pyTMHMM-binaries 1.3.6__cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl

pyTMHMM/__init__.py

@@ -0,0 +1,3 @@
+from pyTMHMM.api import predict
+
+__all__ = ['predict']

pyTMHMM/api.py

@@ -0,0 +1,42 @@
+from collections import defaultdict
+
+import numpy as np
+import os.path
+
+from pyTMHMM.model import parse
+from pyTMHMM.hmm import viterbi, forward, backward
+
+
+GROUP_NAMES = ('i', 'm', 'o')
+
+DEFAULT_MODEL = os.path.join(os.path.dirname(__file__), 'TMHMM2.0.model')
+
+def predict(sequence, model_or_filelike=DEFAULT_MODEL, compute_posterior=True):
+    if isinstance(model_or_filelike, tuple):
+        model = model_or_filelike
+    else:
+        header, model = parse(model_or_filelike)
+
+    _, path = viterbi(sequence, *model)
+
+    if compute_posterior:
+        forward_table, constants = forward(sequence, *model)
+        backward_table = backward(sequence, constants, *model)
+
+        posterior = forward_table * backward_table
+        _, _, _, char_map, label_map, name_map = model
+
+        observations = len(sequence)
+        states = len(name_map)
+
+        table = np.zeros(shape=(observations, 3))
+        for i in range(observations):
+            group_probs = defaultdict(float)
+            for j in range(states):
+                group = label_map[j].lower()
+                group_probs[group] += posterior[i, j]
+
+            for k, group in enumerate(GROUP_NAMES):
+                table[i, k] = group_probs[group]
+        return path, table/table.sum(axis=1, keepdims=True)
+    return path

pyTMHMM/cli.py

@@ -0,0 +1,92 @@
+import argparse
+import itertools
+import textwrap
+
+
+from .api import predict
+from .api import DEFAULT_MODEL
+from .model import parse  # noqa: F401
+from .utils import (
+    dump_posterior_file,
+    load_posterior_file,
+    load_fasta_file,
+)
+
+has_matplotlib = True
+try:
+    import matplotlib
+    matplotlib.use('Agg')
+    import matplotlib.pyplot as plt
+except ImportError:
+    has_matplotlib = False
+
+
+PRETTY_NAMES = {
+    'i': 'inside',
+    'M': 'transmembrane helix',
+    'o': 'outside',
+    'O': 'outside'
+}
+
+
+def summarize(path):
+    """
+    Summarize a path as a list of (start, end, state) triples.
+    """
+    for state, group in itertools.groupby(enumerate(path), key=lambda x: x[1]):
+        group = list(group)
+        start = min(group, key=lambda x: x[0])[0]
+        end = max(group, key=lambda x: x[0])[0]
+        yield start, end, state
+
+
+def plot(posterior_file, outputfile):
+    inside, membrane, outside = load_posterior_file(posterior_file)
+
+    plt.figure(figsize=(16, 8))
+    plt.title('Posterior probabilities')
+    plt.suptitle('pyTMHMM')
+    plt.plot(inside, label='inside', color='blue')
+    plt.plot(membrane, label='transmembrane', color='red')
+    plt.fill_between(range(len(inside)), membrane, color='red')
+    plt.plot(outside, label='outside', color='black')
+    plt.legend(frameon=False, bbox_to_anchor=[0.5, 0],
+               loc='upper center', ncol=3, borderaxespad=1.5)
+    plt.tight_layout(pad=3)
+    plt.savefig(outputfile)
+
+
+def cli():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('-f', '--file', dest='sequence_file',
+                        type=argparse.FileType('r'), required=True,
+                        help='path to file in fasta format with sequences')
+    parser.add_argument('-m', '--model', dest='model_file',
+                        default=DEFAULT_MODEL,
+                        help='path to the model to use')
+    if has_matplotlib:
+        parser.add_argument('-p', '--plot', dest='plot_posterior',
+                            action='store_true',
+                            help='plot posterior probabilies')
+    args = parser.parse_args()
+
+    for entry in load_fasta_file(args.sequence_file):
+        path, posterior = predict(entry.sequence, args.model_file)
+
+        with open(entry.id + '.summary', 'w') as summary_file:
+            for start, end, state in summarize(path):
+                print("{} {} {}".format(start, end, PRETTY_NAMES[state]),
+                      file=summary_file)
+
+        with open(entry.id + '.annotation', 'w') as ann_file:
+            print('>', entry.id, ' ', entry.description, sep='', file=ann_file)
+            for line in textwrap.wrap(path, 79):
+                print(line, file=ann_file)
+
+        plot_filename = entry.id + '.plot'
+        with open(plot_filename, 'w') as plot_file:
+            dump_posterior_file(plot_file, posterior)
+
+        if hasattr(args, 'plot_posterior') and args.plot_posterior:
+            with open(plot_filename, 'r') as fileobj:
+                plot(fileobj, entry.id + '.pdf')