def modisco_score(modisco_dir, imp_scores, output_tsv, output_seqlets_pkl=None, seqlet_len=25, n_cores=1, method="rank", trim_pattern=False): """Find seqlet instances using modisco """ add_file_logging(os.path.dirname(output_tsv), logger, 'modisco-score') mr, tasks, grad_type = load_modisco_results(modisco_dir) # load importance scores we want to score d = HDF5Reader.load(imp_scores) if 'hyp_imp' not in d: # backcompatibility d['hyp_imp'] = d['grads'] if isinstance(d['inputs'], dict): one_hot = d['inputs']['seq'] else: one_hot = d['inputs'] hypothetical_contribs = { f"{task}/{gt}": mean(d['hyp_imp'][task][gt]) for task in tasks for gt in grad_type.split(",") } contrib_scores = { f"{task}/{gt}": hypothetical_contribs[f"{task}/{gt}"] * one_hot for task in tasks for gt in grad_type.split(",") } seqlets = find_instances(mr, tasks, contrib_scores, hypothetical_contribs, one_hot, seqlet_len=seqlet_len, n_cores=n_cores, method=method, trim_pattern=trim_pattern) if len(seqlets) == 0: print("ERROR: no seqlets found!!") return [], None if output_seqlets_pkl: write_pkl(seqlets, output_seqlets_pkl) df = labelled_seqlets2df(seqlets) dfm = pd.DataFrame(d['metadata']['range']) dfm.columns = ["example_" + v for v in dfm.columns] df = df.merge(dfm, left_on="example_idx", how='left', right_on="example_id") df.to_csv(output_tsv, sep='\t') return seqlets, df
def modisco_table(modisco_dir, output_dir, report_url=None, impsf=None): """Write the pattern table to as .html and .csv """ plt.switch_backend('agg') from basepair.modisco.table import ModiscoData, modisco_table, write_modisco_table from basepair.modisco.motif_clustering import hirearchically_reorder_table add_file_logging(output_dir, logger, 'modisco-table') print("Loading required data") data = ModiscoData.load(modisco_dir, imp_scores_h5=None, impsf=impsf) print("Generating the table") df = modisco_table(data) print("Writing the results") write_modisco_table(df, output_dir, report_url, 'pattern_table') print("Writing clustered table") write_modisco_table(hirearchically_reorder_table(df, data.tasks), output_dir, report_url, 'pattern_table.sorted') print("Writing footprints") profiles = OrderedDict([(pattern, { task: data.get_profile_wide(pattern, task).mean(axis=0) for task in data.tasks }) for pattern in data.mr.patterns()]) write_pkl(profiles, Path(output_dir) / 'footprints.pkl') print("Done!")
def modisco_centroid_seqlet_matches2(modisco_dir, imp_scores, output_dir=None, trim_frac=0.08, n_jobs=1, data_class='profile'): """Write pattern matches to .csv """ from basepair.modisco.table import ModiscoData, ModiscoDataSingleBinary if (output_dir is None): output_dir = modisco_dir add_file_logging(output_dir, logger, 'centroid-seqlet-matches') logger.info("Loading required data") if (data_class == 'profile'): data = ModiscoData.load(modisco_dir, imp_scores) else: data = ModiscoDataSingleBinary.load(modisco_dir) logger.info("Generating the table") df = data.get_centroid_seqlet_matches(trim_frac=trim_frac, n_jobs=n_jobs) df.to_csv(os.path.join(output_dir, 'centroid_seqlet_matches.csv')) return None
def modisco2bed(modisco_dir, output_dir, trim_frac=0.08): from pybedtools import Interval from basepair.modisco.results import ModiscoResult add_file_logging(output_dir, logger, 'modisco2bed') ranges = load_ranges(modisco_dir) example_intervals = [ Interval(row.chrom, row.start, row.end) for i, row in ranges.iterrows() ] r = ModiscoResult(os.path.join(modisco_dir, "modisco.h5")) r.export_seqlets_bed(output_dir, example_intervals=example_intervals, position='absolute', trim_frac=trim_frac) r.close()
