def generate_krona(): """Generate Krona plot with all the results via Krona 2.0 XML spec""" print(gray('\nBuilding the taxonomy multiple tree... '), end='') sys.stdout.flush() krona: KronaTree = KronaTree( samples, num_raw_samples=len(raw_samples), stats=stats, min_score=Score( min([ min(scores[sample].values()) for sample in samples if len(scores[sample]) ])), max_score=Score( max([ max(scores[sample].values()) for sample in samples if len(scores[sample]) ])), scoring=scoring, ) polytree.grow(ontology=ncbi, abundances=counts, accs=accs, scores=scores) print(green('OK!')) print(gray('Generating final plot (') + magenta(htmlfile) + gray(')... '), end='') sys.stdout.flush() polytree.toxml(ontology=ncbi, krona=krona) krona.tohtml(htmlfile, pretty=False) print(green('OK!'))
def shared_ctrl_analysis(): """Perform last steps of shared taxa analysis""" shared_ctrl_tree: TaxTree = TaxTree() shared_ctrl_out: SampleDataById = SampleDataById( ['shared', 'accs']) shared_ctrl_tree.allin1(ontology=ontology, counts=shared_ctrl_counts, scores=shared_ctrl_score, min_taxa=get_shared_mintaxa(), include=including, exclude=(exclude_candidates - shared_crossover), out=shared_ctrl_out) shared_ctrl_out.purge_counters() out_counts: SharedCounter = shared_ctrl_out.get_shared_counts() output.write( gray(f' Ctrl-shared: Including {len(out_counts)}' ' shared taxa. Generating sample... ')) if out_counts: sample = Sample(f'{STR_CONTROL_SHARED}_{rank.name.lower()}') samples.append(sample) counts[Sample(sample)] = out_counts accs[Sample(sample)] = shared_ctrl_out.get_accs() scores[sample] = shared_ctrl_out.get_shared_scores() output.write(green('OK!\n')) else: output.write(yellow('VOID\n'))
def _debug_dummy_plot( taxonomy: Taxonomy, htmlfile: Filename, scoring: Scoring = Scoring.SHEL, ): """ Generate dummy Krona plot via Krona 2.0 XML spec and exit """ print(gray(f'Generating dummy Krona plot {htmlfile}...'), end='') sys.stdout.flush() samples: List[Sample] = [ Sample('SINGLE'), ] krona: KronaTree = KronaTree( samples, min_score=Score(35), max_score=Score(100), scoring=scoring, ) polytree: MultiTree = MultiTree(samples=samples) polytree.grow(ontology=taxonomy) polytree.toxml(ontology=taxonomy, krona=krona) krona.tohtml(htmlfile, pretty=True) print(green('OK!'))
def summarize_analysis( *args, **kwargs) -> Tuple[Optional[Sample], Counter[Id], Counter[Id], Scores]: """ Summarize for a cross-analysis (to be usually called in parallel!). """ # Recover input and parameters analysis: str = args[0] ontology: Ontology = kwargs['ontology'] # TODO: Delete the following comment lines in a future release # including = ontology.including # See comment below for the reason # excluding = ontology.excluding # in/excluding are not used anymore counts: Dict[Sample, Counter[Id]] = kwargs['counts'] scores: Dict[Sample, Dict[Id, Score]] = kwargs['scores'] samples: List[Sample] = kwargs['samples'] output: io.StringIO = io.StringIO(newline='') # Declare/define variables summary_counts: Counter[Id] = col.Counter() summary_acc: Counter[Id] = col.Counter() summary_score: Scores = Scores({}) summary: Optional[Sample] = None output.write(gray('Summary for ') + analysis + gray('... ')) target_samples: List[Sample] = [ smpl for smpl in samples if smpl.startswith(analysis) ] assert len(target_samples) >= 1, \ red('ERROR! ') + analysis + gray(' has no samples to summarize!') for smpl in target_samples: summary_counts += counts[smpl] summary_score.update(scores[smpl]) tree = TaxTree() tree.grow(ontology=ontology, counts=summary_counts, scores=summary_score) tree.subtract() tree.shape() summary_counts.clear() summary_score.clear() # Avoid including/excluding here as get_taxa is not as 'clever' as allin1 # and taxa are already included/excluded in the derived samples tree.get_taxa(counts=summary_counts, accs=summary_acc, scores=summary_score) summary_counts = +summary_counts # remove counts <= 0 if summary_counts: # Avoid returning empty sample (summary would be None) summary = Sample(f'{analysis}_{STR_SUMMARY}') output.write( gray('(') + cyan(f'{len(target_samples)}') + gray(' samples)') + green(' OK!\n')) else: output.write(yellow(' VOID\n')) # Print output and return print(output.getvalue(), end='') sys.stdout.flush() return summary, summary_counts, summary_acc, summary_score
def summarize_analysis( *args, **kwargs) -> Tuple[Sample, Counter[Id], Counter[Id], Scores]: """ Summarize for a cross-analysis (to be usually called in parallel!). """ # Recover input and parameters analysis: str = args[0] ontology: Ontology = kwargs['ontology'] including = ontology.including excluding = ontology.excluding counts: Dict[Sample, Counter[Id]] = kwargs['counts'] scores: Dict[Sample, Dict[Id, Score]] = kwargs['scores'] samples: List[Sample] = kwargs['samples'] output: io.StringIO = io.StringIO(newline='') # Declare/define variables summary_counts: Counter[Id] = Counter() summary_acc: Counter[Id] = Counter() summary_score: Scores = Scores({}) summary: Sample = None output.write(gray('Summary for ') + analysis + gray('... ')) target_samples: List[Sample] = [ smpl for smpl in samples if smpl.startswith(analysis) ] assert len(target_samples) >= 1, \ red('ERROR! ') + analysis + gray(' has no samples to summarize!') for smpl in target_samples: summary_counts += counts[smpl] summary_score.update(scores[smpl]) tree = TaxTree() tree.grow(ontology=ontology, counts=summary_counts, scores=summary_score) tree.subtract() tree.shape() summary_counts.clear() summary_score.clear() tree.get_taxa(counts=summary_counts, accs=summary_acc, scores=summary_score, include=including, exclude=excluding) summary_counts = +summary_counts # remove counts <= 0 if summary_counts: # Avoid returning empty sample (summary would be None) summary = Sample(f'{analysis}_{STR_SUMMARY}') output.write( gray('(') + cyan(f'{len(target_samples)}') + gray(' samples)') + green(' OK!\n')) else: output.write(yellow(' VOID\n')) # Print output and return print(output.getvalue(), end='') sys.stdout.flush() return summary, summary_counts, summary_acc, summary_score
def mock_from_scratch(out: Filename, mock_layout: Counter[TaxId]) -> None: """Generate a mock Centrifuge output file from scratch""" with open(out, 'w') as fout: vprint(gray('Generating'), blue(out), gray('file... ')) fout.write('readID\tseqID\ttaxID\tscore\t2ndBestScore\t' 'hitLength\tqueryLength\tnumMatches\n') reads_writen: int = 0 for tid in mock_layout: maxhl: int = random.randint(args.random + 1, MAX_HIT_LENGTH) rank: str = str(ncbi.get_rank(tid)).lower() for _ in range(mock_layout[tid]): hit_length = random.randint(args.random + 1, maxhl) fout.write(f'test{reads_writen}\t{rank}\t' f'{tid}\t{(hit_length-15)**2}\t' f'0\t{hit_length}\t{MAX_HIT_LENGTH}\t1\n') reads_writen += 1 vprint(reads_writen, 'reads', green('OK!\n'))
def mock_from_scratch(out: Filename, mock_layout: Counter[Id]) -> None: """Generate a mock Centrifuge output file from scratch""" with open(out, 'w') as fout: vprint(gray('Generating'), blue(out), gray('file... ')) fout.write('readID\tseqID\ttaxID\tscore\t2ndBestScore\t' 'hitLength\tqueryLength\tnumMatches\n') reads_writen: int = 0 for numtid in mock_layout: tid = Id(numtid) # Convert to Id the excel integer maxhl: int = random.randint(rnd + 1, MAX_HIT_LENGTH) rank: str = str(ncbi.get_rank(tid)).lower() for _ in range(int(mock_layout[numtid])): hit_length = random.randint(rnd + 1, maxhl) fout.write(f'test{reads_writen}\t{rank}\t' f'{tid}\t{(hit_length - 15) ** 2}\t' f'0\t{hit_length}\t{MAX_HIT_LENGTH}\t1\n') reads_writen += 1 vprint(reads_writen, 'reads', green('OK!\n')) if out == TEST_REXT_SMPL: # Test mode: create mock FASTQ for smpl mock_fastq(reads_writen)
def mock_fastq(num_reads: int) -> None: """Do the job in case of Excel file with all the details""" def fastq_seqs(alphabet=single_letter_alphabet): """Generator function that creates mock fastq sequences """ for seq in range(num_reads): yield SeqRecord(Seq('AGTC', alphabet), id=f'test{seq}', name=f'test{seq}', description=f'test{seq}', annotations={'quality': '@@@@'}) print(gray('Writing'), magenta(f'{num_reads}'), gray('reads in'), TEST_REXT_FSTQ, gray('...'), end='', flush=True) SeqIO.write((sq for sq in fastq_seqs()), TEST_REXT_FSTQ, 'quickfastq') print(green(' OK!'))
