strkit 0.10.0__tar.gz → 0.11.1__tar.gz

{strkit-0.10.0/strkit.egg-info → strkit-0.11.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: strkit
-Version: 0.10.0
+Version: 0.11.1
 Summary: A toolkit for analyzing variation in short(ish) tandem repeats.
 Home-page: https://github.com/davidlougheed/strkit
 Author: David Lougheed
@@ -13,7 +13,7 @@ Requires-Python: ~=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: Flask<2.3,>=2.2.5
-Requires-Dist: pysam<0.22,>=0.19
+Requires-Dist: pysam<0.23,>=0.19
 Requires-Dist: numpy<1.27,>=1.23.4
 Requires-Dist: parasail<1.4,>=1.2.4
 Requires-Dist: scikit-learn<1.4,>=1.2.1
@@ -31,13 +31,46 @@ A genotyping and analysis toolkit for short(ish) tandem repeats.
 
 <img src="./docs/images/strkit_logo_small.png" alt="" width="500" height="324" />
 
-&copy; David Lougheed and McGill University 2021-2023 (versions up to and including `0.8.0a1`).
 
-&copy; David Lougheed and McGill University 2021-2023, with portions &copy; McGill University 2023 
-(versions beyond `0.8.0a1`).
+## Copyright and License
+
+* 2021-2023: &copy; David Lougheed (DL) and McGill University 2021-2023 (versions up to and including `0.8.0a1`), 
+  created during graduate research by DL.
+* 2023+: (versions beyond `0.8.0a1`):
+  * Portions &copy; DL and McGill University 2021-2023
+  * Portions &copy; McGill University 2023
+  * Portions &copy; DL 2023
+
+
+### Notice
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+### Exceptions
+
+**Some exclusions to this license apply; specifically portions of 
+[`strkit/viz/templates/browser.html`](strkit/viz/templates/browser.html) and
+the STRkit logo files ([./docs/images/strkit_logo_small.png](./docs/images/strkit_logo_small.png)
+and [./strkit/viz/static/logo.png](./strkit/viz/static/logo.png).)**
 
 The STRkit logo is &copy; David Lougheed 2022, and was designed by Evelyn Lougheed. It is not licensed
-under the terms of the GPL 3.0; all rights are reserved.
+under the terms of the GPL 3.0; it is instead licensed under the terms of the 
+[CC BY-ND 4.0](https://creativecommons.org/licenses/by-nd/4.0/).
+
+Portions of `viz/templates/browser.html` copyright (C) 2021-2022  Observable, Inc.
+Used under the terms of the ISC license.
+
 
