Revision updates.

download_models.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+
+# download model weights (data fold 3, 4 replicates)
+for rep in f3c0,f0 f3c1,f1 f3c2,f2 f3c3,f3; do IFS=","; set -- $rep; 
+  mkdir -p "examples/saved_models/$1/train"
+  local_model="examples/saved_models/$1/train/model0_best.h5"
+  if [ -f "$local_model" ]; then
+    echo "$1 model already exists."
+  else
+    wget --progress=bar:force "https://storage.googleapis.com/seqnn-share/borzoi/$2/model0_best.h5" -O "$local_model"
+  fi
+done
+
+# download and uncompress annotation files
+mkdir -p examples/hg38/genes/gencode41
+mkdir -p examples/hg38/genes/polyadb
+
+if [ -f examples/hg38/genes/gencode41/gencode41_basic_nort.gtf ]; then
+  echo "Gene annotation already exists."
+else
+  wget -O - https://storage.googleapis.com/seqnn-share/helper/gencode41_basic_nort.gtf.gz | gunzip -c > examples/hg38/genes/gencode41/gencode41_basic_nort.gtf
+fi
+
+if [ -f examples/hg38/genes/gencode41/gencode41_basic_nort_protein.gtf ]; then
+  echo "Gene annotation (no read-through, protein-coding) already exists."
+else
+  wget -O - https://storage.googleapis.com/seqnn-share/helper/gencode41_basic_nort_protein.gtf.gz | gunzip -c > examples/hg38/genes/gencode41/gencode41_basic_nort_protein.gtf
+fi
+
+if [ -f examples/hg38/genes/gencode41/gencode41_basic_protein.gtf ]; then
+  echo "Gene annotation (protein-coding) already exists."
+else
+  wget -O - https://storage.googleapis.com/seqnn-share/helper/gencode41_basic_protein.gtf.gz | gunzip -c > examples/hg38/genes/gencode41/gencode41_basic_protein.gtf
+fi
+
+if [ -f examples/hg38/genes/gencode41/gencode41_basic_tss2.bed ]; then
+  echo "TSS annotation already exists."
+else
+  wget -O - https://storage.googleapis.com/seqnn-share/helper/gencode41_basic_tss2.bed.gz | gunzip -c > examples/hg38/genes/gencode41/gencode41_basic_tss2.bed
+fi
+
+if [ -f examples/hg38/genes/gencode41/gencode41_basic_protein_splice.csv.gz ]; then
+  echo "Splice site annotation already exist."
+else
+  wget https://storage.googleapis.com/seqnn-share/helper/gencode41_basic_protein_splice.csv.gz -O examples/hg38/genes/gencode41/gencode41_basic_protein_splice.csv.gz
+fi
+
+if [ -f examples/hg38/genes/gencode41/gencode41_basic_protein_splice.gff ]; then
+  echo "Splice site annotation already exist."
+else
+  wget -O - https://storage.googleapis.com/seqnn-share/helper/gencode41_basic_protein_splice.gff.gz | gunzip -c > examples/hg38/genes/gencode41/gencode41_basic_protein_splice.gff
+fi
+
+if [ -f examples/hg38/genes/polyadb/polyadb_human_v3.csv.gz ]; then
+  echo "PolyA site annotation already exist."
+else
+  wget https://storage.googleapis.com/seqnn-share/helper/polyadb_human_v3.csv.gz -O examples/hg38/genes/polyadb/polyadb_human_v3.csv.gz
+fi
+
+# download and index hg38 genome
+mkdir -p examples/hg38/assembly/ucsc
+
+if [ -f examples/hg38/assembly/ucsc/hg38.fa ]; then
+  echo "Human genome FASTA already exists."
+else
+  wget -O - http://hgdownload.cse.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz | gunzip -c > examples/hg38/assembly/ucsc/hg38.fa
+  python src/scripts/idx_genome.py examples/hg38/assembly/ucsc/hg38.fa
+fi

env_vars.sh

@@ -0,0 +1,50 @@
+#!/bin/bash
+
+# set these variables before running the script
+LOCAL_BORZOI_PATH="/home/jlinder/borzoi"
+LOCAL_BASKERVILLE_PATH="/home/jlinder/baskerville"
+LOCAL_WESTMINSTER_PATH="/home/jlinder/westminster"
+LOCAL_USER="jlinder"
+
+# create env_vars sh scripts in local conda env
+mkdir -p "$CONDA_PREFIX/etc/conda/activate.d"
+mkdir -p "$CONDA_PREFIX/etc/conda/deactivate.d"
+
+file_vars_act="$CONDA_PREFIX/etc/conda/activate.d/env_vars.sh"
+if ! [ -e $file_vars_act ]; then
+    echo '#!/bin/sh' > $file_vars_act
+fi
+
+file_vars_deact="$CONDA_PREFIX/etc/conda/deactivate.d/env_vars.sh"
+if ! [ -e $file_vars_deact ]; then
+    echo '#!/bin/sh' > $file_vars_deact
+fi
+
+# append borzoi (and baskerville/westminster) env variable exports to /activate.d/env_vars.sh
+echo "export BORZOI_DIR=$LOCAL_BORZOI_PATH" >> $file_vars_act
+echo 'export PATH=$BORZOI_DIR/src/scripts:$PATH' >> $file_vars_act
+echo 'export PYTHONPATH=$BORZOI_DIR/src/scripts:$PYTHONPATH' >> $file_vars_act
+
+echo "export BASKERVILLE_DIR=$LOCAL_BASKERVILLE_PATH" >> $file_vars_act
+echo 'export PATH=$BASKERVILLE_DIR/src/baskerville/scripts:$PATH' >> $file_vars_act
+echo 'export PYTHONPATH=$BASKERVILLE_DIR/src/baskerville/scripts:$PYTHONPATH' >> $file_vars_act
+
+echo "export WESTMINSTER_DIR=$LOCAL_WESTMINSTER_PATH" >> $file_vars_act
+echo 'export PATH=$WESTMINSTER_DIR/src/westminster/scripts:$PATH' >> $file_vars_act
+echo 'export PYTHONPATH=$WESTMINSTER_DIR/src/westminster/scripts:$PYTHONPATH' >> $file_vars_act
+
+echo 'export BORZOI_HG38=$BORZOI_DIR/examples/hg38' >> $file_vars_act
+echo 'export BORZOI_MM10=$BORZOI_DIR/examples/mm10' >> $file_vars_act
+
+echo "export BORZOI_CONDA=/home/$LOCAL_USER/anaconda3/etc/profile.d/conda.sh" >> $file_vars_act
+
+# append borzoi env variable unsets to /deactivate.d/env_vars.sh
+echo 'unset BASKERVILLE_DIR' >> $file_vars_deact
+echo 'unset WESTMINSTER_DIR' >> $file_vars_deact
+echo 'unset BORZOI_DIR' >> $file_vars_deact
+echo 'unset BORZOI_HG38' >> $file_vars_deact
+echo 'unset BORZOI_MM10' >> $file_vars_deact
+echo 'unset BORZOI_CONDA' >> $file_vars_deact
+
+# finally activate env variables
+source $file_vars_act