def mock_from_source(out: Filename, mock_layout: Counter[Id]) -> None: """Generate a mock Centrifuge output file from source file""" with open(out, 'w') as fout, open(args.file) as fcfg: vprint(gray('Generating'), blue(out), gray('file... ')) fout.write(fcfg.readline()) # copy cfg output file header reads_writen: int = 0 for line in fcfg: tid = Id(line.split('\t')[2]) if mock_layout[tid]: fout.write(line) mock_layout[tid] -= 1 reads_writen += 1 if not sum(mock_layout.values()): vprint(reads_writen, 'reads', green('OK!\n')) break if sum(mock_layout.values()): print(red('ERROR!\n')) print(gray('Incomplete read copy by taxid:')) mock_layout = +mock_layout # Delete zero counts elements for tid in mock_layout: print(yellow(mock_layout[tid]), gray('reads missing for tid'), tid, '(', cyan(ncbi.get_name(tid)), ')\n')
def read_clark_output( output_file: Filename, scoring: Scoring = Scoring.CLARK_C, minscore: Score = None, ) -> Tuple[str, SampleStats, Counter[Id], Dict[Id, Score]]: """ Read CLARK(-l)(-S) full mode output file Args: output_file: output file name scoring: type of scoring to be applied (see Scoring class) minscore: minimum confidence level for the classification Returns: log string, statistics, abundances counter, scores dict """ output: io.StringIO = io.StringIO(newline='') all_scores: Dict[Id, List[Score]] = {} all_confs: Dict[Id, List[Score]] = {} all_gammas: Dict[Id, List[Score]] = {} all_length: Dict[Id, List[int]] = {} taxids: Set[Id] = set() num_read: int = 0 nt_read: int = 0 num_uncl: int = 0 last_error_read: int = -1 # Number of read of the last error num_errors: int = 0 # Number or reads discarded due to error output.write(gray(f'Loading output file {output_file}... ')) try: with open(output_file, 'r') as file: # Check number of cols in header header = file.readline().split(',') if len(header) != 8: print( red('\nERROR! ') + 'CLARK output format of ', yellow(f'"{output_file}"'), 'not supported.') print(magenta('Expected:'), 'ID,Length,Gamma,1st,score1,2nd,score2,conf') print(magenta('Found:'), ','.join(header), end='') print(blue('HINT:'), 'Use CLARK, CLARK-l, or CLARK-S ' 'with full mode (', blue('-m 0'), ')') raise Exception('Unsupported file format. Aborting.') for raw_line in file: try: output_line = raw_line.strip() (_label, _length, _gamma, _tid1, _score1, _tid2, _score2, _conf) = output_line.split(',') except ValueError: print( yellow('Failure'), 'parsing line elements:' f' {output_line} in {output_file}' '. Ignoring line!') last_error_read = num_read + 1 num_errors += 1 continue try: length: int = int(_length) gamma: Score = Score(float(_gamma)) tid1: Id = Id(_tid1) score1: Score = Score(float(_score1)) tid2: Id = Id(_tid2) score2: Score = Score(float(_score2)) conf: Score = Score(float(_conf)) except ValueError: print( yellow('Failure'), 'parsing line elements:' f' {output_line} in {output_file}' '. Ignoring line!') last_error_read = num_read + 1 num_errors += 1 continue num_read += 1 nt_read += length # Select tid and score between CLARK assignments 1 and 2 tid: Id = tid1 score: Score = score1 if tid1 == UNCLASSIFIED: if tid2 == UNCLASSIFIED: # Just count unclassified reads num_uncl += 1 continue else: # Majority of read unclassified tid = tid2 score = score2 conf = Score(1 - conf) # Get CLARK's h2/(h1+h2) # From CLARK_C(S) score get "single hit equivalent length" shel: Score = Score(score + K_MER_SIZE) taxids.add(tid) # Save all the selected tids (tid1 or tid2) if minscore is not None: # Decide if ignore read if low score if scoring is Scoring.CLARK_C: if conf < minscore: continue elif scoring is Scoring.CLARK_G: if gamma < minscore: continue else: if shel < minscore: continue try: all_scores[tid].append(shel) except KeyError: all_scores[tid] = [ shel, ] try: all_confs[tid].append(conf) except KeyError: all_confs[tid] = [ conf, ] try: all_gammas[tid].append(gamma) except KeyError: all_gammas[tid] = [ gamma, ] try: all_length[tid].append(length) except KeyError: all_length[tid] = [ length, ] except FileNotFoundError: raise Exception(red('\nERROR! ') + f'Cannot read "{output_file}"') if last_error_read == num_read + 1: # Check error in last line: truncated! print(yellow('Warning!'), f'{output_file} seems truncated!') counts: Counter[Id] = col.Counter( {tid: len(all_scores[tid]) for tid in all_scores}) output.write(green('OK!\n')) if num_read == 0: raise Exception( red('\nERROR! ') + f'Cannot read any sequence from "{output_file}"') filt_seqs: int = sum([len(scores) for scores in all_scores.values()]) if filt_seqs == 0: raise Exception(red('\nERROR! ') + 'No sequence passed the filter!') # Get statistics stat: SampleStats = SampleStats(minscore=minscore, nt_read=nt_read, lens=all_length, scores=all_scores, scores2=all_confs, scores3=all_gammas, seq_read=num_read, seq_unclas=num_uncl, seq_filt=filt_seqs, tid_clas=len(taxids)) # Output statistics if num_errors: output.write( gray(' Seqs fail: ') + red(f'{num_errors:_d}\t') + gray('(Last error in read ') + red(f'{last_error_read}') + gray(')\n')) output.write( gray(' Seqs read: ') + f'{stat.seq.read:_d}\t' + gray('[') + f'{stat.nt_read}' + gray(']\n')) output.write( gray(' Seqs clas: ') + f'{stat.seq.clas:_d}\t' + gray('(') + f'{stat.get_unclas_ratio():.2%}' + gray(' unclassified)\n')) output.write( gray(' Seqs pass: '******'{stat.seq.filt:_d}\t' + gray('(') + f'{stat.get_reject_ratio():.2%}' + gray(' rejected)\n')) output.write( gray(' Hit (score): min = ') + f'{stat.sco.mini:.1f},' + gray(' max = ') + f'{stat.sco.maxi:.1f},' + gray(' avr = ') + f'{stat.sco.mean:.1f}\n') output.write( gray(' Conf. score: min = ') + f'{stat.sco2.mini:.1f},' + gray(' max = ') + f'{stat.sco2.maxi:.1f},' + gray(' avr = ') + f'{stat.sco2.mean:.1f}\n') output.write( gray(' Gamma score: min = ') + f'{stat.sco3.mini:.1f},' + gray(' max = ') + f'{stat.sco3.maxi:.1f},' + gray(' avr = ') + f'{stat.sco3.mean:.1f}\n') output.write( gray(' Read length: min = ') + f'{stat.len.mini},' + gray(' max = ') + f'{stat.len.maxi},' + gray(' avr = ') + f'{stat.len.mean}\n') output.write( gray(' TaxIds: by classifier = ') + f'{stat.tid.clas}' + gray(', by filter = ') + f'{stat.tid.filt}\n') # Select score output out_scores: Dict[Id, Score] if scoring is Scoring.SHEL: out_scores = {tid: Score(mean(all_scores[tid])) for tid in all_scores} elif scoring is Scoring.CLARK_C: out_scores = { tid: Score(mean(all_confs[tid]) * 100) for tid in all_confs } elif scoring is Scoring.CLARK_G: out_scores = {tid: Score(mean(all_gammas[tid])) for tid in all_gammas} elif scoring is Scoring.LENGTH: out_scores = {tid: Score(mean(all_length[tid])) for tid in all_length} elif scoring is Scoring.LOGLENGTH: out_scores = { tid: Score(log10(mean(all_length[tid]))) for tid in all_length } elif scoring is Scoring.NORMA: scores: Dict[Id, Score] = { tid: Score(mean(all_scores[tid])) for tid in all_scores } lengths: Dict[Id, Score] = { tid: Score(mean(all_length[tid])) for tid in all_length } out_scores = { tid: Score(scores[tid] / lengths[tid] * 100) for tid in scores } else: print(red('ERROR!'), f'clark: Unsupported Scoring "{scoring}"') raise Exception('Unsupported scoring') # Return return output.getvalue(), stat, counts, out_scores
def robust_contamination_removal(): """Implement robust contamination removal algorithm.""" nonlocal exclude_sets, shared_crossover def compute_qn(data: List[float], dist: str = "Gauss") -> float: """Compute Qn robust estimator of scale (Rousseeuw, 1993)""" c_d: float # Select d parameter depending on the distribution if dist == "Gauss": c_d = 2.2219 elif dist == "Cauchy": # Heavy-tailed distribution c_d = 1.2071 elif dist == "NegExp": # Negative exponential (asymetric) c_d = 3.4760 else: raise Exception(red('\nERROR! ') + 'Unknown distribution') num: int = len(data) sort_data = sorted(data) pairwisedifs: List[float] = [] for (i, x_val) in enumerate(sort_data): for y_val in sort_data[i + 1:]: pairwisedifs.append(abs(x_val - y_val)) k: int = int(num * (num / 2 + 1) / 4) return c_d * sorted(pairwisedifs)[k - 1] exclude_sets = {smpl: set() for smpl in raws[controls:]} vwrite( gray('Robust contamination removal: ' 'Searching for contaminants...\n')) for tid in exclude_candidates: relfreq_ctrl: List[float] = [ accs[ctrl][tid] / accs[ctrl][ontology.ROOT] for ctrl in raws[:controls] ] relfreq_smpl: List[float] = [ accs[smpl][tid] / accs[smpl][ontology.ROOT] for smpl in raws[controls:] ] relfreq: List[float] = relfreq_ctrl + relfreq_smpl crossover: List[bool] # Crossover source (yes/no) # Just-controls contamination check if all([rf < EPS for rf in relfreq_smpl]): vwrite(cyan('just-ctrl:\t'), tid, ontology.get_name(tid), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), '\n') continue # Go for next candidate # Critical contamination check if all([rf > SEVR_CONTM_MIN_RELFREQ for rf in relfreq_ctrl]): vwrite(red('critical:\t'), tid, ontology.get_name(tid), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), '\n') for exclude_set in exclude_sets.values(): exclude_set.add(tid) continue # Go for next candidate # Severe contamination check if any([rf > SEVR_CONTM_MIN_RELFREQ for rf in relfreq_ctrl]): vwrite(yellow('severe: \t'), tid, ontology.get_name(tid), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), '\n') for exclude_set in exclude_sets.values(): exclude_set.add(tid) continue # Go for next candidate # Mild contamination check if all([rf > MILD_CONTM_MIN_RELFREQ for rf in relfreq_ctrl]): vwrite(blue('mild cont:\t'), tid, ontology.get_name(tid), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), '\n') for exclude_set in exclude_sets.values(): exclude_set.add(tid) continue # Go for next candidate # Calculate