 ## Installation
 
@@ -99,7 +132,8 @@ strkit call \
   --min-reads 4 \  # Minimum number of supporting reads needed to make a call
   --min-allele-reads 2 \  # Minimum number of supporting reads needed to call a specific allele size 
   --flank-size 70 \  # Size of the flanking region to use on either side of a region to properly anchor reads
-  --seed 183  # Fixed random number generator seed for replicability
+  --seed 183 \  # Fixed random number generator seed for replicability
+  --processes 10  # Number of parallel processes to use; DEFAULT: 1
 ```
 
 Ideally, you should be using a read file aligned with parameters tuned for tandem repeats. 
@@ -215,33 +249,3 @@ by looking at inheritance patterns. This tool provides a few different ways to d
 
 **For more information on what kind of analyses can be done with this data**, see the
 [Trio analyses with STRkit](./docs/trio_analyses.md) page.
-
-
-
-## Copyright and License
-
-**Some exclusions to this license apply; specifically portions of 
-[`strkit/viz/templates/browser.html`](strkit/viz/templates/browser.html) 
-and files in the `catalogs` directory.**
-
-&copy; David Lougheed 2021-2023 (versions up to and including `0.8.0a1`).
-
-&copy; David Lougheed 2021-2023 with portions &copy; McGill University 2023 (versions beyond `0.8.0a1`).
-
-Portions of `viz/templates/browser.html` copyright (C) 2021-2022  Observable, Inc.
-Used under the terms of the ISC license.
-
-### Notice
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program.  If not, see <https://www.gnu.org/licenses/>.

{strkit-0.10.0 → strkit-0.11.1}/README.md

@@ -6,13 +6,46 @@ A genotyping and analysis toolkit for short(ish) tandem repeats.
 
 <img src="./docs/images/strkit_logo_small.png" alt="" width="500" height="324" />
 
-&copy; David Lougheed and McGill University 2021-2023 (versions up to and including `0.8.0a1`).
 
-&copy; David Lougheed and McGill University 2021-2023, with portions &copy; McGill University 2023 
-(versions beyond `0.8.0a1`).
+## Copyright and License
+
+* 2021-2023: &copy; David Lougheed (DL) and McGill University 2021-2023 (versions up to and including `0.8.0a1`), 
+  created during graduate research by DL.
+* 2023+: (versions beyond `0.8.0a1`):
+  * Portions &copy; DL and McGill University 2021-2023
+  * Portions &copy; McGill University 2023
+  * Portions &copy; DL 2023
+
+
+### Notice
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+### Exceptions
+
+**Some exclusions to this license apply; specifically portions of 
+[`strkit/viz/templates/browser.html`](strkit/viz/templates/browser.html) and
+the STRkit logo files ([./docs/images/strkit_logo_small.png](./docs/images/strkit_logo_small.png)
+and [./strkit/viz/static/logo.png](./strkit/viz/static/logo.png).)**
 
 The STRkit logo is &copy; David Lougheed 2022, and was designed by Evelyn Lougheed. It is not licensed
-under the terms of the GPL 3.0; all rights are reserved.
+under the terms of the GPL 3.0; it is instead licensed under the terms of the 
+[CC BY-ND 4.0](https://creativecommons.org/licenses/by-nd/4.0/).
+
+Portions of `viz/templates/browser.html` copyright (C) 2021-2022  Observable, Inc.
+Used under the terms of the ISC license.
+
 
 ## Installation
 
@@ -74,7 +107,8 @@ strkit call \
   --min-reads 4 \  # Minimum number of supporting reads needed to make a call
   --min-allele-reads 2 \  # Minimum number of supporting reads needed to call a specific allele size 
   --flank-size 70 \  # Size of the flanking region to use on either side of a region to properly anchor reads
-  --seed 183  # Fixed random number generator seed for replicability
+  --seed 183 \  # Fixed random number generator seed for replicability
+  --processes 10  # Number of parallel processes to use; DEFAULT: 1
 ```
 
 Ideally, you should be using a read file aligned with parameters tuned for tandem repeats. 
@@ -190,33 +224,3 @@ by looking at inheritance patterns. This tool provides a few different ways to d
 
 **For more information on what kind of analyses can be done with this data**, see the
 [Trio analyses with STRkit](./docs/trio_analyses.md) page.
-
-
-
-## Copyright and License
-
-**Some exclusions to this license apply; specifically portions of 
-[`strkit/viz/templates/browser.html`](strkit/viz/templates/browser.html) 
-and files in the `catalogs` directory.**
-
-&copy; David Lougheed 2021-2023 (versions up to and including `0.8.0a1`).
-
-&copy; David Lougheed 2021-2023 with portions &copy; McGill University 2023 (versions beyond `0.8.0a1`).
-
-Portions of `viz/templates/browser.html` copyright (C) 2021-2022  Observable, Inc.
-Used under the terms of the ISC license.
-
-### Notice
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program.  If not, see <https://www.gnu.org/licenses/>.

{strkit-0.10.0 → strkit-0.11.1}/setup.py

@@ -15,7 +15,7 @@ setup(
     python_requires="~=3.9",
     install_requires=[
         "Flask>=2.2.5,<2.3",
-        "pysam>=0.19,<0.22",
+        "pysam>=0.19,<0.23",
         "numpy>=1.23.4,<1.27",
         "parasail>=1.2.4,<1.4",
         "scikit-learn>=1.2.1,<1.4",

strkit-0.11.1/strkit/VERSION

@@ -0,0 +1 @@
+0.11.1

{strkit-0.10.0 → strkit-0.11.1}/strkit/call/allele.py

@@ -42,19 +42,24 @@ N_GM_INIT = 3
 
 FLOAT_32_EPSILON = np.finfo(np.float32).eps
 
+CI_PERCENTILE_RANGES = {
+    "95": (2.5, 97.5),
+    "99": (0.5, 99.5),
+}
+
 
 def _array_as_int(n: Union[NDArray[np.int_], NDArray[np.float_]]) -> NDArray[np.int32]:
     return np.rint(n).astype(np.int32)
 
