Prediction of Essential Protein Using Machine Learning Technique

Inzamam-Ul-Hossain, Md.; Islam, Md. Rafiqul

doi:10.1007/978-3-030-91244-4_17

Cited by 2 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The PPI dataset is collected from the DIP [49]. The reason behind considering the yeast dataset is that the PPI of yeast is the more complete dataset among the other species [18]. This PPI dataset is used to calculate the topological features.…”

Section: Topological Featurementioning

confidence: 99%

“…On the other hand, essential proteins act as an important role to understand the structure of the organism, drug design, treatment and diagnosis, antibiotic preparation, cancer research, evolutionary studies, synthetic biology, etc [2]. Without the presence of this type of proteins, infertility or even cell death can be occured [18]. Based on the importance of the essential proteins, it is regarded as an important area in genomic research [22].…”

Section: Introductionmentioning

confidence: 99%

“…SGD [9], DEG [52], SGDP [19], and MIPS [32] are the databases that stored the information on the experimental results. The drawbacks of these experiments are that they are time and resource consuming, required a lot of effort [18]. Also, it can be applied to limited species [53].…”

Section: Introductionmentioning

confidence: 99%

“…So, the performance of the identification of the essential proteins with topological features is low. Also, the PPI network is still incomplete and contains many false positive and true negative values [18]. So, many existing methods have used biological features in addition to the topological features that are determined from the PPI network [53].…”

Section: Introductionmentioning

confidence: 99%

“…Many machine learning techniques are used to identify the essential proteins such as Naïve Bayes, XGBoost, SVM, Random Forest, etc. [18].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Efficiency due to data balancing in the prediction of essential proteins

Hossain

Islam

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Essential proteins are important for the survival of the organism. Those play a vital role to prepare antibiotics, disease diagnosis, understanding the organism structure, etc. That is why essential proteins now become one of the hot topics in current research. In recent times, many methods were proposed to identify the essential proteins. But the identification rate of the essential proteins is still low. Therefore, an efficient approach is required to identify the essential proteins with high performance. In this paper, a machine learning-based efficient method is proposed to identify the essential proteins. To identify the essential proteins, both balanced and imbalanced datasets are used here. For data balancing, different techniques are used to observe the efficiency of the methods. Both topological and biological features are used in this method. The S. Cerevisiae dataset is used to evaluate the proposed method. Another dataset of species E. coli is used to validate the performance of this method. Three classifiers such as Random Forest, LightGBM, XGBoost, and an ensemble method of these three classifiers are used to predict the essential proteins. The best performance is achieved from the balanced dataset from the SMOT+ENN and Random Forest classifier. The results are balanced both in accuracy and F1-score which is also best compared to the existing related methods.

show abstract

Section: Topological Featurementioning

confidence: 99%