Yogesh Goyal

ExPert infers causal perturbations from cell states by learning prototypes across 12 contexts, achieving high recall with low compute and validating findings in disease models.

This paper introduces TwINFER, a framework using twin cell information to improve gene regulatory network inference, resolving directionality and reducing false positives in network motifs.

Keeping SCORE transforms diffusion models into probabilistic classifiers for genomics, providing accurate predictions with uncertainty and interpretability across multiple tasks.

Piscis uses a novel loss function to improve spot detection in RNA FISH images, outperforming existing methods without manual parameter tuning.

CIPHER uses gene co-fluctuations in unperturbed cells to predict transcriptome-wide responses to perturbations, outperforming existing methods and revealing key regulatory structures.

This study investigates how stress exacerbates metabolic and oxidative stress in heterozygous Darier disease, leading to disrupted intercellular adhesion and skin lesions.

The paper identifies biological principles governing postnatal aortic growth, showing it scales with the vertebral column and relies on differentiated cell proliferation rather than stem cells.

The paper identifies dysregulated RNA splicing in alcohol-associated liver disease as a cause of regeneration failure, highlighting ESRP2 deficiency and its impact on key signaling pathways.

The paper shows melanoma cells develop therapy resistance through AP-1-mediated cellular memories that encode transient gene expression and chromatin changes.

The paper identifies molecular factors that mark pluripotency potential in rare somatic cells by analyzing fibroblast reprogramming efficiency.

The paper investigates transcriptional adaptation in mammalian cells using computational analysis, mathematical modeling, and machine learning, identifying widespread prevalence and single-cell manifestations of compensatory gene networks.

singletCode uses synthetic barcodes to identify singlets in scRNA-seq and evaluates doublet detection methods' performance.

ClonoCluster combines clonal origin and transcriptome data to create hybrid clusters, revealing biologically relevant markers across six datasets.

The paper evaluates the concordance between chromatin accessibility and transcriptional changes in response to single-factor perturbations, finding that many expression changes occur independently of accessibility changes.

The paper investigates cell type determination during cardiac differentiation of hiPS cells, finding that cell type specification begins shortly after seeding and is cell-autonomous.

The paper shows that resistant fates in cancer cells are predetermined by intrinsic molecular differences, not microenvironmental factors, and can be influenced by drug type and dose.

The paper identifies transcription factors that maintain cell identity by analyzing their responsiveness to perturbations in human iPSC-derived cardiac myocytes and fibroblasts.

The paper shows that transcriptional bursting in gene networks can produce rare coordinated high expression states in cancer cells, which are linked to drug resistance.