Gene expression prediction - Revision history

Fkolpakov@gmail.com at 15:09, 1 April 2018

2018-04-01T15:09:08Z

Fkolpakov@gmail.com at 12:27, 1 April 2018

2018-04-01T12:27:48Z

Fkolpakov@gmail.com at 12:09, 1 April 2018

2018-04-01T12:09:34Z

Fkolpakov@gmail.com at 12:05, 1 April 2018

2018-04-01T12:05:56Z

Fkolpakov@gmail.com at 16:20, 31 March 2018

2018-03-31T16:20:04Z

Fkolpakov@gmail.com: Created page with " {| class="wikitable" !Method, code, references!!Input data!!Algorithm!!Comment |- |INVOKE (R script)Schmidt217 https://github.com/SchulzLab/TEPIC/tree/master/Mac..."

2018-03-31T16:19:25Z

Created page with " {| class="wikitable" !Method, code, references!!Input data!!Algorithm!!Comment |- |INVOKE (R script)<cite>Schmidt217</cite> https://github.com/SchulzLab/TEPIC/tree/master/Mac..."

New page

{| class="wikitable"
!Method, code, references!!Input data!!Algorithm!!Comment
|-
|INVOKE (R script)<cite>Schmidt217</cite>
https://github.com/SchulzLab/TEPIC/tree/master/MachineLearningPipelines/INVOKE
|
Input:
* TF-genes scores (calculated by TEPIC)
** open chromatin data (DNaseI-seq, NOMe-seq)
** PWM (Jaspar, HOCOMOCO, Uniprobe)
* expression data (RNA-seq)
Output:
* regression coefficients for TF
* model performance: Pearson correlation, Spearman correlation, and MSE
** boxplot showing model performance
** heatmap (top 10 positive and negative coefficients)
** scatter plots for predicted versus the measured gene expression data
|
INVOKE offers linear regression with various regularisation techniques (Lasso, Ridge, Elastic net) to infer potentially important transcriptional regulators by predicting gene expression from TEPIC TF-gene scores.
|
|}

==References==

<biblio>

#Schmidt217 pmid=27899623

</biblio>

[[Category:Virtual_biology]]

@@ Line 3: / Line 3: @@
 !Method, code, references!!Input data!!Algorithm!!Accuracy!!Comment
 |-
-|INVOKE (R script)<cite>Schmidt217</cite>
+|INVOKE (R script)<cite>Schmidt2017</cite>
 https://github.com/SchulzLab/TEPIC/tree/master/MachineLearningPipelines/INVOKE
+|
@@ Line 24: / Line 24: @@
 <br>GM12878 - r =0.58
+|
 |-
@@ Line 40: / Line 58: @@
 * gene expression is expressed by the log-linear regression model
 |mouse ESCs, r=0.806, R<sup>2</sup>=0.65, CV-R<sup>2</sup>=0.64
+|
@@ Line 63: / Line 67: @@
 <biblio>
-#Schmidt217 pmid=27899623
+#Schmidt2017 pmid=27899623
 #Ouyang2009 pmid=19995984
 </biblio>

@@ Line 23: / Line 23: @@
 |-
-|<cite>Ouyang2007</cite>
+|2009 - an approach based on feature extraction of ChIP-Seq signals, principal component analysis, and regression-based component selection <cite>Ouyang2009</cite>
 |Input:
 * ChIP-seq data
@@ Line 62: / Line 62: @@
 #Schmidt217 pmid=27899623
-#Ouyang2007 pmid=19995984
+#Ouyang2009 pmid=19995984
 </biblio>

← Older revision		Revision as of 16:20, 31 March 2018
Line 30:		Line 30:

	</biblio>		</biblio>
−
−	~~[[Category:Virtual_biology]]~~

@@ Line 20: / Line 20: @@
 INVOKE offers linear regression with various regularisation techniques (Lasso, Ridge, Elastic net) to infer potentially important transcriptional regulators by predicting gene expression from TEPIC TF-gene scores.
+|
+|