Re: Thank you!

TITLE: Genomics & Data Science

ABSTRACT:

Data science is currently popular because it allows the extraction of
useful information and commercial value from large-scale datasets.
Here I will describe biomedical data science, particularly from the
framework of genomics, which is one of the leading sub-fields under
the data science umbrella. First, I will talk about the increase in
data generation and data availability in this discipline, and how
genomics has developed methods to cope with data growth, and how these
methods interrelate with data science in general. Then, I'll go
through a number of key applications of biomedical data science,
particularly in relation to drugs and therapeutics, and focus on
finding drug targets for neuropsychiatric disease. This application of
data science makes extensive use of biological regulatory networks and
I will show how one can analyze these networks, in terms of analogies
to social networks and hierarchies.

Fwd: Your upcoming Special Cell Circuits & Epigenomics seminar/visit on April 1st

TITLE:

Personal Genomics & Data Science

In this seminar, I will discuss issues in personal genome analysis.
In particular, I will focus on
disorders of the brain, which affect nearly a fifth of the world's
population. Robust phenotype-genotype associations have been
established for a number of brain disorders including psychiatric
diseases (e.g., schizophrenia, bipolar disorder). However,
understanding the molecular causes of brain disorders is still a
challenge. To address this, the PsychENCODE consortium generated
thousands of transcriptome (bulk and single-cell) datasets from 1,866
individuals. Using these data, we have developed a set of
interpretable machine learning approaches for deciphering functional
genomic elements and linkages in the brain and psychiatric disorders.
In particular, we deconvolved the bulk tissue expression across
individuals using single-cell data via non-negative matrix
factorization and non-negative least squares and found that
differences in the proportions of cell types explain >85% of the
cross-population variation observed. Additionally, we developed an
interpretable deep-learning model embedding the physical regulatory
network to predict phenotype from genotype. Our model uses a
conditional Deep Boltzmann Machine architecture and introduces lateral
connectivity at the visible layer to embed the biological structure
learned from the regulatory network and QTL linkages. It
improves disease prediction (by 6-fold compared to additive polygenic
risk scores), highlights key genes for disorders, and allows
imputation of missing transcriptome information from genotype data
alone.

In the second half of the talk, if there's time, I'll discuss various data
science issues in drug design, in particular in developing a predictor that
gives one's differential sensitivity to a drug, taking into account his or her
personal variants.

==
i0brd19

12~特邀~您聆~取 188 圆~用扣扣Q903401978惘zhi⑥0⑷957佃c-om

澳<我的眼睛怎样地从眼眶跃出，>菛威\<可怜一个人对于幸福太容易上瘾了！等到自私的幸福变成了人生唯一的>尼澌<嫩牛拖犁耙不打不跑>6<饶人算之本，输人算之机。>9<久住令人贱，频来亲也疏。>2<硬把它当作私人游乐的花园？>00<真正的朋友是一个灵魂寓于两个身体，两个灵魂只有一个思想，两颗心跳动是一致的。>24<乞丐跳舞穷快活 青竹竿掏茅坑越掏越臭 >、<凡事豫(预)则立,不豫(预)则废。(《礼记》)>c<谁也不能将阳光装进自己的口袋。谁也不能将真理霸占。>0m特<都具有一种灵活强劲的保证，>邀您住<对你唱着："你独身就一切皆空。">冊嶺㈡<粘米煮山芋糊糊涂涂 >㈩㈣<习与正人居之，不能无正也；犹生长于齐，不能不齐语也。>瀛<墙上栽花高种(中)>10<使你抛弃了我反而得到光荣：>0<人才虽高，不务学问，不能致圣。>缇現<心是灵魂的眼睛，而不是力量的源泉>