median and MAD median but including controls mdn: float = statistics.median(relfreq) # mad:float=statistics.mean([abs(mdn - rf) for rf in relfreq]) q_n: float = compute_qn(relfreq, dist="NegExp") # Calculate crossover in samples outlier_lim: float = mdn + ROBUST_XOVER_OUTLIER * q_n ordomag_lim: float = max( relfreq_ctrl) * 10**ROBUST_XOVER_ORD_MAG crossover = [ rf > outlier_lim and rf > ordomag_lim for rf in relfreq[controls:] ] # Crossover contamination check if any(crossover): vwrite( magenta('crossover:\t'), tid, ontology.get_name(tid), green(f'lims: [{outlier_lim:.1g}]' + ('<' if outlier_lim < ordomag_lim else '>') + f'[{ordomag_lim:.1g}]'), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), gray('crossover:'), blst2str(crossover), '\n') # Exclude just for contaminated samples (not the source) vwrite(magenta('\t->'), gray(f'Include {tid} just in:')) for i in range(len(raws[controls:])): if not crossover[i]: exclude_sets[raws[i + controls]].add(tid) else: vwrite(f' {raws[i + controls]}') if all(crossover): # Shared taxon contaminating control(s) vwrite(' (', yellow('Shared crossover taxon!'), ')') shared_crossover.add(tid) vwrite('\n') continue # Other contamination: remove from all samples vwrite( gray('other cont:\t'), tid, ontology.get_name(tid), green(f'lims: [{outlier_lim:.1g}]' + ('<' if outlier_lim < ordomag_lim else '>') + f'[{ordomag_lim:.1g}]'), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), '\n') for exclude_set in exclude_sets.values(): exclude_set.add(tid)
def control_analysis(): """Perform last steps of control and shared controls analysis""" nonlocal shared_ctrl_counts, shared_ctrl_score def robust_contamination_removal(): """Implement robust contamination removal algorithm.""" nonlocal exclude_sets, shared_crossover def compute_qn(data: List[float], dist: str = "Gauss") -> float: """Compute Qn robust estimator of scale (Rousseeuw, 1993)""" c_d: float # Select d parameter depending on the distribution if dist == "Gauss": c_d = 2.2219 elif dist == "Cauchy": # Heavy-tailed distribution c_d = 1.2071 elif dist == "NegExp": # Negative exponential (asymetric) c_d = 3.4760 else: raise Exception(red('\nERROR! ') + 'Unknown distribution') num: int = len(data) sort_data = sorted(data) pairwisedifs: List[float] = [] for (i, x_val) in enumerate(sort_data): for y_val in sort_data[i + 1:]: pairwisedifs.append(abs(x_val - y_val)) k: int = int(num * (num / 2 + 1) / 4) return c_d * sorted(pairwisedifs)[k - 1] exclude_sets = {smpl: set() for smpl in raws[controls:]} vwrite( gray('Robust contamination removal: ' 'Searching for contaminants...\n')) for tid in exclude_candidates: relfreq_ctrl: List[float] = [ accs[ctrl][tid] / accs[ctrl][ontology.ROOT] for ctrl in raws[:controls] ] relfreq_smpl: List[float] = [ accs[smpl][tid] / accs[smpl][ontology.ROOT] for smpl in raws[controls:] ] relfreq: List[float] = relfreq_ctrl + relfreq_smpl crossover: List[bool] # Crossover source (yes/no) # Just-controls contamination check if all([rf < EPS for rf in relfreq_smpl]): vwrite(cyan('just-ctrl:\t'), tid, ontology.get_name(tid), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), '\n') continue # Go for next candidate # Critical contamination check if all([rf > SEVR_CONTM_MIN_RELFREQ for rf in relfreq_ctrl]): vwrite(red('critical:\t'), tid, ontology.get_name(tid), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), '\n') for exclude_set in exclude_sets.values(): exclude_set.add(tid) continue # Go for next candidate # Severe contamination check if any([rf > SEVR_CONTM_MIN_RELFREQ for rf in relfreq_ctrl]): vwrite(yellow('severe: \t'), tid, ontology.get_name(tid), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), '\n') for exclude_set in exclude_sets.values(): exclude_set.add(tid) continue # Go for next candidate # Mild contamination check if all([rf > MILD_CONTM_MIN_RELFREQ for rf in relfreq_ctrl]): vwrite(blue('mild cont:\t'), tid, ontology.get_name(tid), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), '\n') for exclude_set in exclude_sets.values(): exclude_set.add(tid) continue # Go for next candidate # Calculate median and MAD median but including controls mdn: float = statistics.median(relfreq) # mad:float=statistics.mean([abs(mdn - rf) for rf in relfreq]) q_n: float = compute_qn(relfreq, dist="NegExp") # Calculate crossover in samples outlier_lim: float = mdn + ROBUST_XOVER_OUTLIER * q_n ordomag_lim: float = max( relfreq_ctrl) * 10**ROBUST_XOVER_ORD_MAG crossover = [ rf > outlier_lim and rf > ordomag_lim for rf in relfreq[controls:] ] # Crossover contamination check if any(crossover): vwrite( magenta('crossover:\t'), tid, ontology.get_name(tid), green(f'lims: [{outlier_lim:.1g}]' + ('<' if outlier_lim < ordomag_lim else '>') + f'[{ordomag_lim:.1g}]'), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), gray('crossover:'), blst2str(crossover), '\n') # Exclude just for contaminated samples (not the source) vwrite(magenta('\t->'), gray(f'Include {tid} just in:')) for i in range(len(raws[controls:])): if not crossover[i]: exclude_sets[raws[i + controls]].add(tid) else: vwrite(f' {raws[i + controls]}') if all(crossover): # Shared taxon contaminating control(s) vwrite(' (', yellow('Shared crossover taxon!'), ')') shared_crossover.add(tid) vwrite('\n') continue # Other contamination: remove from all samples vwrite( gray('other cont:\t'), tid, ontology.get_name(tid), green(f'lims: [{outlier_lim:.1g}]' + ('<' if outlier_lim < ordomag_lim else '>') + f'[{ordomag_lim:.1g}]'), gray('relfreq:'), fltlst2str(relfreq_ctrl) + fltlst2str(relfreq_smpl), '\n') for exclude_set in exclude_sets.values(): exclude_set.add(tid) # Get taxids at this rank that are present in the control samples exclude_candidates: Set[Id] = set() for i in range(controls): exclude_candidates.update(taxids[raws[i]][rank]) exclude_sets: Dict[Sample, Set[Id]] shared_crossover: Set[Id] = set() # Shared taxa contaminating controls if controls and (len(raws) - controls >= ROBUST_MIN_SAMPLES): robust_contamination_removal() else: # If this case, just apply strict control exclude_sets = { file: exclude_candidates for file in raws[controls::] } # Add explicit excluding taxa (if any) to exclude sets for exclude_set in exclude_sets.values(): exclude_set.update(excluding) exclude_candidates.update(excluding) # Process each sample excluding control taxa for raw in raws[controls:]: output.write( gray(' Ctrl: From') + f' {raw} ' + gray(f'excluding {len(exclude_sets[raw])} ctrl taxa. ' f'Generating sample... ')) ctrl_tree = TaxTree() ctrl_out = SampleDataById(['counts', 'scores', 'accs']) ctrl_tree.allin1(ontology=ontology, counts=counts[raw], scores=scores[raw], min_taxa=mintaxas[raw], min_rank=rank, just_min_rank=True, include=including, exclude=exclude_sets[raw], out=ctrl_out) ctrl_out.purge_counters() if ctrl_out.counts: # Avoid adding empty samples sample = Sample(f'{raw}_{STR_CONTROL}_{rank.name.lower()}') samples.append(sample) counts[sample] = ctrl_out.get_counts() accs[sample] = ctrl_out.get_accs() scores[sample] = ctrl_out.get_scores() output.write(green('OK!\n')) else: output.write(yellow('VOID\n')) def shared_ctrl_analysis(): """Perform last steps of shared taxa analysis""" shared_ctrl_tree: TaxTree = TaxTree() shared_ctrl_out: SampleDataById = SampleDataById( ['shared', 'accs']) shared_ctrl_tree.allin1(ontology=ontology, counts=shared_ctrl_counts, scores=shared_ctrl_score, min_taxa=get_shared_mintaxa(), include=including, exclude=(exclude_candidates - shared_crossover), out=shared_ctrl_out) shared_ctrl_out.purge_counters() out_counts: SharedCounter = shared_ctrl_out.get_shared_counts() output.write( gray(f' Ctrl-shared: Including {len(out_counts)}' ' shared taxa. Generating sample... ')) if out_counts: sample = Sample(f'{STR_CONTROL_SHARED}_{rank.name.lower()}') samples.append(sample) counts[Sample(sample)] = out_counts accs[Sample(sample)] = shared_ctrl_out.get_accs() scores[sample] = shared_ctrl_out.get_shared_scores() output.write(green('OK!\n')) else: output.write(yellow('VOID\n')) # Shared-control taxa final analysis if shared_ctrl_counts: # Normalize scaled scores by total abundance shared_ctrl_score /= (+shared_ctrl_counts) # Get averaged abundance by number of samples minus ctrl samples shared_ctrl_counts //= (len(raws) - controls) shared_ctrl_analysis() else: output.write( gray(' Ctrl-shared: No taxa! ') + yellow('VOID') + gray(' sample.\n'))
