ITP-Pred: an interpretable method for predicting, therapeutic peptides with fused features low-dimension representation

2020 ◽  
Author(s):  
Lijun Cai ◽  
Li Wang ◽  
Xiangzheng Fu ◽  
Chenxing Xia ◽  
Xiangxiang Zeng ◽  
...  
Keyword(s):  
Short Term Memory ◽  
Feature Fusion ◽  
Chemical Properties ◽  
Feature Representation ◽  
Therapeutic Peptide ◽  
Independent Verification ◽  
Therapeutic Peptides ◽  
Pharmaceutical Industries ◽  
Peptide Prediction ◽  
Physical And Chemical

Abstract The peptide therapeutics market is providing new opportunities for the biotechnology and pharmaceutical industries. Therefore, identifying therapeutic peptides and exploring their properties are important. Although several studies have proposed different machine learning methods to predict peptides as being therapeutic peptides, most do not explain the decision factors of model in detail. In this work, an Interpretable Therapeutic Peptide Prediction (ITP-Pred) model based on efficient feature fusion was developed. First, we proposed three kinds of feature descriptors based on sequence and physicochemical property encoded, namely amino acid composition (AAC), group AAC and coding autocorrelation, and concatenated them to obtain the feature representation of therapeutic peptide. Then, we input it into the CNN-Bi-directional Long Short-Term Memory (BiLSTM) model to automatically learn recognition of therapeutic peptides. The cross-validation and independent verification experiments results indicated that ITP-Pred has a higher prediction performance on the benchmark dataset than other comparison methods. Finally, we analyzed the output of the model from two aspects: sequence order and physical and chemical properties, mining important features as guidance for the design of better models that can complement existing methods.

scholarly journals PPTPP: a novel therapeutic peptide prediction method using physicochemical property encoding and adaptive feature representation learning

2020 ◽  
Vol 36 (13) ◽  
pp. 3982-3987 ◽  
Author(s):  
Yu P Zhang ◽  
Quan Zou
Keyword(s):  
Physicochemical Property ◽  
Prediction Method ◽  
Peptide Identification ◽  
Representation Learning ◽  
Feature Representation ◽  
Supplementary Information ◽  
Therapeutic Peptide ◽  
Therapeutic Peptides ◽  
Peptide Prediction ◽  
Massive Data Processing

Abstract Motivation Peptide is a promising candidate for therapeutic and diagnostic development due to its great physiological versatility and structural simplicity. Thus, identifying therapeutic peptides and investigating their properties are fundamentally important. As an inexpensive and fast approach, machine learning-based predictors have shown their strength in therapeutic peptide identification due to excellences in massive data processing. To date, no reported therapeutic peptide predictor can perform high-quality generic prediction and informative physicochemical properties (IPPs) identification simultaneously. Results In this work, Physicochemical Property-based Therapeutic Peptide Predictor (PPTPP), a Random Forest-based prediction method was presented to address this issue. A novel feature encoding and learning scheme were initiated to produce and rank physicochemical property-related features. Besides being capable of predicting multiple therapeutics peptides with high comparability to established predictors, the presented method is also able to identify peptides’ informative IPP. Results presented in this work not only illustrated the soundness of its working capacity but also demonstrated its potential for investigating other therapeutic peptides. Availability and implementation https://github.com/YPZ858/PPTPP. Supplementary information Supplementary data are available at Bioinformatics online.

Physicochemical studies and rheological modelling of Albizia lebbeck (AL) gum exudates

2014 ◽  
Vol 43 (4) ◽  
pp. 228-244 ◽  
Author(s):  
Nnabuk Okon Eddy ◽  
Inemesit Udofia ◽  
Adamu Uzairu
Keyword(s):  
Chemical Properties ◽  
Physicochemical Analysis ◽  
Rheological Parameters ◽  
Capillary Viscometer ◽  
Albizia Lebbeck ◽  
Content Type ◽  
Molecular Arrangement ◽  
Pharmaceutical Industries ◽  
Physical And Chemical ◽  
Scanning Electron

