Allison S. Walker

Identification of Siderophores with Unexpected Antibacterial Properties from Actinoplanes teichomyceticus

This study identifies siderophores from Actinoplanes teichomyceticus with antibacterial properties, showing activity against Gram-positive bacteria through a metal-dependent mechanism.

Gut microbiome derived folate metabolite suppresses colorectal cancer progression

The paper shows that gut microbiota-derived folinic acid suppresses colorectal cancer progression by inhibiting calpain-2 and stabilizing E-cadherin.

A foundation model enables prediction of natural product molecular properties, bioactivity, and structural similarity from biosynthetic gene cluster sequence

This paper introduces BGC-MLM, a foundation model pretrained on biosynthetic gene clusters to predict molecular properties, bioactivity, and structural similarity, outperforming models without pretraining.

UTILIZING SEQUENCE SIMILARITY NETWORKS FOR CROSS SPECIES ELICITOR IDENTIFICATION OF STREPTOMYCES REGULATORY PROTIENS

This paper uses sequence similarity networks to predict elicitors for TetR-family regulators in Streptomyces, identifying chloramphenicol-responsive homologs of JadR2.

Microbial metabolism of methotrexate produces a STAT3 signaling molecule that alleviates gut inflammation

The paper identifies a gut microbial metabolite of methotrexate that alleviates gut inflammation by promoting mitochondrial STAT3 signaling.

AI-assisted isolation of bioactive Dipyrimicins from Amycolatopsis azurea and identification of its corresponding dip biosynthetic gene cluster

The paper uses a machine learning model to predict antibacterial activity from biosynthetic gene clusters, leading to the isolation of dipyrimicins A and B from Amycolatopsis azurea and linking them to their BGC.

Yatakemycin biosynthesis requires two deoxyribonucleases for toxin self-resistance

This study identifies YtkR4 and YtkR5 as essential deoxyribonucleases for repairing DNA damage caused by yatakemycin, supporting their role in base excision repair.

Statistical Coupling Analysis Predicts Correlated Motions in Dihydrofolate Reductase

This study uses statistical coupling analysis and molecular dynamics to show that dynamically coupled residues in DHFR influence evolution and allosteric communication.

Assessing the ability of ChatGPT to extract natural product bioactivity and biosynthesis data from publications

This study evaluates ChatGPT's ability to extract natural product bioactivity and biosynthesis data from scientific publications, finding it effective for identifying natural product discovery and bioactivity but less accurate for extracting accession numbers.

Machine learning-based exploration, expansion and definition of the atropopeptide family of ribosomally synthesized and posttranslationally modified peptides

This study introduces AtropoFinder, a machine learning tool that identifies atropopeptide biosynthetic gene clusters and expands the known chemical diversity of this RiPP family.