 
-def _calculate_cis(samples, force_int: bool = False, ci: str = "95") -> Union[NDArray[np.int32], NDArray[np.float_]]:
-    r = {
-        "95": (2.5, 97.5),
-        "99": (0.5, 99.5),
-    }[ci]
-    # TODO: enable for numpy >=1.22
-    # percentiles = np.percentile(samples, r, axis=1, method="interpolated_inverted_cdf").transpose()
-    percentiles = np.percentile(samples, r, axis=1, interpolation="nearest").transpose()
+def _calculate_cis(
+    samples,
+    force_int: bool = False,
+    ci: str = Literal["95", "99"],
+) -> Union[NDArray[np.int32], NDArray[np.float_]]:
+    percentiles = np.percentile(
+        samples, CI_PERCENTILE_RANGES[ci], axis=1, method="interpolated_inverted_cdf"
+    ).transpose()
     return _array_as_int(percentiles) if force_int else percentiles
 
 
@@ -139,7 +144,7 @@ def fit_gmm(
 
 
 class CallDict(TypedDict):
-    call: Union[NDArray[np.int32], NDArray[np.float]]
+    call: Union[NDArray[np.int32], NDArray[np.float_]]
     call_95_cis: Union[NDArray[NDArray[np.int32]], NDArray[NDArray[np.float_]]]
     call_99_cis: Union[NDArray[NDArray[np.int32]], NDArray[NDArray[np.float_]]]
     peaks: NDArray[np.float_]

{strkit-0.10.0 → strkit-0.11.1}/strkit/call/call_locus.py

@@ -1,10 +1,12 @@
 from __future__ import annotations
 
+import functools
 import itertools
 import logging
 import multiprocessing as mp
 import numpy as np
 import pysam
+import operator
 import queue
 
 from collections import Counter
@@ -55,10 +57,21 @@ significant_clip_threshold = 100
 significant_clip_snv_take_in = 250
 
 
+# property getters & other partials
+cn_getter = operator.itemgetter("cn")
+weight_getter = operator.itemgetter("w")
+cat_strs = "".join
+
+
+@functools.cache
+def _mask_low_q_base(base_and_qual: tuple[str, int]) -> str:
+    return base_and_qual[0] if base_and_qual[1] > base_wildcard_threshold else "X"
+
+
 def calculate_seq_with_wildcards(qs: str, quals: Optional[list[int]]) -> str:
     if quals is None:
         return qs  # No quality information, so don't do anything
-    return "".join(map(lambda x: x[0] if x[1] > base_wildcard_threshold else "X", zip(qs, quals)))
+    return cat_strs(map(_mask_low_q_base, zip(qs, quals)))
 
 
 def get_read_coords_from_matched_pairs(
@@ -79,7 +92,7 @@ def get_read_coords_from_matched_pairs(
 
     # Skip gaps on either side to find mapped flank indices
 
-    # Binary search for left flank start
+    # Binary search for left flank start -------------------------------------------------------------------------------
     lhs, found = find_pair_by_ref_pos(matched_pairs, left_flank_coord)
 
     # lhs now contains the index for the closest starting coordinate to left_flank_coord
@@ -94,6 +107,7 @@ def get_read_coords_from_matched_pairs(
         lhs -= 1
 
     left_flank_start, _ = matched_pairs[lhs]
+    # ------------------------------------------------------------------------------------------------------------------
 
     for query_coord, ref_coord in matched_pairs[lhs+1:]:
         # Skip gaps on either side to find mapped flank indices
@@ -216,7 +230,7 @@ def calculate_read_distance(
         r1 = read_dict_items[i][1]
         r1_snv_u = r1["snvu"]
 
-        r1_out_of_range: set[int] = {y for y in useful_snvs_range if r1_snv_u[y] == SNV_OUT_OF_RANGE_CHAR}
+        r1_out_of_range: set[int] = set(filter(lambda y: r1_snv_u[y] == SNV_OUT_OF_RANGE_CHAR, useful_snvs_range))
 
         for j in range(i + 1, n_reads):
             r2 = read_dict_items[j][1]
@@ -359,11 +373,13 @@ def call_alleles_with_incorporated_snvs(
             continue
 
         read_useful_snv_bases = tuple(snv_bases[bi] for bi, _pos in useful_snvs)
-        non_blank_read_useful_snv_bases = [bb for bb in read_useful_snv_bases if bb != SNV_OUT_OF_RANGE_CHAR]
+        n_non_blank_read_useful_snv_bases = len(
+            tuple(filter(lambda bb: bb != SNV_OUT_OF_RANGE_CHAR, read_useful_snv_bases))
+        )
 