Purpose – The purpose of this study is to determine the physicochemical and rheological parameters of Albizia lebbeck gum. Design/methodology/approach – Physicochemical analysis was carried out using recommended methods. Gas chromatography mass spectrophotometer and Fourier transformed infra red (FTIR) analyses were carried out using their respective spectrophotometer. Scanning electron microscopy was carried out using scanning electron microscope, while rheological measurements were carried out using Ubbelohde capillary viscometer, digital Brookfield DV 1 viscometer and a rheometer. Findings – Albizia zygia gum is an ionic gum with unique physical and chemical properties. Scanning electron micrograph revealed that the internal structure of the gum is porous with irregular molecular arrangement. Thermodynamic parameters of viscous flow indicated the existence of few inter- and intra-molecular interactions, and the attainment of transition state was linked to bond breaking. Coil overlap transition studies revealed the existence of dilute and concentrated regimes. The viscosity of the gum was also found to decrease with decrease in the charge of cation (such that Al3+ > Ca2+ > K+) and with increase in ionic strength. Research limitations/implications – The paper provided information on physicochemical and rheological characteristics/behaviour of Albizia zygia gum, of Nigerian origin. From this information, possible application of this gum in the food and pharmaceutical industries can be deduced. Originality/value – The paper is original since information concerning Albizia zygia gum of Nigerian origin are not well documented as established in the work. It also adds values on the use of Albizia zygia gum, either on its own or in combination with other gums for industrial purpose.

scholarly journals Rheological characterisation of chitosan/sodium lauryl ether sulfate complexes

2019 ◽  
pp. 152-162
Author(s):  
Jelena Milinkovic-Budincic ◽  
Lidija Petrovic ◽  
Jadranka Fraj ◽  
Sandra Bucko ◽  
Jaroslav Katona ◽  
...  
Keyword(s):  
Rheological Properties ◽  
Chemical Properties ◽  
Cationic Polyelectrolyte ◽  
Rheological Parameters ◽  
Mass Ratio ◽  
Sodium Lauryl Ether Sulfate ◽  
Ether Sulfate ◽  
Lauryl Ether ◽  
Pharmaceutical Industries ◽  
Physical And Chemical

Chitosan is a cationic biopolymer, which attracts more and more attention in recent years, due to its exceptional physical and chemical properties, expressive biocompatibility and possibilities of obtaining from renewable sources. Formed polymer/surfactant complexes affect changes in the rheological properties and the final result is the formation of coacervates. The purpose of this study was to investigate the rheological properties of aqueous solutions of cationic polyelectrolyte, chitosan and sodium lauryl ether sulfate (SLES), an anionic surfactant, widely used in the cosmetics industry. Using the Thermo Haake RS600 rheometer, changes in the rheological and elastic properties of chitosan and SLES mixtures have been identified, gained as a result of the interaction of the components. In all examined samples coefficient of thixotropy was increasing with increase SLES concentration and achieves a maximum value at the mass ratio chitosan:SLES 1:2, after which it reduces. The oscillatory measurements in mixtures, performed by amplitude sweep method at low oscillating frequency 1 Hz, show that the linear viscoelastic region increases with increasing SLES concentration up to the same chitosan:SLES mass ratio. By monitoring the changes in the rheological parameters of the mixtures over five days, it was observed that the viscosity, the coefficient of thixotropy and elasticity were increasing, indicating that changes in the system occur over a longer period of time. In that manner, obtained results indicate the possibility of using rheological methods for a more detailed description of the interaction in the chitosan/SLES mixtures, important for their application in cosmetics and pharmaceutical industries.

TP-MV: Therapeutic protein prediction by multi-view learning

2021 ◽  
Vol 17 ◽  
Author(s):  
Ke Yan ◽  
Hongwu Lv ◽  
Yichen Guo ◽  
Jie Wen ◽  
Bin Liu
Keyword(s):  
Drug Development ◽  
The Other ◽  
Challenging Problem ◽  
Peptide Recognition ◽  
Therapeutic Peptide ◽  
Discriminative Feature ◽  
Protein Prediction ◽  
Benchmark Datasets ◽  
Therapeutic Peptides ◽  
Peptide Prediction

Background: Therapeutic peptide prediction is critical for drug development and therapy. Researchers have been studying this essential task, developing several computational methods to identify different therapeutic peptide types. Objective: Most predictors are the specific methods for certain peptides. Currently, developing methods to predict the presence of multiple peptides remains a challenging problem. Moreover, it is still challenging to combine different features to make the therapeutic prediction. Method: In this paper, we proposed a new ensemble method TP-MV for general therapeutic peptide recognition. TP-MV is developed using the stacking framework in conjunction with the KNN, SVM, ET, RF, and XGB. Then TP-MV constructs a multi-view learning model as meta-classifiers to extract the discriminative feature for different peptides. Results: In the experiment, the proposed method outperforms the other existing methods on the benchmark datasets, indicating that the proposed method has the ability to predict multiple therapeutic peptides simultaneously. Conclusion: The TP-MV is a useful tool for predicting therapeutic peptides.

