Ivan V. Kulakovskiy

Inferring binding specificities of human transcription factors with the wisdom of crowds

The paper benchmarks methods for inferring transcription factor binding specificities using a large community challenge and finds deep learning models outperform traditional methods, though positional weight matrices are competitive.

EPIC: An open community challenge for sequence-based prediction of transcription initiation in five non-model metazoans

EPIC challenges teams to predict transcription initiation from DNA sequence in non-model metazoans, aiming to assess generalizability beyond human and model species.

Identification of methylation-sensitive human transcription factors using meSMiLE-seq

This study identifies DNA binding motifs for 98 human transcription factors using meSMiLE-seq, revealing methylation-sensitive binding preferences for some TFs.

GHT-SELEX demonstrates unexpectedly high intrinsic sequence specificity and complex DNA binding of many human transcription factors

The paper uses GHT-SELEX to show many human TFs have high intrinsic sequence specificity and complex DNA binding, often matching in vivo ChIP-seq results.

Classic machine learning on top of multiple position weight matrices improves genomic prediction of transcription factor binding sites

ArChIPelago combines multiple PWMs using classic machine learning to improve TFBS prediction, outperforming individual PWMs and other models across species.

Rare gain-of-function regulatory mutations explain the missing heritability of bicuspid aortic valve

The paper identifies rare gain-of-function regulatory mutations as significant contributors to the missing heritability of bicuspid aortic valve.

A Joint Promoterome-Proteome Atlas Highlights the Molecular Diversity of Human Skeletal Muscles

The paper creates a promoterome and proteome atlas of human skeletal muscles, revealing molecular diversity and identifying key transcription factors and genetic variants associated with muscle traits.

Transcript-wide m6A methylation defines the efficiency of the cap-independent translation initiation

The paper investigates how global m6A methylation levels affect cap-independent translation efficiency, showing that total m6A levels, not specific localization, determine this process.

Cross-platform DNA motif discovery and benchmarking to explore binding specificities of poorly studied human transcription factors

The paper evaluates cross-platform DNA motif discovery tools using 4,237 experiments to identify reliable transcription factor binding motifs and highlights challenges in motif detection.

A novel class of non-coding variants driving DNA double-strand breaks is associated with complex genetic diseases

The paper identifies a new class of non-coding variants, dsbSNPs, that modulate DNA double-strand break frequency and are enriched in GWAS associations for complex diseases.

GAME: Genomic API for Model Evaluation

GAME provides a standardized framework for benchmarking genomics models across tasks, enabling consistent evaluation and community contributions.

Statistical framework for calling allelic imbalance in high-throughput sequencing data

The paper introduces MIXALIME, a statistical framework for detecting allele-specific events in sequencing data, and demonstrates its application in constructing an atlas of allele-specific chromatin accessibility.

Massively parallel characterization of transcriptional regulatory elements in three diverse human cell types

The paper identifies functional cis-regulatory elements in three human cell types using lentiMPRAs and develops predictive models for CRE function.

A generative framework for enhanced cell-type specificity in rationally designed mRNAs

This paper introduces PARADE, a generative AI framework for designing mRNA UTRs with cell-type specificity, showing improved therapeutic efficacy in preclinical models.

Extensive binding of nebulous human transcription factors to genomic dark matter

The paper identifies genomic binding sites of 166 poorly characterized human transcription factors, revealing that some bind to dark matter DNA and others to regulatory regions.

Codebook: sequence specificity and genomic binding of poorly-characterized human transcription factors

The paper systematically determines the sequence specificity of 332 poorly characterized human transcription factors, identifying over 4,000 experiments and revealing tens of thousands of new TF binding sites.

Evaluation and optimization of sequence-based gene regulatory deep learning models

The paper evaluates and optimizes sequence-based gene regulatory deep learning models using a DREAM Challenge dataset, showing improvements through architectural and training strategy refinements.

Systematic Identification of Post-Transcriptional Regulatory Modules

The paper systematically identifies post-transcriptional regulatory modules by integrating multimodal data on RBP interactions and functions.

LegNet: a best-in-class deep learning model for short DNA regulatory regions

LegNet is a deep learning model for predicting gene expression from DNA sequences, outperforming existing models and enabling promoter sequence design.

Human tissues exhibit diverse composition of translation machinery

The paper analyzes transcriptomic and proteomic data to identify tissue-specific expression of translation machinery components and highlights sexual dimorphism in translation factors.

A GO catalogue of human DNA-binding transcription factors

The paper curates a comprehensive catalogue of human DNA-binding transcription factors using Gene Ontology definitions and provides access to it via an online resource.

A standard knockout procedure alters expression of adjacent loci at the translational level

The paper investigates how a standard knockout procedure in yeast affects the expression of neighboring genes at the translational level, revealing significant changes in protein abundance.

Landscape of allele-specific transcription factor binding in the human genome

The paper identifies allele-specific transcription factor binding events across the human genome using ChIP-Seq data, revealing regulatory variants linked to disease and molecular mechanisms.

Systematic identification of cis-interacting lncRNAs and their targets

The paper identifies cis-interacting lncRNAs and their targets using RNA-chromatin and Hi-C data across 18 human cell types.

Functional Annotation of Human Long Non-Coding RNAs via Molecular Phenotyping

The paper functionally annotates human long non-coding RNAs by systematically knocking down 285 lncRNAs and analyzing molecular phenotypes using CAGE sequencing.

Multi-faceted deregulation of gene expression and protein synthesis with age

This study examines age-related changes in the transcriptome and translatome of mouse tissues, revealing U-shaped gene expression patterns and age-related declines in protein synthesis.

Enhanced C/EBPs binding to C>T mismatches facilitates fixation of CpG mutations

The paper identifies enhanced C/EBP binding to C>T mismatches as a mechanism for selective accumulation of [C>T]G mutations in transcription factor binding sites.

Coat color allele and mtDNA haplotype distributions in Russian cat populations: a citizen-science research

The paper analyzes coat color alleles and mtDNA haplotypes in Russian cats to study population genetics and phylogeography, finding genetic homogeneity and unique mitotypes.