-        if nbr := len(non_blank_read_useful_snv_bases):  # TODO: parametrize
+        if n_non_blank_read_useful_snv_bases:  # TODO: parametrize
             read_dict_items_with_at_least_one_snv.append(read_item)
-            if nbr >= 2:  # TODO: parametrize
+            if n_non_blank_read_useful_snv_bases >= 2:  # TODO: parametrize
                 read_dict_items_with_many_snvs.append(read_item)
         else:
             read_dict_items_with_no_snvs.append(read_item)
@@ -371,7 +387,7 @@ def call_alleles_with_incorporated_snvs(
         read["snvu"] = read_useful_snv_bases  # Store read-level 'useful' SNVs
 
         if print_snvs:
-            print(rn, f"\t{read['cn']:.0f}", "\t", "".join(read_useful_snv_bases), nbr)
+            print(rn, f"\t{read['cn']:.0f}", "\t", cat_strs(read_useful_snv_bases), n_non_blank_read_useful_snv_bases)
 
     n_reads_with_many_snvs: int = len(read_dict_items_with_many_snvs)
     n_reads_with_at_least_one_snv: int = len(read_dict_items_with_at_least_one_snv)
@@ -424,25 +440,23 @@ def call_alleles_with_incorporated_snvs(
     cluster_labels = c.labels_
     cluster_indices = tuple(range(n_alleles))
 
-    cluster_reads: list[list[ReadDict]] = []
+    cluster_reads: list[tuple[ReadDict, ...]] = []
     cns: Union[list[list[int]], list[list[float]]] = []
     c_ws: list[Union[NDArray[np.int_], NDArray[np.float_]]] = []
 
     for ci in cluster_indices:
-        crs: list[ReadDict] = []
-
         # Find reads for cluster
-        for i, (_, r) in enumerate(read_dict_items_with_at_least_one_snv):
-            if cluster_labels[i] == ci:
-                crs.append(r)
+        crs: tuple[ReadDict, ...] = tuple(
+            r for i, (_, r) in enumerate(read_dict_items_with_at_least_one_snv)
+            if cluster_labels[i] == ci
+        )
 
         # Calculate copy number set
-        cns.append([r["cn"] for r in crs])
+        cns.append(list(map(cn_getter, crs)))
 
         # Calculate weights array
-        ws = np.fromiter((r["w"] for r in crs), dtype=np.float_)
-        ws = ws / np.sum(ws)
-        c_ws.append(ws)
+        ws = np.fromiter(map(weight_getter, crs), dtype=np.float_)
+        c_ws.append(ws / np.sum(ws))
 
         cluster_reads.append(crs)
 
@@ -501,9 +515,7 @@ def call_alleles_with_incorporated_snvs(
         for rd in cluster_reads_ordered[i]:
             rd["p"] = i
 
-    # Make peak weights sum to 1
-    peak_weights = np.concatenate(tuple(cc["peak_weights"] for cc in cdd), axis=0)
-    peak_weights /= np.sum(peak_weights)
+    peak_weights_pre_adj = np.concatenate(tuple(cc["peak_weights"] for cc in cdd), axis=0)
 
     # All call_datas are truth-y; all arrays should be ordered by peak_order
     call_data = {
@@ -513,7 +525,8 @@ def call_alleles_with_incorporated_snvs(
         "peaks": np.concatenate(tuple(cc["peaks"] for cc in cdd_ordered), axis=None),
 
         # TODO: Readjust peak weights when combining or don't include
-        "peak_weights": peak_weights,
+        # Make peak weights sum to 1
+        "peak_weights": peak_weights_pre_adj / np.sum(peak_weights_pre_adj),
 
