Anand V. Sastry

Mining all publicly available expression data to compute dynamic microbial transcriptional regulatory networks

The paper develops a workflow to reconstruct dynamic transcriptional regulatory networks from public gene expression data using Bacillus subtilis as a case study.

Machine learning uncovers the Pseudomonas syringae transcriptome in microbial communities and during infection

The paper uses iModulon analysis to uncover the transcriptional regulatory network of Pseudomonas syringae across diverse conditions and interactions.

Deep learning-based codon optimization with large-scale synonymous variant datasets enables generalized tunable protein expression

The paper develops deep learning models trained on synonymous variant datasets to predict and optimize protein expression in E. coli.

Lab evolution, transcriptomics, and modeling reveal mechanisms of paraquat tolerance

The paper uses adaptive laboratory evolution and transcriptomic analysis to identify six mechanisms of paraquat tolerance in E. coli.

Pan-genomic analysis of transcriptional modules across Salmonella Typhimurium reveals the regulatory landscape of different strains

This study uses machine learning to analyze RNA-Seq data from multiple Salmonella Typhimurium strains, revealing transcriptional modules and regulatory patterns across the pan-genome.

Advanced transcriptomic analysis reveals the role of efflux pumps and media composition in antibiotic responses of Pseudomonas aeruginosa

This study uses transcriptomic data to construct a regulatory network of Pseudomonas aeruginosa, revealing roles of efflux pumps and media composition in antibiotic responses.

Antibody optimization enabled by artificial intelligence predictions of binding affinity and naturalness

Language models trained on high-throughput affinity data predict KD of unseen antibody variants across three orders of magnitude, and a "naturalness" score can be optimised alongside affinity.

Machine-learning from Pseudomonas putida transcriptomes reveals its transcriptional regulatory network

This study uses machine learning to uncover the genome-scale transcriptional regulatory network in Pseudomonas putida using gene expression data.

Machine learning of all Mycobacterium Tuberculosis H37Rv RNA-seq data reveals complex interplay between metabolism, stress response, and infection

The paper uses machine learning to analyze M. tuberculosis RNA-seq data, identifying gene modules and their roles in metabolism, stress response, and infection.

Optimal dimensionality selection for independent component analysis of transcriptomic data

This paper introduces OptICA, a method for selecting optimal dimensionality in ICA of transcriptomic data, showing it outperforms existing methods across multiple datasets.

Machine learning uncovers a data-driven transcriptional regulatory network for the Crenarchaeal thermoacidophile Sulfolobus acidocaldarius

The paper uses machine learning to uncover a transcriptional regulatory network in Sulfolobus acidocaldarius, identifying new gene regulators and regulatory modules.

Machine Learning of Pseudomonas aeruginosa transcriptomes identifies independently modulated sets of genes associated with known transcriptional regulators

The paper uses machine learning to analyze Pseudomonas aeruginosa transcriptomes and identifies gene sets regulated by known transcriptional factors, revealing insights into biosynthetic clusters and metabolic regulation.

A multi-scale transcriptional regulatory network knowledge base for Escherichia coli

The paper constructs a transcriptional regulatory network for Escherichia coli using machine learning on a large RNA-seq compendium, identifying regulatory modules and novel regulons.

Matrix factorization recovers consistent regulatory signals from disparate datasets

The paper uses matrix factorization to uncover consistent regulatory signals across diverse gene expression datasets, demonstrating its utility in multi-omics analysis.

Machine learning uncovers independently regulated modules in the Bacillus subtilis transcriptome

The paper uses machine learning to identify gene modules in Bacillus subtilis, revealing known and novel regulatory roles and population-level sporulation states.

Elucidation of regulatory modes for five two-component systems in Escherichia coli reveals novel relationships

The paper identifies regulons of five two-component systems in E. coli using RNA-seq and ChIP-exo data, revealing novel regulatory relationships and non-cognate inducers.

iModulonDB: a knowledgebase of microbial transcriptional regulation derived from machine learning

iModulonDB provides a knowledgebase of microbial transcriptional regulation derived from machine learning, offering curated gene sets and their activity levels across three bacterial species.

Reconstruction of Fur pan-regulon uncovers the complexity and diversity of transcriptional regulation in E. coli

The paper reconstructs the Fur pan-regulon in E. coli strains, revealing core, accessory, and unique regulons and their functional diversity.

The Escherichia coli Transcriptome Mostly Consists of Independently Regulated Modules

The paper decomposes the Escherichia coli transcriptome into 70 independent regulatory signals, showing that 50 correspond to known transcriptional regulators and revealing a principle of signal summation in prokaryotic gene regulation.

Experimental evolution reveals the genetic basis and systems biology of superoxide stress tolerance

This study uses adaptive laboratory evolution to generate E. coli strains with increased superoxide stress tolerance and identifies genetic and transcriptomic mechanisms underlying this adaptation.

The y-ome defines the thirty-four percent of Escherichia coli genes that lack experimental evidence of function

The paper identifies 34% of Escherichia coli genes with no experimental evidence of function, termed the y-ome, and characterizes their properties.

Cellular responses to reactive oxygen species can be predicted on multiple biological scales from molecular mechanisms

The paper develops a quantitative framework to predict ROS stress responses in E. coli across molecular, network, and genetic levels.

ssbio: A Python Framework for Structural Systems Biology

The paper introduces ssbio, a Python framework for integrating structural biology data into genome-scale systems biology workflows.