scholarly journals Human Protein Sequence Classification using Machine Learning and Statistical Classification Techniques

2019 ◽  
Vol 8 (2) ◽  
pp. 3591-3599
Keyword(s):  
Machine Learning ◽  
Protein Sequence ◽  
Protein Function ◽  
Sequence Data ◽  
Human Protein ◽  
Statistical Classification ◽  
Classification Technique ◽  
Unknown Protein ◽  
Protein Sequence Data

In the field of computational biology, to gauge the meaningful and accurate feature for protein function predications, either the profile-based protein data or sequence-based data has been used. As we know that the prediction of enzyme class from an unknown protein is most interacted research in the current era. In this context, machine learning and statistical classification technique has been used. In this article, we have use six different machine learning and statistical classification technique such as CRT, QUEST, CHAID, C5.0, ANN and SVM for classification of 4314 number of human protein sequence data. These data are extracted form UniprotKB databank with the help of PROFEAT server. The extracted data are categorized in seven different classes. To manipulate the high dimensional protein sequence data with some missing value, the SPSS has been used for classification and estimation of the performance of classification technique. The experimental results highlight that the class C4, C5, C6 and C7 data are imbalanced that affect the overall performance of classification technique. This article provides an extensive comparative analysis of different classification technique on sequence-based protein data. The experimental analysis highlights that the SVM and C5.0 classification technique gives better result than others and can be used for protein classification and predictions.

scholarly journals Improving Generalizability of Protein Sequence Models with Data Augmentations

2021 ◽  
Author(s):  
Hongyu Shen ◽  
Layne C. Price ◽  
Taha Bahadori ◽  
Franziska Seeger
Keyword(s):  
Machine Learning ◽  
Protein Sequence ◽  
Data Augmentation ◽  
Sequence Data ◽  
Protein Sequences ◽  
Representation Learning ◽  
Amino Acid Replacement ◽  
Fine Tuning ◽  
Protein Sequence Data ◽  
Tuning Methods

AbstractWhile protein sequence data is an emerging application domain for machine learning methods, small modifications to protein sequences can result in difficult-to-predict changes to the protein’s function. Consequently, protein machine learning models typically do not use randomized data augmentation procedures analogous to those used in computer vision or natural language, e.g., cropping or synonym substitution. In this paper, we empirically explore a set of simple string manipulations, which we use to augment protein sequence data when fine-tuning semi-supervised protein models. We provide 276 different comparisons to the Tasks Assessing Protein Embeddings (TAPE) baseline models, with Transformer-based models and training datasets that vary from the baseline methods only in the data augmentations and representation learning procedure. For each TAPE validation task, we demonstrate improvements to the baseline scores when the learned protein representation is fixed between tasks. We also show that contrastive learning fine-tuning methods typically outperform masked-token prediction in these models, with increasing amounts of data augmentation generally improving performance for contrastive learning protein methods. We find the most consistent results across TAPE tasks when using domain-motivated transformations, such as amino acid replacement, as well as restricting the Transformer attention to randomly sampled sub-regions of the protein sequence. In rarer cases, we even find that information-destroying augmentations, such as randomly shuffling entire protein sequences, can improve downstream performance.

scholarly journals New families in the classification of glycosyl hydrolases based on amino acid sequence similarities

1993 ◽  
Vol 293 (3) ◽  
pp. 781-788 ◽  
Author(s):  
B Henrissat ◽  
A Bairoch
Keyword(s):  
Amino Acid ◽  
Amino Acid Sequence ◽  
Protein Sequence ◽  
Sequence Data ◽  
Data Bank ◽  
The Other ◽  
Glycosyl Hydrolases ◽  
Protein Sequence Data ◽  
Sequence Similarities

301 glycosyl hydrolases and related enzymes corresponding to 39 EC entries of the I.U.B. classification system have been classified into 35 families on the basis of amino-acid-sequence similarities [Henrissat (1991) Biochem. J. 280, 309-316]. Approximately half of the families were found to be monospecific (containing only one EC number), whereas the other half were found to be polyspecific (containing at least two EC numbers). A > 60% increase in sequence data for glycosyl hydrolases (181 additional enzymes or enzyme domains sequences have since become available) allowed us to update the classification not only by the addition of more members to already identified families, but also by the finding of ten new families. On the basis of a comparison of 482 sequences corresponding to 52 EC entries, 45 families, out of which 22 are polyspecific, can now be defined. This classification has been implemented in the SWISS-PROT protein sequence data bank.

scholarly journals Semi-Supervised Learning for Classification of Protein Sequence Data

2008 ◽  
Vol 16 (1) ◽  
pp. 5-29 ◽  
Author(s):  
Brian R. King ◽  
Chittibabu Guda
Keyword(s):  
Supervised Learning ◽  
Protein Sequence ◽  
Sequence Data ◽  
Predictive Performance ◽  
Support Vector ◽  
Classification Problems ◽  
Protein Sequence Data ◽  
Protein Sequence Classification ◽  
Comparative Results