         "peak_stdevs": np.concatenate(tuple(cc["peak_stdevs"] for cc in cdd_ordered), axis=0),
         "modal_n_peaks": n_alleles,  # n. of alleles = n. of peaks always -- if we phased using SNVs
@@ -904,7 +917,8 @@ def call_locus(
     # reference genome. If we have a rare realignment (e.g., a large expansion), we cannot use SNVs.
     have_rare_realigns: bool = False
     for rn, read in read_dict_items:
-        n_same_cn_no_realign = sum(1 for _, r2 in read_dict_items if not r2.get("realn") and r2["cn"] == read["cn"])
+        read_cn = read["cn"]
+        n_same_cn_no_realign = sum(1 for _, r2 in read_dict_items if not r2.get("realn") and r2["cn"] == read_cn)
         if read.get("realn") and n_same_cn_no_realign == 0:
             have_rare_realigns = True
             break
@@ -960,9 +974,9 @@ def call_locus(
     if single_or_dist_assign:  # Didn't use SNVs, so call the 'old-fashioned' way - using only copy number
         # Dicts are ordered in Python; very nice :)
         rdvs = tuple(read_dict.values())
-        rcns = tuple(map(lambda rr: rr["cn"], rdvs))
+        rcns = tuple(map(cn_getter, rdvs))
         read_cns = np.fromiter(rcns, dtype=np.float_ if fractional else np.int_)
-        read_weights = np.fromiter(map(lambda rr: rr["w"], rdvs), dtype=np.float_)
+        read_weights = np.fromiter(map(weight_getter, rdvs), dtype=np.float_)
         read_weights = read_weights / np.sum(read_weights)  # Normalize to probabilities
 
         call_data = call_alleles(
@@ -1005,9 +1019,7 @@ def call_locus(
         stdevs: NDArray[np.float_] = call_stdevs[:call_modal_n]
         weights: NDArray[np.float_] = call_weights[:call_modal_n]
 
-        allele_reads: list[list[str]] = []
-        for _ in range(call_modal_n):
-            allele_reads.append([])
+        allele_reads: list[list[str]] = [list() for _ in range(call_modal_n)]
 
         for r, rd in read_dict_items:
             # Need latter term for peaks that we overwrite if we revert to "dist" assignment:
@@ -1053,7 +1065,7 @@ def call_locus(
         "stdevs": call_stdevs.tolist(),  # from np.ndarray
         "modal_n": call_modal_n,
         "n_reads": call_peak_n_reads,
-        **({"kmers": [dict(c) for c in peak_kmers]} if count_kmers in ("peak", "both") else {}),
+        **({"kmers": list(map(dict, peak_kmers))} if count_kmers in ("peak", "both") else {}),
     } if call_data else None
 
     # Calculate call time ----------------------------------------------------------------------------------------------
@@ -1066,11 +1078,15 @@ def call_locus(
 
     # Finally, compile the call into a dictionary with all information to return ---------------------------------------
 
-    def _ndarray_serialize(x: Iterable) -> list[Union[int, float, np.int_, np.float_]]:
-        return [(round(y) if not fractional else round_to_base_pos(y, motif_size)) for y in x]
+    if fractional:
+        def _ndarray_serialize(x: Iterable) -> list[Union[float, np.float_]]:
+            return [round_to_base_pos(y, motif_size) for y in x]
+    else:
+        def _ndarray_serialize(x: Iterable) -> list[Union[int, float, np.int_, np.float_]]:
+            return list(map(round, x))
 
     def _nested_ndarray_serialize(x: Iterable) -> list[list[Union[int, float, np.int_, np.float_]]]:
-        return [_ndarray_serialize(y) for y in x]
+        return list(map(_ndarray_serialize, x))
 
     call_val = apply_or_none(_ndarray_serialize, call)
     call_95_cis_val = apply_or_none(_nested_ndarray_serialize, call_95_cis)

{strkit-0.10.0 → strkit-0.11.1}/strkit/mi/base.py

@@ -13,6 +13,15 @@ __all__ = [
 ]
 
 
+def _line_filter_fn(s: str) -> bool:
+    """
+    Filter function to skip blank lines and comments
+    :param s: line of a file
+    :return: whether the line is not blank and is not a comment
+    """
+    return s and not s.startswith("#")
+
+
 # noinspection PyUnusedLocal
 class BaseCalculator(ABC):
     def __init__(
@@ -73,33 +82,22 @@ class BaseCalculator(ABC):
     def mt_corr(self) -> str:
         return self._mt_corr
 
