Justin B. Kinney

PoolParty is a Python package that simplifies the design of DNA sequence libraries for assays like DMS and MPRA, offering a structured and reproducible approach.

GaugeFixer is a Python package that efficiently fixes gauge freedoms in sequence-function models, enabling faster and more scalable analysis of large parameter sets.

The paper compares origin recognition mechanisms in yeast and human cells, revealing evolutionary differences in DNA replication initiation.

The paper derives a saddle-point approximation for genotypic density in additive fitness landscapes and shows it follows a power law near maximal fitness, revealing that these landscapes have stubby peaks.

The paper establishes the relationship between Gaussian process priors and regularized regression in sequence-to-function mapping, showing how to construct regularizers that correspond to explicit Gaussian process priors and characterize implicit function space priors.

This study introduces pVEP, a framework showing how genetic background affects AI predictions of variant effects, revealing variant effects vary across haplotypes.

The paper identifies a developmental timer in C. elegans that coordinates microRNA transcription across tissues through a feedback loop between MYRF-1 and LIN-42.

This paper introduces SEAM, a deep learning framework that identifies functional binding sites and mutation impacts in regulatory DNA, revealing two classes of regulatory signals in human and Drosophila loci.

This study identifies HENMT1 as a methyltransferase that protects 3'-tRNA fragments from degradation, enhancing their ability to silence endogenous retroviruses.

This paper analyzes gauge freedoms in sequence-function models and shows their relationship to symmetry and parameter interpretability.

This paper introduces a family of gauges for sequence-function models to remove gauge freedoms and improve model interpretation.

gpmap-tools uses Gaussian processes to infer and visualize genotype-phenotype maps with higher-order epistasis; across 262,144 Shine-Dalgarno variants it reveals register-specific peaks linked by three-nucleotide-offset ridges.

This paper introduces SQUID, a framework for interpreting genomic deep neural networks using surrogate models, showing improved motif consistency and variant-effect predictions.

MAVE-NN learns genotype-phenotype maps from MAVE data by using a neural network-based information-theoretic framework, enabling biophysically interpretable models.

The paper introduces a non-parametric Bayesian method for density estimation in sequence space and applies it to study pre-mRNA splicing and karyotypic diversity in human cancer.

The paper identifies sequence-specificity in DNA replication origins mediated by Orc4 α-helix in S. cerevisiae and links its evolution to gene silencing mechanisms.

This paper introduces biophysical models of cis-regulation as interpretable neural networks, demonstrating their inference from MPRAs data.

Logomaker is a Python API for generating publication-quality sequence logos from numerical matrices, with support for customization and vector graphics.

MPAthic improves quantitative modeling of sequence-function relationships in MPAs by accurately quantifying epistatic interactions, outperforming existing software.

The paper introduces a Fock space structure and diagrammatic methods to simplify equations governing stochastic chemical systems involving multi-particle complexes.