Word2vec neural model-based technique to generate protein vectors for combating COVID-19: a machine learning approach

Abstract

The world was ambushed in 2019 by the COVID-19 virus which affected the health, economy, and lifestyle of individuals worldwide. One way of combating such a public health concern is by using appropriate, rapid, and unbiased diagnostic tools for quick detection of infected people. However, a current dearth of bioinformatics tools necessitates modeling studies to help diagnose COVID-19 cases. Molecular-based methods such as the real-time reverse transcription polymerase chain reaction (rRT-PCR) for detecting COVID-19 is time consuming and prone to contamination. Modern bioinformatics tools have made it possible to create large databases of protein sequences of various diseases, apply data mining techniques, and accurately diagnose diseases. However, the current sequence alignment tools that use these databases are not able to detect novel COVID-19 viral sequences due to high sequence dissimilarity. The objective of this study, therefore, was to develop models that can accurately classify COVID-19 viral sequences rapidly using protein vectors generated by neural word embedding technique. Five machine learning models; K nearest neighbor regression (KNN), support vector machine (SVM), random forest (RF), Linear discriminant analysis (LDA), and Logistic regression were developed using datasets from the National Center for Biotechnology. Our results suggest, the RF model performed better than all other models on the training dataset with 99% accuracy score and 99.5% accuracy on the testing dataset. The implication of this study is that, rapid detection of the COVID-19 virus in suspected cases could potentially save lives as less time will be needed to ascertain the status of a patient.

Multimodal Biomedical Data Fusion Using Sparse Canonical Correlation Analysis and Cooperative Learning: A Cohort Study on COVID-19

“…Using NLP techniques, particularly the Word2Vec model for viral embedding, has been recognized in prior research. But while earlier studies were often unimodal and focused on tasks like viral classification or evolution tracking, our method differs by integrating this with other data modalities, offering a more comprehensive view [48][49][50][51] . The merit of this method is evident in its ability to encapsulate the cumulative effects of multiple viral mutations and their relationships, a task that single-modal approaches might find challenging.…”

Extracting information and inferences from a large text corpus

“…Another limitation in word embedding is separating opposite word pairs such as “black” and “white”. The word pairs like these are usually semantically very close in vector space hence reducing the performance of word vectors in tasks such as sentiment analysis [ 31 – 33 ].…”

Fusing Sequence and Structural Knowledge by Heterogeneous Models to Accurately and Interpretively Predict Drug–Target Affinity

“…In addition to employing one-hot encoding, the utilization of complex feature representations for the drug SMILES and target sequences could potentially exert a substantial impact on the performance of DTA prediction. Within the scope of this investigation, a variety of complex feature representations were explored for the sequences of targets, encompassing the physical-chemical properties of amino acids, position-specific scoring matrix (PSSM) [29], Hidden Markov Models matrix (HMM) [30], Protbert [31], CNN, and Word2Vec [32]. For drugs, only the physical-chemical properties of atoms were considered.…”