def main(): """Main entry point to script.""" # Argument Parser Configuration parser = argparse.ArgumentParser( description='Extract reads following Centrifuge/Kraken output', epilog=f'%(prog)s - {__author__} - {__date__}') parser.add_argument('-V', '--version', action='version', version=f'%(prog)s release {__version__} ({__date__})') parser.add_argument('-f', '--file', action='store', metavar='FILE', required=True, help='Centrifuge output file.') parser.add_argument('-l', '--limit', action='store', metavar='NUMBER', type=int, default=None, help=('Limit of FASTQ reads to extract. ' 'Default: no limit')) parser.add_argument( '-m', '--maxreads', action='store', metavar='NUMBER', type=int, default=None, help=('Maximum number of FASTQ reads to search for the taxa. ' 'Default: no maximum')) parser.add_argument( '-n', '--nodespath', action='store', metavar='PATH', default=TAXDUMP_PATH, help=('path for the nodes information files (nodes.dmp and names.dmp' + ' from NCBI')) parser.add_argument( '-i', '--include', action='append', metavar='TAXID', type=TaxId, default=[], help=('NCBI taxid code to include a taxon and all underneath ' + '(multiple -i is available to include several taxid). ' + 'By default all the taxa is considered for inclusion.')) parser.add_argument( '-x', '--exclude', action='append', metavar='TAXID', type=TaxId, default=[], help=('NCBI taxid code to exclude a taxon and all underneath ' + '(multiple -x is available to exclude several taxid)')) parser.add_argument( '-y', '--minscore', action='store', metavar='NUMBER', type=lambda txt: Score(float(txt)), default=None, help=('minimum score/confidence of the classification of a read ' 'to pass the quality filter; all pass by default')) filein = parser.add_mutually_exclusive_group(required=True) filein.add_argument('-q', '--fastq', action='store', metavar='FILE', default=None, help='Single FASTQ file (no paired-ends)') filein.add_argument('-1', '--mate1', action='store', metavar='FILE', default=None, help='Paired-ends FASTQ file for mate 1s ' '(filename usually includes _1)') parser.add_argument('-2', '--mate2', action='store', metavar='FILE', default=None, help='Paired-ends FASTQ file for mate 2s ' '(filename usually includes _2)') # timing initialization start_time: float = time.time() # Program header print(f'\n=-= {sys.argv[0]} =-= v{__version__} =-= {__date__} =-=\n') sys.stdout.flush() # Parse arguments args = parser.parse_args() output_file = args.file nodesfile: Filename = Filename(os.path.join(args.nodespath, NODES_FILE)) namesfile: Filename = Filename(os.path.join(args.nodespath, NAMES_FILE)) excluding: Set[TaxId] = set(args.exclude) including: Set[TaxId] = set(args.include) fastq_1: Filename fastq_2: Filename = args.mate2 if not fastq_2: fastq_1 = args.fastq else: fastq_1 = args.mate1 # Load NCBI nodes, names and build children plasmidfile: Filename = None ncbi: Taxonomy = Taxonomy(nodesfile, namesfile, plasmidfile, False, excluding, including) # Build taxonomy tree print(gray('Building taxonomy tree...'), end='') sys.stdout.flush() tree = TaxTree() tree.grow(taxonomy=ncbi, look_ancestors=False) print(green(' OK!')) # Get the taxa print(gray('Filtering taxa...'), end='') sys.stdout.flush() ranks: Ranks = Ranks({}) tree.get_taxa(ranks=ranks, include=including, exclude=excluding) print(green(' OK!')) taxids: Set[TaxId] = set(ranks) taxlevels: TaxLevels = Rank.ranks_to_taxlevels(ranks) num_taxlevels = Counter({rank: len(taxlevels[rank]) for rank in taxlevels}) num_taxlevels = +num_taxlevels # Statistics about including taxa print(f' {len(taxids)}\033[90m taxid selected in \033[0m', end='') print(f'{len(num_taxlevels)}\033[90m different taxonomical levels:\033[0m') for rank in num_taxlevels: print(f' Number of different {rank}: {num_taxlevels[rank]}') assert taxids, red('ERROR! No taxids to search for!') # Get the records records: List[SeqRecord] = [] num_seqs: int = 0 # timing initialization start_time_load: float = time.perf_counter() print(gray(f'Loading output file {output_file}...'), end='') sys.stdout.flush() try: with open(output_file, 'rU') as file: file.readline() # discard header for num_seqs, record in enumerate(SeqIO.parse(file, 'centrifuge')): tid: TaxId = record.annotations['taxID'] if tid not in taxids: continue # Ignore read if low confidence score: Score = Score(record.annotations['score']) if args.minscore is not None and score < args.minscore: continue records.append(record) except FileNotFoundError: raise Exception(red('ERROR!') + 'Cannot read "' + output_file + '"') print(green(' OK!')) # Basic records statistics print( gray(' Load elapsed time: ') + f'{time.perf_counter() - start_time_load:.3g}' + gray(' sec')) print(f' \033[90mMatching reads: \033[0m{len(records):_d} \033[90m\t' f'(\033[0m{len(records)/num_seqs:.4%}\033[90m of sample)') sys.stdout.flush() # FASTQ sequence dealing # records_ids: List[SeqRecord] = [record.id for record in records] records_ids: Set[SeqRecord] = {record.id for record in records} seqs1: List[SeqRecord] = [] seqs2: List[SeqRecord] = [] extracted: int = 0 i: int = 0 if fastq_2: print( f'\033[90mLoading FASTQ files {fastq_1} and {fastq_2}...\n' f'Mseqs: \033[0m', end='') sys.stdout.flush() try: with open(fastq_1, 'rU') as file1, open(fastq_2, 'rU') as file2: for i, (rec1, rec2) in enumerate( zip(SeqIO.parse(file1, 'quickfastq'), SeqIO.parse(file2, 'quickfastq'))): if not records_ids or (args.maxreads and i >= args.maxreads ) or (args.limit and extracted >= args.limit): break elif not i % 1000000: print(f'{i//1000000:_d}', end='') sys.stdout.flush() elif not i % 100000: print('.', end='') sys.stdout.flush() try: records_ids.remove(rec1.id) except KeyError: pass else: seqs1.append(rec1) seqs2.append(rec2) extracted += 1 except FileNotFoundError: raise Exception('\n\033[91mERROR!\033[0m Cannot read FASTQ files') else: print(f'\033[90mLoading FASTQ files {fastq_1}...\n' f'Mseqs: \033[0m', end='') sys.stdout.flush() try: with open(fastq_1, 'rU') as file1: for i, rec1 in enumerate(SeqIO.parse(file1, 'quickfastq')): if not records_ids or (args.maxreads and i >= args.maxreads ) or (args.limit and extracted >= args.limit): break elif not i % 1000000: print(f'{i//1000000:_d}', end='') sys.stdout.flush() elif not i % 100000: print('.', end='') sys.stdout.flush() try: records_ids.remove(rec1.id) except KeyError: pass else: seqs1.append(rec1) extracted += 1 except FileNotFoundError: raise Exception('\n\033[91mERROR!\033[0m Cannot read FASTQ file') print(cyan(f' {i/1e+6:.3g} Mseqs'), green('OK! ')) def format_filename(fastq: Filename) -> Filename: """Auxiliary function to properly format the output filenames. Args: fastq: Complete filename of the fastq input file Returns: Filename of the rextracted fastq output file """ fastq_filename, _ = os.path.splitext(fastq) output_list: List[str] = [fastq_filename, '_rxtr'] if including: output_list.append('_incl') output_list.extend('_'.join(including)) if excluding: output_list.append('_excl') output_list.extend('_'.join(excluding)) output_list.append('.fastq') return Filename(''.join(output_list)) filename1: Filename = format_filename(fastq_1) SeqIO.write(seqs1, filename1, 'quickfastq') print(gray('Wrote'), magenta(f'{len(seqs1)}'), gray('reads in'), filename1) if fastq_2: filename2: Filename = format_filename(fastq_2) SeqIO.write(seqs2, filename2, 'quickfastq') print(gray('Wrote'), magenta(f'{len(seqs1)}'), gray('reads in'), filename2) # Timing results print(gray('Total elapsed time:'), time.strftime("%H:%M:%S", time.gmtime(time.time() - start_time)))
def process_report( *args, **kwargs ) -> Tuple[Sample, TaxTree, SampleDataByTaxId, SampleStats, Err]: """ Process Centrifuge/Kraken report files (to be usually called in parallel!). """ # TODO: Full review to report support # Recover input and parameters filerep: Filename = args[0] taxonomy: Taxonomy = kwargs['taxonomy'] mintaxa: int = kwargs['mintaxa'] collapse: bool = taxonomy.collapse including: Set[TaxId] = taxonomy.including excluding: Set[TaxId] = taxonomy.excluding debug: bool = kwargs['debug'] output: io.StringIO = io.StringIO(newline='') def vwrite(*args): """Print only if verbose/debug mode is enabled""" if kwargs['debug']: output.write(' '.join(str(item) for item in args)) sample: Sample = Sample(filerep) # Read Centrifuge/Kraken report file to get abundances log: str abundances: Counter[TaxId] log, abundances, _ = read_report(filerep) output.write(log) # Remove root counts, in case if kwargs['root']: vwrite(gray('Removing'), abundances[ROOT], gray('"ROOT" reads... ')) abundances[ROOT] = 0 vwrite(green('OK!'), '\n') # Build taxonomy tree output.write(' \033[90mBuilding taxonomy tree...\033[0m') tree = TaxTree() tree.grow(taxonomy=taxonomy, counts=abundances) # Grow tax tree from root node output.write('\033[92m OK! \033[0m\n') # Prune the tree output.write(' \033[90mPruning taxonomy tree...\033[0m') tree.prune(mintaxa, None, collapse, debug) tree.shape() output.write('\033[92m OK! \033[0m\n') # Get the taxa with their abundances and taxonomical levels output.write(' \033[90mFiltering taxa...\033[0m') new_abund: Counter[TaxId] = col.Counter() new_accs: Counter[TaxId] = col.Counter() ranks: Ranks = Ranks({}) tree.get_taxa(abundance=new_abund, accs=new_accs, ranks=ranks, mindepth=0, maxdepth=0, include=including, exclude=excluding) new_abund = +new_abund # remove zero and negative counts if including or excluding: # Recalculate accumulated counts new_tree = TaxTree() new_tree.grow(taxonomy, new_abund) # Grow tree with new abund new_tree.shape() new_abund = col.Counter() # Reset abundances new_accs = col.Counter() # Reset accumulated new_tree.get_taxa(new_abund, new_accs) # Get new accumulated counts out: SampleDataByTaxId = SampleDataByTaxId() out.set(counts=new_abund, ranks=ranks, accs=new_accs) output.write('\033[92m OK! \033[0m\n') print(output.getvalue()) sys.stdout.flush() return sample, tree, out, SampleStats(), Err.NO_ERROR