-    def _make_loci_dict(self) -> dict:
+    def _make_loci_dict(self) -> dict[tuple[str, str, str], list[str, ...]]:
         if not self._loci_file:
             return {}
 
         with open(self._loci_file, "r") as lf:
             return {
                 tuple(d[:3]): d[3:]
-                for d in (
-                    line.split("\t")
-                    for line in map(lambda x: x.strip(), lf)
-                    if line and not line.startswith("#")
-                )
+                for d in map(lambda line: line.split("\t"), filter(_line_filter_fn, map(str.strip, lf)))
             }
 
-    def _make_exclude_set(self) -> set:
+    def _make_exclude_set(self) -> set[tuple[str, str, str]]:
         if not self._exclude_file:
             return set()
 
         with open(self._exclude_file, "r") as lf:
-            return {
-                tuple(d[:3])
-                for d in (
-                    line.split("\t")
-                    for line in map(lambda x: x.strip(), lf)
-                    if line and not line.startswith("#")
-                )
-            }
+            return set(map(lambda line: tuple(line.split("\t")[:3]), filter(_line_filter_fn, map(str.strip, lf))))
 
     def should_exclude_locus(self, locus: tuple[str, str, str]) -> bool:
         return locus in self._exclude_set
@@ -136,8 +134,8 @@ class BaseCalculator(ABC):
     def calculate(self, included_contigs: set) -> Optional[MIResult]:
         res: float = 0
         res_pm1: float = 0
-        res_95_ci: float = 0
-        res_99_ci: float = 0
+        res_95_ci: Optional[float] = None
+        res_99_ci: Optional[float] = None
         n_total: int = 0
 
         contig_results = []

{strkit-0.10.0 → strkit-0.11.1}/strkit/mi/result.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 import itertools
 import logging
-
+import math
 import numpy as np
 import sys
 import scipy.stats as sst
@@ -486,11 +486,13 @@ class MIResult:
             self._logger.warning("Cannot correct for multiple testing when test is not enabled")
             return
 
-        loci = [locus for cr in self.contig_results for locus in cr]
         p_values = [locus.p_value for cr in self.contig_results for locus in cr]
         not_tested = {i for i, p in enumerate(p_values) if p is None}
 
-        loci_filt = [locus for i, locus in enumerate(loci) if i not in not_tested]
+        loci_filt = [
+            locus for i, locus in enumerate(locus for cr in self.contig_results for locus in cr)
+            if i not in not_tested
+        ]
         p_values_filt = np.fromiter((p for i, p in enumerate(p_values) if i not in not_tested), dtype=np.float64)
 
         if (mtm := self._mt_corr) != "none":
@@ -517,16 +519,44 @@ class MIResult:
     def _res_str(res: Union[float, int]) -> str:
         return f"{res:.1f}" if isinstance(res, float) else str(res)
 
+    def _std_err_for_bernoulli(self, val: float) -> float:
+        return math.sqrt((val * (1 - val)) / self._n_loci_seen)
+
+    def _estimate_ci_for_bernoulli(self, val: float) -> tuple[float, float]:
+        std_err = self._std_err_for_bernoulli(val)
+        # 1.96 standard deviations for 95% CI, by CLM
+        return val - 1.96*std_err, val + 1.96*std_err
+
     def write_report_json(self, json_path: str, bin_width: int = 10):
         hist, _bins = self.calculate_histogram(bin_width=bin_width)
 
+        # get 95% CI from standard error, which we estimate from Bernoulli distribution of resulting percentage
+
         obj = {
-            "mi": self.mi_value,
-            "mi_pm1": self.mi_value_pm1,
-            "mi_95": self.mi_value_95_ci,
-            "mi_99": self.mi_value_99_ci,
+            "mi": {
+                "val": self.mi_value,
+                "est_std_err": self._std_err_for_bernoulli(self.mi_value),
+                "est_95_ci": self._estimate_ci_for_bernoulli(self.mi_value),
+            },
+            "mi_pm1": {
+                "val": self.mi_value_pm1,
+                "est_std_err": self._std_err_for_bernoulli(self.mi_value_pm1),
+                "est_95_ci": self._estimate_ci_for_bernoulli(self.mi_value_pm1),
+            },
+            "mi_95": {
+                "val": self.mi_value_95_ci,
+                "est_std_err": self._std_err_for_bernoulli(self.mi_value_95_ci),
+                "est_95_ci": self._estimate_ci_for_bernoulli(self.mi_value_95_ci),
+            } if self.mi_value_95_ci else None,
+            "mi_99": {
+                "val": self.mi_value_99_ci,
+                "est_std_err": self._std_err_for_bernoulli(self.mi_value_99_ci),
+                "est_95_ci": self._estimate_ci_for_bernoulli(self.mi_value_99_ci),
+            } if self.mi_value_99_ci else None,
+
             "n_loci_trio_called": sum((len(lr) for lr in self.contig_results)),
             "n_loci_total": self._n_loci_seen,
+
             "test": self._test_to_perform,
             "hist": hist,
             "significant_loci": [dict(nm) for nm in self.sorted_output_loci],

