Arvind Ramanathan

The ModelSEED Biochemistry Database, 2026 update: grading multi-source thermodynamics

The paper updates the ModelSEED Biochemistry Database with expanded compounds and reactions, integrating multi-source thermodynamic data and grading reaction reliability.

Mechanistic insights into the association and activation of the SARS-CoV-2 2'-O-Methyltransferase (NSP16)

This study uses molecular dynamics simulations and AI/ML to elucidate how nsp10 activates nsp16's methylation function by stabilizing its SAM pocket and enabling RNA binding.

Classification of Human Transcription Factors Based on Their Effector Domains via Unsupervised Learning

The paper classifies human transcription factors based on effector domain sequences using unsupervised learning and identifies features correlating with transcriptional activity and co-evolution with DNA-binding domains.

Sequence-Based Generative AI-Guided Design of Versatile Tryptophan Synthases

This paper uses a generative AI model to design novel tryptophan synthase variants with enhanced catalytic activity and substrate promiscuity, outperforming natural and optimized versions.

Unsupervised learning of progress coordinates during weighted ensemble simulations: Application to millisecond protein folding

This paper develops a deep learning method to identify progress coordinates during weighted ensemble simulations, improving folding rate constant estimation by >3-fold in protein folding simulations.

A Deep Learning-Driven Sampling Technique to Explore the Phase Space of an RNA Stem-Loop

This paper adapts a deep learning-driven sampling technique for RNA stem-loop folding, showing it can efficiently explore phase space with lower computational cost than traditional methods.

GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics.

GenSLMs use large language models to analyze SARS-CoV-2 genomes, enabling rapid identification of variants of concern and providing insights into evolutionary dynamics.

BigNeuron: A resource to benchmark and predict best-performing algorithms for automated reconstruction of neuronal morphology

BigNeuron benchmarks automatic neuron reconstruction algorithms using gold standard annotations and image quality metrics, showing that consensus methods outperform individual algorithms.

Mechanisms of Coupling between Angiotensin Converting Enzyme 2 and Nicotinic Acetylcholine Receptors

The paper identifies a sequence similarity between ACE2 and nAChR-binding proteins and shows potential physical interaction between ACE2 and nAChR in PC12 cells.

Predictive uncertainty in mechanistic models of cellular processes calibrated to experimental data

The paper introduces a Bayesian and machine learning approach to assess predictive uncertainty in mechanistic models of apoptosis using experimental data, showing that non-quantitative data can improve model accuracy when combined.

Visual Analytics for Deep Embeddings of Large Scale Molecular Dynamics Simulations

The paper develops an interactive visual analytics system to evaluate and analyze deep embeddings of large-scale molecular dynamics simulations.