Structural and functional analysis of protein

Yadav, Neetu Singh; Kumar, Pawan; Singh, Indra

doi:10.1016/b978-0-323-89775-4.00026-2

Cited by 2 publications

(1 citation statement)

References 138 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To alleviate this issue, we introduce contrastive learning to boost the generative capacity of networks pθ and ϵ θ by enriching the supervised signals. However, it is unwise to construct positive instances by performing data augmentations on therapeutic peptides, as even minor perturbations may lead to significant functional changes (Yadav, Kumar, and Singh 2022). Hence, our focus lies on employing effective strategies for selecting negative instances.…”

Section: Multi-modal Contrastive Learning Strategymentioning

confidence: 99%

A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide Generation

Wang,

Liu,

Huang

et al. 2024

AAAI

View full text Add to dashboard Cite

Therapeutic peptides represent a unique class of pharmaceutical agents crucial for the treatment of human diseases. Recently, deep generative models have exhibited remarkable potential for generating therapeutic peptides, but they only utilize sequence or structure information alone, which hinders the performance in generation. In this study, we propose a Multi-Modal Contrastive Diffusion model (MMCD), fusing both sequence and structure modalities in a diffusion framework to co-generate novel peptide sequences and structures. Specifically, MMCD constructs the sequence-modal and structure-modal diffusion models, respectively, and devises a multi-modal contrastive learning strategy with inter-contrastive and intra-contrastive in each diffusion timestep, aiming to capture the consistency between two modalities and boost model performance. The inter-contrastive aligns sequences and structures of peptides by maximizing the agreement of their embeddings, while the intra-contrastive differentiates therapeutic and non-therapeutic peptides by maximizing the disagreement of their sequence/structure embeddings simultaneously. The extensive experiments demonstrate that MMCD performs better than other state-of-the-art deep generative methods in generating therapeutic peptides across various metrics, including antimicrobial/anticancer score, diversity, and peptide-docking.

show abstract

Section: Multi-modal Contrastive Learning Strategymentioning

confidence: 99%

A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide Generation

Wang,

Liu,

Huang

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

Genome-Wide Identification and Characterisation of Cytokinin-O-Glucosyltransferase (CGT) Genes of Rice Specific to Potential Pathogens

Palnam

Shanmugam

Tyagi

et al. 2022

Plants

View full text Add to dashboard Cite

Cytokinin glucosyltransferases (CGTs) are key enzymes of plants for regulating the level and function of cytokinins. In a genomic identification of rice CGTs, 41 genes with the plant secondary product glycosyltransferases (PSPG) motif of 44-amino-acid consensus sequence characteristic of plant uridine diphosphate (UDP)-glycosyltransferases (UGTs) were identified. In-silico physicochemical characterisation revealed that, though the CGTs belong to the same subfamily, they display varying molecular weights, ranging from 19.6 kDa to 59.7 kDa. The proteins were primarily acidic (87.8%) and hydrophilic (58.6%) and were observed to be distributed in the plastids (16), plasma membrane (13), mitochondria (5), and cytosol (4). Phylogenetic analysis of the CGTs revealed that their evolutionary relatedness ranged from 70–100%, and they aligned themselves into two major clusters. In a comprehensive analysis of the available transcriptomics data of rice samples representing different growth stages only the CGT, Os04g25440.1 was significantly expressed at the vegetative stage, whereas 16 other genes were highly expressed only at the reproductive growth stage. On the contrary, six genes, LOC_Os07g30610.1, LOC_Os04g25440.1, LOC_Os07g30620.1, LOC_Os04g25490.1, LOC_Os04g37820.1, and LOC_Os04g25800.1, were significantly upregulated in rice plants inoculated with Rhizoctonia solani (RS), Xoo (Xanthomonas oryzae pv. oryzae) and Mor (Magnaporthe oryzae). In a qRT-PCR analysis of rice sheath tissue susceptible to Rhizoctonia solani, Mor, and Xoo pathogens, compared to the sterile distilled water control, at 24 h post-infection only two genes displayed significant upregulation in response to all the three pathogens: LOC_Os07g30620.1 and LOC_Os04g25820.1. On the other hand, the expression of genes LOC_Os07g30610.1, LOC_Os04g25440, LOC_Os04g25490, and LOC_Os04g25800 were observed to be pathogen-specific. These genes were identified as the candidate-responsive CGT genes and could serve as potential susceptibility genes for facilitating pathogen infection.

show abstract

Structural and functional analysis of protein

Cited by 2 publications

References 138 publications

A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide Generation

A Multi-Modal Contrastive Diffusion Model for Therapeutic Peptide Generation

Genome-Wide Identification and Characterisation of Cytokinin-O-Glucosyltransferase (CGT) Genes of Rice Specific to Potential Pathogens

Contact Info

Product

Resources

About