{strkit-0.10.0 → strkit-0.11.1}/strkit/viz/templates/browser.html

@@ -211,6 +211,7 @@
         let igvContainer = null;
         let reportMetadataTable = null;
 
+        let sampleDisplay = null;
         let regionDisplay = null;
         let motifDisplay = null;
         let refGenome = null;
@@ -284,7 +285,7 @@
         const renderCall = () => {
             const callData = state.callData;
 
-            console.log("call data", callData);
+            console.debug("call data", callData);
 
             /** @type number[] */
             const cns = Object.values(callData.reads).map(read => read.cn);
@@ -456,13 +457,19 @@
         const fetchParams = () =>
             fetch(`/params`)
                 .then(r => r.json())
-                .then(ps => {params = ps;})
+                .then(ps => {
+                  params = ps;
+                  console.debug("params", ps);
+                })
                 .catch(console.error);
 
         const fetchReportMetadata = () =>
             fetch("/report-metadata")
                 .then(r => r.json())
-                .then(rm => {reportMetadata = rm;})
+                .then(rm => {
+                  reportMetadata = rm;
+                  console.debug("report metadata", rm);
+                })
                 .catch(console.error);
 
         const handleSearchResultClick = i => {
@@ -489,6 +496,7 @@
             igvContainer = document.getElementById("igv-browser");
             reportMetadataTable = document.getElementById("report-metadata");
 
+            sampleDisplay = document.getElementById("sample");
             regionDisplay = document.getElementById("region");
             motifDisplay = document.getElementById("motif");
             refGenome = document.getElementById("ref-genome");
@@ -540,6 +548,10 @@
             });
 
             fetchReportMetadata().then(() => {
+                if (reportMetadata.sample_id) {
+                    sampleDisplay.innerText = reportMetadata.sample_id;
+                }
+
                 const other = {};
 
                 const renderObj = (k, v) => {
@@ -588,7 +600,7 @@
             background-image: url("{{ url_for('static', filename='logo.png') }}");
             background-attachment: fixed;
             background-repeat: no-repeat;
-            background-position: bottom right;
+            background-position: bottom 24px right 36px;
             background-size: 300px auto;
         }
 
@@ -626,6 +638,11 @@
             font-weight: normal;
         }
 
+        #sample {
+            font-style: italic;
+            color: #666;
+        }
+
         #locus-search {
             position: relative;
         }
@@ -851,21 +868,23 @@
         }
 
 
-        @media screen and (max-width: 1100px) {
+        @media screen and (max-width: 1320px) {
             h1 {
                 font-size: 20px;
             }
-
-            #tab-overview {
-                flex-direction: column;
-            }
         }
 
-        @media screen and (max-width: 880px) {
+        @media screen and (max-width: 1100px) {
             h1 {
                 font-size: 18px;
             }
 
+            #tab-overview {
+                flex-direction: column;
+            }
+        }
+
+        @media screen and (max-width: 980px) {
             header {
                 flex-direction: column;
             }
@@ -891,7 +910,7 @@
 <div id="strkit">
     <header>
         <h1>
-            STRkit Browser: <span id="region"></span> &mdash; <span id="motif"></span>
+            STRkit Browser: <span id="sample"></span> <span id="region"></span> &mdash; <span id="motif"></span>
         </h1>
         <div id="locus-search">
             <label for="locus-search-box">Select locus:</label>

{strkit-0.10.0 → strkit-0.11.1/strkit.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: strkit
-Version: 0.10.0
+Version: 0.11.1
 Summary: A toolkit for analyzing variation in short(ish) tandem repeats.
 Home-page: https://github.com/davidlougheed/strkit
 Author: David Lougheed
@@ -13,7 +13,7 @@ Requires-Python: ~=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: Flask<2.3,>=2.2.5
-Requires-Dist: pysam<0.22,>=0.19
+Requires-Dist: pysam<0.23,>=0.19
 Requires-Dist: numpy<1.27,>=1.23.4
 Requires-Dist: parasail<1.4,>=1.2.4
 Requires-Dist: scikit-learn<1.4,>=1.2.1
@@ -31,13 +31,46 @@ A genotyping and analysis toolkit for short(ish) tandem repeats.
 