def modisco_centroid_seqlet_matches(modisco_dir, imp_scores, output_dir, trim_frac=0.08, n_jobs=1, impsf=None): """Write pattern matches to .csv """ from basepair.modisco.table import ModiscoData assert os.path.exists(output_dir) add_file_logging(output_dir, logger, 'centroid-seqlet-matches') logger.info("Loading required data") data = ModiscoData.load(modisco_dir, imp_scores, impsf=impsf) logger.info("Generating the table") df = data.get_centroid_seqlet_matches(trim_frac=trim_frac, n_jobs=n_jobs) df.to_csv(os.path.join(output_dir, 'centroid_seqlet_matches.csv'))
def imp_score(model_dir, output_file, method="grad", split='all', batch_size=512, num_workers=10, h5_chunk_size=512, max_batches=-1, shuffle_seq=False, memfrac=0.45, exclude_chr='', overwrite=False, gpu=None): """Run importance scores for a BPNet model Args: model_dir: path to the model directory output_file: output file path (HDF5 format) method: which importance scoring method to use ('grad', 'deeplift' or 'ism') split: for which dataset split to compute the importance scores h5_chunk_size: hdf5 chunk size. exclude_chr: comma-separated list of chromosomes to exclude overwrite: if True, overwrite the output directory gpu (int): which GPU to use locally. If None, GPU is not used """ add_file_logging(os.path.dirname(output_file), logger, 'modisco-score') if gpu is not None: create_tf_session(gpu, per_process_gpu_memory_fraction=memfrac) else: # Don't use any GPU's os.environ['CUDA_VISIBLE_DEVICES'] = '' if os.path.exists(output_file): if overwrite: os.remove(output_file) else: raise ValueError(f"File exists {output_file}. Use overwrite=True to overwrite it") if exclude_chr: exclude_chr = exclude_chr.split(",") else: exclude_chr = [] # load the config files logger.info("Loading the config files") model_dir = Path(model_dir) hp = HParams.load(model_dir / "hparams.yaml") ds = DataSpec.load(model_dir / "dataspec.yaml") tasks = list(ds.task_specs) # validate that the correct dataset was used if hp.data.name != 'get_StrandedProfile_datasets': logger.warn("hp.data.name != 'get_StrandedProfile_datasets'") if split == 'valid': assert len(exclude_chr) == 0 incl_chromosomes = hp.data.kwargs['valid_chr'] excl_chromosomes = None elif split == 'test': assert len(exclude_chr) == 0 incl_chromosomes = hp.data.kwargs['test_chr'] excl_chromosomes = None elif split == 'train': assert len(exclude_chr) == 0 incl_chromosomes = None excl_chromosomes = hp.data.kwargs['valid_chr'] + hp.data.kwargs['test_chr'] + hp.data.kwargs.get('exclude_chr', []) elif split == 'all': incl_chromosomes = None excl_chromosomes = hp.data.kwargs.get('exclude_chr', []) + exclude_chr logger.info("Excluding chromosomes: {excl_chromosomes}") else: raise ValueError("split needs to be from {train,valid,test,all}") logger.info("Creating the dataset") from basepair.datasets import StrandedProfile seq_len = hp.data.kwargs['peak_width'] dl_valid = StrandedProfile(ds, incl_chromosomes=incl_chromosomes, excl_chromosomes=excl_chromosomes, peak_width=seq_len, shuffle=False, target_transformer=None) bpnet = BPNet.from_mdir(model_dir) writer = HDF5BatchWriter(output_file, chunk_size=h5_chunk_size) for i, batch in enumerate(tqdm(dl_valid.batch_iter(batch_size=batch_size, num_workers=num_workers))): if max_batches > 0: logging.info(f"max_batches: {max_batches} exceeded. Stopping the computation") if i > max_batches: break # append the bias model predictions # (batch['inputs'], batch['targets']) = bm((batch['inputs'], batch['targets'])) # store the original batch containing 'inputs' and 'targets' wdict = batch if shuffle_seq: # Di-nucleotide shuffle the sequences if 'seq' in batch['inputs']: batch['inputs']['seq'] = onehot_dinucl_shuffle(batch['inputs']['seq']) else: batch['inputs'] = onehot_dinucl_shuffle(batch['inputs']) # loop through all tasks, pred_summary and strands for task_i, task in enumerate(tasks): for pred_summary in ['count', 'weighted']: # figure out the number of channels nstrands = batch['targets'][f'profile/{task}'].shape[-1] strand_hash = ["pos", "neg"] for strand_i in range(nstrands): hyp_imp = bpnet.imp_score(batch['inputs'], task=task, strand=strand_hash[strand_i], method=method, pred_summary=pred_summary, batch_size=None) # don't second-batch # put importance scores to the dictionary wdict[f"/hyp_imp/{task}/{pred_summary}/{strand_i}"] = hyp_imp writer.batch_write(wdict) writer.close()
def imp_score_seqmodel(model_dir, output_file, dataspec=None, peak_width=1000, seq_width=None, intp_pattern='*', # specifies which imp. scores to compute # skip_trim=False, # skip trimming the output method="deeplift", batch_size=512, max_batches=-1, shuffle_seq=False, memfrac=0.45, num_workers=10, h5_chunk_size=512, exclude_chr='', include_chr='', overwrite=False, skip_bias=False, gpu=None): """Run importance scores for a BPNet model Args: model_dir: path to the model directory output_file: output file path (HDF5 format) method: which importance scoring method to use ('grad', 'deeplift' or 'ism') split: for which dataset split to compute the importance scores h5_chunk_size: hdf5 chunk size. exclude_chr: comma-separated list of chromosomes to exclude overwrite: if True, overwrite the output directory skip_bias: if True, don't store the bias tracks in teh output gpu (int): which GPU to use locally. If None, GPU is not used """ add_file_logging(os.path.dirname(output_file), logger, 'modisco-score-seqmodel') if gpu is not None: create_tf_session(gpu, per_process_gpu_memory_fraction=memfrac) else: # Don't use any GPU's os.environ['CUDA_VISIBLE_DEVICES'] = '' if os.path.exists(output_file): if overwrite: os.remove(output_file) else: raise ValueError(f"File exists {output_file}. Use overwrite=True to overwrite it") if seq_width is None: logger.info("Using seq_width = peak_width") seq_width = peak_width # make sure these are int's seq_width = int(seq_width) peak_width = int(peak_width) # Split intp_patterns = intp_pattern.split(",") # Allow chr inclusion / exclusion if exclude_chr: exclude_chr = exclude_chr.split(",") else: exclude_chr = None if include_chr: include_chr = include_chr.split(",") else: include_chr = None logger.info("Loading the config files") model_dir = Path(model_dir) if dataspec is None: # Specify dataspec dataspec = model_dir / "dataspec.yaml" ds = DataSpec.load(dataspec) logger.info("Creating the dataset") from basepair.datasets import StrandedProfile dl_valid = StrandedProfile(ds, incl_chromosomes=include_chr, excl_chromosomes=exclude_chr, peak_width=peak_width, seq_width=seq_width, shuffle=False, taskname_first=True, # Required to work nicely with imp-score target_transformer=None) # Setup importance score trimming if seq_width > peak_width: # Trim # make sure we can nicely trim the peak logger.info("Trimming the output") assert (seq_width - peak_width) % 2 == 0 trim_start = (seq_width - peak_width) // 2 trim_end = seq_width - trim_start assert trim_end - trim_start == peak_width elif seq_width == peak_width: trim_start = 0 trim_end = peak_width else: raise ValueError("seq_width < peak_width") seqmodel = SeqModel.from_mdir(model_dir) # get all possible interpretation names # make sure they match the specified glob intp_names = [name for name, _ in seqmodel.get_intp_tensors(preact_only=False) if fnmatch_any(name, intp_patterns)] logger.info(f"Using the following interpretation targets:") for n in intp_names: print(n) writer = HDF5BatchWriter(output_file, chunk_size=h5_chunk_size) for i, batch in enumerate(tqdm(dl_valid.batch_iter(batch_size=batch_size, num_workers=num_workers))): # store the original batch containing 'inputs' and 'targets' wdict = batch if skip_bias: wdict['inputs'] = {'seq': wdict['inputs']['seq']} # ignore all other inputs if max_batches > 0: logging.info(f"max_batches: {max_batches} exceeded. Stopping the computation") if i > max_batches: break if shuffle_seq: # Di-nucleotide shuffle the sequences batch['inputs']['seq'] = onehot_dinucl_shuffle(batch['inputs']['seq']) for name in intp_names: hyp_imp = seqmodel.imp_score(batch['inputs']['seq'], name=name, method=method, batch_size=None) # don't second-batch # put importance scores to the dictionary # also trim the importance scores appropriately so that # the output will always be w.r.t. the peak center wdict[f"/hyp_imp/{name}"] = hyp_imp[:, trim_start:trim_end] # trim the sequence as well if isinstance(wdict['inputs'], dict): # Trim the sequence wdict['inputs']['seq'] = wdict['inputs']['seq'][:, trim_start:trim_end] else: wdict['inputs'] = wdict['inputs'][:, trim_start:trim_end] writer.batch_write(wdict) writer.close()
def modisco_instances_to_bed(modisco_h5, instances_parq, imp_score_h5, output_dir, trim_frac=0.08): from basepair.modisco.pattern_instances import load_instances add_file_logging(output_dir, logger, 'modisco-instances-to-bed') output_dir = Path(output_dir) output_dir.mkdir(parents=True, exist_ok=True) mr = ModiscoResult(modisco_h5) mr.open() print("load task_id") d = HDF5Reader(imp_score_h5) d.open() if 'hyp_imp' not in d.f.keys(): # backcompatibility d['hyp_imp'] = d['grads'] id_hash = pd.DataFrame({ "peak_id": d.f['/metadata/interval_from_task'][:], "example_idx": np.arange(d.f['/metadata/interval_from_task'].shape[0]) }) # load the instances data frame print("load all instances") df = load_instances(instances_parq, motifs=None, dedup=True) # import pdb # pdb.set_trace() df = df.merge(id_hash, on="example_idx") # append peak_id patterns = df.pattern.unique().tolist() pattern_pssms = { pattern: mr.get_pssm(*pattern.split("/")) for pattern in patterns } append_pattern_loc(df, pattern_pssms, trim_frac=trim_frac) # write out the results example_cols = [ 'example_chr', 'example_start', 'example_end', 'example_id', 'peak_id' ] df_examples = df[example_cols].drop_duplicates().sort_values( ["example_chr", "example_start"]) df_examples.to_csv(output_dir / "scored_regions.bed", sep='\t', header=False, index=False) df["pattern_start_rel"] = df.pattern_start + df.example_start df["pattern_end_rel"] = df.pattern_end + df.example_start df["strand"] = df.revcomp.astype(bool).map({True: "-", False: "+"}) # TODO - update this - ? pattern_cols = [ 'example_chr', 'pattern_start_rel', 'pattern_end_rel', 'example_id', 'percnormed_score', 'strand', 'peak_id', 'seqlet_score' ] (output_dir / "README").write_text("score_regions.bed columns: " + ", ".join(example_cols) + "\n" + "metacluster_<>/pattern_<>.bed columns: " + ", ".join(pattern_cols)) df_pattern = df[pattern_cols] for pattern in df.pattern.unique(): out_path = output_dir / (pattern + ".bed.gz") out_path.parent.mkdir(parents=True, exist_ok=True) dfp = df_pattern[df.pattern == pattern].drop_duplicates().sort_values( ["example_chr", "pattern_start_rel"]) dfp.to_csv(out_path, compression='gzip', sep='\t', header=False, index=False)
def modisco_score2(modisco_dir, output_file, trim_frac=0.08, imp_scores=None, importance=None, ignore_filter=False, n_jobs=20): """Modisco score instances Args: modisco_dir: modisco directory - used to obtain centroid_seqlet_matches.csv and modisco.h5 output_file: output file path for the tsv file. If the suffix is tsv.gz, then also gzip the file trim_frac: how much to trim the pattern when scanning imp_scores: hdf5 file of importance scores (contains `importance` score) if None, then load the default importance scores from modisco importance: which importance scores to use n_jobs: number of parallel jobs to use Writes a gzipped tsv file(tsv.gz) """ add_file_logging(os.path.dirname(output_file), logger, 'modisco-score2') modisco_dir = Path(modisco_dir) modisco_kwargs = read_json(f"{modisco_dir}/kwargs.json") if importance is None: importance = modisco_kwargs['grad_type'] # Centroid matches cm_path = modisco_dir / 'centroid_seqlet_matches.csv' if not cm_path.exists(): logger.info(f"Generating centroid matches to {cm_path.resolve()}") modisco_centroid_seqlet_matches(modisco_dir, imp_scores, modisco_dir, trim_frac=trim_frac, n_jobs=n_jobs) logger.info(f"Loading centroid matches from {cm_path.resolve()}") dfm_norm = pd.read_csv(cm_path) mr = ModiscoResult(modisco_dir / "modisco.h5") mr.open() tasks = mr.tasks() # HACK prune the tasks of importance (in case it's present) tasks = [t.replace(f"/{importance}", "") for t in tasks] logger.info(f"Using tasks: {tasks}") if imp_scores is not None: logger.info(f"Loading the importance scores from: {imp_scores}") imp = ImpScoreFile(imp_scores, default_imp_score=importance) else: imp = ImpScoreFile.from_modisco_dir( modisco_dir, ignore_include_samples=ignore_filter) seq, contrib, hyp_contrib, profile, ranges = imp.get_all() logger.info("Scanning for patterns") dfl = [] for pattern_name in tqdm(mr.patterns()): pattern = mr.get_pattern(pattern_name).trim_seq_ic(trim_frac) match, importance = pattern.scan_importance(contrib, hyp_contrib, tasks, n_jobs=n_jobs, verbose=False) seq_match = pattern.scan_seq(seq, n_jobs=n_jobs, verbose=False) dfm = pattern.get_instances( tasks, match, importance, seq_match, norm_df=dfm_norm[dfm_norm.pattern == pattern_name], verbose=False, plot=False) dfl.append(dfm) logger.info("Merging") # merge and write the results dfp = pd.concat(dfl) # append the ranges logger.info("Append ranges") ranges.columns = ["example_" + v for v in ranges.columns] dfp = dfp.merge(ranges, on="example_idx", how='left') logger.info("Table info") dfp.info() logger.info( f"Writing the resuling pd.DataFrame of shape {dfp.shape} to {output_file}" ) # write to a parquet file dfp.to_parquet(output_file, partition_on=['pattern'], engine='fastparquet') logger.info("Done!")
def modisco_plot( modisco_dir, output_dir, # filter_npy=None, # ignore_dist_filter=False, figsize=(10, 10), impsf=None): """Plot the results of a modisco run Args: modisco_dir: modisco directory output_dir: Output directory for writing the results figsize: Output figure size impsf: [optional] modisco importance score file (ImpScoreFile) """ plt.switch_backend('agg') add_file_logging(output_dir, logger, 'modisco-plot') from basepair.plot.vdom import write_heatmap_pngs from basepair.plot.profiles import plot_profiles from basepair.utils import flatten output_dir = Path(output_dir) output_dir.parent.mkdir(parents=True, exist_ok=True) # load modisco mr = ModiscoResult(f"{modisco_dir}/modisco.h5") if impsf is not None: d = impsf else: d = ImpScoreFile.from_modisco_dir(modisco_dir) logger.info("Loading the importance scores") d.cache() # load all thr_one_hot = d.get_seq() # thr_hypothetical_contribs tracks = d.get_profiles() thr_hypothetical_contribs = dict() thr_contrib_scores = dict() # TODO - generalize this thr_hypothetical_contribs['weighted'] = d.get_hyp_contrib() thr_contrib_scores['weighted'] = d.get_contrib() tasks = d.get_tasks() # Count importance (if it exists) if d.contains_imp_score("counts/pre-act"): count_imp_score = "counts/pre-act" thr_hypothetical_contribs['count'] = d.get_hyp_contrib( imp_score=count_imp_score) thr_contrib_scores['count'] = d.get_contrib(imp_score=count_imp_score) elif d.contains_imp_score("count"): count_imp_score = "count" thr_hypothetical_contribs['count'] = d.get_hyp_contrib( imp_score=count_imp_score) thr_contrib_scores['count'] = d.get_contrib(imp_score=count_imp_score) else: # Don't do anything pass thr_hypothetical_contribs = OrderedDict( flatten(thr_hypothetical_contribs, separator='/')) thr_contrib_scores = OrderedDict(flatten(thr_contrib_scores, separator='/')) # # load importance scores # modisco_kwargs = read_json(f"{modisco_dir}/kwargs.json") # d = HDF5Reader.load(modisco_kwargs['imp_scores']) # if 'hyp_imp' not in d: # # backcompatibility # d['hyp_imp'] = d['grads'] # tasks = list(d['targets']['profile']) # if isinstance(d['inputs'], dict): # one_hot = d['inputs']['seq'] # else: # one_hot = d['inputs'] # # load used strand distance filter # included_samples = load_included_samples(modisco_dir) # grad_type = "count,weighted" # always plot both importance scores # thr_hypothetical_contribs = OrderedDict([(f"{gt}/{task}", mean(d['hyp_imp'][task][gt])[included_samples]) # for task in tasks # for gt in grad_type.split(",")]) # thr_one_hot = one_hot[included_samples] # thr_contrib_scores = OrderedDict([(f"{gt}/{task}", thr_hypothetical_contribs[f"{gt}/{task}"] * thr_one_hot) # for task in tasks # for gt in grad_type.split(",")]) # tracks = OrderedDict([(task, d['targets']['profile'][task][included_samples]) for task in tasks]) # ------------------------------------------------- all_seqlets = mr.seqlets() all_patterns = mr.patterns() if len(all_patterns) == 0: print("No patterns found") return # 1. Plots with tracks and contrib scores print("Writing results for contribution scores") plot_profiles(all_seqlets, thr_one_hot, tracks=tracks, importance_scores=thr_contrib_scores, legend=False, flip_neg=True, rotate_y=0, seq_height=.5, patterns=all_patterns, n_bootstrap=100, fpath_template=str(output_dir / "{pattern}/agg_profile_contribcores"), mkdir=True, figsize=figsize) # 2. Plots only with hypothetical contrib scores print("Writing results for hypothetical contribution scores") plot_profiles(all_seqlets, thr_one_hot, tracks={}, importance_scores=thr_hypothetical_contribs, legend=False, flip_neg=True, rotate_y=0, seq_height=1, patterns=all_patterns, n_bootstrap=100, fpath_template=str(output_dir / "{pattern}/agg_profile_hypcontribscores"), figsize=figsize) print("Plotting heatmaps") for pattern in tqdm(all_patterns): write_heatmap_pngs(all_seqlets[pattern], d, tasks, pattern, output_dir=str(output_dir / pattern)) mr.close()
def modisco_run( imp_scores, output_dir, null_imp_scores=None, hparams=None, override_hparams="", grad_type="weighted", subset_tasks=None, filter_subset_tasks=False, filter_npy=None, exclude_chr="", seqmodel=False, # interpretation glob # hparams=None, num_workers=10, max_strand_distance=0.1, overwrite=False, skip_dist_filter=False, use_all_seqlets=False, merge_tasks=False, gpu=None, ): """ Run modisco Args: imp_scores: path to the hdf5 file of importance scores null_imp_scores: Path to the null importance scores grad_type: for which output to compute the importance scores hparams: None, modisco hyper - parameeters: either a path to modisco.yaml or a ModiscoHParams object override_hparams: hyper - parameters overriding the settings in the hparams file output_dir: output file directory filter_npy: path to a npy file containing a boolean vector used for subsetting exclude_chr: comma-separated list of chromosomes to exclude seqmodel: If enabled, then the importance scores came from `imp-score-seqmodel` subset_tasks: comma-separated list of task names to use as a subset filter_subset_tasks: if True, run modisco only in the regions for that TF hparams: hyper - parameter file summary: which summary statistic to use for the profile gradients skip_dist_filter: if True, distances are not used to filter use_all_seqlets: if True, don't restrict the number of seqlets split: On which data split to compute the results merge_task: if True, importance scores for the tasks will be merged gpu: which gpu to use. If None, don't use any GPU's Note: when using subset_tasks, modisco will run on all the importance scores. If you wish to run it only for the importance scores for a particular task you should subset it to the peak regions of interest using `filter_npy` """ plt.switch_backend('agg') add_file_logging(output_dir, logger, 'modisco-run') import os if gpu is not None: create_tf_session(gpu) else: # Don't use any GPU's os.environ['CUDA_VISIBLE_DEVICES'] = '' os.environ['MKL_THREADING_LAYER'] = 'GNU' # import theano import modisco import modisco.tfmodisco_workflow.workflow if seqmodel: assert '/' in grad_type if subset_tasks == '': logger.warn("subset_tasks == ''. Not using subset_tasks") subset_tasks = None if subset_tasks == 'all': # Use all subset tasks e.g. don't subset subset_tasks = None if subset_tasks is not None: subset_tasks = subset_tasks.split(",") if len(subset_tasks) == 0: raise ValueError("Provide one or more subset_tasks. Found None") if filter_subset_tasks and subset_tasks is None: print("Using filter_subset_tasks=False since `subset_tasks` is None") filter_subset_tasks = False if exclude_chr: exclude_chr = exclude_chr.split(",") else: exclude_chr = [] output_dir = Path(output_dir) output_dir.mkdir(parents=True, exist_ok=True) output_path = output_dir / "modisco.h5" remove_exists(output_path, overwrite) output_distances = output_dir / "strand_distances.h5" remove_exists(output_distances, overwrite) if filter_npy is not None: filter_npy = os.path.abspath(filter_npy) # save the hyper-parameters write_json( dict( imp_scores=os.path.abspath(imp_scores), grad_type=grad_type, output_dir=str(output_dir), subset_tasks=subset_tasks, filter_subset_tasks=filter_subset_tasks, hparams=hparams, null_imp_scores=null_imp_scores, # TODO - pack into hyper-parameters as well? filter_npy=filter_npy, exclude_chr=",".join(exclude_chr), skip_dist_filter=skip_dist_filter, use_all_seqlets=use_all_seqlets, max_strand_distance=max_strand_distance, gpu=gpu), os.path.join(output_dir, "kwargs.json")) print("-" * 40) # parse the hyper-parameters if hparams is None: print(f"Using default hyper-parameters") hp = ModiscoHParams() else: if isinstance(hparams, str): print(f"Loading hyper-parameters from file: {hparams}") hp = ModiscoHParams.load(hparams) else: assert isinstance(hparams, ModiscoHParams) hp = hparams if override_hparams: print(f"Overriding the following hyper-parameters: {override_hparams}") hp = tf.contrib.training.HParams( **hp.get_modisco_kwargs()).parse(override_hparams) if use_all_seqlets: hp.max_seqlets_per_metacluster = None # save the hyper-parameters print("Using the following hyper-parameters for modisco:") print("-" * 40) related_dump_yaml(ModiscoHParams(**hp.values()), os.path.join(output_dir, "hparams.yaml"), verbose=True) print("-" * 40) # TODO - replace with imp_scores d = HDF5Reader.load(imp_scores) if 'hyp_imp' not in d: # backcompatibility d['hyp_imp'] = d['grads'] if seqmodel: tasks = list(d['targets']) else: tasks = list(d['targets']['profile']) if subset_tasks is not None: # validate that all the `subset_tasks` # are present in `tasks` for st in subset_tasks: if st not in tasks: raise ValueError( f"subset task {st} not found in tasks: {tasks}") logger.info( f"Using the following tasks: {subset_tasks} instead of the original tasks: {tasks}" ) tasks = subset_tasks if isinstance(d['inputs'], dict): one_hot = d['inputs']['seq'] else: one_hot = d['inputs'] n = len(one_hot) # -------------------- # apply filters if not skip_dist_filter: print("Using profile prediction for the strand filtering") grad_type_filtered = 'weighted' distances = np.array([ np.array([ correlation( np.ravel(d['hyp_imp'][task][grad_type_filtered][0][i]), np.ravel(d['hyp_imp'][task][grad_type_filtered][1][i])) for i in range(n) ]) for task in tasks if len(d['hyp_imp'][task][grad_type_filtered]) == 2 ]).T.mean(axis=-1) # average the distances across tasks dist_filter = distances < max_strand_distance print(f"Fraction of sequences kept: {dist_filter.mean()}") HDF5BatchWriter.dump(output_distances, { "distances": distances, "included_samples": dist_filter }) else: dist_filter = np.ones((n, ), dtype=bool) # add also the filter numpy if filter_npy is not None: print(f"Loading a filter file from {filter_npy}") filter_vec = np.load(filter_npy) dist_filter = dist_filter & filter_vec if filter_subset_tasks: assert subset_tasks is not None interval_from_task = pd.Series(d['metadata']['interval_from_task']) print( f"Subsetting the intervals accoring to subset_tasks: {subset_tasks}" ) print(f"Number of original regions: {dist_filter.sum()}") dist_filter = dist_filter & interval_from_task.isin( subset_tasks).values print( f"Number of filtered regions after filter_subset_tasks: {dist_filter.sum()}" ) # filter by chromosome if exclude_chr: logger.info(f"Excluding chromosomes: {exclude_chr}") chromosomes = d['metadata']['range']['chr'] dist_filter = dist_filter & ( ~pd.Series(chromosomes).isin(exclude_chr)).values # ------------------------------------------------------------- # setup importance scores if seqmodel: thr_one_hot = one_hot[dist_filter] thr_hypothetical_contribs = { f"{task}/{gt}": d['hyp_imp'][task][gt.split("/")[0]][gt.split("/")[1]][dist_filter] for task in tasks for gt in grad_type.split(",") } thr_contrib_scores = { f"{task}/{gt}": thr_hypothetical_contribs[f"{task}/{gt}"] * thr_one_hot for task in tasks for gt in grad_type.split(",") } task_names = [ f"{task}/{gt}" for task in tasks for gt in grad_type.split(",") ] else: if merge_tasks: thr_one_hot = np.concatenate([ one_hot[dist_filter] for task in tasks for gt in grad_type.split(",") ]) thr_hypothetical_contribs = { "merged": np.concatenate([ mean(d['hyp_imp'][task][gt])[dist_filter] for task in tasks for gt in grad_type.split(",") ]) } thr_contrib_scores = { "merged": thr_hypothetical_contribs['merged'] * thr_one_hot } task_names = ['merged'] else: thr_one_hot = one_hot[dist_filter] thr_hypothetical_contribs = { f"{task}/{gt}": mean(d['hyp_imp'][task][gt])[dist_filter] for task in tasks for gt in grad_type.split(",") } thr_contrib_scores = { f"{task}/{gt}": thr_hypothetical_contribs[f"{task}/{gt}"] * thr_one_hot for task in tasks for gt in grad_type.split(",") } task_names = [ f"{task}/{gt}" for task in tasks for gt in grad_type.split(",") ] if null_imp_scores is not None: logger.info(f"Using null_imp_scores: {null_imp_scores}") null_isf = ImpScoreFile(null_imp_scores) null_per_pos_scores = { f"{task}/{gt}": v.sum(axis=-1) for gt in grad_type.split(",") for task, v in null_isf.get_contrib(imp_score=gt).items() if task in tasks } else: # default Null distribution. Requires modisco 5.0 logger.info(f"Using default null_imp_scores") null_per_pos_scores = modisco.coordproducers.LaplaceNullDist( num_to_samp=10000) # ------------------------------------------------------------- # run modisco tfmodisco_results = modisco.tfmodisco_workflow.workflow.TfModiscoWorkflow( # Modisco defaults sliding_window_size=hp.sliding_window_size, flank_size=hp.flank_size, target_seqlet_fdr=hp.target_seqlet_fdr, min_passing_windows_frac=hp.min_passing_windows_frac, max_passing_windows_frac=hp.max_passing_windows_frac, min_metacluster_size=hp.min_metacluster_size, max_seqlets_per_metacluster=hp.max_seqlets_per_metacluster, seqlets_to_patterns_factory=modisco.tfmodisco_workflow. seqlets_to_patterns.TfModiscoSeqletsToPatternsFactory( trim_to_window_size=hp.trim_to_window_size, # default: 30 initial_flank_to_add=hp.initial_flank_to_add, # default: 10 kmer_len=hp.kmer_len, # default: 8 num_gaps=hp.num_gaps, # default: 3 num_mismatches=hp.num_mismatches, # default: 2 n_cores=num_workers, final_min_cluster_size=hp.final_min_cluster_size) # default: 30 )( task_names=task_names, contrib_scores=thr_contrib_scores, # -> task score hypothetical_contribs=thr_hypothetical_contribs, one_hot=thr_one_hot, null_per_pos_scores=null_per_pos_scores) # ------------------------------------------------------------- # save the results grp = h5py.File(output_path) tfmodisco_results.save_hdf5(grp)