Sanjay Kumar Mohanty

Generative AI Framework SynGlue for the Rational Design of Clinically Relevant Protein Degraders

Saveena Solanki, Sanjay Kumar Mohanty, Shiva Satija, Sonam Chauhan et autres

This dataset contains processed protein-level quantitative proteomics results from a TMT-multiplex LC-MS/MS study of human 22Rv1 cells under vehicle and compound-treatment conditions at 6 h and 24 h. Files include filtered protein abundance and annotations, normalized protein abundance, and differential-expression statistics. Twenty-four …

Scalable molecular representations enabled by multimodal fusion and sequence distillation

Suvendu Kumar, Saveena Solanki, Mudit Gupta, Sonam Chauhan et autres

Molecular prediction depends on how chemical structures are represented, yet descriptors capture only partial aspects of chemical information. Here, we show that the Chemical Dice Integrator combines six complementary molecular views spanning physicochemical properties, molecular topology, two-dimensional structural images, bioactivity profiles, quantum …

in (code pays fourni par la source)

Generative AI Framework SynGlue for the Rational Design of Clinically Relevant Protein Degraders

Saveena Solanki, Sanjay Kumar Mohanty, Shiva Satija, Sonam Chauhan et autres

This dataset contains processed protein-level quantitative proteomics results from a TMT-multiplex LC-MS/MS study of human 22Rv1 cells under vehicle and compound-treatment conditions at 6 h and 24 h. Files include filtered protein abundance and annotations, normalized protein abundance, and differential-expression statistics. Twenty-four …

Scalable Molecular Representations Enabled by Multimodal Fusion and Sequence Distillation

Suvendu Kumar, Saveena Solanki, Mudit Gupta, Sonam Chauhan et autres

Chemical Dice Integrator is a deep learning framework for integrating heterogeneous molecular representations into a unified chemical embedding space for cheminformatics, bioinformatics, and AI-driven molecular discovery.

in (code pays fourni par la source)

Scalable Molecular Representations Enabled by Multimodal Fusion and Sequence Distillation

Suvendu Kumar, Saveena Solanki, Mudit Gupta, Sonam Chauhan et autres

Chemical Dice Integrator is a deep learning framework for integrating heterogeneous molecular representations into a unified chemical embedding space for cheminformatics, bioinformatics, and AI-driven molecular discovery.

in (code pays fourni par la source)

MutAIverse: an AI-powered, mechanism-backed platform for discovering novel DNA adducts and their precursor genotoxins

Shiva Satija, Sanjay Kumar Mohanty, Sachin B. Jorvekar, Saveena Solanki et autres

Genotoxin exposure leads to DNA adduct formation, potentially causing mutations if unrepaired. Current DNA adductomics platforms or analytical workflows are limited by incomplete spectral libraries, reliance on experimentally validated adducts, limited cellular contexts, and inefficient computational methodologies. We introduce MutAIverse, an advanced …

in (code pays fourni par la source)

MutAIverse: an AI-powered, mechanism-backed platform for discovering novel DNA adducts and their precursor genotoxins

Shiva Satija, Sanjay Kumar Mohanty, Sachin B. Jorvekar, Anshul Verma et autres

Abstract Genotoxin exposure leads to DNA adduct formation, potentially causing mutations if unrepaired. Current DNA adductomics platforms or analytical workflows are limited by incomplete spectral libraries, reliance on experimentally validated adducts, limited cellular contexts, and inefficient computational methodologies. We introduce MutAIverse, an …

Evolutionary-guided advanced deep-learning architecture powers mammalian GPCRome agonist predictions

Aayushi Mittal, Mudit Gupta, Sanjay Kumar Mohanty, Aakash Gaur et autres

G-protein-coupled receptors constitute a highly conserved superfamily that orchestrates essential signaling processes across species. Contemporary computational approaches for predicting ligand-receptor interactions are hindered by restricted receptor coverage, limited incorporation of odorant receptors, and datasets that insufficiently capture cross-species diversity. Here, we present …

in (code pays fourni par la source)

Unveiling the antineoplastic potential of Rezafungin: An integrated computational framework for metronomic repurposing

Shaurya Prakash, Sanjay Kumar Mohanty, Antresh Kumar

Cancer drug development faces major challenges, including high costs, long timelines, and multidrug resistance, creating a need for repurposing strategies. Here, we explored rezafungin (RF), a long-acting echinocandin antifungal, as a hypothesis-generating anticancer candidate using an integrated computational framework combining pharmacokinetic assessment, …

in (code pays fourni par la source)

Author response: Deep learning reveals endogenous sterols as allosteric modulators of the GPCR–Gα interface

Sanjay Kumar Mohanty, Aayushi Mittal, Aakash Gaur, Subhadeep Duari et autres

An AI-driven computational toolkit, Gcoupler, integrates ligand design, statistical modeling, and graph neural networks to predict endogenous metabolites that allosterically modulate the GPCR–Gα interface and regulate downstream signaling.

in (code pays fourni par la source)

Deep learning reveals endogenous sterols as allosteric modulators of the GPCR–Gα interface

Sanjay Kumar Mohanty, Aayushi Mittal, Nasr Farooqi, Aakash Gaur et autres

Endogenous intracellular allosteric modulators of GPCRs remain largely unexplored, with limited binding and phenotype data available. This gap arises from the lack of robust computational methods for unbiased cavity identification, cavity-specific ligand design, synthesis, and validation across GPCR topology. Here, we developed …

in (code pays fourni par la source)

Chemical Dice Integrator (CDI): A Scalable Framework for Multimodal Molecular Representation Learning

Suvendu Kumar, Saveena Solanki, Sanjay Kumar Mohanty, Shiva Satija et autres

ABSTRACT The machine learning landscape for molecular property prediction is fragmented, with numerous Featurizers each capturing a narrow, specialized view of chemical structure. This heterogeneity forces a suboptimal choice of representation a priori, limiting model generalizability. We introduce the Chemical Dice Integrator …

in (code pays fourni par la source)