Biology subjects

Satija, S.

Publications and source records attributed to Satija, S..

5 recordsLinked to original sources

bioRxiv2026

Scalable Computational Phenomics of Nuclear Morphology

Interpretable computational pathology is constrained by a trade-off between scalable learned representations and biologically explicit phenotypes. Here we present NucXplore, a nuclear phenomics framework that converts each hematoxylin-and-eosin (H&E)-stained nucleus into 129 explicitly defined features spanning morphology, chromatin, intensity, texture, color, and spatial context. A Rust-based implementation accelerates extraction 17.6-fold over the Python reference implementation. Across three histopathology cohorts, NucXplore outperformed classical descriptors and larger deep-learning embeddings while retaining feature attribution. Applied to human skin, hierarchical multiple-instance models resolved eight cellular compartments and decoded age and sun-exposure states, revealing a largely shared aging program with age and cell-specific exposure-dependent recalibration. Conditional flow matching and neural ODE integration transformed cross-sectional phenotypes into model-implied trajectories, uncovering a midlife velocity minimum, late-life re-acceleration, and cell-specific changes in trajectory magnitude and direction. Source-free domain adaptation enabled preliminary transfer of age-associated predictions to an independent hospital cohort. NucXplore thus unifies interpretable representation, high-performance computing, and dynamical modeling for cellular phenotyping from routine histology.

pathology↗

bioRxiv2025

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

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 (CDI), a hierarchical framework that unifies six orthogonal molecular representations, physicochemical (Mordred), topological (GROVER), visual (ImageMol), biological (Signaturizer), quantum-mechanical (MOPAC), and linguistic (ChemBERTa), into a single, coherent embedding. The framework consists of CDI-Basic, a two-tiered autoencoder that fuses these modalities, and CDI-Generalised, a Mamba State-Space Model (SSM) that learns a direct, efficient map from SMILES strings to the unified embedding space. Extensive benchmarking across 23 classification (171 tasks) and 10 regression datasets demonstrates that CDI embeddings consistently achieve superior predictive performance compared to individual Featurizers and standard feature aggregation methods. The CDI-Generalised model achieves this performance with exceptional computational efficiency, outperforming deep learning Featurizers in terms of speed and resource overhead. Furthermore, we demonstrate that the CDI embedding is chemically intuitive, allowing for the sensitive distinction of nuanced structural variants, such as chiral enantiomers and kekulized SMILES forms. By bridging multimodal chemical intelligence with scalable, sequence-based inference, CDI offers a strong foundation for molecular machine learning.

bioinformatics↗

bioRxiv2025

SynGlue: AI-Driven Designer for Clinically Actionable Multi-Target Therapeutics

The rational design of protein degraders, such as proteolysis-targeting chimeras (PROTACs), requires the simultaneous optimization of multiple molecular properties, a complex challenge that limits efficient discovery. Here, we introduce SynGlue, a generative artificial intelligence (AI) framework that addresses this challenge through two core modules: data-driven, leveraging large-scale protein-ligand intelligence, and structure-guided, for physics-aware molecular design. SynGlue harness MagnetDB, a curated database of 6.37 million experimental protein-ligand interactions, and couples it with deep learning models that quantitatively predict degradation potency (DC50), maximal degradation (Dmax), and guide ternary-complex-compatible linker design. Benchmarked against 6,935 compounds, SynGlue demonstrates superior performance in relevant pharmacology prediction. To validate SynGlue, we engineered degraders for BRD4 and GSPT1. Our data-driven design for BRD4 yielded compounds with novel warhead scaffolds (<50% warhead similarity with known PROTACs), which proved to be potent degraders in vitro (DC50 = 0.19 nM) and efficacious in vivo in mouse models. Independently, our structure-guided de novo design for GSPT1 produced ultrapotent degraders (DC50 {approx} 0.0011 M) that are also effective both in vitro and in vivo, uncovering a new oncogenic dependency. By unifying data-driven and physics-aware design, SynGlue establishes a generalizable AI framework for the rapid development of clinically relevant protein degraders, with principled extension to other multi-target modalities.

bioinformatics↗

bioRxiv2025

MutAIverse: An AI-Powered, Mechanism-backed Platform for Discovering Novel DNA Adducts and their precursor Genotoxins

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 AI-driven DNA adductomics analysis platform that overcomes these limitations by leveraging intracellular mechanistic modeling of genotoxin bioactivation to construct a comprehensive DNA adduct library and offers advanced spectral mapping. MutAIverse integrates experimentally validated and chemically valid putative DNA adducts, enabling interpretable retrograde tracking to parental genotoxins. Validation of MutAIverse against experimental MS/MS datasets demonstrated the detection of both known and novel adducts. Furthermore, application to in-house generated DNA adductomics data from tissue biopsies of smokeless tobacco-induced head and neck cancer patients revealed selective enrichment of both novel and known DNA adducts; a subset of them was validated using MS/MS analysis. Collectively, MutAIverse provides a robust, end-to-end, and interpretable platform for advanced DNA adductomics analysis.

bioinformatics↗

bioRxiv2020

Multi-Omics and Integrated Network Approach to Unveil Evolutionary Patterns, Mutational Hotspots, Functional Crosstalk and Regulatory Interactions in SARS-CoV-2

SARS-CoV-2 pandemic resulted in 92 million cases in a span of one year. The study focuses on understanding population specific variations attributing its high rate of infections in specific geographical regions particularly in USA. Rigorous phylogenomic network analysis of complete SARS-CoV-2 genomes (245) inferred five central clades named a (ancestral), b, c, d and e (subtype e1 & e2). The clade d & e2 were found exclusively comprising of USA. Clades were distinguished by 10 co-mutational combinations in Nsp3, ORF8, Nsp13, S, Nsp12, Nsp2 and Nsp6. Our analysis revealed that only 67.46% of SNP mutations were at amino acid level. T1103P mutation in Nsp3 was predicted to increase protein stability in 238 strains except 6 strains which were marked as ancestral type; whereas co-mutation (P409L & Y446C) in Nsp13 were found in 64 genomes from USA highlighting its 100% co-occurrence. Docking highlighted mutation (D614G) caused reduction in binding of Spike proteins with ACE2, but it also showed better interaction with TMPRSS2 receptor contributing to high transmissibility among USA strains. We also found host proteins, MYO5A, MYO5B, MYO5C had maximum interaction with viral proteins (N, S, M). Thus, blocking the internalization pathway by inhibiting MYO5 proteins which could be an effective target for COVID-19 treatment. The functional annotations of the HPI network were found to be closely associated with hypoxia and thrombotic conditions confirming the vulnerability and severity of infection. We also screened CpG islands in Nsp1 & N conferring ability of SARS-CoV-2 to enter and trigger ZAP activity inside host cell. ImportanceIn the current study we presented a global view of mutational pattern observed in SARS-CoV-2 virus transmission. This provided a who-infect-whom geographical model since the early pandemic. This is hitherto the most comprehensive comparative genomics analysis of full-length genomes for co-mutations at different geographical regions specially in USA strains. Compositional structural biology results suggested that mutations have balance of contrary forces effect on pathogenicity suggesting only few mutations to effective at translation level but not all. Novel HPI analysis and CpG predictions elucidates the proof of concept of hypoxia and thrombotic conditions in several patients. Thus, the current study focuses the understanding of population specific variations attributing high rate of SARS-CoV-2 infections in specific geographical regions which may eventually be vital for the most severely affected countries and regions for sharp development of custom-made vindication strategies.

microbiology↗