def process_output( *args, **kwargs ) -> Tuple[Sample, TaxTree, SampleDataByTaxId, SampleStats, Err]: """ Process Centrifuge/LMAT output files (to be usually called in parallel!). """ # timing initialization start_time: float = time.perf_counter() # Recover input and parameters target_file: Filename = args[0] debug: bool = kwargs['debug'] is_ctrl: bool = args[1] if debug: print(gray('Processing'), blue('ctrl' if is_ctrl else 'sample'), target_file, gray('...')) sys.stdout.flush() taxonomy: Taxonomy = kwargs['taxonomy'] mintaxa: int = kwargs['ctrlmintaxa'] if is_ctrl else kwargs['mintaxa'] minscore: Score = kwargs['ctrlminscore'] if is_ctrl else kwargs['minscore'] including: Set[TaxId] = taxonomy.including excluding: Set[TaxId] = taxonomy.excluding scoring: Scoring = kwargs['scoring'] lmat: bool = kwargs['lmat'] output: io.StringIO = io.StringIO(newline='') def vwrite(*args): """Print only if verbose/debug mode is enabled""" if kwargs['debug']: output.write(' '.join(str(item) for item in args)) sample: Sample = Sample(os.path.splitext(target_file)[0]) error: Err = Err.NO_ERROR # Read Centrifuge/LMAT output files to get abundances read_method: Callable[[Filename, Scoring, Optional[Score]], # Input Tuple[str, SampleStats, Counter[TaxId], Dict[TaxId, Score]] # Output ] if lmat: read_method = read_lmat_output else: read_method = read_output log: str counts: Counter[TaxId] scores: Dict[TaxId, Score] log, stat, counts, scores = read_method(target_file, scoring, minscore) output.write(log) # Update field in stat about control nature of the sample stat.is_ctrl = is_ctrl # Move cellular_organisms counts to root, in case if taxonomy.collapse and counts[CELLULAR_ORGANISMS]: vwrite(gray('Moving'), counts[CELLULAR_ORGANISMS], gray('"CELLULAR_ORGANISMS" reads to "ROOT"... ')) if counts[ROOT]: stat.num_taxa -= 1 scores[ROOT] = ( (scores[CELLULAR_ORGANISMS] * counts[CELLULAR_ORGANISMS] + scores[ROOT] * counts[ROOT]) / (counts[CELLULAR_ORGANISMS] + counts[ROOT])) else: scores[ROOT] = scores[CELLULAR_ORGANISMS] counts[ROOT] += counts[CELLULAR_ORGANISMS] counts[CELLULAR_ORGANISMS] = 0 scores[CELLULAR_ORGANISMS] = NO_SCORE # Remove root counts, in case if kwargs['root'] and counts[ROOT]: vwrite(gray('Removing'), counts[ROOT], gray('"ROOT" reads... ')) stat.seq = stat.seq._replace(filt=stat.seq.filt - counts[ROOT]) stat.num_taxa -= 1 counts[ROOT] = 0 scores[ROOT] = NO_SCORE vwrite(green('OK!'), '\n') # Building taxonomy tree output.write(gray('Building from raw data... ')) vwrite(gray('\n Building taxonomy tree with all-in-1... ')) tree = TaxTree() ancestors: Set[TaxId] orphans: Set[TaxId] ancestors, orphans = taxonomy.get_ancestors(counts.keys()) out = SampleDataByTaxId(['all']) tree.allin1(taxonomy=taxonomy, counts=counts, scores=scores, ancestors=ancestors, min_taxa=mintaxa, include=including, exclude=excluding, out=out) out.purge_counters() vwrite(green('OK!'), '\n') # Give stats about orphan taxid if debug: vwrite(gray(' Checking taxid loss (orphans)... ')) lost: int = 0 if orphans: for orphan in orphans: vwrite(yellow('Warning!'), f'Orphan taxid={orphan}\n') lost += counts[orphan] vwrite( yellow('WARNING!'), f'{len(orphans)} orphan taxids (' f'{len(orphans)/len(counts):.2%} of total)\n' f'{lost} orphan sequences (' f'{lost/sum(counts.values()):.3%} of total)\n') else: vwrite(green('OK!\n')) # Check the lost of taxids (plasmids typically) under some conditions if debug and not excluding and not including: vwrite(gray(' Additional checking of taxid loss... ')) lost = 0 for taxid in counts: if not out.counts[taxid]: lost += 1 vwrite(yellow('Warning!'), f'Lost taxid={taxid}: ' f'{taxonomy.get_name(taxid)}\n') if lost: vwrite( yellow('WARNING!'), f'Lost {lost} taxids (' f'{lost/len(counts):.2%} of total)' '\n') else: vwrite(green('OK!\n')) # Print last message and check if the sample is void if out.counts: output.write(sample + blue(' ctrl ' if is_ctrl else ' sample ') + green('OK!\n')) elif is_ctrl: output.write(sample + red(' ctrl VOID!\n')) error = Err.VOID_CTRL else: output.write(sample + blue(' sample ') + yellow('VOID\n')) error = Err.VOID_SAMPLE # Timing results output.write( gray('Load elapsed time: ') + f'{time.perf_counter() - start_time:.3g}' + gray(' sec\n')) print(output.getvalue()) sys.stdout.flush() return sample, tree, out, stat, error
def read_output( output_file: Filename, scoring: Scoring = Scoring.SHEL, minscore: Score = None, ) -> Tuple[str, SampleStats, Counter[TaxId], Dict[TaxId, Score]]: """ Read Centrifuge output file Args: output_file: output file name scoring: type of scoring to be applied (see Scoring class) minscore: minimum confidence level for the classification Returns: log string, statistics, abundances counter, scores dict """ output: io.StringIO = io.StringIO(newline='') all_scores: Dict[TaxId, List[Score]] = {} all_length: Dict[TaxId, List[int]] = {} num_read: int = 0 nt_read: int = 0 num_uncl: int = 0 error_read: int = None output.write(gray(f'Loading output file {output_file}... ')) try: with open(output_file, 'r') as file: file.readline() # discard header for output_line in file: try: _, _, _tid, _score, _, _, _length, *_ = output_line.split( '\t') except ValueError: print( red('Error'), f'parsing line: ({output_line}) ' f'in {output_file}. Ignoring line!') error_read = num_read + 1 continue tid = TaxId(_tid) try: # From Centrifuge score get "single hit equivalent length" shel = Score(float(_score)**0.5 + 15) length = int(_length) except ValueError: print(red('Error'), f'parsing score ({_score}) for query', f'length ({_length}) for taxid {_tid}', f'in {output_file}. Ignoring line!') continue num_read += 1 nt_read += length if tid == UNCLASSIFIED: # Just count unclassified reads num_uncl += 1 continue elif minscore is not None and shel < minscore: continue # Ignore read if low confidence try: all_scores[tid].append(shel) except KeyError: all_scores[tid] = [ shel, ] try: all_length[tid].append(length) except KeyError: all_length[tid] = [ length, ] except FileNotFoundError: raise Exception(red('\nERROR! ') + f'Cannot read "{output_file}"') if error_read == num_read + 1: # Check if error in last line: truncated! print(yellow('Warning!'), f'{output_file} seems truncated!') counts: Counter[TaxId] = Counter( {tid: len(all_scores[tid]) for tid in all_scores}) output.write(green('OK!\n')) if num_read == 0: raise Exception( red('\nERROR! ') + f'Cannot read any sequence from"{output_file}"') filt_seqs: int = sum([len(scores) for scores in all_scores.values()]) if filt_seqs == 0: raise Exception(red('\nERROR! ') + 'No sequence passed the filter!') # Get statistics stat: SampleStats = SampleStats(minscore=minscore, nt_read=nt_read, scores=all_scores, lens=all_length, seq_read=num_read, seq_unclas=num_uncl, seq_filt=filt_seqs) # Output statistics output.write( gray(' Seqs read: ') + f'{stat.seq.read:_d}\t' + gray('[') + f'{stat.nt_read}' + gray(']\n')) output.write( gray(' Seqs clas: ') + f'{stat.seq.clas:_d}\t' + gray('(') + f'{stat.get_unclas_ratio():.2%}' + gray(' unclassified)\n')) output.write( gray(' Seqs pass: '******'{stat.seq.filt:_d}\t' + gray('(') + f'{stat.get_reject_ratio():.2%}' + gray(' rejected)\n')) output.write( gray(' Scores: min = ') + f'{stat.sco.mini:.1f},' + gray(' max = ') + f'{stat.sco.maxi:.1f},' + gray(' avr = ') + f'{stat.sco.mean:.1f}\n') output.write( gray(' Length: min = ') + f'{stat.len.mini},' + gray(' max = ') + f'{stat.len.maxi},' + gray(' avr = ') + f'{stat.len.mean}\n') output.write(f' {stat.num_taxa}' + gray(f' taxa with assigned reads\n')) # Select score output out_scores: Dict[TaxId, Score] if scoring is Scoring.SHEL: out_scores = {tid: Score(mean(all_scores[tid])) for tid in all_scores} elif scoring is Scoring.LENGTH: out_scores = {tid: Score(mean(all_length[tid])) for tid in all_length} elif scoring is Scoring.LOGLENGTH: out_scores = { tid: Score(log10(mean(all_length[tid]))) for tid in all_length } elif scoring is Scoring.NORMA: scores: Dict[TaxId, Score] = { tid: Score(mean(all_scores[tid])) for tid in all_scores } lengths: Dict[TaxId, Score] = { tid: Score(mean(all_length[tid])) for tid in all_length } out_scores = { tid: Score(scores[tid] / lengths[tid] * 100) for tid in scores } else: raise Exception(f'\n\033[91mERROR!\033[0m Unknown Scoring "{scoring}"') # Return return output.getvalue(), stat, counts, out_scores
def generate_excel(): """Generate Excel with results via pandas DataFrame""" xlsx_name: Filename = Filename(htmlfile.split('.html')[0] + '.xlsx') print(gray(f'Generating Excel {str(excel).lower()} summary (') + magenta(xlsx_name) + gray(')... '), end='') sys.stdout.flush() xlsxwriter = pd.ExcelWriter(xlsx_name) list_rows: List = [] # Save raw samples basic statistics data_frame: pd.DataFrame = pd.DataFrame.from_dict( {raw: stats[raw].to_dict() for raw in raw_samples}) data_frame.to_excel(xlsxwriter, sheet_name='_sample_stats') # Save taxid related statistics per sample if excel is Excel.FULL: polytree.to_items(taxonomy=ncbi, items=list_rows) # Generate the pandas DataFrame from items and export to Excel iterable_1 = [samples, [COUNT, UNASSIGNED, SCORE]] cols1 = pd.MultiIndex.from_product(iterable_1, names=['Samples', 'Stats']) iterable_2 = [['Details'], ['Rank', 'Name']] cols2 = pd.MultiIndex.from_product(iterable_2) cols = cols1.append(cols2) data_frame = pd.DataFrame.from_items(list_rows, orient='index', columns=cols) data_frame.index.names = ['TaxId'] data_frame.to_excel(xlsxwriter, sheet_name=str(excel)) elif excel is Excel.CMPLXCRUNCHER: target_ranks: List = [Rank.NO_RANK] if args.controls: target_ranks = [ Rank.SPECIES, Rank.GENUS, # Ranks of interest Rank.FAMILY, Rank.ORDER ] # for cmplxcruncher for rank in target_ranks: # Once for no rank dependency (NO_RANK) indexes: List[int] sheet_name: str columns: List[str] if args.controls: indexes = [ i for i in range(len(raw_samples), len(samples)) if (samples[i].startswith(STR_CONTROL) and rank.name.lower() in samples[i]) ] sheet_name = f'{STR_CONTROL}_{rank.name.lower()}' columns = [samples[i].split('_')[2] for i in indexes] else: # No rank dependency indexes = list(range(len(raw_samples))) sheet_name = f'raw_samples_{rank.name.lower()}' columns = [samples[i].split('_')[0] for i in indexes] list_rows = [] polytree.to_items(taxonomy=ncbi, items=list_rows, sample_indexes=indexes) data_frame = pd.DataFrame.from_items(list_rows, orient='index', columns=columns) data_frame.index.names = ['TaxId'] data_frame.to_excel(xlsxwriter, sheet_name=sheet_name) else: raise Exception(red('\nERROR!'), f'Unknown Excel option "{excel}"') xlsxwriter.save() print(green('OK!'))
