From 83609bdedbb5eda9808b69c0b69f37b21af23d7d Mon Sep 17 00:00:00 2001
From: ndwarshuis <ndwar@yavin4.ch>
Date: Fri, 3 Sep 2021 18:44:29 -0400
Subject: [PATCH] ADD single donor causal inference

---
 tables/causal_inference_single.tex | 32 ++++++++++++++++++++++++++++++
 tex/thesis.tex                     | 25 +++++++++++++++++++----
 2 files changed, 53 insertions(+), 4 deletions(-)
 create mode 100644 tables/causal_inference_single.tex

diff --git a/tables/causal_inference_single.tex b/tables/causal_inference_single.tex
new file mode 100644
index 0000000..15c4892
--- /dev/null
+++ b/tables/causal_inference_single.tex
@@ -0,0 +1,32 @@
+
+% Table created by stargazer v.5.2.2 by Marek Hlavac, Harvard University. E-mail: hlavac at fas.harvard.edu
+% Date and time: Fri, Sep 03, 2021 - 06:28:50 PM
+\begin{tabular}{@{\extracolsep{5pt}}lccc} 
+\\[-1.8ex]\hline 
+\hline \\[-1.8ex] 
+ % & \multicolumn{3}{c}{\textit{Dependent variable:}} \\ 
+% \cline{2-4} 
+\\[-1.8ex] & log(Fold Change) & \ptmemp{} & \dpthp{} \\ 
+% \\[-1.8ex] & (1) & (2) & (3)\\ 
+\hline \\[-1.8ex] 
+ Activation Method [DMS] & 0.668$^{***}$ & $-$0.011 & 0.063$^{***}$ \\ 
+  Feed Criteria [Glucose] & $-$0.047 & 0.006 & 0.010 \\ 
+  IL2 Feed Conc. [IU/ml] & 0.006 & 0.002$^{**}$ & 0.001 \\ 
+  Initial Cell Viability & $-$0.048 & 0.005 & 0.009 \\ 
+  Media Age (days) & $-$0.001 & $-$0.001$^{***}$ & 0.0001 \\ 
+  Thaw Media Age (days) & 0.0002 & 0.0005$^{***}$ & $-$0.0002 \\ 
+  IL2 Reconstituted Age & $-$0.001 & $-$0.0001 & 0.0001 \\ 
+  Operator [2] & $-$0.658$^{***}$ & 0.058 & 0.115$^{***}$ \\ 
+  Operator [3] & $-$0.652$^{*}$ & $-$0.214$^{***}$ & 0.183$^{***}$ \\ 
+  Media Sampled [True] & 0.314 & 0.067 & 0.011 \\ 
+  Constant & 7.770$^{*}$ & $-$0.208 & $-$1.389$^{**}$ \\ 
+ \hline \\[-1.8ex] 
+% Observations & 80 & 80 & 80 \\ 
+R$^{2}$ & 0.486 & 0.534 & 0.722 \\ 
+Adjusted R$^{2}$ & 0.412 & 0.466 & 0.682 \\ 
+% Residual Std. Error (df = 69) & 0.434 & 0.070 & 0.059 \\ 
+% F Statistic (df = 10; 69) & 6.536$^{***}$ & 7.891$^{***}$ & 17.931$^{***}$ \\ 
+\hline 
+\hline \\[-1.8ex] 
+\textit{Note:}  & \multicolumn{3}{r}{$^{*}$p$<$0.1; $^{**}$p$<$0.05; $^{***}$p$<$0.01} \\ 
+\end{tabular} 
diff --git a/tex/thesis.tex b/tex/thesis.tex
index 0e0523a..fe99b28 100644
--- a/tex/thesis.tex
+++ b/tex/thesis.tex
@@ -2565,7 +2565,6 @@ longitudinally, so we included a boolean categorical to represented this
 modification as removing conditioned media as the cell are expanding could
 disrupt signaling pathways.
 
-% TABLE these tables have extra crap in them that I don't need to show
 \begin{table}[!h] \centering
   \caption{Causal Inference on treatment variables only}
   \label{tab:ci_treat}
@@ -2578,6 +2577,13 @@ disrupt signaling pathways.
   \input{../tables/causal_inference_control.tex}
 \end{table}
 
+\begin{table}[!h] \centering
+  \caption{Causal Inference on treatment variables and control variables (single
+  donor)}
+  \label{tab:ci_single}
+  \input{../tables/causal_inference_single.tex}
+\end{table}
+
 \begin{figure*}[ht!]
   \begingroup
 
@@ -2624,10 +2630,10 @@ controlling for additional noise, the models explained much more variability
 %   X}.
 Furthermore, the coefficient for activation method in the case of fold change
 changed very little but still remained quite high (note the log-transformation)
-with \SI{143}{\percent} increase in fold change compared to beads. Furthermore,
-the coefficient for \ptmemp{} dropped to a \SI{2.7}{\percent} increase and
+with \SI{131}{\percent} increase in fold change compared to beads. Furthermore,
+the coefficient for \ptmemp{} dropped to a \SI{3.5}{\percent} increase and
 almost became non-significant at $\upalpha$ = 0.05, and the \dpthp{} response
-increased to almost a \SI{9}{\percent} increase and became highly significant.
+increased to a \SI{7.4}{\percent} increase and became highly significant.
 Looking at the bioreactor treatment, we see that using the bioreactor in the
 case of fold change and \ptmemp{} is actually harmful to the response, while at
 the same time it seems to increase the \dpthp{} response. We should note that
@@ -2637,6 +2643,17 @@ bioreactor helped or hurt a certain response. For example, using a Grex entails
 changing the cell surface and feeding strategy for the T cells, and any one of
 these ‘mediating variables’ might actually be the cause of the responses.
 
+Finally, we stratified on the most common donor (vendor ID 338 from Astarte
+Biotech) as this was responsible for almost half the data (80 runs) and repeated
+the regression (\Cref{tab:ci_single}). Note that in this case, we did not
+include any of the donor-dependent variables as well as any of the variables
+that were the same value for these 80 runs. In this analysis, fold change and
+\dpthp{} remained high (but slightly lowered from the full analysis) and
+\ptmemp{} was non-significant. Given this, it appears that high \ptmemp{} may
+have been due to other donors besides this one, and that high fold change and
+\dpthp{} may have been driven by this single donor but more extreme in other
+donors.
+
 \section{Discussion}
 
 % DISCUSSION this is fluffy