Interesting paper by alumnus Renqiang Min on “Video Generation from Text,” using a generative #MachineLearning model.
http://www.AAAI.org/GuideBook2018/16152-72279-GB.pdf (Press report by @SilverJacket: New algorithm can create movies from just a few snippets of text
http://www.ScienceMag.org/news/2018/02/new-algorithm-can-create-movies-just-few-snippets-text )
Video Generation from Text Yitong Li†∗, Martin Renqiang Min‡ , Dinghan Shen† , David Carlson† , Lawrence Carin† †
https://www.nature.com/articles/nature25980
A single-cell RNA-seq survey of the developmental landscape of the human prefrontal cortex
Suijuan Zhong
, Shu Zhang
[…]
Xiaoqun Wang
Nature
doi:10.1038/nature25980
Received: 13 November 2017 Revised: 22 November 2017 Accepted: 29 November 2017 https://www.nature.com/articles/s41525-017-0040-5.pdf
Fast, scalable prediction of deleterious #noncoding variants from functional & population genomic data https://www.Nature.com/articles/ng.3810 LINSIGHT, by @ASiepel et al., combines DNAse & conservation information
Yi-Fei Huang, Brad Gulko & Adam Siepel
Nature Genetics 49, 618–624 (2017)
doi:10.1038/ng.3810
Published online:
13 March 2017
Common #schizophrenia alleles are enriched in mutation-intolerant genes & in regions under strong background selection
https://www.nature.com/articles/s41588-018-0059-2 50 novel SCZ loci & 145 loci in total, from #GWAS – associated w/ 33 candidate causal genes
QT:{{”
We report a new genome-wide association study of schizophrenia (11,260 cases and 24,542 controls), and through meta-analysis with existing data we identify 50 novel associated loci and 145 loci in total. Through integrating genomic fine-mapping with brain expression and chromosome conformation data, we identify candidate causal genes within 33 loci.
“}}
Common schizophrenia alleles are enriched in mutation-intolerant genes and in regions under strong background selection
Nature Genetics (2018)
doi:10.1038/s41588-018-0059-2
Dynamic Topic Models
https://mimno.infosci.cornell.edu/info6150/readings/dynamic_topic_models.pdf Classic work by @Blei_lab & J Lafferty adapts the #LDA formalism describing documents in terms of latent topics – to allow these to evolve over time
Points of significance – #MachineLearning: supervised methods https://www.Nature.com/articles/nmeth.4551 Nice discussion of the k in k-NN & the slack parm. C, penalizing misclassified points in SVM — both which act somewhat analogously as regularizers. Good for #teaching
Genic Intolerance to Functional Variation & the Interpretation of Personal Genomes
http://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1003709 Nice plot of the number of rare v common variants in each gene to find outliers particularly tolerant to impactful (eg #LOF) mutations
http://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1003709
Petrovski et al ’13
Credit scores, cardiovascular disease risk & human capital
http://www.PNAS.org/content/111/48/17087 Non-obvious correlations creating potential #privacy risks
linkstream2 microblog 