def read_kraken_output( output_file: Filename, scoring: Scoring = Scoring.KRAKEN, minscore: Score = None, ) -> Tuple[str, SampleStats, Counter[Id], Dict[Id, Score]]: """ Read Kraken output file Args: output_file: output file name scoring: type of scoring to be applied (see Scoring class) minscore: minimum confidence level for the classification Returns: log string, statistics, abundances counter, scores dict """ output: io.StringIO = io.StringIO(newline='') all_scores: Dict[Id, List[Score]] = {} all_kmerel: Dict[Id, List[Score]] = {} all_length: Dict[Id, List[int]] = {} taxids: Set[Id] = set() num_read: int = 0 nt_read: int = 0 num_uncl: int = 0 last_error_read: int = -1 # Number of read of the last error num_errors: int = 0 # Number or reads discarded due to error output.write(gray(f'Loading output file {output_file}... ')) try: with open(output_file, 'r') as file: # Check number of cols in header header = file.readline().split('\t') if len(header) != 5: print( red('\nERROR! ') + 'Kraken output format of ', yellow(f'"{output_file}"'), 'not supported.') print(magenta('Expected:'), 'C/U, ID, taxid, length, list of mappings') print(magenta('Found:'), '\t'.join(header), end='') print(blue('HINT:'), 'Use Kraken or Kraken2 direct output.') raise Exception('Unsupported file format. Aborting.') for raw_line in file: try: output_line = raw_line.strip() (_clas, _label, _tid, _length, _maps) = output_line.split('\t') except ValueError: print( yellow('Failure'), 'parsing line elements:' f' {output_line} in {output_file}' '. Ignoring line!') last_error_read = num_read + 1 num_errors += 1 continue try: length: int = sum(map(int, _length.split('|'))) num_read += 1 nt_read += length if _clas == UNCLASSIFIED: # Just count unclassified reads num_uncl += 1 continue tid: Id = Id(_tid) maps: List[str] = _maps.split() try: maps.remove('|:|') except ValueError: pass mappings: Counter[Id] = col.Counter() for pair in maps: couple: List[str] = pair.split(':') mappings[Id(couple[0])] += int(couple[1]) # From Kraken score get "single hit equivalent length" shel: Score = Score(mappings[tid] + K_MER_SIZE) score: Score = Score(mappings[tid] / sum(mappings.values()) * 100) # % relative to all k-mers except ValueError: print( yellow('Failure'), 'parsing line elements:' f' {output_line} in {output_file}' '. Ignoring line!') last_error_read = num_read + 1 num_errors += 1 continue else: taxids.add(tid) # Save all the tids of classified reads if minscore is not None: # Decide if ignore read if low score if scoring is Scoring.KRAKEN: if score < minscore: continue else: if shel < minscore: continue try: all_scores[tid].append(shel) except KeyError: all_scores[tid] = [ shel, ] try: all_kmerel[tid].append(score) except KeyError: all_kmerel[tid] = [ score, ] try: all_length[tid].append(length) except KeyError: all_length[tid] = [ length, ] except FileNotFoundError: raise Exception(red('\nERROR! ') + f'Cannot read "{output_file}"') if last_error_read == num_read + 1: # Check error in last line: truncated! print(yellow('Warning!'), f'{output_file} seems truncated!') counts: Counter[Id] = col.Counter( {tid: len(all_scores[tid]) for tid in all_scores}) output.write(green('OK!\n')) if num_read == 0: raise Exception( red('\nERROR! ') + f'Cannot read any sequence from "{output_file}"') filt_seqs: int = sum([len(scores) for scores in all_scores.values()]) if filt_seqs == 0: raise Exception(red('\nERROR! ') + 'No sequence passed the filter!') # Get statistics stat: SampleStats = SampleStats(minscore=minscore, nt_read=nt_read, lens=all_length, scores=all_scores, scores2=all_kmerel, seq_read=num_read, seq_unclas=num_uncl, seq_filt=filt_seqs, tid_clas=len(taxids)) # Output statistics if num_errors: output.write( gray(' Seqs fail: ') + red(f'{num_errors:_d}\t') + gray('(Last error in read ') + red(f'{last_error_read}') + gray(')\n')) output.write( gray(' Seqs read: ') + f'{stat.seq.read:_d}\t' + gray('[') + f'{stat.nt_read}' + gray(']\n')) output.write( gray(' Seqs clas: ') + f'{stat.seq.clas:_d}\t' + gray('(') + f'{stat.get_unclas_ratio():.2%}' + gray(' unclassified)\n')) output.write( gray(' Seqs pass: '******'{stat.seq.filt:_d}\t' + gray('(') + f'{stat.get_reject_ratio():.2%}' + gray(' rejected)\n')) output.write( gray(' Scores SHEL: min = ') + f'{stat.sco.mini:.1f},' + gray(' max = ') + f'{stat.sco.maxi:.1f},' + gray(' avr = ') + f'{stat.sco.mean:.1f}\n') output.write( gray(' Coverage(%): min = ') + f'{stat.sco2.mini:.1f},' + gray(' max = ') + f'{stat.sco2.maxi:.1f},' + gray(' avr = ') + f'{stat.sco2.mean:.1f}\n') output.write( gray(' Read length: min = ') + f'{stat.len.mini},' + gray(' max = ') + f'{stat.len.maxi},' + gray(' avr = ') + f'{stat.len.mean}\n') output.write( gray(' TaxIds: by classifier = ') + f'{stat.tid.clas}' + gray(', by filter = ') + f'{stat.tid.filt}\n') # Select score output out_scores: Dict[Id, Score] if scoring is Scoring.SHEL: out_scores = {tid: Score(mean(all_scores[tid])) for tid in all_scores} elif scoring is Scoring.KRAKEN: out_scores = {tid: Score(mean(all_kmerel[tid])) for tid in all_kmerel} elif scoring is Scoring.LENGTH: out_scores = {tid: Score(mean(all_length[tid])) for tid in all_length} elif scoring is Scoring.LOGLENGTH: out_scores = { tid: Score(log10(mean(all_length[tid]))) for tid in all_length } elif scoring is Scoring.NORMA: scores: Dict[Id, Score] = { tid: Score(mean(all_scores[tid])) for tid in all_scores } lengths: Dict[Id, Score] = { tid: Score(mean(all_length[tid])) for tid in all_length } out_scores = { tid: Score(scores[tid] / lengths[tid] * 100) for tid in scores } else: print(red('ERROR!'), f'kraken: Unsupported Scoring "{scoring}"') raise Exception('Unsupported scoring') # Return return output.getvalue(), stat, counts, out_scores
def process_output( *args, **kwargs) -> Tuple[Sample, TaxTree, SampleDataById, SampleStats, Err]: """ Process classifiers output files (to be usually called in parallel!). """ # timing initialization start_time: float = time.perf_counter() # Recover input and parameters target_file: Filename = args[0] debug: bool = kwargs['debug'] is_ctrl: bool = args[1] if debug: print(gray('Processing'), blue('ctrl' if is_ctrl else 'sample'), target_file, gray('...')) sys.stdout.flush() ontology: Ontology = kwargs['ontology'] mintaxa: Optional[int] = (kwargs['ctrlmintaxa'] if is_ctrl else kwargs['mintaxa']) minscore: Score = kwargs['ctrlminscore'] if is_ctrl else kwargs['minscore'] including: Union[Tuple, Set[Id]] = ontology.including excluding: Union[Tuple, Set[Id]] = ontology.excluding scoring: Scoring = kwargs['scoring'] classifier: Classifier = kwargs['classifier'] genfmt: GenericFormat = kwargs['genfmt'] output: io.StringIO = io.StringIO(newline='') def vwrite(*args): """Print only if verbose/debug mode is enabled""" if kwargs['debug']: output.write(' '.join(str(item) for item in args)) sample: Sample = Sample(os.path.splitext(target_file)[0]) error: Err = Err.NO_ERROR # Read taxonomic classifier output files to get abundances read_method: Callable[ # Format: [[Input], Output] [Filename, Scoring, Optional[Score]], Tuple[str, SampleStats, Counter[Id], Dict[Id, Score]]] log: str stat: SampleStats counts: Counter[Id] scores: Dict[Id, Score] if classifier is Classifier.GENERIC: # Direct call to generic method log, stat, counts, scores = read_generic_output( target_file, scoring, minscore, genfmt) else: # Use read_method if classifier is Classifier.KRAKEN: read_method = read_kraken_output elif classifier is Classifier.CLARK: read_method = read_clark_output elif classifier is Classifier.LMAT: read_method = read_lmat_output elif classifier is Classifier.CENTRIFUGE: read_method = read_output else: raise Exception(red('\nERROR!'), f'taxclass: Unknown classifier "{classifier}".') log, stat, counts, scores = read_method(target_file, scoring, minscore) output.write(log) # Complete/Update fields in stats stat.is_ctrl = is_ctrl # set control nature of the sample if mintaxa is not None: # manual mintaxa has precedence over automatic stat.mintaxa = mintaxa else: # update local value with the automatically guessed value mintaxa = stat.mintaxa # Move cellular_organisms counts to root, in case if ontology.collapse and counts[CELLULAR_ORGANISMS]: vwrite(gray('Moving'), counts[CELLULAR_ORGANISMS], gray('"CELLULAR_ORGANISMS" reads to "ROOT"... \n')) if counts[ontology.ROOT]: stat.decrease_filtered_taxids() scores[ontology.ROOT] = Score( (scores[CELLULAR_ORGANISMS] * counts[CELLULAR_ORGANISMS] + scores[ontology.ROOT] * counts[ontology.ROOT]) / (counts[CELLULAR_ORGANISMS] + counts[ontology.ROOT])) else: scores[ontology.ROOT] = scores[CELLULAR_ORGANISMS] counts[ontology.ROOT] += counts[CELLULAR_ORGANISMS] counts[CELLULAR_ORGANISMS] = 0 scores[CELLULAR_ORGANISMS] = NO_SCORE # Remove root counts, in case if kwargs['root'] and counts[ontology.ROOT]: vwrite(gray('Removing'), counts[ontology.ROOT], gray('"ROOT" reads... ')) stat.seq = stat.seq._replace(filt=stat.seq.filt - counts[ontology.ROOT]) stat.decrease_filtered_taxids() counts[ontology.ROOT] = 0 scores[ontology.ROOT] = NO_SCORE vwrite(green('OK!'), '\n') # Building ontology tree output.write( gray('Building from raw data with mintaxa = ') + f'{mintaxa:_d}' + gray(' ... \n')) vwrite(gray(' Building ontology tree with all-in-1... ')) tree = TaxTree() ancestors: Set[Id] orphans: Set[Id] ancestors, orphans = ontology.get_ancestors(counts.keys()) out = SampleDataById(['all']) tree.allin1(ontology=ontology, counts=counts, scores=scores, ancestors=ancestors, min_taxa=mintaxa, include=including, exclude=excluding, out=out) out.purge_counters() vwrite(green('OK!'), '\n') # Stats: Complete final value for TaxIDs after tree building and folding final_taxids: int = len(out.counts) if out.counts is not None else 0 stat.set_final_taxids(final_taxids) # Check for additional loss of reads (due to include/exclude an orphans) output.write(gray(' Check for more seqs lost ([in/ex]clude affects)... ')) if out.counts is not None: discard: int = sum(counts.values()) - sum(out.counts.values()) if discard: output.write( blue('\n Info:') + f' {discard} ' + gray('additional seqs discarded (') + f'{discard/sum(counts.values()):.3%} ' + gray('of accepted)\n')) else: output.write(green('OK!