Ravi Shankar

ProMaya: a hierarchical universal Deep Learning framework for accurate and interpretable Protein-Protein interaction identification

ProMaya identifies protein-protein interactions using a hierarchical graph-transformer framework, achieving >95% accuracy across nine species and outperforming existing tools by >12%.

GANGE: Achieving Sequencing Without Sequencing With Diffusion Guided Generative Genomic Transformer

GANGE is a deep-learning system that generates accurate genomic sequences from low-coverage, error-prone reads, reducing sequencing costs and enabling regulomics research without genome data.

DMRU: Generative Deep-Learning to unravel condition specific cytosine methylation in plants

DMRU is a generative deep-learning model that identifies condition-specific DNA methylation in plants with high accuracy across species and conditions.

PTF-Vac: An explainable and generative deep co-learning encoders-decoders system for ab-initio discovery of plant transcription factor binding sites

PTF-Vac discovers plant transcription factor binding sites using a generative deep learning model that outperforms existing methods and is independent of species and predefined motifs.

Decoding stress specific transcriptional regulation by causality aware Graph-Transformer deep learning

The paper introduces CTF-BIND, a deep learning framework that detects TF binding from RNA-seq data without ChIP-seq, achieving 93% accuracy in plant stress response analysis.

Explainable Deep-Learning on condition specific expression profiles reveals critical cytosines in gene regulation

The paper uses deep learning to identify critical cytosines in gene regulation across plant species by analyzing methylation and expression data.

Comprehensive analysis of computational approaches in plant transcription factors binding regions discovery

This paper evaluates computational methods for identifying transcription factor binding regions in plants, identifies issues with existing tools, fixes them, and provides corrected scripts.

PTFSpot: Deep co-learning on transcription factors and their binding regions attains impeccable universality in plants

PTFSpot uses a transformer-based deep learning approach to universally detect transcription factor binding regions in plants, outperforming existing tools by >30% and achieving >90% accuracy across unencountered species and TF families.

DeepPlnc: Bi-modal Deep Learning for Highly Accurate Plant lncRNA Discovery

DeepPlnc is a deep learning system for plant lncRNA discovery that outperforms existing tools with high accuracy and robustness to sequence ambiguity.

Sentences, Words, Attention: A "Transforming" Aphorism for the Discovery of pre-miRNA Regions across Plant Genomes

The paper introduces miWords, a transformer-based deep learning method for identifying pre-miRNA regions in plant genomes, achieving high accuracy across multiple species.

RBPSpot: Learning on Appropriate Contextual Information for RBP Binding Sites Discovery

RBPSpot identifies RBP binding sites using contextual sequence features and a DNN, achieving ~90% accuracy and outperforming existing tools across multiple datasets.

miRbiom: Machine-Learning on Bayesian Causal Nets of RBP-miRNA interactions successfully predicts miRNA profiles

miRbiom uses Bayesian causal networks of RBP-miRNA interactions to predict miRNA profiles with high accuracy without requiring separate miRNA profiling experiments.