  
Drug Repurposing ◽  
New Drugs ◽  
Drug Candidates ◽  
Therapeutic Benefits ◽  
Therapeutic Value ◽  
Traditional Drug ◽  
Approved Drugs ◽  
Structure Complexity ◽  
Refractory Diseases

Drug repurposing or repositioning refers to “studying of clinically approved drugs in one disease to see if they have therapeutic value and do not trigger side effects in other diseases.” Nowadays, it is a vital drug discovery approach to explore new therapeutic benefits of existing drugs or drug candidates in various human diseases including neurological disorders. This approach overcomes the shortage faced during traditional drug development in grounds of financial support and timeline. It is especially hopeful in some refractory diseases including neurological diseases. The feature that structure complexity of the nervous system and influence of blood–brain barrier permeability often becomes more difficult to develop new drugs in neuropathological conditions than diseases in other organs; therefore, drug repurposing is particularly of utmost importance. In this chapter, we discuss the role of drug repurposing in neurological diseases and make a summarization of repurposing candidates currently in clinical trials for neurological diseases and potential mechanisms as well as preliminary results. Subsequently we also outline drug repurposing approaches and limitations and challenges in the future investigations.

Sign in / Sign up

Export Citation Format

Share Document