\n')) else: output.write(red('No counts in sample tree!\n')) # Warn or give detailed stats about orphan taxid and orphan seqs if debug: vwrite(gray(' Checking taxid loss (orphans)... ')) lost: int = 0 if orphans: for orphan in orphans: vwrite(yellow(' Warning!'), gray('Orphan taxid'), f'{orphan}\n') lost += counts[orphan] vwrite( yellow(' WARNING!'), f'{len(orphans)} orphan taxids (' f'{len(orphans)/len(counts):.2%} of accepted)\n' f' and {lost} orphan sequences (' f'{lost/sum(counts.values()):.3%} of accepted)\n') else: vwrite(green('OK!\n')) elif orphans: output.write( yellow('\n Warning!') + f' {len(orphans)} orphan taxids' + gray(' (rerun with --debug for details)\n')) # Check the removal of TaxIDs (accumulation of leaves in parents) if debug and not excluding and including == {ontology.ROOT}: vwrite(gray(' Assess accumulation due to "folding the tree"...\n')) migrated: int = 0 if out.counts is not None: for taxid in counts: if out.counts[taxid] == 0: migrated += 1 vwrite( blue(' Info:'), gray(f'Folded TaxID {taxid} (') + f'{ontology.get_name(taxid)}' + gray(') with ') + f'{counts[taxid]}' + gray(' original seqs\n')) if migrated: vwrite( blue(' INFO:'), f'{migrated} TaxIDs folded (' f'{migrated/len(+counts):.2%} of TAF —TaxIDs after filtering—)' '\n') vwrite( blue(' INFO:'), f'Final assigned TaxIDs: {final_taxids} ' f'(reduced to {final_taxids/len(+counts):.2%} of ' 'number of TAF)\n') else: vwrite(blue(' INFO:'), gray('No migration!'), green('OK!\n')) # Print last message and check if the sample is void if out.counts: output.write(sample + blue(' ctrl ' if is_ctrl else ' sample ') + green('OK!\n')) elif is_ctrl: output.write(sample + red(' ctrl VOID!\n')) error = Err.VOID_CTRL else: output.write(sample + blue(' sample ') + yellow('VOID\n')) error = Err.VOID_SAMPLE # Timing results output.write( gray('Load elapsed time: ') + f'{time.perf_counter() - start_time:.3g}' + gray(' sec\n')) print(output.getvalue()) sys.stdout.flush() return sample, tree, out, stat, error
def read_lmat_output( output_file: Filename, scoring: Scoring = Scoring.LMAT, minscore: Score = None, ) -> Tuple[str, SampleStats, Counter[Id], Dict[Id, Score]]: """ Read LMAT output (iterate over all the output files) Args: output_file: output file name (prefix) scoring: type of scoring to be applied (see Scoring class) minscore: minimum confidence level for the classification Returns: log string, abundances counter, scores dict """ output: io.StringIO = io.StringIO(newline='') all_scores: Dict[Id, List[Score]] = {} all_length: Dict[Id, List[int]] = {} nt_read: int = 0 matchings: Counter[Match] = Counter() output_files: List[Filename] = [] # Select files to process depending on if the output files are explicitly # given or directory name is provided (all the output files there) if os.path.isdir(output_file): # Just the directory name is provided dirname = os.path.normpath(output_file) for file in os.listdir(dirname): # Add all LMAT output files in dir if ('_output' in file and file.endswith('.out') and 'canVfin' not in file and 'pyLCA' not in file): output_files.append(Filename(file)) else: # Explicit path and file name prefix is given dirname, basename = os.path.split(output_file) for file in os.listdir(dirname): # Add selected output files in dir if (file.startswith(basename) and file.endswith('.out') and 'canVfin' not in file and 'pyLCA' not in file): output_files.append(Filename(file)) if not output_files: raise Exception( f'\n\033[91mERROR!\033[0m Cannot read from "{output_file}"') # Read LMAT output files for output_name in output_files: path: Filename = Filename(os.path.join(dirname, output_name)) output.write(f'\033[90mLoading output file {path}...\033[0m') try: with open(path, 'r') as io_file: for seq in SeqIO.parse(io_file, "lmat"): tid: Id = seq.annotations['final_taxid'] score: Score = seq.annotations['final_score'] match: Match = Match.lmat(seq.annotations['final_match']) matchings[match] += 1 length: int = len(seq) nt_read += length if minscore is not None: if score < minscore: # Ignore read if low score continue if match in [Match.DIRECTMATCH, Match.MULTIMATCH]: try: all_scores[tid].append(score) except KeyError: all_scores[tid] = [ score, ] try: all_length[tid].append(length) except KeyError: all_length[tid] = [ length, ] except FileNotFoundError: raise Exception(red('\nERROR!') + f'Cannot read "{path}"') output.write(green('OK!\n')) abundances: Counter[Id] = Counter( {tid: len(all_scores[tid]) for tid in all_scores}) # Basic output statistics read_seqs: int = sum(matchings.values()) if read_seqs == 0: raise Exception( red('\nERROR! ') + f'Cannot read any sequence from"{output_file}"') filt_seqs: int = sum([len(scores) for scores in all_scores.values()]) if filt_seqs == 0: raise Exception(red('\nERROR! ') + 'No sequence passed the filter!') stat: SampleStats = SampleStats(minscore=minscore, nt_read=nt_read, scores=all_scores, lens=all_length, seq_read=read_seqs, seq_filt=filt_seqs, seq_clas=matchings[Match.DIRECT] + matchings[Match.MULTI]) output.write( gray(' Seqs read: ') + f'{stat.seq.read:_d}\t' + gray('[') + f'{stat.nt_read}' + gray(']\n')) output.write( gray(' Seqs clas: ') + f'{stat.seq.clas:_d}\t' + gray('(') + f'{stat.get_unclas_ratio():.2%}' + gray(' unclassified)\n')) output.write( gray(' Seqs pass: '******'{stat.seq.filt:_d}\t' + gray('(') + f'{stat.get_reject_ratio():.2%}' + gray(' rejected)\n')) multi_rel: float = matchings[Match.MULTI] / read_seqs direct_rel: float = matchings[Match.DIRECT] / read_seqs nodbhits_rel: float = matchings[Match.NODBHITS] / read_seqs tooshort_rel: float = matchings[Match.READTOOSHORT] / read_seqs lowscore_rel: float = matchings[Match.LOWSCORE] / read_seqs output.write(f'\033[90m DB Matching: ' f'Multi =\033[0m {multi_rel:.1%}\033[90m ' f'Direct =\033[0m {direct_rel:.1%}\033[90m ' f'ReadTooShort =\033[0m {tooshort_rel:.1%}\033[90m ' f'LowScore =\033[0m {lowscore_rel:.1%}\033[90m ' f'NoDbHits =\033[0m {nodbhits_rel:.1%}\033[90m\n') output.write( gray(' Scores: min = ') + f'{stat.sco.mini:.1f},' + gray(' max = ') + f'{stat.sco.maxi:.1f},' + gray(' avr = ') + f'{stat.sco.mean:.1f}\n') output.write( gray(' Length: min = ') + f'{stat.len.mini},' + gray(' max = ') + f'{stat.len.maxi},' + gray(' avr = ') + f'{stat.len.mean}\n') output.write(f' {stat.num_taxa}' + gray(f' taxa with assigned reads\n')) # Select score output out_scores: Dict[Id, Score] if scoring is Scoring.LMAT: out_scores = {tid: Score(mean(all_scores[tid])) for tid in all_scores} else: print(red('ERROR!'), f' LMAT: Unsupported Scoring "{scoring}"') raise Exception('Unsupported scoring') # Return return output.getvalue(), stat, abundances, out_scores
def generate_excel(): """Generate Excel with results via pandas DataFrame""" xlsx_name: Filename = Filename(htmlfile.split('.html')[0] + '.xlsx') print(gray(f'Generating Excel {str(excel).lower()} summary (') + magenta(xlsx_name) + gray(')... '), end='') sys.stdout.flush() xlsxwriter = pd.ExcelWriter(xlsx_name) list_rows: List = [] # Save raw samples basic statistics data_frame: pd.DataFrame = pd.DataFrame.from_dict( {raw: stats[raw].to_dict() for raw in raw_samples}) data_frame.to_excel(xlsxwriter, sheet_name='_sample_stats') # Save taxid related statistics per sample if excel is Excel.FULL: polytree.to_items(ontology=ncbi, items=list_rows) # Generate the pandas DataFrame from items and export to Excel iterable_1 = [samples, [COUNT, UNASSIGNED, SCORE]] cols1 = pd.MultiIndex.from_product(iterable_1, names=['Samples', 'Stats']) iterable_2 = [['Details'], ['Rank', 'Name']] cols2 = pd.MultiIndex.from_product(iterable_2) cols = cols1.append(cols2) data_frame = pd.DataFrame.from_items(list_rows, orient='index', columns=cols) data_frame.index.names = ['Id'] data_frame.to_excel(xlsxwriter, sheet_name=str(excel)) elif excel is Excel.CMPLXCRUNCHER: target_ranks: List = [Rank.NO_RANK] if args.controls: # if controls, add specific sheet for rank target_ranks.extend(Rank.selected_ranks) for rank in target_ranks: # Once for no rank dependency (NO_RANK) indexes: List[int] sheet_name: str columns: List[str] if args.controls: indexes = [ i for i in range(len(raw_samples), len(samples)) # Check if sample ends in _(STR_CONTROL)_(rank) if (STR_CONTROL in samples[i].split('_')[-2:] and rank.name.lower() in samples[i].split('_')[-1:]) ] sheet_name = f'{STR_CONTROL}_{rank.name.lower()}' columns = [ samples[i].replace( '_' + STR_CONTROL + '_' + rank.name.lower(), '') for i in indexes ] if rank is Rank.NO_RANK: # No rank dependency indexes = list(range(len(raw_samples))) sheet_name = f'raw_samples_{rank.name.lower()}' columns = raw_samples list_rows = [] polytree.to_items(ontology=ncbi, items=list_rows, sample_indexes=indexes) data_frame = pd.DataFrame.from_items(list_rows, orient='index', columns=columns) data_frame.index.names = ['Id'] data_frame.to_excel(xlsxwriter, sheet_name=sheet_name) else: raise Exception(red('\nERROR!'), f'Unknown Excel option "{excel}"') xlsxwriter.save() print(green('OK!'))
