Biology subjects

Pokharel, S.

Publications and source records attributed to Pokharel, S..

4 recordsLinked to original sources

bioRxiv2024

pLM-DBPs: Enhanced DNA-Binding Protein Prediction in Plants Using Embeddings From Protein Language Models

DNA-binding proteins (DBPs) play critical roles in gene regulation, development, and environmental response across various species, including plants, animals, and microorganisms. While various machine learning and deep learning models have been developed to distinguish DNA-binding proteins (DBPs) from non-DNA-binding proteins (NDBPs), most available tools have focused on human and mouse datasets. As a result, there are limited studies specifically addressing plant-based DNA-binding proteins, which restricts our understanding of their unique roles and functions in plant biology. Developing an efficient framework for improving DBP prediction in plants would enhance our knowledge and enable precise gene expression control, accelerate crop improvement, enhance stress resilience, and optimize metabolic engineering for agricultural advancement. In this work, we developed a tool that uses a protein language model (pLM) pre-trained on millions of sequences. We evaluated several leading models, including ProtT5, Ankh, and ESM-2, and leveraged their high-dimensional, information-rich representations to improve the accuracy of DNA-binding protein prediction in plants significantly. Our final model, pLM-DBPs, a feed-forward neural network classifier utilizing ProtT5-based representations, outperformed existing approaches with a Matthews Correlation Coefficient (MCC) of 83.8% on the independent test set. This represents a 10% improvement over the previous state-of-the-art model for plant-based DBP prediction, highlighting its superior performance compared to the existing approaches.

bioinformatics↗

bioRxiv2024

CaLMPhosKAN: Prediction of General Phosphorylation Sites in Proteins via Fusion of Codon Aware Embeddings with Amino Acid Aware Embeddings and Wavelet-based Kolmogorov Arnold Network

The mapping from codon to amino acid is surjective due to the high degeneracy of the codon alphabet, suggesting that codon space might harbor higher information content. Embeddings from the codon language model have recently demonstrated success in various downstream tasks. However, predictive models for phosphorylation sites, arguably the most studied Post-Translational Modification (PTM), and PTM sites in general, have predominantly relied on amino acid-level representations. This work introduces a novel approach for prediction of phosphorylation sites by incorporating codon-level information through embeddings from a recently developed codon language model trained exclusively on protein-coding DNA sequences. Protein sequences are first meticulously mapped to reliable coding sequences and encoded using this encoder to generate codon-aware embeddings. These embeddings are then integrated with amino acid-aware embeddings obtained from a protein language model through an early fusion strategy. Subsequently, a window-level representation of the site of interest is formed from the fused embeddings within a defined window frame. A ConvBiGRU network extracts features capturing spatiotemporal correlations between proximal residues within the window, followed by a Kolmogorov-Arnold Network (KAN) based on the Derivative of Gaussian (DoG) wavelet transform function to produce the prediction inference for the site. We dub the overall model integrating these elements as CaLMPhosKAN. On independent testing with Serine-Threonine (combined) and Tyrosine test sets, CaLMPhosKAN outperforms existing approaches. Furthermore, we demonstrate the models effectiveness in predicting sites within intrinsically disordered regions of proteins. Overall, CaLMPhosKAN emerges as a robust predictor of general phosphosites in proteins. CaLMPhosKAN will be released publicly soon.

bioinformatics↗

bioRxiv2023

High prevalence of Bovine Tuberculosis reported in Cattle and Buffalo of Eastern Nepal

Livestock farming, specifically of cattle and buffalo, is crucial to Nepals economy, with more than 66% of the population involved in agriculture and animal husbandry. Animal tuberculosis (TB) caused by Mycobacterium bovis is a chronic disease that affects these animals and results in economic losses due to reduced milk and meat productivity, fertility and mortality. M. bovis also infects humans, non-human primates, goats and other mammals, and can afflict both cattle and buffalo. Our study is a part of routine surveillance of prevalent diseases, including M. bovis, in cattle and buffalo. We collected blood samples (n=400, 100 samples from each district) from selected eastern districts of Nepal. We used a Rapid Bovine TB Test Kit to test these samples for presence of M. bovis. Of the 400 samples collected, 74 animals (18.75%) tested positive for M. bovis, with the majority of positive samples coming from cattle (n=71, 17.75%) and only three from buffalo (<1%). Among the screened breeds of cattle and buffalo, Holstein Friesian cattle (HF) (n=43, 58%), Jersey-cross cattle (JX) (n=20, 27%), Local buffalo (n=8, 10.8%) and Murra breed buffalo (n=3, 4.1%) were found to carry M. bovis. The majority (50%) of infected animals were between 3-6 years old. Morang (n= 24 positive in cattle; n=1 positive in buffalo) and Jhapa (n= 22 positive in cattle; n=2 positive in buffalo) had the highest prevalence of M. bovis, while all the positive cases in Sunsari (n=19) and Udaypur (n=6) were in cattle. The fact that over 18% of the samples tested positive for M. bovis is of great concern. It is critical to thoroughly test animal products from these livestock prior to human consumption. To prevent and mitigate M. bovis-related infections in Nepal, a more comprehensive screening strategy coupled with more effective animal husbandry practices needs to be adapted.

microbiology↗

bioRxiv2022

Cdc42 prevents precocious Rho1 activation during cytokinesis in a Pak1-dependent manner

Cytokinesis consists of a series of coordinated multi-step events that partition a dividing cell. Accurate regulation of cytokinesis is essential for proliferation and genome integrity. In fission yeast, these coordinated events ensure that the actomyosin ring and septum start ingressing only after chromosome segregation. How cytokinetic events are coordinated remains unclear. The GTPase Cdc42 is required for the delivery of certain cell wall-building enzymes while the GTPase Rho1 is required for activation of these enzymes. Here we show that Cdc42 prevents early Rho1 activation during cytokinesis. Using an active Rho-probe, we show that even though the Rho1 activators Rgf1 and Rgf3 localize to the division site in early anaphase, Rho1 is not activated until late anaphase, just before the onset of ring constriction. We find that loss of Cdc42 activation enables precocious Rho1 activation in early anaphase. Furthermore, this inhibition of Rho1 activation is dependent on the downstream Cdc42 effector Pak1 kinase. Disrupting pak1 function results in early Rho1 activation accompanied by precocious septum deposition and ring constriction. We provide functional and genetic evidence which indicates that Pak1 regulates Rho1 activation likely via the regulation of its GEF Rgf1. Our work proposes a mechanism of Rho1 regulation by active Cdc42 to coordinate timely septum formation and cytokinesis fidelity.

cell biology↗