scholarly journals Forecasting Variation Trends of Stocks via Multiscale Feature Fusion and Long Short-Term Memory Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Yezhen Liu ◽  
Xilong Yu ◽  
Yanhua Wu ◽  
Shuhong Song
Keyword(s):  
Short Term Memory ◽  
Feature Fusion ◽  
Feature Representation ◽  
Data Sets ◽  
Short Term ◽  
Term Memory ◽  
History Data ◽  
Gate Structure ◽  
Validity Indices ◽  
Long Short Term Memory

Forecasting stock price trends accurately appears a huge challenge because the environment of stock markets is extremely stochastic and complicated. This challenge persistently motivates us to seek reliable pathways to guide stock trading. While the Long Short-Term Memory (LSTM) network has the dedicated gate structure quite suitable for the prediction based on contextual features, we propose a novel LSTM-based model. Also, we devise a multiscale convolutional feature fusion mechanism for the model to extensively exploit the contextual relationships hidden in consecutive time steps. The significance of our designed scheme is twofold. (1) Benefiting from the gate structure designed for both long- and short-term memories, our model can use the given stock history data more adaptively than traditional models, which greatly guarantees the prediction performance in financial time series (FTS) scenarios and thus profits the prediction of stock trends. (2) The multiscale convolutional feature fusion mechanism can diversify the feature representation and more extensively capture the FTS feature essence than traditional models, which fairly facilitates the generalizability. Empirical studies conducted on three classic stock history data sets, i.e., S&P 500, DJIA, and VIX, demonstrated the effectiveness and stability superiority of the suggested method against a few state-of-the-art models using multiple validity indices. For example, our method achieved the highest average directional accuracy (around 0.71) on the three employed stock data sets.

Size Distribution Analysis of Kaolin Using Laser Diffraction Technique

2011 ◽  
Vol 341-342 ◽  
pp. 108-112 ◽  
Author(s):  
Felix N.L. Ling ◽  
Khairul Anuar Kassim ◽  
Ahmad Tarmizi Abdul Karim
Keyword(s):  
Chemical Composition ◽  
Size Distribution ◽  
Chemical Properties ◽  
Diffraction Theory ◽  
Laser Diffraction ◽  
Distribution Analysis ◽  
Uniformity Coefficient ◽  
Size Uniformity ◽  
Pharmaceutical Industries ◽  
Physical And Chemical

Kaolin is widely used in ceramic, paper, and pharmaceutical industries. The suitability use of kaolin in industries will depend on its physical and chemical properties. The physical and chemical composition of Kaolin is dependent on its geological origin, geographic source and processing. Processed kaolin available in the market is normally graded by the manufacturer based on its physical and chemical composition. This paper is focused on the size distribution analysis of nine types/batches of processed kaolin and one raw kaolin soil by using laser diffraction technique (based on Fraunhofer diffraction theory) in accordance to BS ISO 13320:2009. The laser diffraction technique is widely used in the powder industries in determining the particle size distribution because of its simplicity and its repeatability. All the specimens were pre-sieved with a sieve of 2mm aperture size. The effective size, uniformity coefficient and coefficient of curvature of the material were also calculated to facilitate the size distribution analysis. The findings of this paper are expected to benefit industries in which size the distribution of the kaolin will directly or indirectly contribute to its suitability use.

scholarly journals A Deep Multimodal Model for Predicting Affective Responses Evoked by Movies Based on Shot Segmentation

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Chunxiao Wang ◽  
Jingjing Zhang ◽  
Wei Jiang ◽  
Shuang Wang
Keyword(s):  
Short Term Memory ◽  
Feature Fusion ◽  
Pearson Correlation ◽  
Feature Representation ◽  
Visual Features ◽  
Visual Feature ◽  
Temporal Attention ◽  
Video Content Analysis ◽  
Wide Range ◽  
Experienced Emotion

