Biology subjects

R, V.

Publications and source records attributed to R, V..

3 recordsLinked to original sources

bioRxiv2024

Human like severe hypertriglyceridemia in a high fat fed chicken model

Cardiovascular disease (CVD) is the biggest cause of mortality globally. Controlling the risk factors for CVD such as blood cholesterol and triglycerides is the hallmark of primary prevention of CVD. There are several drugs to control cholesterol that are available but not many approaches to reducing triglycerides safely are available. High blood triglycerides or hypertriglyceridemia in humans is classified as moderate (200-400 mg/dl plasma levels) severe (400-800 mg/dl) and very severe (>800 mg/dl). There are not many appropriate in vivo models to study human like severe hypertriglyceridemia. We show here that high fat fed chickens rapidly and in a sustained manner respond by demonstrating triglyceride levels reminiscent of severe hypertriglyceridemia in humans. Such a model could be useful in better understanding this human disease as well as serve to test new therapies.

pharmacology and toxicology↗

bioRxiv2018

DeepProteomics: Protein family classification using Shallow and Deep Networks

The knowledge regarding the function of proteins is necessary as it gives a clear picture of biological processes. Nevertheless, there are many protein sequences found and added to the databases but lacks functional annotation. The laboratory experiments take a considerable amount of time for annotation of the sequences. This arises the need to use computational techniques to classify proteins based on their functions. In our work, we have collected the data from Swiss-Prot containing 40433 proteins which is grouped into 30 families. We pass it to recurrent neural network(RNN), long short term memory(LSTM) and gated recurrent unit(GRU) model and compare it by applying trigram with deep neural network and shallow neural network on the same dataset. Through this approach, we could achieve maximum of around 78% accuracy for the classification of protein families.

genomics↗

bioRxiv2018

Protein Family Classification using Deep Learning

Protein classification is responsible for the biological sequence, we came up with an idea which deals with the classification of proteomics using deep learning algorithm. This algorithm focuses mainly to classify sequences of protein-vector which is used for the representation of proteomics. Selection of the type protein representation is challenging based on which output in terms of accuracy is depended on, The protein representation used here is n-gram i.e. 3-gram and Keras embedding used for biological sequences like protein. In this paper we are working on the Protein classification to show the strength and representation of biological sequence of the proteins.

genomics↗