def read_output( output_file: Filename, scoring: Scoring = Scoring.SHEL, minscore: Score = None, ) -> Tuple[str, SampleStats, Counter[Id], Dict[Id, Score]]: """ Read Centrifuge output file Args: output_file: output file name scoring: type of scoring to be applied (see Scoring class) minscore: minimum confidence level for the classification Returns: log string, statistics, abundances counter, scores dict """ output: io.StringIO = io.StringIO(newline='') all_scores: Dict[Id, List[Score]] = {} all_length: Dict[Id, List[int]] = {} taxids: Set[Id] = set() num_read: int = 0 nt_read: int = 0 num_uncl: int = 0 last_error_read: int = -1 # Number of read of the last error num_errors: int = 0 # Number or reads discarded due to error output.write(gray(f'Loading output file {output_file}... ')) try: with open(output_file, 'r') as file: file.readline() # discard header for output_line in file: try: _, _, _tid, _score, _, _, _length, *_ = output_line.split( '\t') except ValueError: print( yellow('Failure'), 'parsing line elements:' f' {output_line} in {output_file}' '. Ignoring line!') last_error_read = num_read + 1 num_errors += 1 continue tid = Id(_tid) try: # From Centrifuge score get "single hit equivalent length" shel = Score(float(_score)**0.5 + 15) length = int(_length) except ValueError: print(yellow('Failure'), f'parsing score ({_score}) for ', f'query length {_length} for taxid {_tid}', f'in {output_file}. Ignoring line!') last_error_read = num_read + 1 num_errors += 1 continue num_read += 1 nt_read += length if tid == UNCLASSIFIED: # Just count unclassified reads num_uncl += 1 continue else: taxids.add(tid) # Save all the tids of classified reads if minscore is not None and shel < minscore: continue # Ignore read if low confidence try: all_scores[tid].append(shel) except KeyError: all_scores[tid] = [ shel, ] try: all_length[tid].append(length) except KeyError: all_length[tid] = [ length, ] except FileNotFoundError: raise Exception(red('\nERROR! ') + f'Cannot read "{output_file}"') if last_error_read == num_read + 1: # Check error in last line: truncated! print(yellow('Warning!'), f'{output_file} seems truncated!') counts: Counter[Id] = col.Counter( {tid: len(all_scores[tid]) for tid in all_scores}) output.write(green('OK!\n')) if num_read == 0: raise Exception( red('\nERROR! ') + f'Cannot read any sequence from "{output_file}"') filt_seqs: int = sum([len(scores) for scores in all_scores.values()]) if filt_seqs == 0: raise Exception(red('\nERROR! ') + 'No sequence passed the filter!') # Get statistics stat: SampleStats = SampleStats(minscore=minscore, nt_read=nt_read, scores=all_scores, lens=all_length, seq_read=num_read, seq_unclas=num_uncl, seq_filt=filt_seqs, tid_clas=len(taxids)) # Output statistics if num_errors: output.write( gray(' Seqs fail: ') + red(f'{num_errors:_d}\t') + gray('(Last error in read ') + red(f'{last_error_read}') + gray(')\n')) output.write( gray(' Seqs read: ') + f'{stat.seq.read:_d}\t' + gray('[') + f'{stat.nt_read}' + gray(']\n')) output.write( gray(' Seqs clas: ') + f'{stat.seq.clas:_d}\t' + gray('(') + f'{stat.get_unclas_ratio():.2%}' + gray(' unclassified)\n')) output.write( gray(' Seqs pass: '******'{stat.seq.filt:_d}\t' + gray('(') + f'{stat.get_reject_ratio():.2%}' + gray(' rejected)\n')) output.write( gray(' Scores: min = ') + f'{stat.sco.mini:.1f}' + gray(', max = ') + f'{stat.sco.maxi:.1f}' + gray(', avr = ') + f'{stat.sco.mean:.1f}\n') output.write( gray(' Length: min = ') + f'{stat.len.mini}' + gray(', max = ') + f'{stat.len.maxi}' + gray(', avr = ') + f'{stat.len.mean}\n') output.write( gray(' TaxIds: by classifier = ') + f'{stat.tid.clas}' + gray(', by filter = ') + f'{stat.tid.filt}\n') # Select score output out_scores: Dict[Id, Score] if scoring is Scoring.SHEL: out_scores = {tid: Score(mean(all_scores[tid])) for tid in all_scores} elif scoring is Scoring.LENGTH: out_scores = {tid: Score(mean(all_length[tid])) for tid in all_length} elif scoring is Scoring.LOGLENGTH: out_scores = { tid: Score(log10(mean(all_length[tid]))) for tid in all_length } elif scoring is Scoring.NORMA: scores: Dict[Id, Score] = { tid: Score(mean(all_scores[tid])) for tid in all_scores } lengths: Dict[Id, Score] = { tid: Score(mean(all_length[tid])) for tid in all_length } out_scores = { tid: Score(scores[tid] / lengths[tid] * 100) for tid in scores } else: print(red('ERROR!'), f' Centrifuge: Unsupported Scoring "{scoring}"') raise Exception('Unsupported scoring') # Return return output.getvalue(), stat, counts, out_scores
def read_generic_output( output_file: Filename, scoring: Scoring = Scoring.GENERIC, minscore: Score = None, genfmt: GenericFormat = None ) -> Tuple[str, SampleStats, Counter[Id], Dict[Id, Score]]: """ Read an output file from a generic classifier Args: output_file: output file name scoring: type of scoring to be applied (see Scoring class) minscore: minimum confidence level for the classification genfmt: GenericFormat object specifying the files format Returns: log string, statistics, abundances counter, scores dict """ # Initialization of variables output: io.StringIO = io.StringIO(newline='') all_scores: Dict[Id, List[Score]] = {} all_length: Dict[Id, List[int]] = {} taxids: Set[Id] = set() num_read: int = 0 nt_read: int = 0 num_uncl: int = 0 last_error_read: int = -1 # Number of read of the last error num_errors: int = 0 # Number or reads discarded due to error output.write(gray(f'Loading output file {output_file}... ')) # Check format if not isinstance(genfmt, GenericFormat): raise Exception( red('\nERROR!'), 'Missing GenericFormat when reading a generic output.') try: with open(output_file, 'r') as file: # Main loop processing each file line for raw_line in file: raw_line = raw_line.strip(' \n\t') splitting: str if genfmt.typ is GenericType.CSV: splitting = ',' elif genfmt.typ is GenericType.TSV: splitting = '\t' elif genfmt.typ is GenericType.SSV: splitting = ' ' else: raise Exception(f'ERROR! Unknown GenericType {genfmt.typ}') output_line: List[str] = raw_line.split(splitting) if len(output_line) < GenericFormat.MIN_COLS: if num_read == 0 and last_error_read < 0: last_error_read = 0 print(yellow('Warning!'), 'Skipping header of ' f'{output_file}') continue # Not account for the header as an error raise Exception( red('\nERROR!') + ' Line ' + yellow(f'{output_line}') + '\n\tin ' + yellow(f'{output_file}') + ' has < ' + blue(f'{GenericFormat.MIN_COLS}') + ' required ' + 'columns.\n\tPlease check the file.') try: tid: Id = Id(output_line[genfmt.tid - 1].strip(' "')) length: int = int(output_line[genfmt.len - 1].strip(' "')) if tid == genfmt.unc: # Avoid read score for unclass reads num_read += 1 nt_read += length num_uncl += 1 continue score: Score = Score( float(output_line[genfmt.sco - 1].strip(' "'))) except ValueError: if num_read == 0 and last_error_read < 0: last_error_read = 0 print(yellow('Warning!'), 'Skipping header of ' f'{output_file}') continue # Not account for the header as a failure print( yellow('Failure'), 'parsing line elements:' f' {output_line} in {output_file}' '. Ignoring line!') last_error_read = num_read + 1 num_errors += 1 if num_read > 100 and num_errors > 0.5 * num_read: print( red('ERROR!'), 'Unreliable file processing: rate of problematic' f' reads is {num_errors/num_read*100:_d}, beyond' ' 50%, after 100 reads. Please check the format ' f'of the file "{output_file}".') raise else: continue num_read += 1 nt_read += length taxids.add(tid) # Save all the tids of classified reads if minscore is not None and score < minscore: continue # Discard read if low confidence try: all_scores[tid].append(score) except KeyError: all_scores[tid] = [ score, ] try: all_length[tid].append(length) except KeyError: all_length[tid] = [ length, ] except FileNotFoundError: raise Exception(red('\nERROR! ') + f'Cannot read "{output_file}"') if last_error_read == num_read + 1: # Check error in last line: truncated! print(yellow('Warning!'), f'{output_file} seems truncated!') counts: Counter[Id] = col.Counter( {tid: len(all_scores[tid]) for tid in all_scores}) output.write(green('OK!\n')) if num_read == 0: raise Exception( red('\nERROR! ') + f'Cannot read any sequence from "{output_file}"') filt_seqs: int = sum([len(scores) for scores in all_scores.values()]) if filt_seqs == 0: raise Exception(red('\nERROR! ') + 'No sequence passed the filter!') # Get statistics stat: SampleStats = SampleStats(minscore=minscore, nt_read=nt_read, lens=all_length, scores=all_scores, seq_read=num_read, seq_unclas=num_uncl, seq_filt=filt_seqs, tid_clas=len(taxids)) # Output statistics if num_errors: output.write( gray(' Seqs fail: ') + red(f'{num_errors:_d}\t') + gray('(Last error in read ') + red(f'{last_error_read}') + gray(')\n')) output.write( gray(' Seqs read: ') + f'{stat.seq.read:_d}\t' + gray('[') + f'{stat.nt_read}' + gray(']\n')) output.write( gray(' Seqs clas: ') + f'{stat.seq.clas:_d}\t' + gray('(') + f'{stat.get_unclas_ratio():.2%}' + gray(' unclassified)\n')) output.write( gray(' Seqs pass: '******'{stat.seq.filt:_d}\t' + gray('(') + f'{stat.get_reject_ratio():.2%}' + gray(' rejected)\n')) output.write( gray(' Scores: min = ') + f'{stat.sco.mini:.1f},' + gray(' max = ') + f'{stat.sco.maxi:.1f},' + gray(' avr = ') + f'{stat.sco.mean:.1f}\n') output.write( gray(' Read length: min = ') + f'{stat.len.mini},' + gray(' max = ') + f'{stat.len.maxi},' + gray(' avr = ') + f'{stat.len.mean}\n') output.write( gray(' TaxIds: by classifier = ') + f'{stat.tid.clas}' + gray(', by filter = ') + f'{stat.tid.filt}\n') # Select score output out_scores: Dict[Id, Score] if scoring is Scoring.GENERIC: out_scores = {tid: Score(mean(all_scores[tid])) for tid in all_scores} elif scoring is Scoring.LENGTH: out_scores = {tid: Score(mean(all_length[tid])) for tid in all_length} elif scoring is Scoring.LOGLENGTH: out_scores = { tid: Score(log10(mean(all_length[tid]))) for tid in all_length } elif scoring is Scoring.NORMA: scores: Dict[Id, Score] = { tid: Score(mean(all_scores[tid])) for tid in all_scores } lengths: Dict[Id, Score] = { tid: Score(mean(all_length[tid])) for tid in all_length } out_scores = { tid: Score(scores[tid] / lengths[tid] * 100) for tid in scores } else: raise Exception(red('\nERROR!'), f'Generic: Unsupported Scoring "{scoring}"') # Return return output.getvalue(), stat, counts, out_scores