 <img src="./docs/images/strkit_logo_small.png" alt="" width="500" height="324" />
 
-&copy; David Lougheed and McGill University 2021-2023 (versions up to and including `0.8.0a1`).
 
-&copy; David Lougheed and McGill University 2021-2023, with portions &copy; McGill University 2023 
-(versions beyond `0.8.0a1`).
+## Copyright and License
+
+* 2021-2023: &copy; David Lougheed (DL) and McGill University 2021-2023 (versions up to and including `0.8.0a1`), 
+  created during graduate research by DL.
+* 2023+: (versions beyond `0.8.0a1`):
+  * Portions &copy; DL and McGill University 2021-2023
+  * Portions &copy; McGill University 2023
+  * Portions &copy; DL 2023
+
+
+### Notice
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+### Exceptions
+
+**Some exclusions to this license apply; specifically portions of 
+[`strkit/viz/templates/browser.html`](strkit/viz/templates/browser.html) and
+the STRkit logo files ([./docs/images/strkit_logo_small.png](./docs/images/strkit_logo_small.png)
+and [./strkit/viz/static/logo.png](./strkit/viz/static/logo.png).)**
 
 The STRkit logo is &copy; David Lougheed 2022, and was designed by Evelyn Lougheed. It is not licensed
-under the terms of the GPL 3.0; all rights are reserved.
+under the terms of the GPL 3.0; it is instead licensed under the terms of the 
+[CC BY-ND 4.0](https://creativecommons.org/licenses/by-nd/4.0/).
+
+Portions of `viz/templates/browser.html` copyright (C) 2021-2022  Observable, Inc.
+Used under the terms of the ISC license.
+
 
 ## Installation
 
@@ -99,7 +132,8 @@ strkit call \
   --min-reads 4 \  # Minimum number of supporting reads needed to make a call
   --min-allele-reads 2 \  # Minimum number of supporting reads needed to call a specific allele size 
   --flank-size 70 \  # Size of the flanking region to use on either side of a region to properly anchor reads
-  --seed 183  # Fixed random number generator seed for replicability
+  --seed 183 \  # Fixed random number generator seed for replicability
+  --processes 10  # Number of parallel processes to use; DEFAULT: 1
 ```
 
 Ideally, you should be using a read file aligned with parameters tuned for tandem repeats. 
@@ -215,33 +249,3 @@ by looking at inheritance patterns. This tool provides a few different ways to d
 
 **For more information on what kind of analyses can be done with this data**, see the
 [Trio analyses with STRkit](./docs/trio_analyses.md) page.
-
-
-
-## Copyright and License
-
-**Some exclusions to this license apply; specifically portions of 
-[`strkit/viz/templates/browser.html`](strkit/viz/templates/browser.html) 
-and files in the `catalogs` directory.**
-
-&copy; David Lougheed 2021-2023 (versions up to and including `0.8.0a1`).
-
-&copy; David Lougheed 2021-2023 with portions &copy; McGill University 2023 (versions beyond `0.8.0a1`).
-
-Portions of `viz/templates/browser.html` copyright (C) 2021-2022  Observable, Inc.
-Used under the terms of the ISC license.
-
-### Notice
-
-This program is free software: you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation, either version 3 of the License, or
-(at your option) any later version.
-
-This program is distributed in the hope that it will be useful,
-but WITHOUT ANY WARRANTY; without even the implied warranty of
-MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-GNU General Public License for more details.
-
-You should have received a copy of the GNU General Public License
-along with this program.  If not, see <https://www.gnu.org/licenses/>.

{strkit-0.10.0 → strkit-0.11.1}/strkit.egg-info/requires.txt

@@ -1,5 +1,5 @@
 Flask<2.3,>=2.2.5
-pysam<0.22,>=0.19
+pysam<0.23,>=0.19
 numpy<1.27,>=1.23.4
 parasail<1.4,>=1.2.4
 scikit-learn<1.4,>=1.2.1

strkit-0.10.0/strkit/VERSION

@@ -1 +0,0 @@
-0.10.0