jl02142
commented
3 weeks ago The gene/protein identifiers ("lcl|NZ_CP018093.1_prot_FSC454_RS07665_1515") are unique to me - which database or program are these from? I've written a bash script you can copy and paste into a text file in the same directory you are attempting to run OrthoRefine from. Running it will generate a file called "OrthoRefine_debug.log.txt", which you can copy or post back. As a privacy warning, it will print all the file names in the current directory - which you may want to review before posting them.
#!/usr/bin/env bash
# print current files names only in dir
ls > OrthoRefine_debug.log.txt
echo >> OrthoRefine_debug.log.txt
#print contents of "input.txt" to OrthoRefine_debug.log.txt
cat input.txt >> OrthoRefine_debug.log.txt
echo >> OrthoRefine_debug.log.txt
# check if file "No.tsv" exist in current directory
if [ -f "N0.tsv" ]; then
echo "N0.tsv exists" >> OrthoRefine_debug.log.txt
# check if file "N0.tsv" is in dos or unix format
if file "N0.tsv" | grep -q "CRLF"; then
echo "N0.tsv is in dos format" >> OrthoRefine_debug.log.txt
else
echo "N0.tsv is in unix format" >> OrthoRefine_debug.log.txt
fi
else
echo "N0.tsv does not exist" >> OrthoRefine_debug.log.txt
fi
echo >> OrthoRefine_debug.log.txt
# read the first column of each line from "input.txt" and write to array
IFS=$'\n' read -d '' -r -a lines < input.txt
# verify that each element of array exists as a feature table file. E.g. "GCF_000005845.2" as "GCF_000005845.2_ASM584v2_feature_table.txt"
for i in "${lines[@]}" ; do
if [ -f "$i"*_feature_table.txt ]; then
echo "$i"*_feature_table.txt exists >> OrthoRefine_debug.log.txt
else
echo "$i"_feature_table.txt does not exist >> OrthoRefine_debug.log.txt
fi
done
echo >> OrthoRefine_debug.log.txt
# verify that each element of array exists as a fasta file. E.g. "GCF_000005845.2" as "GCF_000005845.2_ASM584v2_protein.faa"
for i in "${lines[@]}" ; do
if [ -f "$i"*_protein.faa ]; then
echo "$i"*_protein.faa exists >> OrthoRefine_debug.log.txt
else
echo "$i"_protein.faa does not exist >> OrthoRefine_debug.log.txt
fi
done
echo >> OrthoRefine_debug.log.txt
# Check that both the feature table and fasta file exist for the same element of array lines
for i in "${!lines[@]}" ; do
if [ -f "${lines[$i]}"*_feature_table.txt ] && [ -f "${lines[$i]}"*_protein.faa ]; then
echo "Both feature table and fasta file exist for ${lines[$i]}" >> OrthoRefine_debug.log.txt
# Store the index of the first occurrence
first_occurrence=$i
break
fi
done
# Store the 11th column from the output above in a new array
IFS=$'\n' read -d '' -r -a new_array <<< "$(grep -m 10 "^CDS" "${lines[first_occurrence]}"*_feature_table.txt | awk '{print $11}')"
# Verify each element of new_array can be found in the asscoiated fasta file
for i in "${new_array[@]}" ; do
if grep -q "$i" "${lines[first_occurrence]}"*_protein.faa; then
echo "$i" exists in "${lines[first_occurrence]}"*_protein.faa >> OrthoRefine_debug.log.txt
else
echo "$i" does not exist in "${lines[first_occurrence]}"*_protein.faa >> OrthoRefine_debug.log.txt
fi
done
echo >> OrthoRefine_debug.log.txt
# Verify that each element of new_array can be found in "N0.tsv"
for i in "${new_array[@]}" ; do
if grep -q "$i" N0.tsv; then
echo "$i" exists in N0.tsv >> OrthoRefine_debug.log.txt
# store the line from N0.tsv where the element was found into another array without overwriting the previous element without splitting the line
tmp=$(grep "$i" N0.tsv)
N0_lines+="$tmp\n"
else
echo "$i" does not exist in N0.tsv >> OrthoRefine_debug.log.txt
fi
done
echo >> OrthoRefine_debug.log.txt
# print array N0_lines
for i in "${N0_lines[@]}" ; do
echo -e "$i" >> OrthoRefine_debug.log.txt # -e allows for newline char printing
done
# find the longest line by tabs and comma count in N0_lines
longest_line=$(echo -e "${N0_lines[@]}" | awk -F"\t|," '{print NF}' | sort -n | tail -1)
# for each element of N0_lines, extract the 4th column to end of line and store in another array
IFS=$'\n' read -d '' -r -a new_array2 <<< "$(echo -e "${N0_lines[@]}" | awk -F"\t|," -v e=$longest_line '{ for (i=4;i<e;++i) print $i }' | tr -d ' ')"
# for each element of new_array2, continue to search the feature table files 11th column until the element is found
for i in "${new_array2[@]}" ; do
found_flag=0
for j in "${lines[@]}" ; do
if grep -q "$i" "$j"*_feature_table.txt; then
echo "$i" exists in "$j"*_feature_table.txt >> OrthoRefine_debug.log.txt
found_flag=1
break
fi
done
if [ $found_flag -eq 0 ]; then
echo "$i" does not exist in any feature_table.txt >> OrthoRefine_debug.log.txt
fi
done
juansebe1
Hello! I'm trying to make a test of this tool with a small dataset, but I got a message of 'Segmentation fault' and I don't know what's going, could you help me to solve it?
./orthorefine.exe --input input.txt --OF_file N0.tsv --window_size 8 --synteny_ratio 0.5 Segmentation fault
input.txt
Head of N0.tsv: HOG OG Gene Tree Parent Clade F.hispaniensis F.opportunistica-142155 F.salina N0.HOG0000000 OG0000000 n0 lcl|NZ_CP018093.1_prot_FSC454_RS07665_1515, lcl|NZ_CP018093.1_prot_FSC454_RS03685_724 lc>N0.HOG0000001 OG0000001 n0 lcl|NZ_CP022375.1_prot_WP_198150407.1_912, lcl|NZ_CP022375.1_prot_WP_198150407.1_1283, lcl>N0.HOG0000002 OG0000002 n1 lcl|NZ_CP018093.1_prot_WP_197456248.1_1581, lcl|NZ_CP018093.1_prot_WP_197456248.1_582 lc>N0.HOG0000003 OG0000002 n3 lcl|NZ_CP018093.1_prot_WP_156470857.1_1013, lcl|NZ_CP018093.1_prot_WP_244148270.1_1829, lc>N0.HOG0000004 OG0000003 n0 lcl|NZ_CP018093.1_prot_FSC454_RS02585_506, lcl|NZ_CP018093.1_prot_FSC454_RS00585_115, lcl|>N0.HOG0000005 OG0000004 n1 lcl|NZ_CP018093.1_prot_WP_066046703.1_444 lcl|NZ_CP022375.1_prot_WP_071629540.1_1295>N0.HOG0000006 OG0000004 n4 lcl|NZ_CP018093.1_prot_WP_014715333.1_1297 lcl|NZ_CP022375.1_prot_WP_071629258.1_988 >N0.HOG0000007 OG0000004 n6 lcl|NZ_CP018093.1_prot_WP_003033846.1_1161 lcl|NZ_CP022375.1_prot_WP_071629064.1_771 >N0.HOG0000008 OG0000005 n0 lcl|NZ_CP018093.1_prot_FSC454_RS10000_1199, lcl|NZ_CP018093.1_prot_FSC454_RS06065_1201, lc>N0.HOG0000009 OG0000006 n0 lcl|NZ_CP018093.1_prot_WP_071794787.1_854, lcl|NZ_CP018093.1_prot_WP_071794788.1_855, lcl|>N0.HOG0000010 OG0000007 n1 lcl|NZ_CP018093.1_prot_WP_066046330.1_168 lcl|NZ_CP022375.1_prot_WP_071628521.1_157 >N0.HOG0000011 OG0000007 n3 lcl|NZ_CP018093.1_prot_WP_066045340.1_1632 lcl|NZ_CP022375.1_prot_WP_071629755.1_1531>N0.HOG0000012 OG0000008 n0 lcl|NZ_CP018093.1_prot_FSC454_RS01480_292, lcl|NZ_CP018093.1_prot_WP_231865178.1_1110, lcl>N0.HOG0000013 OG0000009 n1 lcl|NZ_CP018093.1_prot_FSC454_RS05915_1169 lcl|NZ_CP022375.1_prot_WP_071629056.1_763 >N0.HOG0000014 OG0000009 n3 lcl|NZ_CP018093.1_prot_WP_066045627.1_372 lcl|NZ_CP022375.1_prot_WP_071629606.1_1370>N0.HOG0000015 OG0000010 n0 lcl|NZ_CP018093.1_prot_WP_066046902.1_1055, lcl|NZ_CP018093.1_prot_WP_080555366.1_704 lc>N0.HOG0000016 OG0000011 n0 lcl|NZ_CP018093.1_prot_FSC454_RS03655_718 lcl|NZ_CP022375.1_prot_WP_071628872.1_552 >N0.HOG0000017 OG0000012 n0 lcl|NZ_CP018093.1_prot_WP_066044704.1_770 lcl|NZ_CP022375.1_prot_WP_071628925.1_609 >N0.HOG0000018 OG0000013 n1 lcl|NZ_CP018093.1_prot_WP_156860530.1_1116, lcl|NZ_CP018093.1_prot_WP_066045399.1_1117 lc>N0.HOG0000019 OG0000013 n3 lcl|NZ_CP018093.1_prot_WP_156860531.1_1542, lcl|NZ_CP018093.1_prot_WP_156860529.1_1115, lc>N0.HOG0000020 OG0000014 n1 lcl|NZ_CP018093.1_prot_WP_066045288.1_1653 lcl|NZ_CP022375.1_prot_WP_071629770.1_1546>N0.HOG0000021 OG0000014 n3 lcl|NZ_CP018093.1_prot_WP_244148253.1_1179 lcl|NZ_CP022375.1_prot_WP_071629238.1_963,>N0.HOG0000022 OG0000015 n1 lcl|NZ_CP018093.1_prot_WP_066046621.1_1788 lcl|NZ_CP022375.1_prot_WP_071629866.1_1651>N0.HOG0000023 OG0000015 n3 lcl|NZ_CP018093.1_prot_WP_066046618.1_1787 lcl|NZ_CP022375.1_prot_WP_071629865.1_1650>N0.HOG0000024 OG0000016 n1 lcl|NZ_CP018093.1_prot_WP_066046651.1_1806 lcl|NZ_CP022375.1_prot_WP_071629921.1_1711>N0.HOG0000025 OG0000016 n4 lcl|NZ_CP018093.1_prot_WP_014549092.1_1805 lcl|NZ_CP022375.1_prot_WP_071629920.1_1710>N0.HOG0000026 OG0000017 n1 lcl|NZ_CP018093.1_prot_WP_066045151.1_48 lcl|NZ_CP022375.1_prot_WP_071628416.1_40 >