Predicting the emotions evoked in a viewer watching movies is an important research element in affective video content analysis over a wide range of applications. Generally, the emotion of the audience is evoked by the combined effect of the audio-visual messages of the movies. Current research has mainly used rough middle- and high-level audio and visual features to predict experienced emotions, but combining semantic information to refine features to improve emotion prediction results is still not well studied. Therefore, on the premise of considering the time structure and semantic units of a movie, this paper proposes a shot-based audio-visual feature representation method and a long short-term memory (LSTM) model incorporating a temporal attention mechanism for experienced emotion prediction. First, the shot-based audio-visual feature representation defines a method for extracting and combining audio and visual features of each shot clip, and the advanced pretraining models in the related audio-visual tasks are used to extract the audio and visual features with different semantic levels. Then, four components are included in the prediction model: a nonlinear multimodal feature fusion layer, a temporal feature capture layer, a temporal attention layer, and a sentiment prediction layer. This paper focuses on experienced emotion prediction and evaluates the proposed method on the extended COGNIMUSE dataset. The method performs significantly better than the state-of-the-art while significantly reducing the number of calculations, with increases in the Pearson correlation coefficient (PCC) from 0.46 to 0.62 for arousal and from 0.18 to 0.34 for valence in experienced emotion.

Statistical criteria of stellar population types

1966 ◽  
Vol 24 ◽  
pp. 101-110
Author(s):  
W. Iwanowska
Keyword(s):  
Stellar Population ◽  
Chemical Properties ◽  
Spectrophotometric Study ◽  
Physical And Chemical Properties ◽  
Population Type ◽  
The Galaxy ◽  
Distribution Parameters ◽  
Physical And Chemical ◽  
Statistical Criteria ◽  
And Chemical Properties

In connection with the spectrophotometric study of population-type characteristics of various kinds of stars, a statistical analysis of kinematical and distribution parameters of the same stars is performed at the Toruń Observatory. This has a twofold purpose: first, to provide a practical guide in selecting stars for observing programmes, second, to contribute to the understanding of relations existing between the physical and chemical properties of stars and their kinematics and distribution in the Galaxy.

Biophysical Measurement of Molecular Weight of Foot-and-Mouth Disease RNA Fragments

1974 ◽  
Vol 32 ◽  
pp. 262-263
Author(s):  
Sydney S. Breese ◽  
Howard L. Bachrach
Keyword(s):  
Chemical Properties ◽  
Foot And Mouth Disease ◽  
Mouth Disease ◽  
Distilled Water ◽  
Bovine Plasma ◽  
Mouth Disease Virus ◽  
Foot And Mouth ◽  
Carbon Coated ◽  
Rna Fragments ◽  
Physical And Chemical

Continuing studies on the physical and chemical properties of foot-and-mouth disease virus (FMDV) have included electron microscopy of RNA strands released when highly purified virus (1) was dialyzed against demlneralized distilled water. The RNA strands were dried on formvar-carbon coated electron microscope screens pretreated with 0.1% bovine plasma albumin in distilled water. At this low salt concentration the RNA strands were extended and were stained with 1% phosphotungstic acid. Random dispersions of strands were recorded on electron micrographs, enlarged to 30,000 or 40,000 X and the lengths measured with a map-measuring wheel. Figure 1 is a typical micrograph and Fig. 2 shows the distributions of strand lengths for the three major types of FMDV (A119 of 6/9/72; C3-Rezende of 1/5/73; and O1-Brugge of 8/24/73.

Tailoring microstructures of materials through biomimetics

1993 ◽  
Vol 51 ◽  
pp. 500-501
Author(s):  
Mehmet Sarikaya ◽  
Ilhan A. Aksay
Keyword(s):  
Chemical Properties ◽  
Design And Synthesis ◽  
Structure Sensitive ◽  
Macro Scale ◽  
Methods Of Synthesis ◽  
Successive Level ◽  
Engineering Materials ◽  
Physical And Chemical ◽  
And Chemical Properties ◽  
Synthesis Of Materials

Biomimetics involves investigation of structure, function, and methods of synthesis of biological composite materials. The goal is to apply this information to the design and synthesis of materials for engineering applications.Properties of engineering materials are structure sensitive through the whole spectrum of dimensions from nanometer to macro scale. The goal in designing and processing of technological materials, therefore, is to control microstructural evolution at each of these dimensions so as to achieve predictable physical and chemical properties. Control at each successive level of dimension, however, is a major challenge as is the retention of integrity between successive levels. Engineering materials are rarely fabricated to achieve more than a few of the desired properties and the synthesis techniques usually involve high temperature or low pressure conditions that are energy inefficient and environmentally damaging.In contrast to human-made materials, organisms synthesize composites whose intricate structures are more controlled at each scale and hierarchical order.

Sign in / Sign up

Export Citation Format

Share Document