Joint ICTP-SISSA-UniTS Data Science Seminar - Single-cell dynamics in chromatin regulation: machine learning methods to understand gene regulation
Starts 4 May 2021 15:00
Ends 4 May 2021 16:00
Central European Time
The ICTP Quantitative Life Sciences Section is glad to announce the Joint ICTP-SISSA-UniTS Data Science Seminar by Jake Yeung, Human Frontier Science Program (HFSP) Fellow, Hubrecht Institute for Developmental Biology and Stem Cell Research, Utrecht, The Netherlands
Cells are the basic units of life. Although every cell in the body has essentially the same genetic code, histone modifications decorate the genome of different cells to establish distinct regions of the chromatin that are active or repressed. These cell type-specific chromatin states allow cells to turn on different genes and perform different functions. Recently, new techniques have begun to map these histone modifications at the single-cell level, opening up new machine learning opportunities to infer gene regulatory principles at unprecedented resolutions.
In this talk, I present two projects highlighting machine learning methods applied to these experimental technologies to reveal global insights in chromatin regulation in single cells.
First, I present a new technology, sortChIC (sort-assisted chromatin immunocleavage), and apply it to understand chromatin regulation during blood formation. I show machine learning methods to learn interpretable maps from these high-dimensional count data to predict regulators driving blood formation. Specifically, I infer transcription factor activities in single cells, revealing how blood stem cells rewire regulatory networks to become distinct mature blood cell types.
Second, I present scChIX (single-cell chromatin immunocleavage and unmixing), an integrated machine learning and experimental framework to understand the interplay between histone modifications in single cells. scChIX generates linked maps of active and repressive chromatin, allowing integrated analysis of different histone modifications in single cells. These linked maps reveal switching between active and repressive states during development of B cells in the blood.
Overall, machine learning methods integrated into new experimental technologies reveal global gene regulatory principles.