diff --git a/BUILD_NOTES_tch.txt b/BUILD_NOTES_tch.txt
index 7fe0b15..2a2257f 100644
--- a/BUILD_NOTES_tch.txt
+++ b/BUILD_NOTES_tch.txt
@@ -9,7 +9,7 @@ Then set the following environment variables:
export LIBTORCH={path/to/}libtorch
export DYLD_LIBRARY_PATH=${LIBTORCH}/lib
-export LD_LIBRARY_PATH=${DYLD_LIBRARY_PATH}
+export LD_LIBRARY_PATH="${LD_LIBRARY_PATH:+${LD_LIBRARY_PATH}:}${DYLD_LIBRARY_PATH}"
You can check that everything is working by running `modkit open-chromatin predict --dryrun`.
diff --git a/book/src/images/chromatin_stenciling_3_no_alpha.png b/book/src/images/chromatin_stenciling_3_no_alpha.png
new file mode 100644
index 0000000..7e49e29
Binary files /dev/null and b/book/src/images/chromatin_stenciling_3_no_alpha.png differ
diff --git a/book/src/images/me_no_alpha.png b/book/src/images/me_no_alpha.png
new file mode 100644
index 0000000..ec28eb5
Binary files /dev/null and b/book/src/images/me_no_alpha.png differ
diff --git a/book/src/intro_entropy.md b/book/src/intro_entropy.md
index 96780c3..6ac8641 100644
--- a/book/src/intro_entropy.md
+++ b/book/src/intro_entropy.md
@@ -9,7 +9,7 @@ Probably the simplest visual description of methylation entropy is the following
-
+
diff --git a/book/src/intro_open_chromatin.md b/book/src/intro_open_chromatin.md
index ab8d2aa..0ac070c 100644
--- a/book/src/intro_open_chromatin.md
+++ b/book/src/intro_open_chromatin.md
@@ -3,7 +3,7 @@
Nanopore sequencing can detect multiple base modifications simultaneously and we can leverage this capability by introducing exogenous base modifications at specific functional regions.
One such method uses a 6mA methyltransferase such as EcoGII or Hia5 to label accessible regions of chromatinized DNA, usually by treatment of cell nuclei with the enzyme.
-
+
## Predict regions of open chromatin
Modkit comes with a machine learning model that has been trained to identify regions of open chromatin based on 6mA signal.
diff --git a/docs/images/chromatin_stenciling_3_no_alpha.png b/docs/images/chromatin_stenciling_3_no_alpha.png
new file mode 100644
index 0000000..7e49e29
Binary files /dev/null and b/docs/images/chromatin_stenciling_3_no_alpha.png differ
diff --git a/docs/images/me_no_alpha.png b/docs/images/me_no_alpha.png
new file mode 100644
index 0000000..ec28eb5
Binary files /dev/null and b/docs/images/me_no_alpha.png differ
diff --git a/docs/intro_entropy.html b/docs/intro_entropy.html
index 374e911..fc53a25 100644
--- a/docs/intro_entropy.html
+++ b/docs/intro_entropy.html
@@ -185,7 +185,7 @@ , “This information is important because such ‘phased’ methylation states can inform us about the epigenetic diversity of cell populations as well as the local regulation states of the epigenome”.
Probably the simplest visual description of methylation entropy is the following, a version of which appears in many of the methods papers:
-

+

Citation: Lee et al.
diff --git a/docs/intro_open_chromatin.html b/docs/intro_open_chromatin.html
index e1f5a73..9e4c418 100644
--- a/docs/intro_open_chromatin.html
+++ b/docs/intro_open_chromatin.html
@@ -180,7 +180,7 @@
Nanopore sequencing can detect multiple base modifications simultaneously and we can leverage this capability by introducing exogenous base modifications at specific functional regions.
One such method uses a 6mA methyltransferase such as EcoGII or Hia5 to label accessible regions of chromatinized DNA, usually by treatment of cell nuclei with the enzyme.
-
+
Modkit comes with a machine learning model that has been trained to identify regions of open chromatin based on 6mA signal.
You can invoke this model with the following command: