def bpnet_contrib( model_dir, output_file, method="grad", dataspec=None, regions=None, fasta_file=None, # alternative to dataspec shuffle_seq=False, shuffle_regions=False, max_regions=None, # reference='zeroes', # Currently the only option # peak_width=1000, # automatically inferred from 'config.gin.json' # seq_width=None, contrib_wildcard='*/profile/wn,*/counts/pre-act', # specifies which contrib. scores to compute batch_size=512, gpu=0, memfrac_gpu=0.45, num_workers=10, storage_chunk_size=512, exclude_chr='', include_chr='', overwrite=False, skip_bias=False): """Run contribution scores for a BPNet model """ from bpnet.extractors import _chrom_sizes add_file_logging(os.path.dirname(output_file), logger, 'bpnet-contrib') if gpu is not None: create_tf_session(gpu, per_process_gpu_memory_fraction=memfrac_gpu) 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" ) config = read_json(os.path.join(model_dir, 'config.gin.json')) seq_width = config['seq_width'] peak_width = config['seq_width'] # NOTE - seq_width has to be the same for the input and the target # # infer from the command line # 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 contrib_wildcards = contrib_wildcard.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) logger.info("Creating the dataset") from bpnet.datasets import StrandedProfile, SeqClassification if fasta_file is not None: if regions is None: raise ValueError( "fasta_file specified. Expecting regions to be specified as well" ) dl_valid = SeqClassification( fasta_file=fasta_file, intervals_file=regions, incl_chromosomes=include_chr, excl_chromosomes=exclude_chr, auto_resize_len=seq_width, ) chrom_sizes = _chrom_sizes(fasta_file) else: if dataspec is None: logger.info("Using dataspec used to train the model") # Specify dataspec dataspec = model_dir / "dataspec.yml" ds = DataSpec.load(dataspec) dl_valid = StrandedProfile(ds, incl_chromosomes=include_chr, excl_chromosomes=exclude_chr, intervals_file=regions, peak_width=peak_width, shuffle=False, seq_width=seq_width) chrom_sizes = _chrom_sizes(ds.fasta_file) # Setup contribution score trimming (not required currently) 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, contrib_wildcards) ] logger.info(f"Using the following interpretation targets:") for n in intp_names: print(n) if max_regions is not None: if len(dl_valid) > max_regions: logging.info( f"Using {max_regions} regions instead of the original {len(dl_valid)}" ) else: logging.info( f"--max-regions={max_regions} is larger than the dataset size: {len(dl_valid)}. " "Using the dataset size for max-regions") max_regions = len(dl_valid) else: max_regions = len(dl_valid) max_batches = np.ceil(max_regions / batch_size) writer = HDF5BatchWriter(output_file, chunk_size=storage_chunk_size) for i, batch in enumerate( tqdm(dl_valid.batch_iter(batch_size=batch_size, shuffle=shuffle_regions, num_workers=num_workers), total=max_batches)): # store the original batch containing 'inputs' and 'targets' if skip_bias: batch['inputs'] = { 'seq': batch['inputs']['seq'] } # ignore all other inputs if max_batches > 0: 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_contrib = seqmodel.contrib_score( batch['inputs']['seq'], name=name, method=method, batch_size=None) # don't second-batch # put contribution scores to the dictionary # also trim the contribution scores appropriately so that # the output will always be w.r.t. the peak center batch[f"/hyp_contrib/{name}"] = hyp_contrib[:, trim_start:trim_end] # trim the sequence as well # Trim the sequence batch['inputs']['seq'] = batch['inputs']['seq'][:, trim_start:trim_end] # ? maybe it would it be better to have an explicit ContribFileWriter. # that way the written schema would be fixed writer.batch_write(batch) # add chromosome sizes writer.f.attrs['chrom_sizes'] = json.dumps(chrom_sizes) writer.close() logger.info(f"Done. Contribution score file was saved to: {output_file}")
def __init__(self, ds, peak_width=200, seq_width=None, incl_chromosomes=None, excl_chromosomes=None, intervals_file=None, intervals_format='bed', include_metadata=True, tasks=None, include_classes=False, shuffle=True, interval_transformer=None, track_transform=None, total_count_transform=lambda x: np.log(1 + x)): """Dataset for loading the bigwigs and fastas Args: ds (bpnet.dataspecs.DataSpec): data specification containing the fasta file, bed files and bigWig file paths chromosomes (list of str): a list of chor peak_width: resize the bed file to a certain width intervals_file: if specified, use these regions to train the model. If not specified, the regions are inferred from the dataspec. intervals_format: interval_file format. Available: bed, bed3, bed3+labels shuffle: True track_transform: function to be applied to transform the tracks (shape=(batch, seqlen, channels)) total_count_transform: transform to apply to the total counts TODO - shall we standardize this to have also the inverse operation? """ if isinstance(ds, str): self.ds = DataSpec.load(ds) else: self.ds = ds self.peak_width = peak_width if seq_width is None: self.seq_width = peak_width else: self.seq_width = seq_width assert intervals_format in ['bed3', 'bed3+labels', 'bed'] self.shuffle = shuffle self.intervals_file = intervals_file self.intervals_format = intervals_format self.incl_chromosomes = incl_chromosomes self.excl_chromosomes = excl_chromosomes self.total_count_transform = total_count_transform self.track_transform = track_transform self.include_classes = include_classes # not specified yet self.fasta_extractor = None self.bw_extractors = None self.bias_bw_extractors = None self.include_metadata = include_metadata self.interval_transformer = interval_transformer # Load chromosome lengths self.chrom_lens = _chrom_sizes(self.ds.fasta_file) if self.intervals_file is None: # concatenate the bed files self.dfm = pd.concat([TsvReader(task_spec.peaks, num_chr=False, incl_chromosomes=incl_chromosomes, excl_chromosomes=excl_chromosomes, chromosome_lens=self.chrom_lens, resize_width=max(self.peak_width, self.seq_width) ).df.iloc[:, :3].assign(task=task) for task, task_spec in self.ds.task_specs.items() if task_spec.peaks is not None]) assert list(self.dfm.columns)[:4] == [0, 1, 2, "task"] if self.shuffle: self.dfm = self.dfm.sample(frac=1) self.tsv = None self.dfm_tasks = None else: self.tsv = TsvReader(self.intervals_file, num_chr=False, # optional label_dtype=int if self.intervals_format == 'bed3+labels' else None, mask_ambigous=-1 if self.intervals_format == 'bed3+labels' else None, # -------------------------------------------- incl_chromosomes=incl_chromosomes, excl_chromosomes=excl_chromosomes, chromosome_lens=self.chrom_lens, resize_width=max(self.peak_width, self.seq_width) ) if self.shuffle: self.tsv.shuffle_inplace() self.dfm = self.tsv.df # use the data-frame from tsv self.dfm_tasks = self.tsv.get_target_names() # remember the tasks if tasks is None: self.tasks = list(self.ds.task_specs) else: self.tasks = tasks if self.include_classes: assert self.dfm_tasks is not None if self.dfm_tasks is not None: assert set(self.tasks).issubset(self.dfm_tasks) # setup bias maps per task self.task_bias_tracks = {task: [bias for bias, spec in self.ds.bias_specs.items() if task in spec.tasks] for task in self.tasks}