diff --git a/environment.yml b/environment.yml index d08bb6c..a693efe 100644 --- a/environment.yml +++ b/environment.yml @@ -11,3 +11,4 @@ dependencies: - scikit-bio - snakemake - biopython + - tqdm diff --git a/phylofiller/converter.py b/phylofiller/converter.py index d5788e1..232af10 100644 --- a/phylofiller/converter.py +++ b/phylofiller/converter.py @@ -3,49 +3,33 @@ from Bio.Seq import Seq import collections import sys +from tqdm import tqdm +import re -def easel_table2pd(lines) -> pd.DataFrame: - # easel is using a strange tab format. Instead of splitting via a single - # del. char like \t columns are aligned for visual inspection. Hints of - # column starts/ends are given by the second line with dashes, but it does - # not cover ALL columns :-/ - # Thus, I here try to make a consistent annotation of column fields (-) - # and spearators (#) - line_fields = lines[1].replace('- ', '-#').replace(' -', '#-').replace( - ' ', '-') - # leading whitespaces most likely indicate NO empty column. - # Thus, I add these positions to the first real column. - if line_fields.startswith('#'): - line_fields = '-'+line_fields[1:] - - column_positions = [] - curr_pos = 0 - for i, field in enumerate(line_fields.split('#')): - column_positions.append((curr_pos, curr_pos + len(field))) - curr_pos += len(field) + 1 +def easel_table2pd(lines, verbose=True) -> pd.DataFrame: + headers = [] + for m in re.finditer(r"\S+", lines[2]): + header_start, header_end = m.start(), m.end() + while lines[1][header_start] == "-": + header_start -= 1 + while (header_end < len(lines[0])) and (lines[1][header_end] == "-"): + header_end += 1 + headers.append(lines[0][header_start:header_end].strip()) rows = [] - for row_num, line in enumerate(lines): - if row_num == 1: - # this is the ---- line and no content + for row_num, line in tqdm(enumerate(lines), disable=not verbose): + if row_num <= 1: continue if row_num > 1 and line.startswith('#'): continue # as this is a trailing comment line - row = [] - for col_num, (start, stop) in enumerate(column_positions): - if col_num == 0: - row.append(line[:stop].strip()) - elif col_num+1 == len(column_positions): - row.append(line[start-1:].strip()) - else: - row.append(line[start-1:stop].strip()) - rows.append(row) + rows.append(line.rstrip().split()) table = pd.DataFrame( - data=rows[1:], - columns=rows[0], - index=range(len(rows)-1)) + data=rows, + columns=headers, + index=range(len(rows)) + ) # automatic datatype conversion from "object" to int and float to # saveguard the user from sorting implicitely lexiographically when @@ -57,13 +41,13 @@ def easel_table2pd(lines) -> pd.DataFrame: if col in table.columns: table[col] = table[col].astype(float) - if (any(pd.Series(table.columns).value_counts() > 1)): + if (any(pd.Series(table.columns).value_counts() > 1)) and verbose: print("warning: column names are not unique!", file=sys.stderr) return table -def parse_easel_output(fp_input: str) -> pd.DataFrame: +def parse_easel_output(fp_input: str, verbose=True) -> pd.DataFrame: """Parses Infernal (soon also Hmmer) as a pandas DataFrame. Parameters @@ -109,7 +93,8 @@ def parse_easel_output(fp_input: str) -> pd.DataFrame: model_clen = line.split()[-1].split('=')[-1].replace(']', '') elif line.startswith('>> '): # next three lines will be an overview table - hit_info = easel_table2pd(lines[line_number+1:line_number+3+1]) + hit_info = easel_table2pd(lines[line_number+1:line_number+3+1], + verbose=verbose) # target name is in the >> line hit_info['target name'] = line[3:].strip() diff --git a/phylofiller/test/data/easel2sam/exp_parse_easle_output.txt b/phylofiller/test/data/easel2sam/exp_parse_easle_output.txt index 89d54bf..130cbdc 100644 --- a/phylofiller/test/data/easel2sam/exp_parse_easle_output.txt +++ b/phylofiller/test/data/easel2sam/exp_parse_easle_output.txt @@ -1,24 +1,24 @@ -;rank;;E-value;score;bias;mdl;mdl from;mdl to;;seq from;seq to;;acc;trunc;gc;target name;query sequence;target sequence;model name;model clen;software;software version;fp_query;fp_target -0;(1);!;4.2e-23;84.6;0.1;hmm;710;930;.];284427;284630;+ ..;0.86;-;0.44;Scaffold6;AGAGACCGAUAGCGCACAAGUAGAGUGAUCGAAAGAUGAAAAGAACUUUGAAAAGAGAGUUAAAaAGUACGUGAAAUUGUUGAAAGGGAAGCGCUUGUGACCAGACUUGGGCUuGGUUGAUCAUCCgGGGUUCUCCCuGGUGCACUCUUCCGGCccAGGCCAGCAUCAGUUcGCCcuGGGGGAuAAAGGCuuCGGGAAuGUGGCUCuCUCCGGGGAGUGUU;AAAUGCCGAUGGUGUACGAUUA--CUGAUCAAAAGAUGAA-AGAACUUAAGAAAGAGAGCUAA-AAGUACGUGAG---GUUGAAAG-GAAACGCUUGGCACUAGAUUUGGGCUUGGUUGAUU-----GAGGUCCCUUCAGUGCACUCU---GGCCUAUGCUGGUAUUAACUUGCCUAAGGGAAUAAAGGCUUG-GGGAUGUAGUUCUCUCCUGGGAGUGUU;FSSC_ITS+28S-rDNA--956-bp.fna;930;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -1;(2);!;7e-17;64.0;0.0;hmm;802;928;..;4687313;4687190;- ..;0.91;-;0.54;Scaffold3;GCUUGUGACCAGACUUGGGCUuGGUUGAUCAUCCgGGGUUCUCCCuGGUGCACUCUUCCGGCccAGGCCAGCAUCAGUUcGCCcuGGGGGAuAAAGGCuuCGGGAAuGUGGCUCuCUCCGGGGAGUG;GCUCGAGACCAGACCUGGGCUUGGUUGAUCAUCCAG-GUUCUUCCUGGUGCACUCUUCUGGCUUAUGCCAGCAUCGAUUUGUCUUGAGGAACAAUGGUUUCCGGGAUGUGACUA--CCCGGGCAGUG;FSSC_ITS+28S-rDNA--956-bp.fna;930;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -2;(3);?;0.016;16.6;0.0;hmm;752;808;..;1013790;1013850;+ ..;0.78;-;0.39;Scaffold1;GAACUUUGAAAAGAGAGUUAAAaAGUACGUGAAAUUGUUGA....AAGGGAAGCGCUUGUG;AAAUUUUAAAAAGAGAGUUAAGCAGUACGUGAAAUUGUCGUucgcAUUGGACCCGUUGGUG;FSSC_ITS+28S-rDNA--956-bp.fna;930;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -3;(4);?;1.1;10.6;1.0;hmm;693;821;..;2222270;2222153;- ..;0.73;-;0.46;Scaffold5;AAAGCUAAAUACCGGCCAGAGACCGAUAGCGCACAAGUAGAGUGAUCGAAAGAUGAAAAGAACUUUGAAAAGAGAGUUAAAaAGUACGUGAAAUUGUUGAAAGGGAAGCGCUUGUGAC...CAGACUUGGGC;AAGGCAAGCUACCACCUUCAAAGAAAUAGUGUCCGGCAAGAAGGAUCGAAAGG--------------AGAAGGAGGUUAUAGAGGACGGGAAAUUGGUGUAAUAAAAGCGUCAAUGACagaCAGACGAGGUC;FSSC_ITS+28S-rDNA--956-bp.fna;930;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -4;(5);?;5.7;8.2;0.7;hmm;756;861;..;3020655;3020767;+ ..;0.79;-;0.58;Scaffold2;UUUGAAAAGAGAGUUAAAaAGUACGUGAAAUUGUUGAAAGGGAAGCGCUUGUGACCAG.......ACUUGGGCUuGGUUGAUCAUCCgGGGUUCUCCCuGGUGCACUCUUCCG;UCUGGAGAGGGAAUAAAAAAGCUGGAGAAAUGGCGCGGGGGAAAGGGCUCUUUGCCAGgggggagUGUGGAGCUUGGGCGAUGAUGACGGGUGAUACCUGGGGCAUGAUGCGG;FSSC_ITS+28S-rDNA--956-bp.fna;930;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -5;(1);!;2.7e-265;885.0;0.0;hmm;2;826;..;2966345;2965521;- ..;0.99;-;0.54;Scaffold3;ACcCCuAUuGGACGAGAUGGAAAGCUCGCCAAGCCCCGUCAGCUaCACAACACCCAUUGGGGuCUGGUcUGuCCAGCCGAGACgCCcGAGGGUCAGGCUUGUGGuCUGGUCAAGAACUUGUCcCUGAUGUGcUAcGUCAGUGUCGGcUCUCCcUCcGAACCucUGAUuGAGUUCAUGAUCAACCGAGGUAUGGAaGUCGUGGAAGAGUACGAgCCCCUGAGAUAcCCgCAUGCuACCAAGAUcUUuGUCAAuGGUGUcUGGUGuGGUGUcCACUCgGACCCcAAGCAUCUCGUCAGcCAGGUccUGGACACaCGACGAAAGUCGUAccUGCAGUAcGAGGUGUCgCUuGUUCGUGACAUUCGAGAuCGAGAGUUCAAGGUCUUCUCCGACGCuGGCCGAGUCAUGAGgCCGGUCUUUACGGUuCAGCAGGAGGAuGACCAcGAgUCUGGUAUuGCCAAGGGAGCuuUGGUuCUGACCAAGGACcUuGUCAACAAGcUuGCuAAGGAGCAGGCGGAGCCaCCAGAGGACCCAUCaauGAAGAUUGGAUGGGAGGGUCUGAUCCGaGCcGGaACcAUCGAGUACCUCGAUGCuGAGGAAGAGGAGaCGGCuAUGAUUUGCAUGACuCCUGAGGAuCUuGAcCUCUAuCGcAUGCAAAAGGCuGGUUACGUcGUaGAuGAcGAUAACACGGACGACCCcAACAGGAGaUUGAAGACcAAGACgAACCCCACAACUCACAUGUACACUCAUUGUGAGAUUCACCCcAGuAUGAUUCUuGGCAUuUGuGCCAGUAUCAUUCCcUUCCCcGAUCACAACCAGGUAuACgAC;ACCCCUAUUGGACGAGAUGGAAAGCUCGCCAAGCCCCGUCAGCUACACAACACCCAUUGGGGUCUGGUCUGUCCAGCCGAGACACCCGAGGGUCAGGCUUGUGGUCUGGUCAAGAACUUGUCCCUGAUGUGUUACGUCAGUGUCGGUUCUCCUUCUGAACCUCUGAUCGAGUUCAUGAUCAACCGAGGCAUGGAAGUCGUGGAAGAGUACGAGCCCCUGAGAUACCCGCAUGCUACCAAGAUCUUUGUCAAUGGUGUCUGGUGCGGUGUCCACUCGGACCCCAAGCAUCUCGUCAGCCAGGUCCUGGACACACGACGAAAGUCGUACCUGCAAUACGAGGUGUCGCUCGUCCGUGACAUUCGAGAUCGAGAGUUCAAGGUCUUCUCCGACGCUGGCCGAGUCAUGAGGCCAGUCUUUACGGUUCAGCAGGAGGAUGACCACGAGUCUGGUAUCGCCAAGGGAGCUUUGGUUCUGACCAAGGACCUUGUCAACAAGCUUGCUAAGGAGCAGGCGGAGCCACCAGAGGACCCAUCAAUGAAGAUUGGAUGGGAGGGUCUGAUCCGAGCCGGAACCAUCGAGUACCUCGAUGCUGAGGAAGAGGAGACGGCUAUGAUUUGCAUGACUCCUGAGGAUCUUGACCUCUAUCGCAUGCAAAAGGCUGGUUACGUCGUAGAUGACGAUAACACGGACGACCCCAACAGGAGAUUGAAGACCAAGACGAACCCCACAACUCACAUGUACACUCAUUGUGAGAUUCACCCCAGUAUGAUUCUUGGCAUUUGUGCUAGUAUCAUCCCCUUCCCCGAUCACAACCAGGUAUGCGCC;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -6;(2);!;1.1e-243;813.4;0.0;hmm;787;1588;.];2965391;2964591;- ..;0.96;-;0.53;Scaffold3;CAGUAUCAU.UCCcUUCCCcGAUCACAACCAGGUAuACgACaCGaUCCAUGGAGUUCCUCAAGUUCCGUGAaCUGCCaGCcGGuCAGAACGCCAUcGUCGCuAUCGCUUGcUACUCuGGUUAcAACCAGGAAGAUUCCGUCAUuAUGAACCAGAGuAGUAUCGAuCGAGGCuUGUUCCGcAGUcUGUUCUUCaGAUCcUACUCuGAcCAGGAGAAGAAGGUCGGuCUgAACUACACGGAAGUGUUuGAGAAGCCCUUCCAGCAGUCGACgCUUCGuAUGAAGCAcGGUACcUACGACAAGCUGGAcGAGGAuGGUAUcGUGGCcCCcGGuGUGCGAGUGUCgGGUGAaGAUAUCAUcAUCGGCAAGACuGCGCCGAUuGAuCAAGAGAACCAGGAUCUgGGuACCAGGACaACgGUGCACCAGCGUCGUGAUAUCUCcACgCCGCUGCGAAGuACcGAgAACGGuAUCGUuGAuucGGUCAUUGUGACuGUCAAuGCcGACAACGUCAAGUAcGUCAAGGUCCGUGUGAGGACGACCAAGAUUCCuCAGAUUGGuGACAAGUUuGCCUCUCGUCACGGACAGAAGGGUACCAUUGGUGUuACcUACcGaCAGGAGGAuAUGCCcUUcagCAGGGAGGGuGUGACaCCaGACAUuAUCAUuAACCCCCACGCCAUUCCgUCGCGAAUGACAAUUGCcCAUUUGAUUGAAUGCCUCCUCAGUAAGGUGUCAACgCUcGAAGGCAUGGAGGGUGAuGCaACaCCuUUCACcGAuGUCACuGUcGACUCcGUuUCGGAGCUGCUCCG;CAACAUUCUuUACUAUCCGCAAA--AACCUCUGGCGACAACACGAUCCAUGGAGUUCCUCAAGUUCCGUGAACUACCAGCCGGUCAGAAUGCCAUCGUCGCUAUCGCUUGCUACUCUGGUUACAACCAGGAAGAUUCCGUCAUUAUGAACCAGAGUAGUAUCGAUCGAGGCCUGUUCCGCAGUCUGUUCUUCAGAUCCUACUCUGACCAGGAGAAGAAGGUCGGACUGAACUACACGGAAGUGUUCGAGAAGCCCUUCCAGCAGUCGACGCUUCGUAUGAAGCACGGUACUUACGACAAGCUGGACGAGGAUGGUAUCGUGGCCCCCGGUGUCCGAGUGUCAGGUGAAGACAUCAUCAUCGGCAAGACUGCGCCGAUUGACCAAGAGAACCAGGAUCUGGGUACCAGGACGACGGUGCACCAGCGUCGUGAUAUCUCCACGCCGCUGCGAAGUACCGAGAACGGUAUCGUCGAUUCGGUCAUUGUGACUGUCAAUGCCGACAACGUCAAGUACGUCAAGGUCCGUGUGAGGACGACCAAGAUUCCUCAGAUUGGUGACAAGUUCGCCUCUCGUCACGGACAGAAGGGUACAAUUGGUGUCACCUACCGGCAGGAGGAUAUGCCCUUCAGCAGGGAGGGUGUGACACCAGACAUUAUCAUUAACCCCCACGCCAUUCCCUCGCGAAUGACAAUUGCCCAUUUGAUUGAAUGCCUCCUCAGUAAGGUGUCAACGCUCGAAGGCAUGGAGGGUGAUGCAACGCCUUUCACCGAUGUCACCGUCGACUCCGUUUCGGAGCUGCUCCG;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -7;(3);!;1.7e-34;120.9;0.0;hmm;828;1525;..;2315121;2315839;+ ..;0.66;-;0.51;Scaffold4;CGaUCCAUGGAGUUCCUCAAGUUCC..................GUGAaCUGCCaGCcGGuCAGAACGCCAUcGUCGCuAUCGCUUGcUACUCuGGUUAcAACCAGGAAGAUUCCGUCAUuAUGAACCAGAGuAGUAUCGAuCGAGGCuUGUUCCGcAGUcUGUUCUUCaGAUCcUACUCuGAcCAGGAGAAGAAGGUCGGuCUgAACUACACGGAA.GUGUUuGAGAAGCCCUUCCAGCAGUCGACgCUUCGuAUGAAG....CAcGGU..........ACc......UACGACAAGCUGGAcGAGGAuGGUAUcGUGGCcCCcGGuGUGCGAGUGUCgGGUGAaGAUAUCAUcAU..............CGGCAAGACuGCGCCGAUuGAuCAAGAGAACCAGGAUCUgGGuACCAGGAC.aACgGU.GCACCAGCG....UCGUGAUAUCUCcACgCCGCUGCGAAGuACcGAgAACGGuAUCGUuGAuucGGUCAUUGUGACuGUCAAuGCcGACAACGUCA...AGUAcGUCAAGGUCCGUGUGAGGACGACCAAGAUUCCuCAGAUUGGuGACAAGUUuGCCUCUCGUCACGGACAGAAGGGUACCAUUGGUGUuACcUACcGaCAGGAGGAuAUGCCcUUcagCAGGGAGGGuGUGACaCCaGACAUuAUCAUuAACCCCCACGCCAUUCCgUCGCGAAUGACAAUUGCcCAUUUGAUUGAAUGCCUCCUCAGUAAGGUGUCAACgCUcGAAGG;CGACCCAUGGUUAUCUCCAAGACCAuccagcuuauuggcuaugAUAAGCUCCCCGCAGGCCAGAACGCGACUGUCGUCGUCAUGUCGUACUCUGGAUAUGAUAUCGAAGAUGCUUUGGUUCUGAACAAGGCGUCGAUCGACAGAGGAUUUGGACGCUGCCAGGUCUUCCGCAAAUACACG-ACCGAGCUACA-----------AAAAUACCCUAAUgGUCGCCGAGA-GCGCAUC-GG----CGAUCCCCAAAAUGAAGaaggCAAGGUcaagcaaagaAUCaagaagCAUGAAGGUCUCGACGACGAUGGUUUGG--------------CCAUUGUGGGAUACAGAAUUCAUAAUggcgaggccaugauCAAGAAGGAAACACCCCUUGACCA-GACAACCACC-----GGCAUCGGAAUgGAUCGUgGACCCAGCGaauaCCGUGAUUCUUCAGUCUCGUACCGUAUUGCUGAUCCGGCAUACAUUGACAAGGUGAUGGUAUC---CCAAACAGAGAAGGACAcuaCAGUUAUCAAGGUCCAGACCAGACAGACUCGUCGUCCAGAGCUUGGAGACAAGUUUUCAUCUCGUCACGGUCAAAAGGGUGUGGUUGGCAUCAUUGUUGAUCAGGAGGAUCUGCCCUUCUCUGACAAGGGCCUGACCCCUGAUAUCAUCAUGAACCCUCACGGUUUCCCGUCUCGAAUGACGGUCGGCAAGCUGCUCGAGUGCUUGACGGGCAAGGCUUCCAUUAUCCAUGG;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -8;(4);!;1.6e-26;94.6;0.0;hmm;761;1564;..;1337459;1336642;- ..;0.63;-;0.55;Scaffold6;CCcAGuAUGAUUCUuGGCAUuUGuGCCAGUAUCAUUCCcUUCCCcGAUCACAACCAGGUAuACgACaCGaUCCAUGGAGUUCCUC...A..A........GUUCCGUGAaCUGC.CaGCcGGuCAGAACGCCAUcGUCGCuAUCGCUUGcUACUCuGGUUAcAACCAGGAAGAUUCCGUCAUuAUGAACCAGAGuAGUAUCGAuCGAGGCuUGUUCCGcAGUcUGUUCUUCaGAUCcUACUCuG.AcCAGGAGAAGAAGGUCGGuCUgAACUA...CACG.....G.........A..AGUGUUuGAGAAGCCCUUC...CAGCA.GUCGACgCUUCGuAUGAAGCAcGGUAC.cUACGACAAGCUGGAcGAGGAuGGUAUcGUGGCcCCcGGuG..UGCGAGUGUCgGGU.GAaGAUAUCAUcAUCG...GCAAGACuGCGCCGAUuGAuCAAGAGAACCAGGAUCUgG.GuACCAGGACaACgGUGCACCAGCGUCGUGAUAUCUCcACgCCGCUGCG..AAGuAC........cGAgAACGGuAUCGUuGAuucGGUCAUUGUGACuG...UCAAuGCcGACAACG............UCAAGUAcGUCAAGGUCCGUGUGAGGACGACCAAGAUUCCuCAG.AUUGGuGACAAGUUuGCCUCUCGUCACGGACAGAAGGGUACCAUUGGUGUuACcUACcGaCAGGAGGAuAUGCCcUUcagCAGGGAGGGuGUGACaCCaGACAUuAUCAUuAACCCCCACGCCAUUCCgUCGCGAAUGACAAUUGCcCAUUUGAUUGAAUGCCUCCUCAGUAAGGUGUCAACgCUcGAAGGCAUGGAGGGUGAuGCaACaCCuUUCACcGAuGUCACuGU;CCCAGUACUAAUCUUCGCUACCGAACCGACAACAAGUCAUACC--GCAUACAAACUGGACAAACACCCGU-CGUGCGAGCACCUCuucAcaAcacauaugGUUUCGACAACUUCcCCAACGGCAUGAACGCAGUUGUUGCCGUCAUCUCGUAUACUGGAUAUGACAUGGACGACGCCAUGAUUCUCAACAAGAGCGCCCAUGAGCGUGGUUUUGGGCA----------------UGGUACUAUCuACAAGACAAAGAAGAUCUCUCUCAAGGAugaCUCGcgaacAaaggccaccAagAGUGUUACCAAGGCUUUUGgcuUCGCAcCUCACAGCUACGUG---AGCGCGUCAUaCCAGGGAAUGCUGGAUGACGACGGCCU---GCCUCACGUGGgcCGCAUGAUCCAGGAgGGAGAUGUAAUCUGCGcguGGCACACAGUGACGCCCGACUACAAUGGCAAG---CUGGuGAACCUGGAUGGC-------------------AU---CACU-CACUACGaaAAGUACaaggauggCGAGACGGGCUUUGUCGAAGAGGUCCGCCUGAUCGgagCCGAAACCGGCAACGagccucuccagaCCAUCUCUGUCAAGUUCCGUGUU-------CCUCGAUCCCCCAUcAUCGGUGACAAGUUCUCGUCCAGACACGGACAGAAGGGUGUCGCCUCGCAAAAGUGGCCAACGGUGGAUCUGCCCUUCUCGGAGACUGGCAUCCAACCGGACAUCAUCAUUAACCCCCACGCUUUCCCUUCCCGUAUGACGAUAGGCAUGUUUGUGGAAUCGCUCGCCGGCAAGGCUGGCGCGCUGCAUGGCCUUGCGCAAGACUCGACACCGUUCAAGUUUGACGAGGA;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -9;(5);!;5.9e-08;33.1;0.0;hmm;17;320;..;2314349;2314665;+ ..;0.69;-;0.53;Scaffold4;GAUG.GAAAGCUCGCCAAGCCCCGUCAGCUaCACAACACCCAUUGGGGuCUGGUcUGuCCAGCCGAGACgCCcGAGGGUCAGGCUUGUGGuCUGGUCAAGAACUUGUCcCUGAUGUGcUAcGUCA......GUGUCGGcUCUCCcUCcGAACCucUGAUuGAGUUCAUGAUCAACCGAGGUAUGGAaGUCGUGG......AAGAG...UACGAgCCCCUGAGAUAcCCgCAUGCuACCAAG...AUcUUuGUCAAuGGUGUcUGGUGuGGUGUcCACUCgGACCCcAAGCAUCUCGUCAGcCAGGUccUGGACAC.aCGACGAA;GACGcGAAAGGUCUCAGGCCCUCGUGCGCUCCAACCGUCGCAAUGGGGUAUGCUGUGCACUUCGGAUACACCUGAAGGAGAAGCCUGCGGUCUGGUGAAGAACUUGGCUUUGAUGACACAUAUCAccacaaAUGUCGAG------GAAGGACCCGUGAAGGAGACUAUCCUGACGAUCGACAAGGAAGUUGAGGcuaucgAGAAAuucUCUGGCUCAAUGAUGCACCGGGAAGGGAGCUACgucAUCCAUGUCAAUGGUACGCCAUUC-GCAUUGACACGGAAUCCGAAGAGGUUCGCACAAAGGUUCAGGACAUuGCGACGAA;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -10;(6);!;0.0059;16.5;0.0;hmm;438;542;..;5920205;5920315;+ ..;0.80;-;0.6;Scaffold1;ACCAcGAgUCUGGUAUuGCCAAGGGAGCuuUGGUuCUGACCAAGGACcU......uGUCAACAAGcUuGCuAAGGAGCAGGCGGAGCCaCCAGAGGACCCAUCaauGAAGA;CCCUGAAGGCUGGCGUUGACAAGGGCAUCUUUGAGCAGCCCAAGGGUCCuuccggUGGCACCAAGCUUGCCAAGAAGCAGCCUGAGCCCAAGAAGGCUGCCGCUGAGAAGA;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -11;(7);?;0.037;13.9;0.1;hmm;551;715;..;478876;478690;- ..;0.62;-;0.55;Scaffold4;GAGGGUCUGAUCCGaGCcGGaACcAUCGAGUACCUCGAUGCuGAGGAAGAGGAG.aCGGCuAUGAUUUGCAUGACuCCUGAGG...........AuCUu.......GA..cCUCUAuCGcAUGCAAAA.....GGCuGGUUACGUcGUaGAuGAcGAUAACACGGACGACCCcAACAG....GAGaUUGAAGACc;GAGGUUGAGAUUCCAGAGGAGAUUGAAGAGGAAGAAGAGGUCGAAGAGGAAGAGgAUGACGAGGAUA-------CUCUUGAGGucgagggcgagAUCAUcgcugaaGAgcCAUCCGGCGAA-GAAGAAgagccGGCCGUAGAAGUUGUGGAGGAAGAUGACCCGGACGACACCAUCAGuccgGAAGCUGAAGAGG;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -12;(8);?;0.071;12.9;0.0;hmm;669;899;..;2314870;2315072;+ ..;0.59;-;0.51;Scaffold4;UcGUaGAuGAcGAUAACACGGACGACCCcAACAGGAGaU.UGAAGACcAAGACgAACCCCACAACUCACAUGUACACUCAUUGUGAGAUUCACCCcAGuAUGAUUCUuGGCAUuUGuGCCAGUAUCAUUCCcUUCCCcGAUCACAACCAGGUAuACgACaCGaUCCAUGGAGUUCCUCAAGUUCCGUGAaCUGCCaGCcGGuCAGAACGCCAUcGUCGCuAUCGCUUGcUAC;UGGAUGUGAACGAGGAGAAUGACGCCCUCAUCACCAUCUaCGAAGACCAAG----------UGACGCAAAGUACCACGCAUCUGGAGAUUGAGCCGUUCACCAUCCUGGGUGCAGUUGCAGGACUGAUUCCAUUCCCUCACCACAACCAAU----CGCCU-------CGUAAUACCUAC----CAAUGUGC----UAUGGGUAAACAAGCCAUUGGUGCCAUCGCCUACAAC;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -13;(9);?;0.31;10.8;0.0;hmm;421;600;..;3659261;3659088;- ..;0.62;-;0.56;Scaffold4;GGUuCAGCAGGAGGAuGACCAcG...AgUCUGGUAUuGCCAAGGGAGCuuUGGUuCUGACCAAGGACcUuGUCAACAAGcUuGCuAAGGAGCAGGCGGAGCCaCCAGAGGACCCAUCaauGAAGAUUGGAUGGGAGGGUCUGAUCCGaGCcGGaACcAUCGAGUACCUCGAUGCuGAGGAAGA;GGACCUGGAUGACGAUGCCCGUGcccAGCGCGACGAGGAGCAGGGAGUCAAGGACAUUAUCAAUGACCUCAAAAAGCAGCUCGCCAACAAGCAGGCUGAGCUGGCC-CGCACCCAGAAC--AAGAUCUU----GCGUACUCGUAUCGAGCAG--ACCAUCAAGCAGCUCAAGUCGGAGAUUGA;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -14;(10);?;1.0;9.1;0.0;hmm;56;140;..;1338065;1337981;- ..;0.74;-;0.53;Scaffold6;CAUUGGGGuCUGGUcUGuCCAGCCGAGACgCCcGAGGGUCAGGCUUGUGGuCUGGUCAAGAACUUGUCcCUGAUGUGcUAcGUCA;UCAUGGGGCUUCAUGUGUCCUGUCCACACGCCUGAUGGUGCGCCUUGUGGUCUUCUGAACCAUCUUGCGCACAAGUGCAAGAUUA;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -15;(11);?;1.7;8.3;0.8;hmm;426;595;..;3674449;3674606;+ ..;0.64;-;0.59;Scaffold2;AGCAGGA...GGAuGACCAcGAgUCUGGUAUuGCCAAGGGAGCuuUGGUuCUGACCAAGGACcUuGUCAACAAGcUuGCuAAGGAGCAGGCGGAGCCaCCAGAGGACCCAUCaauGAAGAUUGGAUGGGAGGGUCUGAUCCGaGCcGGaACcAUCGAGUACCUCGAUGCuGAG;ACCAGGAuauGCACGACAGCCUGACUGGCAUCGCCGAGGAGGCCCAGAAGACGGCUAAGGAUCUGGAGUCGAAGCUUGCCGAGGCGUUGGCCAAGGU---UGAGGAUGGAGAGAAGCAGGU------GGAGGUUCU----CGAGGCCCA--AAUCAAGGUCAAGGAUGCCGAG;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -16;(1);!;2.6e-192;642.5;0.1;hmm;1;632;[];6427210;6427837;+ ..;0.99;-;0.54;Scaffold2;AGUCGACCACCGUAAGUCaaaCCCUCaUcGCGAuCUGCUuAUCUCGGGUCGUGGAACCCCGCCuGguauCUCGGGCGGGGUauuCAUCAgUCACUucaUGCUGACAAUCAucuACAGACCGGUCACUUGAUCUACCAGUGCGGUGGUAUCGACAAGCGAACCAUCGAGAAGUUCGAGAAGGUUGGUGACAUCUCCCCCGAUCGCGCCUUGCUaUuccaCAUCGAAUUCCcCGUCGAAUUCCCUCCcuCGCGAuaCGCuCUGCGCCCGCUuCUCCCGAGUCcCAAAAuUUUUGCGGUuCGACCGuaAuUUUUUUuGGUGGGGCAUuUACCCCGCCaCUCGgGcGACGUUGGACAAAGCCCUGAUCCCUGCACAC.AAAAACACCAAACCCUCUUGGCGCGCAUCaUCACGUGGUucaCaaCAGAcgCUaACcGguuCAACAAuAGGAAGCCGCUGAGCUCGGuAAGGGUUCCUUCAAGUACGCCUGGGUCCUUGACAAGCUCAAGGCCGAGCGUGAGCGUGGUAUCACCAUCGAcAUUGCcCUCUGGAAGUUCGAGACUCCCCGCUACUAUGUCACCGUCAUUGGUAUGUcGCuGucgucuCucUCacuCauGUCUCacCaCUAACaAUCaACA;AGUCGACCACCGUAAGUCAAACCCCCAUCGCGAUCUGCUUAUCUCGGGUCGUGGAACCCCGCCUGGUAUCUCGGGCGGGGUACUCAUCAGUCACUUCAUGCUGACAAUCAUCUACAGACCGGUCACUUGAUCUACCAGUGCGGUGGUAUCGACAAGCGAACCAUCGAGAAGUUCGAGAAGGUUGGUGACAUCUCCCCCGAUCGCGCCUUGCUAUUCCACAUCGAAUUCCCCGUCGAAUUCCCUCUUCCGCGACACGCUCUGCGCCCGCUUCUCCCGAGUCCCAAAAAUUUUGCGGUUCGACCGUAAUUUUUUU-GGUGGGGCAUUUACCCCGCCACUCGGGCGACGUUGGACG-AGCCCUGAACCCUGCACACaAAAAACACCAAACCCUCUUGGCGCG---CAUCACGUGGUUCACAACAGACACUAACAGGUUCAACAAUAGGAAGCCGCUGAGCUCGGUAAGGGUUCCUUCAAGUACGCCUGGGUCCUUGACAAGCUCAAGGCCGAGCGUGAGCGUGGUAUCACCAUCGAUAUUGCUCUCUGGAAGUUCGAGACUCCCCGCUACUAUGUCACCGUCAUUGGUAUGUCGCCCUCAUCUCUCUCAAUCACGUCUCAUCAUUAACAAUCAACA;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -17;(2);?;0.042;16.1;0.0;hmm;468;568;..;4896877;4896777;- ..;0.66;-;0.53;Scaffold3;UCCUUCAAGUACGCCUGGGUCCUUGACAAGCUCAAGGCCGAGCGUGAGCGUGGUAUCACCAUCGAcAUUGCcCUCUGGAAGUUC......GAGACUCCCCGCUACUA;UUCCUCGAGUAUG---GUGCCAUUGACAAGGCUCCCGAGGAGCGAAAGCGUGGUAUCACCAUUUCCACUGCUCACAUCGAGUACucuaccGACAA---CCGCCACUA;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -18;(3);?;0.048;15.9;0.0;hmm;438;541;..;3187913;3188016;+ ..;0.85;-;0.54;Scaffold2;CAAuAGGAAGCCGCUGAGCUCGGuAAGGGUUCCUUCAAGUACGCCUGGGUCCUUGACAAGCUCAAGGCCGAGCGUGAGCGUGGUAUCACCAUCGAcAUUGCcCU;CGAAGGCAAGCUGAAAAGUCUGGCAAGCAGUCUUUUGCUCUUGCAUGGGUCAUGGACCAGAGAAGUGAAGAGCGAGAACGCGGCGUGACCAUUGACAUCGCCAC;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -19;(4);?;0.17;14.1;0.0;hmm;78;309;..;2145448;2145215;- ..;0.65;-;0.54;Scaffold7;GGGUauuCAUC....AgUCACUucaUGCUGACAAUCAucuACAGACCGGUCACUUGAUCUACCAGUGCGGUGGUAUCGACAAGCGAACCAUCGAGAAGUUCGAGAAGG........UUGGUGACAUCUCCCCCGAUCGCGCCUU....GCUaUuccaCAUCGAAUUCCcCGUCGAAUUCCCUCCcuCGCGAuaCGCuCUGCGCCCGCUuCUCCCGAGUCcCAAAAuUUUUGCGGUuCGACCGuaAuUU;GGGGAUCCGUCggggAGUCCCAUCGUGCGUAGAGUCCGUUAGAGAUUGAU-----GAGCUGACAGUG-------AAAGACUUGGGAA-CAUGGAGAGGGAAGAGAGACuccuacucUCCGAAUCAUCCGCCGCAACUGCGUUAUcuccGCUGGUCAGCA-CCAAUCAUGGGUCGCUUGACCCUCCGCACCACCCGCUCAUCGUCCGCUCCUCUCAAGUCUCAAUUCAUACGGGCUACGUAUAUAAAUU;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -20;(5);?;0.56;12.4;0.0;hmm;298;505;..;573210;573407;+ ..;0.69;-;0.51;Scaffold7;CGACCGuaAuUUUUUUuGGUGGGGCAUuUACCCCGCCaCUCGgGcGACGUUGGACAAAGCCCUGAUCCCUGCACACAAAAACACCAAACCC......UCUUGGCGCGCAUCaUCACGUGGUucaCaaCAGAcgCUaACcGguuCAAC...AAuAGGAAGCCGCUGAGCUCGGuAAGGGUUCCUUCAAGUACGCCUGGGUCCUUGACAAGCUCAAGGC;CCACCGUCAUAUU----GGUC-AGCUUUUACCGAGCCGUUAUAGAG-UGUCGUA------CCCGAUCG--GGUGACAAUUCCAUCAAUGCCgaggauUAUUGAC--GAAUCGGAACGUGAGUGUCGGAACAAGA--UCCAGUUCCACgacCAAUGAGAG-CCCUGAGCUCGGCGAGGGCCACUUAACGUUAGGCUUGCACUUUGUCUAUUUCAAGGU;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -21;(6);?;4.9;9.3;0.0;hmm;150;293;..;6008452;6008603;+ ..;0.71;-;0.57;Scaffold1;CGACAAGCGAACCAUCGAGAAGUUCGAGAAGGUUGGUGACAUCUCCCCCGAUCGCGCCUUGCUaUuccaCAUCGAAUUCCcCGUCGAAUUC.....CCUCCcuCGCGAuaCGCuCU...GCGCCCGCUuCUCCCGAGUCcCAAAAuUUUUGC;CUUCAAGCCUGCCUAUGAGAAGUUCGCCAGCCUGGGUGACAAGAUCCCCAAGCUCGUCUUCACCACCUACUUCGGUGACAUCGUCCACAACcucgaCCUCCUCCCCAAGGAGGUCUaugGUGUCCACAUCGACCUUGUCCGCAACCCUGAGC;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna -22;(7);?;9.7;8.3;0.1;hmm;55;249;..;6008632;6008801;+ ..;0.66;-;0.62;Scaffold1;AACCCCGCCuGguauCUCGGGCGGGGUauuCAUCAgUCACUucaUGCUGACAAUCAucuACAGACCGGUCACUUGAUCUACCAGUGCGGUGGUAUCGACAAGCGAACCAUCGAGAAGUUCGAGAAGGUUGGUGACAUCUCCCCCGAUCGCGCCUUGCUaUuccaCAUCGAAUUCCcCGUCGAAUUCCCUCCcuCG;CCCCAAGACUGUCCUCUCUGCCGGUGUCGUCGACGGCCGCAACAUCUGGAAGACCAACCUGAAGCGCGC------------CAUCG-----AGAUUGUCGAGACUGCCAUCCAGAAGCUCGGCAAGGACCGUGUCAUUGCCGCCACCUCCUCUUCCCUCCUCCACA--------CCCCUCACACUCUCGCCAGCG;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +rank;;E-value;score;bias;mdl;mdl from;mdl to;;seq from;seq to;;;acc;trunc;gc;target name;query sequence;target sequence;model name;model clen;software;software version;fp_query;fp_target +0;(1);!;4.2e-23;84.6;0.1;hmm;710;930;.];284427;284630;+;..;0.86;-;0.44;Scaffold6;AGAGACCGAUAGCGCACAAGUAGAGUGAUCGAAAGAUGAAAAGAACUUUGAAAAGAGAGUUAAAaAGUACGUGAAAUUGUUGAAAGGGAAGCGCUUGUGACCAGACUUGGGCUuGGUUGAUCAUCCgGGGUUCUCCCuGGUGCACUCUUCCGGCccAGGCCAGCAUCAGUUcGCCcuGGGGGAuAAAGGCuuCGGGAAuGUGGCUCuCUCCGGGGAGUGUU;AAAUGCCGAUGGUGUACGAUUA--CUGAUCAAAAGAUGAA-AGAACUUAAGAAAGAGAGCUAA-AAGUACGUGAG---GUUGAAAG-GAAACGCUUGGCACUAGAUUUGGGCUUGGUUGAUU-----GAGGUCCCUUCAGUGCACUCU---GGCCUAUGCUGGUAUUAACUUGCCUAAGGGAAUAAAGGCUUG-GGGAUGUAGUUCUCUCCUGGGAGUGUU;FSSC_ITS+28S-rDNA--956-bp.fna;930;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +1;(2);!;7e-17;64.0;0.0;hmm;802;928;..;4687313;4687190;-;..;0.91;-;0.54;Scaffold3;GCUUGUGACCAGACUUGGGCUuGGUUGAUCAUCCgGGGUUCUCCCuGGUGCACUCUUCCGGCccAGGCCAGCAUCAGUUcGCCcuGGGGGAuAAAGGCuuCGGGAAuGUGGCUCuCUCCGGGGAGUG;GCUCGAGACCAGACCUGGGCUUGGUUGAUCAUCCAG-GUUCUUCCUGGUGCACUCUUCUGGCUUAUGCCAGCAUCGAUUUGUCUUGAGGAACAAUGGUUUCCGGGAUGUGACUA--CCCGGGCAGUG;FSSC_ITS+28S-rDNA--956-bp.fna;930;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +2;(3);?;0.016;16.6;0.0;hmm;752;808;..;1013790;1013850;+;..;0.78;-;0.39;Scaffold1;GAACUUUGAAAAGAGAGUUAAAaAGUACGUGAAAUUGUUGA....AAGGGAAGCGCUUGUG;AAAUUUUAAAAAGAGAGUUAAGCAGUACGUGAAAUUGUCGUucgcAUUGGACCCGUUGGUG;FSSC_ITS+28S-rDNA--956-bp.fna;930;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +3;(4);?;1.1;10.6;1.0;hmm;693;821;..;2222270;2222153;-;..;0.73;-;0.46;Scaffold5;AAAGCUAAAUACCGGCCAGAGACCGAUAGCGCACAAGUAGAGUGAUCGAAAGAUGAAAAGAACUUUGAAAAGAGAGUUAAAaAGUACGUGAAAUUGUUGAAAGGGAAGCGCUUGUGAC...CAGACUUGGGC;AAGGCAAGCUACCACCUUCAAAGAAAUAGUGUCCGGCAAGAAGGAUCGAAAGG--------------AGAAGGAGGUUAUAGAGGACGGGAAAUUGGUGUAAUAAAAGCGUCAAUGACagaCAGACGAGGUC;FSSC_ITS+28S-rDNA--956-bp.fna;930;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +4;(5);?;5.7;8.2;0.7;hmm;756;861;..;3020655;3020767;+;..;0.79;-;0.58;Scaffold2;UUUGAAAAGAGAGUUAAAaAGUACGUGAAAUUGUUGAAAGGGAAGCGCUUGUGACCAG.......ACUUGGGCUuGGUUGAUCAUCCgGGGUUCUCCCuGGUGCACUCUUCCG;UCUGGAGAGGGAAUAAAAAAGCUGGAGAAAUGGCGCGGGGGAAAGGGCUCUUUGCCAGgggggagUGUGGAGCUUGGGCGAUGAUGACGGGUGAUACCUGGGGCAUGAUGCGG;FSSC_ITS+28S-rDNA--956-bp.fna;930;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +5;(1);!;2.7e-265;885.0;0.0;hmm;2;826;..;2966345;2965521;-;..;0.99;-;0.54;Scaffold3;ACcCCuAUuGGACGAGAUGGAAAGCUCGCCAAGCCCCGUCAGCUaCACAACACCCAUUGGGGuCUGGUcUGuCCAGCCGAGACgCCcGAGGGUCAGGCUUGUGGuCUGGUCAAGAACUUGUCcCUGAUGUGcUAcGUCAGUGUCGGcUCUCCcUCcGAACCucUGAUuGAGUUCAUGAUCAACCGAGGUAUGGAaGUCGUGGAAGAGUACGAgCCCCUGAGAUAcCCgCAUGCuACCAAGAUcUUuGUCAAuGGUGUcUGGUGuGGUGUcCACUCgGACCCcAAGCAUCUCGUCAGcCAGGUccUGGACACaCGACGAAAGUCGUAccUGCAGUAcGAGGUGUCgCUuGUUCGUGACAUUCGAGAuCGAGAGUUCAAGGUCUUCUCCGACGCuGGCCGAGUCAUGAGgCCGGUCUUUACGGUuCAGCAGGAGGAuGACCAcGAgUCUGGUAUuGCCAAGGGAGCuuUGGUuCUGACCAAGGACcUuGUCAACAAGcUuGCuAAGGAGCAGGCGGAGCCaCCAGAGGACCCAUCaauGAAGAUUGGAUGGGAGGGUCUGAUCCGaGCcGGaACcAUCGAGUACCUCGAUGCuGAGGAAGAGGAGaCGGCuAUGAUUUGCAUGACuCCUGAGGAuCUuGAcCUCUAuCGcAUGCAAAAGGCuGGUUACGUcGUaGAuGAcGAUAACACGGACGACCCcAACAGGAGaUUGAAGACcAAGACgAACCCCACAACUCACAUGUACACUCAUUGUGAGAUUCACCCcAGuAUGAUUCUuGGCAUuUGuGCCAGUAUCAUUCCcUUCCCcGAUCACAACCAGGUAuACgAC;ACCCCUAUUGGACGAGAUGGAAAGCUCGCCAAGCCCCGUCAGCUACACAACACCCAUUGGGGUCUGGUCUGUCCAGCCGAGACACCCGAGGGUCAGGCUUGUGGUCUGGUCAAGAACUUGUCCCUGAUGUGUUACGUCAGUGUCGGUUCUCCUUCUGAACCUCUGAUCGAGUUCAUGAUCAACCGAGGCAUGGAAGUCGUGGAAGAGUACGAGCCCCUGAGAUACCCGCAUGCUACCAAGAUCUUUGUCAAUGGUGUCUGGUGCGGUGUCCACUCGGACCCCAAGCAUCUCGUCAGCCAGGUCCUGGACACACGACGAAAGUCGUACCUGCAAUACGAGGUGUCGCUCGUCCGUGACAUUCGAGAUCGAGAGUUCAAGGUCUUCUCCGACGCUGGCCGAGUCAUGAGGCCAGUCUUUACGGUUCAGCAGGAGGAUGACCACGAGUCUGGUAUCGCCAAGGGAGCUUUGGUUCUGACCAAGGACCUUGUCAACAAGCUUGCUAAGGAGCAGGCGGAGCCACCAGAGGACCCAUCAAUGAAGAUUGGAUGGGAGGGUCUGAUCCGAGCCGGAACCAUCGAGUACCUCGAUGCUGAGGAAGAGGAGACGGCUAUGAUUUGCAUGACUCCUGAGGAUCUUGACCUCUAUCGCAUGCAAAAGGCUGGUUACGUCGUAGAUGACGAUAACACGGACGACCCCAACAGGAGAUUGAAGACCAAGACGAACCCCACAACUCACAUGUACACUCAUUGUGAGAUUCACCCCAGUAUGAUUCUUGGCAUUUGUGCUAGUAUCAUCCCCUUCCCCGAUCACAACCAGGUAUGCGCC;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +6;(2);!;1.1e-243;813.4;0.0;hmm;787;1588;.];2965391;2964591;-;..;0.96;-;0.53;Scaffold3;CAGUAUCAU.UCCcUUCCCcGAUCACAACCAGGUAuACgACaCGaUCCAUGGAGUUCCUCAAGUUCCGUGAaCUGCCaGCcGGuCAGAACGCCAUcGUCGCuAUCGCUUGcUACUCuGGUUAcAACCAGGAAGAUUCCGUCAUuAUGAACCAGAGuAGUAUCGAuCGAGGCuUGUUCCGcAGUcUGUUCUUCaGAUCcUACUCuGAcCAGGAGAAGAAGGUCGGuCUgAACUACACGGAAGUGUUuGAGAAGCCCUUCCAGCAGUCGACgCUUCGuAUGAAGCAcGGUACcUACGACAAGCUGGAcGAGGAuGGUAUcGUGGCcCCcGGuGUGCGAGUGUCgGGUGAaGAUAUCAUcAUCGGCAAGACuGCGCCGAUuGAuCAAGAGAACCAGGAUCUgGGuACCAGGACaACgGUGCACCAGCGUCGUGAUAUCUCcACgCCGCUGCGAAGuACcGAgAACGGuAUCGUuGAuucGGUCAUUGUGACuGUCAAuGCcGACAACGUCAAGUAcGUCAAGGUCCGUGUGAGGACGACCAAGAUUCCuCAGAUUGGuGACAAGUUuGCCUCUCGUCACGGACAGAAGGGUACCAUUGGUGUuACcUACcGaCAGGAGGAuAUGCCcUUcagCAGGGAGGGuGUGACaCCaGACAUuAUCAUuAACCCCCACGCCAUUCCgUCGCGAAUGACAAUUGCcCAUUUGAUUGAAUGCCUCCUCAGUAAGGUGUCAACgCUcGAAGGCAUGGAGGGUGAuGCaACaCCuUUCACcGAuGUCACuGUcGACUCcGUuUCGGAGCUGCUCCG;CAACAUUCUuUACUAUCCGCAAA--AACCUCUGGCGACAACACGAUCCAUGGAGUUCCUCAAGUUCCGUGAACUACCAGCCGGUCAGAAUGCCAUCGUCGCUAUCGCUUGCUACUCUGGUUACAACCAGGAAGAUUCCGUCAUUAUGAACCAGAGUAGUAUCGAUCGAGGCCUGUUCCGCAGUCUGUUCUUCAGAUCCUACUCUGACCAGGAGAAGAAGGUCGGACUGAACUACACGGAAGUGUUCGAGAAGCCCUUCCAGCAGUCGACGCUUCGUAUGAAGCACGGUACUUACGACAAGCUGGACGAGGAUGGUAUCGUGGCCCCCGGUGUCCGAGUGUCAGGUGAAGACAUCAUCAUCGGCAAGACUGCGCCGAUUGACCAAGAGAACCAGGAUCUGGGUACCAGGACGACGGUGCACCAGCGUCGUGAUAUCUCCACGCCGCUGCGAAGUACCGAGAACGGUAUCGUCGAUUCGGUCAUUGUGACUGUCAAUGCCGACAACGUCAAGUACGUCAAGGUCCGUGUGAGGACGACCAAGAUUCCUCAGAUUGGUGACAAGUUCGCCUCUCGUCACGGACAGAAGGGUACAAUUGGUGUCACCUACCGGCAGGAGGAUAUGCCCUUCAGCAGGGAGGGUGUGACACCAGACAUUAUCAUUAACCCCCACGCCAUUCCCUCGCGAAUGACAAUUGCCCAUUUGAUUGAAUGCCUCCUCAGUAAGGUGUCAACGCUCGAAGGCAUGGAGGGUGAUGCAACGCCUUUCACCGAUGUCACCGUCGACUCCGUUUCGGAGCUGCUCCG;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +7;(3);!;1.7e-34;120.9;0.0;hmm;828;1525;..;2315121;2315839;+;..;0.66;-;0.51;Scaffold4;CGaUCCAUGGAGUUCCUCAAGUUCC..................GUGAaCUGCCaGCcGGuCAGAACGCCAUcGUCGCuAUCGCUUGcUACUCuGGUUAcAACCAGGAAGAUUCCGUCAUuAUGAACCAGAGuAGUAUCGAuCGAGGCuUGUUCCGcAGUcUGUUCUUCaGAUCcUACUCuGAcCAGGAGAAGAAGGUCGGuCUgAACUACACGGAA.GUGUUuGAGAAGCCCUUCCAGCAGUCGACgCUUCGuAUGAAG....CAcGGU..........ACc......UACGACAAGCUGGAcGAGGAuGGUAUcGUGGCcCCcGGuGUGCGAGUGUCgGGUGAaGAUAUCAUcAU..............CGGCAAGACuGCGCCGAUuGAuCAAGAGAACCAGGAUCUgGGuACCAGGAC.aACgGU.GCACCAGCG....UCGUGAUAUCUCcACgCCGCUGCGAAGuACcGAgAACGGuAUCGUuGAuucGGUCAUUGUGACuGUCAAuGCcGACAACGUCA...AGUAcGUCAAGGUCCGUGUGAGGACGACCAAGAUUCCuCAGAUUGGuGACAAGUUuGCCUCUCGUCACGGACAGAAGGGUACCAUUGGUGUuACcUACcGaCAGGAGGAuAUGCCcUUcagCAGGGAGGGuGUGACaCCaGACAUuAUCAUuAACCCCCACGCCAUUCCgUCGCGAAUGACAAUUGCcCAUUUGAUUGAAUGCCUCCUCAGUAAGGUGUCAACgCUcGAAGG;CGACCCAUGGUUAUCUCCAAGACCAuccagcuuauuggcuaugAUAAGCUCCCCGCAGGCCAGAACGCGACUGUCGUCGUCAUGUCGUACUCUGGAUAUGAUAUCGAAGAUGCUUUGGUUCUGAACAAGGCGUCGAUCGACAGAGGAUUUGGACGCUGCCAGGUCUUCCGCAAAUACACG-ACCGAGCUACA-----------AAAAUACCCUAAUgGUCGCCGAGA-GCGCAUC-GG----CGAUCCCCAAAAUGAAGaaggCAAGGUcaagcaaagaAUCaagaagCAUGAAGGUCUCGACGACGAUGGUUUGG--------------CCAUUGUGGGAUACAGAAUUCAUAAUggcgaggccaugauCAAGAAGGAAACACCCCUUGACCA-GACAACCACC-----GGCAUCGGAAUgGAUCGUgGACCCAGCGaauaCCGUGAUUCUUCAGUCUCGUACCGUAUUGCUGAUCCGGCAUACAUUGACAAGGUGAUGGUAUC---CCAAACAGAGAAGGACAcuaCAGUUAUCAAGGUCCAGACCAGACAGACUCGUCGUCCAGAGCUUGGAGACAAGUUUUCAUCUCGUCACGGUCAAAAGGGUGUGGUUGGCAUCAUUGUUGAUCAGGAGGAUCUGCCCUUCUCUGACAAGGGCCUGACCCCUGAUAUCAUCAUGAACCCUCACGGUUUCCCGUCUCGAAUGACGGUCGGCAAGCUGCUCGAGUGCUUGACGGGCAAGGCUUCCAUUAUCCAUGG;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +8;(4);!;1.6e-26;94.6;0.0;hmm;761;1564;..;1337459;1336642;-;..;0.63;-;0.55;Scaffold6;CCcAGuAUGAUUCUuGGCAUuUGuGCCAGUAUCAUUCCcUUCCCcGAUCACAACCAGGUAuACgACaCGaUCCAUGGAGUUCCUC...A..A........GUUCCGUGAaCUGC.CaGCcGGuCAGAACGCCAUcGUCGCuAUCGCUUGcUACUCuGGUUAcAACCAGGAAGAUUCCGUCAUuAUGAACCAGAGuAGUAUCGAuCGAGGCuUGUUCCGcAGUcUGUUCUUCaGAUCcUACUCuG.AcCAGGAGAAGAAGGUCGGuCUgAACUA...CACG.....G.........A..AGUGUUuGAGAAGCCCUUC...CAGCA.GUCGACgCUUCGuAUGAAGCAcGGUAC.cUACGACAAGCUGGAcGAGGAuGGUAUcGUGGCcCCcGGuG..UGCGAGUGUCgGGU.GAaGAUAUCAUcAUCG...GCAAGACuGCGCCGAUuGAuCAAGAGAACCAGGAUCUgG.GuACCAGGACaACgGUGCACCAGCGUCGUGAUAUCUCcACgCCGCUGCG..AAGuAC........cGAgAACGGuAUCGUuGAuucGGUCAUUGUGACuG...UCAAuGCcGACAACG............UCAAGUAcGUCAAGGUCCGUGUGAGGACGACCAAGAUUCCuCAG.AUUGGuGACAAGUUuGCCUCUCGUCACGGACAGAAGGGUACCAUUGGUGUuACcUACcGaCAGGAGGAuAUGCCcUUcagCAGGGAGGGuGUGACaCCaGACAUuAUCAUuAACCCCCACGCCAUUCCgUCGCGAAUGACAAUUGCcCAUUUGAUUGAAUGCCUCCUCAGUAAGGUGUCAACgCUcGAAGGCAUGGAGGGUGAuGCaACaCCuUUCACcGAuGUCACuGU;CCCAGUACUAAUCUUCGCUACCGAACCGACAACAAGUCAUACC--GCAUACAAACUGGACAAACACCCGU-CGUGCGAGCACCUCuucAcaAcacauaugGUUUCGACAACUUCcCCAACGGCAUGAACGCAGUUGUUGCCGUCAUCUCGUAUACUGGAUAUGACAUGGACGACGCCAUGAUUCUCAACAAGAGCGCCCAUGAGCGUGGUUUUGGGCA----------------UGGUACUAUCuACAAGACAAAGAAGAUCUCUCUCAAGGAugaCUCGcgaacAaaggccaccAagAGUGUUACCAAGGCUUUUGgcuUCGCAcCUCACAGCUACGUG---AGCGCGUCAUaCCAGGGAAUGCUGGAUGACGACGGCCU---GCCUCACGUGGgcCGCAUGAUCCAGGAgGGAGAUGUAAUCUGCGcguGGCACACAGUGACGCCCGACUACAAUGGCAAG---CUGGuGAACCUGGAUGGC-------------------AU---CACU-CACUACGaaAAGUACaaggauggCGAGACGGGCUUUGUCGAAGAGGUCCGCCUGAUCGgagCCGAAACCGGCAACGagccucuccagaCCAUCUCUGUCAAGUUCCGUGUU-------CCUCGAUCCCCCAUcAUCGGUGACAAGUUCUCGUCCAGACACGGACAGAAGGGUGUCGCCUCGCAAAAGUGGCCAACGGUGGAUCUGCCCUUCUCGGAGACUGGCAUCCAACCGGACAUCAUCAUUAACCCCCACGCUUUCCCUUCCCGUAUGACGAUAGGCAUGUUUGUGGAAUCGCUCGCCGGCAAGGCUGGCGCGCUGCAUGGCCUUGCGCAAGACUCGACACCGUUCAAGUUUGACGAGGA;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +9;(5);!;5.9e-08;33.1;0.0;hmm;17;320;..;2314349;2314665;+;..;0.69;-;0.53;Scaffold4;GAUG.GAAAGCUCGCCAAGCCCCGUCAGCUaCACAACACCCAUUGGGGuCUGGUcUGuCCAGCCGAGACgCCcGAGGGUCAGGCUUGUGGuCUGGUCAAGAACUUGUCcCUGAUGUGcUAcGUCA......GUGUCGGcUCUCCcUCcGAACCucUGAUuGAGUUCAUGAUCAACCGAGGUAUGGAaGUCGUGG......AAGAG...UACGAgCCCCUGAGAUAcCCgCAUGCuACCAAG...AUcUUuGUCAAuGGUGUcUGGUGuGGUGUcCACUCgGACCCcAAGCAUCUCGUCAGcCAGGUccUGGACAC.aCGACGAA;GACGcGAAAGGUCUCAGGCCCUCGUGCGCUCCAACCGUCGCAAUGGGGUAUGCUGUGCACUUCGGAUACACCUGAAGGAGAAGCCUGCGGUCUGGUGAAGAACUUGGCUUUGAUGACACAUAUCAccacaaAUGUCGAG------GAAGGACCCGUGAAGGAGACUAUCCUGACGAUCGACAAGGAAGUUGAGGcuaucgAGAAAuucUCUGGCUCAAUGAUGCACCGGGAAGGGAGCUACgucAUCCAUGUCAAUGGUACGCCAUUC-GCAUUGACACGGAAUCCGAAGAGGUUCGCACAAAGGUUCAGGACAUuGCGACGAA;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +10;(6);!;0.0059;16.5;0.0;hmm;438;542;..;5920205;5920315;+;..;0.80;-;0.6;Scaffold1;ACCAcGAgUCUGGUAUuGCCAAGGGAGCuuUGGUuCUGACCAAGGACcU......uGUCAACAAGcUuGCuAAGGAGCAGGCGGAGCCaCCAGAGGACCCAUCaauGAAGA;CCCUGAAGGCUGGCGUUGACAAGGGCAUCUUUGAGCAGCCCAAGGGUCCuuccggUGGCACCAAGCUUGCCAAGAAGCAGCCUGAGCCCAAGAAGGCUGCCGCUGAGAAGA;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +11;(7);?;0.037;13.9;0.1;hmm;551;715;..;478876;478690;-;..;0.62;-;0.55;Scaffold4;GAGGGUCUGAUCCGaGCcGGaACcAUCGAGUACCUCGAUGCuGAGGAAGAGGAG.aCGGCuAUGAUUUGCAUGACuCCUGAGG...........AuCUu.......GA..cCUCUAuCGcAUGCAAAA.....GGCuGGUUACGUcGUaGAuGAcGAUAACACGGACGACCCcAACAG....GAGaUUGAAGACc;GAGGUUGAGAUUCCAGAGGAGAUUGAAGAGGAAGAAGAGGUCGAAGAGGAAGAGgAUGACGAGGAUA-------CUCUUGAGGucgagggcgagAUCAUcgcugaaGAgcCAUCCGGCGAA-GAAGAAgagccGGCCGUAGAAGUUGUGGAGGAAGAUGACCCGGACGACACCAUCAGuccgGAAGCUGAAGAGG;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +12;(8);?;0.071;12.9;0.0;hmm;669;899;..;2314870;2315072;+;..;0.59;-;0.51;Scaffold4;UcGUaGAuGAcGAUAACACGGACGACCCcAACAGGAGaU.UGAAGACcAAGACgAACCCCACAACUCACAUGUACACUCAUUGUGAGAUUCACCCcAGuAUGAUUCUuGGCAUuUGuGCCAGUAUCAUUCCcUUCCCcGAUCACAACCAGGUAuACgACaCGaUCCAUGGAGUUCCUCAAGUUCCGUGAaCUGCCaGCcGGuCAGAACGCCAUcGUCGCuAUCGCUUGcUAC;UGGAUGUGAACGAGGAGAAUGACGCCCUCAUCACCAUCUaCGAAGACCAAG----------UGACGCAAAGUACCACGCAUCUGGAGAUUGAGCCGUUCACCAUCCUGGGUGCAGUUGCAGGACUGAUUCCAUUCCCUCACCACAACCAAU----CGCCU-------CGUAAUACCUAC----CAAUGUGC----UAUGGGUAAACAAGCCAUUGGUGCCAUCGCCUACAAC;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +13;(9);?;0.31;10.8;0.0;hmm;421;600;..;3659261;3659088;-;..;0.62;-;0.56;Scaffold4;GGUuCAGCAGGAGGAuGACCAcG...AgUCUGGUAUuGCCAAGGGAGCuuUGGUuCUGACCAAGGACcUuGUCAACAAGcUuGCuAAGGAGCAGGCGGAGCCaCCAGAGGACCCAUCaauGAAGAUUGGAUGGGAGGGUCUGAUCCGaGCcGGaACcAUCGAGUACCUCGAUGCuGAGGAAGA;GGACCUGGAUGACGAUGCCCGUGcccAGCGCGACGAGGAGCAGGGAGUCAAGGACAUUAUCAAUGACCUCAAAAAGCAGCUCGCCAACAAGCAGGCUGAGCUGGCC-CGCACCCAGAAC--AAGAUCUU----GCGUACUCGUAUCGAGCAG--ACCAUCAAGCAGCUCAAGUCGGAGAUUGA;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +14;(10);?;1.0;9.1;0.0;hmm;56;140;..;1338065;1337981;-;..;0.74;-;0.53;Scaffold6;CAUUGGGGuCUGGUcUGuCCAGCCGAGACgCCcGAGGGUCAGGCUUGUGGuCUGGUCAAGAACUUGUCcCUGAUGUGcUAcGUCA;UCAUGGGGCUUCAUGUGUCCUGUCCACACGCCUGAUGGUGCGCCUUGUGGUCUUCUGAACCAUCUUGCGCACAAGUGCAAGAUUA;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +15;(11);?;1.7;8.3;0.8;hmm;426;595;..;3674449;3674606;+;..;0.64;-;0.59;Scaffold2;AGCAGGA...GGAuGACCAcGAgUCUGGUAUuGCCAAGGGAGCuuUGGUuCUGACCAAGGACcUuGUCAACAAGcUuGCuAAGGAGCAGGCGGAGCCaCCAGAGGACCCAUCaauGAAGAUUGGAUGGGAGGGUCUGAUCCGaGCcGGaACcAUCGAGUACCUCGAUGCuGAG;ACCAGGAuauGCACGACAGCCUGACUGGCAUCGCCGAGGAGGCCCAGAAGACGGCUAAGGAUCUGGAGUCGAAGCUUGCCGAGGCGUUGGCCAAGGU---UGAGGAUGGAGAGAAGCAGGU------GGAGGUUCU----CGAGGCCCA--AAUCAAGGUCAAGGAUGCCGAG;FSSC_RPB2--1588-bp.fna;1588;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +16;(1);!;2.6e-192;642.5;0.1;hmm;1;632;[];6427210;6427837;+;..;0.99;-;0.54;Scaffold2;AGUCGACCACCGUAAGUCaaaCCCUCaUcGCGAuCUGCUuAUCUCGGGUCGUGGAACCCCGCCuGguauCUCGGGCGGGGUauuCAUCAgUCACUucaUGCUGACAAUCAucuACAGACCGGUCACUUGAUCUACCAGUGCGGUGGUAUCGACAAGCGAACCAUCGAGAAGUUCGAGAAGGUUGGUGACAUCUCCCCCGAUCGCGCCUUGCUaUuccaCAUCGAAUUCCcCGUCGAAUUCCCUCCcuCGCGAuaCGCuCUGCGCCCGCUuCUCCCGAGUCcCAAAAuUUUUGCGGUuCGACCGuaAuUUUUUUuGGUGGGGCAUuUACCCCGCCaCUCGgGcGACGUUGGACAAAGCCCUGAUCCCUGCACAC.AAAAACACCAAACCCUCUUGGCGCGCAUCaUCACGUGGUucaCaaCAGAcgCUaACcGguuCAACAAuAGGAAGCCGCUGAGCUCGGuAAGGGUUCCUUCAAGUACGCCUGGGUCCUUGACAAGCUCAAGGCCGAGCGUGAGCGUGGUAUCACCAUCGAcAUUGCcCUCUGGAAGUUCGAGACUCCCCGCUACUAUGUCACCGUCAUUGGUAUGUcGCuGucgucuCucUCacuCauGUCUCacCaCUAACaAUCaACA;AGUCGACCACCGUAAGUCAAACCCCCAUCGCGAUCUGCUUAUCUCGGGUCGUGGAACCCCGCCUGGUAUCUCGGGCGGGGUACUCAUCAGUCACUUCAUGCUGACAAUCAUCUACAGACCGGUCACUUGAUCUACCAGUGCGGUGGUAUCGACAAGCGAACCAUCGAGAAGUUCGAGAAGGUUGGUGACAUCUCCCCCGAUCGCGCCUUGCUAUUCCACAUCGAAUUCCCCGUCGAAUUCCCUCUUCCGCGACACGCUCUGCGCCCGCUUCUCCCGAGUCCCAAAAAUUUUGCGGUUCGACCGUAAUUUUUUU-GGUGGGGCAUUUACCCCGCCACUCGGGCGACGUUGGACG-AGCCCUGAACCCUGCACACaAAAAACACCAAACCCUCUUGGCGCG---CAUCACGUGGUUCACAACAGACACUAACAGGUUCAACAAUAGGAAGCCGCUGAGCUCGGUAAGGGUUCCUUCAAGUACGCCUGGGUCCUUGACAAGCUCAAGGCCGAGCGUGAGCGUGGUAUCACCAUCGAUAUUGCUCUCUGGAAGUUCGAGACUCCCCGCUACUAUGUCACCGUCAUUGGUAUGUCGCCCUCAUCUCUCUCAAUCACGUCUCAUCAUUAACAAUCAACA;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +17;(2);?;0.042;16.1;0.0;hmm;468;568;..;4896877;4896777;-;..;0.66;-;0.53;Scaffold3;UCCUUCAAGUACGCCUGGGUCCUUGACAAGCUCAAGGCCGAGCGUGAGCGUGGUAUCACCAUCGAcAUUGCcCUCUGGAAGUUC......GAGACUCCCCGCUACUA;UUCCUCGAGUAUG---GUGCCAUUGACAAGGCUCCCGAGGAGCGAAAGCGUGGUAUCACCAUUUCCACUGCUCACAUCGAGUACucuaccGACAA---CCGCCACUA;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +18;(3);?;0.048;15.9;0.0;hmm;438;541;..;3187913;3188016;+;..;0.85;-;0.54;Scaffold2;CAAuAGGAAGCCGCUGAGCUCGGuAAGGGUUCCUUCAAGUACGCCUGGGUCCUUGACAAGCUCAAGGCCGAGCGUGAGCGUGGUAUCACCAUCGAcAUUGCcCU;CGAAGGCAAGCUGAAAAGUCUGGCAAGCAGUCUUUUGCUCUUGCAUGGGUCAUGGACCAGAGAAGUGAAGAGCGAGAACGCGGCGUGACCAUUGACAUCGCCAC;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +19;(4);?;0.17;14.1;0.0;hmm;78;309;..;2145448;2145215;-;..;0.65;-;0.54;Scaffold7;GGGUauuCAUC....AgUCACUucaUGCUGACAAUCAucuACAGACCGGUCACUUGAUCUACCAGUGCGGUGGUAUCGACAAGCGAACCAUCGAGAAGUUCGAGAAGG........UUGGUGACAUCUCCCCCGAUCGCGCCUU....GCUaUuccaCAUCGAAUUCCcCGUCGAAUUCCCUCCcuCGCGAuaCGCuCUGCGCCCGCUuCUCCCGAGUCcCAAAAuUUUUGCGGUuCGACCGuaAuUU;GGGGAUCCGUCggggAGUCCCAUCGUGCGUAGAGUCCGUUAGAGAUUGAU-----GAGCUGACAGUG-------AAAGACUUGGGAA-CAUGGAGAGGGAAGAGAGACuccuacucUCCGAAUCAUCCGCCGCAACUGCGUUAUcuccGCUGGUCAGCA-CCAAUCAUGGGUCGCUUGACCCUCCGCACCACCCGCUCAUCGUCCGCUCCUCUCAAGUCUCAAUUCAUACGGGCUACGUAUAUAAAUU;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +20;(5);?;0.56;12.4;0.0;hmm;298;505;..;573210;573407;+;..;0.69;-;0.51;Scaffold7;CGACCGuaAuUUUUUUuGGUGGGGCAUuUACCCCGCCaCUCGgGcGACGUUGGACAAAGCCCUGAUCCCUGCACACAAAAACACCAAACCC......UCUUGGCGCGCAUCaUCACGUGGUucaCaaCAGAcgCUaACcGguuCAAC...AAuAGGAAGCCGCUGAGCUCGGuAAGGGUUCCUUCAAGUACGCCUGGGUCCUUGACAAGCUCAAGGC;CCACCGUCAUAUU----GGUC-AGCUUUUACCGAGCCGUUAUAGAG-UGUCGUA------CCCGAUCG--GGUGACAAUUCCAUCAAUGCCgaggauUAUUGAC--GAAUCGGAACGUGAGUGUCGGAACAAGA--UCCAGUUCCACgacCAAUGAGAG-CCCUGAGCUCGGCGAGGGCCACUUAACGUUAGGCUUGCACUUUGUCUAUUUCAAGGU;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +21;(6);?;4.9;9.3;0.0;hmm;150;293;..;6008452;6008603;+;..;0.71;-;0.57;Scaffold1;CGACAAGCGAACCAUCGAGAAGUUCGAGAAGGUUGGUGACAUCUCCCCCGAUCGCGCCUUGCUaUuccaCAUCGAAUUCCcCGUCGAAUUC.....CCUCCcuCGCGAuaCGCuCU...GCGCCCGCUuCUCCCGAGUCcCAAAAuUUUUGC;CUUCAAGCCUGCCUAUGAGAAGUUCGCCAGCCUGGGUGACAAGAUCCCCAAGCUCGUCUUCACCACCUACUUCGGUGACAUCGUCCACAACcucgaCCUCCUCCCCAAGGAGGUCUaugGUGUCCACAUCGACCUUGUCCGCAACCCUGAGC;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna +22;(7);?;9.7;8.3;0.1;hmm;55;249;..;6008632;6008801;+;..;0.66;-;0.62;Scaffold1;AACCCCGCCuGguauCUCGGGCGGGGUauuCAUCAgUCACUucaUGCUGACAAUCAucuACAGACCGGUCACUUGAUCUACCAGUGCGGUGGUAUCGACAAGCGAACCAUCGAGAAGUUCGAGAAGGUUGGUGACAUCUCCCCCGAUCGCGCCUUGCUaUuccaCAUCGAAUUCCcCGUCGAAUUCCCUCCcuCG;CCCCAAGACUGUCCUCUCUGCCGGUGUCGUCGACGGCCGCAACAUCUGGAAGACCAACCUGAAGCGCGC------------CAUCG-----AGAUUGUCGAGACUGCCAUCCAGAAGCUCGGCAAGGACCGUGUCAUUGCCGCCACCUCCUCUUCCCUCCUCCACA--------CCCCUCACACUCUCGCCAGCG;FSSC_TEF1-665-bp.fna;632;INFERNAL;1.1.2;Markergenes/FSSC/allFSSC.cm;Sequences_Fusarium/taxid_99000016/FW16.genome.fna diff --git a/phylofiller/test/data/mini.tbl b/phylofiller/test/data/mini.tbl new file mode 100644 index 0000000..06c3177 --- /dev/null +++ b/phylofiller/test/data/mini.tbl @@ -0,0 +1,31 @@ +#target name accession query name accession mdl mdl from mdl to seq from seq to strand trunc pass gc bias score E-value inc description of target +#------------------- --------- -------------------- --------- --- -------- -------- --------- --------- ------ ----- ---- ---- ----- ------ --------- --- --------------------- +chr1 - 5S_rRNA RF00001 cm 1 119 228746133 228746015 - no 1 0.61 0.0 118.9 6.6e-24 ! - +chr1 - 5S_rRNA RF00001 cm 1 119 228748374 228748256 - no 1 0.61 0.0 118.9 6.6e-24 ! - +chr1 - 5S_rRNA RF00001 cm 1 119 228750615 228750497 - no 1 0.61 0.0 118.9 6.6e-24 ! - +chr1 - 5S_rRNA RF00001 cm 1 119 228752856 228752738 - no 1 0.61 0.0 118.9 6.6e-24 ! - +chr1 - 5S_rRNA RF00001 cm 1 119 228755097 228754979 - no 1 0.61 0.0 118.9 6.6e-24 ! - +chr1 - 5S_rRNA RF00001 cm 1 119 228757312 228757194 - no 1 0.61 0.0 118.9 6.6e-24 ! - +chr1 - 5S_rRNA RF00001 cm 1 119 228759532 228759414 - no 1 0.61 0.0 118.9 6.6e-24 ! - +chr11 - U2 RF00004 cm 1 193 62609281 62609091 - no 1 0.44 0.0 191.2 9.7e-40 ! - +chr10 - U2 RF00004 cm 1 193 103124792 103124602 - no 1 0.45 0.0 179.5 6.2e-37 ! - +chr17 - U2 RF00004 cm 1 193 41464785 41464594 - no 1 0.43 0.0 172.6 2.8e-35 ! - +chr6 - tRNA RF00005 cm 1 71 28442402 28442329 - no 1 0.50 0.0 76.8 2.4e-14 ! - +chr7 - tRNA RF00005 cm 1 71 149007281 149007352 + no 1 0.56 0.0 73.9 1.6e-13 ! - +chr16 - tRNA RF00005 cm 1 71 73512288 73512216 - no 1 0.51 0.0 73.8 1.7e-13 ! - +chr19 - Hammerhead_HH10 RF02277 cm 43 110 48561534 48561600 + no 1 0.39 0.0 25.9 7.8 ? - +chr1 - Hammerhead_HH10 RF02277 cm 1 125 87448923 87448817 - no 1 0.39 0.0 25.8 8.1 ? - +chr7 - Betaproteobacteria_toxic_sRNA RF02278 cm 1 64 44640963 