Protein sequence data continue to become available at an exponential rate. Annotation of functional and structural attributes of these data lags far behind, with only a small fraction of the data understood and labeled by experimental methods. Classification methods that are based on semi-supervised learning can increase the overall accuracy of classifying partly labeled data in many domains, but very few methods exist that have shown their effect on protein sequence classification. We show how proven methods from text classification can be applied to protein sequence data, as we consider both existing and novel extensions to the basic methods, and demonstrate restrictions and differences that must be considered. We demonstrate comparative results against the transductive support vector machine, and show superior results on the most difficult classification problems. Our results show that large repositories of unlabeled protein sequence data can indeed be used to improve predictive performance, particularly in situations where there are fewer labeled protein sequences available, and/or the data are highly unbalanced in nature.

scholarly journals AC2: An Efficient Protein Sequence Compression Tool Using Artificial Neural Networks and Cache-Hash Models

Entropy ◽  
2021 ◽  
Vol 23 (5) ◽  
pp. 530
Author(s):  
Milton Silva ◽  
Diogo Pratas ◽  
Armando J. Pinho
Keyword(s):  
Protein Sequence ◽  
Sequence Data ◽  
Specific Protein ◽  
General Purpose ◽  
Amino Acid Sequences ◽  
Input Size ◽  
Protein Sequence Data ◽  
Analysis Application ◽  
Straightforward Solution ◽  
Human Coronaviruses

Recently, the scientific community has witnessed a substantial increase in the generation of protein sequence data, triggering emergent challenges of increasing importance, namely efficient storage and improved data analysis. For both applications, data compression is a straightforward solution. However, in the literature, the number of specific protein sequence compressors is relatively low. Moreover, these specialized compressors marginally improve the compression ratio over the best general-purpose compressors. In this paper, we present AC2, a new lossless data compressor for protein (or amino acid) sequences. AC2 uses a neural network to mix experts with a stacked generalization approach and individual cache-hash memory models to the highest-context orders. Compared to the previous compressor (AC), we show gains of 2–9% and 6–7% in reference-free and reference-based modes, respectively. These gains come at the cost of three times slower computations. AC2 also improves memory usage against AC, with requirements about seven times lower, without being affected by the sequences’ input size. As an analysis application, we use AC2 to measure the similarity between each SARS-CoV-2 protein sequence with each viral protein sequence from the whole UniProt database. The results consistently show higher similarity to the pangolin coronavirus, followed by the bat and human coronaviruses, contributing with critical results to a current controversial subject. AC2 is available for free download under GPLv3 license.

scholarly journals Machine learning for psychiatric patient triaging: an investigation of cascading classifiers

2018 ◽  
Vol 25 (11) ◽  
pp. 1481-1487 ◽  
Author(s):  
Vivek Kumar Singh ◽  
Utkarsh Shrivastava ◽  
Lina Bouayad ◽  
Balaji Padmanabhan ◽  
Anna Ialynytchev ◽  
...  
Keyword(s):  
Machine Learning ◽  
Psychiatric Patient ◽  
Classification Accuracy ◽  
Psychiatric Patients ◽  
Patient Records ◽  
Classification Technique ◽  
Machine Learning Approach ◽  
The One ◽  
Unique Dataset

Abstract Objective Develop an approach, One-class-at-a-time, for triaging psychiatric patients using machine learning on textual patient records. Our approach aims to automate the triaging process and reduce expert effort while providing high classification reliability. Materials and Methods The One-class-at-a-time approach is a multistage cascading classification technique that achieves higher triage classification accuracy compared to traditional multiclass classifiers through 1) classifying one class at a time (or stage), and 2) identification and application of the highest accuracy classifier at each stage. The approach was evaluated using a unique dataset of 433 psychiatric patient records with a triage class label provided by “I2B2 challenge,” a recent competition in the medical informatics community. Results The One-class-at-a-time cascading classifier outperformed state-of-the-art classification techniques with overall classification accuracy of 77% among 4 classes, exceeding accuracies of existing multiclass classifiers. The approach also enabled highly accurate classification of individual classes—the severe and mild with 85% accuracy, moderate with 64% accuracy, and absent with 60% accuracy. Discussion The triaging of psychiatric cases is a challenging problem due to the lack of clear guidelines and protocols. Our work presents a machine learning approach using psychiatric records for triaging patients based on their severity condition. Conclusion The One-class-at-a-time cascading classifier can be used as a decision aid to reduce triaging effort of physicians and nurses, while providing a unique opportunity to involve experts at each stage to reduce false positive and further improve the system’s accuracy.

Sign in / Sign up

Export Citation Format

Share Document