run_config.yaml

# which steps to exclude during run.
# example: [1, 2] to only run steps 3 and 4
excluded_steps: []

# names of step1 input files
# can make pdb_fn "search" to automatically search
# the PDB database and download a PDB structure
# close to the first parent sequence
seq_fn: bgl3_sequences.fasta
pdb_fn: search

# run parameters
num_bl: 8  # number of blocks in library
minBL: 25  # minimum length of blocks in library
maxBL: 400  # maximum length of blocks in library

# specify first vector overhang. start_oh_pos represents position of first
# overhang base position to the first codon's start in the parent sequences,
# indexing from 0
# Example 1: parent sequence: "ATGGATC...", overhang sequence: "TATG"
#     -> start_oh_pos = -1 to make the "ATG" in both sequences to line up
# Example 2: parent sequence "CATGTAC...", overhang sequence: "TATG"
#     -> start_oh_pos = -4 to append the overhang onto the sequences
#         with no overlap
# start_oh_pos can range from -4 to -1, inclusive.
start_oh_seq: TATG  # first vector overhang
start_oh_pos: -1 

# specify end vector overhang. end_oh_pos represent position of first
# overhang base position to first base pair of the last codon in the sequence,
# indexing from 0. end_oh_pos can range from 0 to 3, inclusive.
end_oh_seq: TGAG
end_oh_pos: 0

# prefix on step 1 output files
out_prefix: bgl3

# name of step 2 output file
libraries_fn: bgl3_libraries.json

# gg_prob threshold for acceptable libraries (needs to be str for some reason)
gg_prob_threshold: "0.95"

# name of step 3 output file
chosen_lib_fn: bgl3_chosen_lib.json

# name of step 4 output file
frags_order_fn: bgl3_frag_order.fasta