44640900 - no 1 0.53 0.0 29.2 0.84 ? - +chr6 - Betaproteobacteria_toxic_sRNA RF02278 cm 1 64 125477691 125477636 - no 1 0.52 0.0 28.8 1.1 ? - +chr3 - Betaproteobacteria_toxic_sRNA RF02278 cm 1 64 122276154 122276069 - no 1 0.52 0.0 25.7 6.3 ? - +chr12 - Betaproteobacteria_toxic_sRNA RF02278 cm 1 64 106339815 106339752 - no 1 0.61 0.0 25.6 6.8 ? - +chr10 - TtnuCD1 RF02279 hmm 5 60 35816692 35816639 - - 6 0.35 0.0 25.8 0.033 ? - +chr20 - TtnuCD1 RF02279 hmm 5 53 24807863 24807912 + - 6 0.32 0.2 22.0 0.53 ? - +# +# Program: cmsearch +# Version: 1.1.3 (Nov 2019) +# Pipeline mode: SEARCH +# Query file: Rfam/Rfam.cm +# Target file: genome/hg19.fa +# Option settings: /usr/lib/infernal/cmsearch --tblout cmsearch_Rfam/cmsearch.Rfam.hg19.tbl Rfam/Rfam.cm genome/hg19.fa +# [ok] diff --git a/phylofiller/test/test_converter.py b/phylofiller/test/test_converter.py index cb47b52..a76e5fb 100644 --- a/phylofiller/test/test_converter.py +++ b/phylofiller/test/test_converter.py @@ -15,6 +15,10 @@ def _str2pd(input): table = table.rename(columns={ c: '' for c in table.columns if c.startswith('Unnamed: ')}) table = table.fillna("") + try: + table.index = list(map(int, table.index)) + except ValueError: + pass return table @@ -28,7 +32,7 @@ def tearDown(self): pass def test_parse_easel_output(self): - obs = parse_easel_output(self.fp_infernal) + obs = parse_easel_output(self.fp_infernal, verbose=False) self.assertEqual('INFERNAL', obs['software'].iloc[0]) self.assertEqual('1.1.2', obs['software version'].iloc[0]) self.assertEqual('Markergenes/FSSC/allFSSC.cm', @@ -50,10 +54,10 @@ def test_easel_table2pd(self): " ---- --------- ------ ----- --- -------- -------- --------" "--- ----------- ---- ----- ----", " (1) ! 4.2e-23 84.6 0.1 hmm 710 930 .] 284" - "427 284630 + .. 0.86 - 0.44"]) + "427 284630 + .. 0.86 - 0.44"], verbose=False) exp = (';rank;;E-value;score;bias;mdl;mdl from;mdl to;;seq from;seq to' - ';;acc;trunc;gc\n0;(1);!;4.2e-23;84.6;0.1;hmm;710;930;.];284427' - ';284630;+ ..;0.86;-;0.44\n') + ';;;acc;trunc;gc\n0;(1);!;4.2e-23;84.6;0.1;hmm;710;930;.];' + '284427;284630;+;..;0.86;-;0.44\n') assert_frame_equal(_str2pd(exp), obs.astype(str)) obs = easel_table2pd( @@ -62,10 +66,10 @@ def test_easel_table2pd(self): " ---- --------- ------ ----- --------- ------- ------- --- " "----- ---- -----------", " (1) ! 2.7e-265 885.0 0.0 Scaffold3 2966345 2965521 - hmm " - " - 0.54 -"]) - exp = (';rank;;E-value;score;bias;;sequence;start;end;;mdl;trunc;gc;;d' - 'escription\n0;(1);!;2.7e-265;885.0;0.0;;Scaffold3;2966345;2965' - '521;-;hmm;-;0.54;;-\n') + " - 0.54 -"], verbose=False) + exp = (";rank;;E-value;score;bias;sequence;start;end;;mdl;trunc;gc;des" + "cription\n0;(1);!;2.7e-265;885.0;0.0;Scaffold3;2966345;2965521" + ";-;hmm;-;0.54;-\n") assert_frame_equal(_str2pd(exp), obs.astype(str)) obs = easel_table2pd( @@ -94,21 +98,21 @@ def test_easel_table2pd(self): " (10) ? 1.1 9.1 0.0 Scaffold6 1338065 1337981 - hmm " " - 0.53 -", " (11) ? 1.7 8.3 0.8 Scaffold2 3674449 3674606 + hmm " - " - 0.59 -"]) + " - 0.59 -"], verbose=False) exp = ( - ';rank;;E-value;score;bias;;sequence;start;end;;mdl;trunc;gc;;desc' - 'ription\n0;(1);!;2.7e-265;885.0;0.0;;Scaffold3;2966345;2965521;-;' - 'hmm;-;0.54;;-\n1;(2);!;1.1e-243;813.4;0.0;;Scaffold3;2965391;2964' - '591;-;hmm;-;0.53;;-\n2;(3);!;1.7e-34;120.9;0.0;;Scaffold4;2315121' - ';2315839;+;hmm;-;0.51;;-\n3;(4);!;1.6e-26;94.6;0.0;;Scaffold6;133' - '7459;1336642;-;hmm;-;0.55;;-\n4;(5);!;5.9e-08;33.1;0.0;;Scaffold4' - ';2314349;2314665;+;hmm;-;0.53;;-\n5;(6);!;0.0059;16.5;0.0;;Scaffo' - 'ld1;5920205;5920315;+;hmm;-;0.6;;-\n6;(7);?;0.037;13.9;0.1;;Scaf' - 'fold4;478876;478690;-;hmm;-;0.55;;-\n7;(8);?;0.071;12.9;0.0;;Scaf' - 'fold4;2314870;2315072;+;hmm;-;0.51;;-\n8;(9);?;0.31;10.8;0.0;;Sca' - 'ffold4;3659261;3659088;-;hmm;-;0.56;;-\n9;(10);?;1.1;9.1;0.0;;Sca' - 'ffold6;1338065;1337981;-;hmm;-;0.53;;-\n10;(11);?;1.7;8.3;0.8;;Sc' - 'affold2;3674449;3674606;+;hmm;-;0.59;;-\n') + ';rank;;E-value;score;bias;sequence;start;end;;mdl;trunc;gc;desc' + 'ription\n0;(1);!;2.7e-265;885.0;0.0;Scaffold3;2966345;2965521;-;' + 'hmm;-;0.54;-\n1;(2);!;1.1e-243;813.4;0.0;Scaffold3;2965391;2964' + '591;-;hmm;-;0.53;-\n2;(3);!;1.7e-34;120.9;0.0;Scaffold4;2315121' + ';2315839;+;hmm;-;0.51;-\n3;(4);!;1.6e-26;94.6;0.0;Scaffold6;133' + '7459;1336642;-;hmm;-;0.55;-\n4;(5);!;5.9e-08;33.1;0.0;Scaffold4' + ';2314349;2314665;+;hmm;-;0.53;-\n5;(6);!;0.0059;16.5;0.0;Scaffo' + 'ld1;5920205;5920315;+;hmm;-;0.6;-\n6;(7);?;0.037;13.9;0.1;Scaf' + 'fold4;478876;478690;-;hmm;-;0.55;-\n7;(8);?;0.071;12.9;0.0;Scaf' + 'fold4;2314870;2315072;+;hmm;-;0.51;-\n8;(9);?;0.31;10.8;0.0;Sca' + 'ffold4;3659261;3659088;-;hmm;-;0.56;-\n9;(10);?;1.1;9.1;0.0;Sca' + 'ffold6;1338065;1337981;-;hmm;-;0.53;-\n10;(11);?;1.7;8.3;0.8;Sc' + 'affold2;3674449;3674606;+;hmm;-;0.59;-\n') assert_frame_equal(_str2pd(exp), obs.astype(str)) def test_create_CIGAR(self): @@ -144,15 +148,23 @@ def test_create_CIGAR(self): def test_easle2sam(self): with open(self.fp_sam, 'r') as f: exp = ''.join(f.readlines()) - obs = easle2sam(parse_easel_output(self.fp_infernal)) + obs = easle2sam(parse_easel_output( + self.fp_infernal, verbose=False)) self.assertEqual(exp, obs) def test_parse_easel_output_format113(self): obs = parse_easel_output( - get_data_path('easel2sam/SLCC2753.RF014787.cmout')) + get_data_path('easel2sam/SLCC2753.RF014787.cmout'), verbose=False) # just test if the new format (since 1.1.3) can be parsed to 17 hits self.assertEqual(obs.shape[0], 17) + def test_infernalColOffset(self): + with open(get_data_path('mini.tbl')) as f: + lines = f.readlines() + obs = easel_table2pd(lines, verbose=False) + self.assertEqual(obs.shape[0], 21) + self.assertEqual(obs.shape[1], 18) + class KrakenTests(TestCase): def setUp(self):