phyddle 0.3.0__tar.gz → 0.3.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -1,5 +1,5 @@
1
1
  [bumpversion]
2
- current_version = 0.3.0
2
+ current_version = 0.3.1
3
3
 
4
4
  [bumpversion:file:pyproject.toml]
5
5
 
@@ -221,7 +221,8 @@ Upload to distribution to TestPyPI
221
221
  python3 -m twine upload --repository --skip-existing testpypi dist/*
222
222
 
223
223
  # verify TestPyPI install works (e.g. for x.x.x => v0.0.7)
224
- python3 -m pip install --index-url https://test.pypi.org/simple/ --no-deps phyddle-x.x.x.*
224
+ ## python3 -m pip install --index-url https://test.pypi.org/simple/ --no-deps phyddle-x.x.x.* # does not work as of 250227
225
+ python3 -m pip install -i https://test.pypi.org/simple/ phyddle==x.x.x
225
226
 
226
227
  # should be able to import within Python session now, e.g.
227
228
  # >>> from phyddle import command_line
@@ -237,6 +238,7 @@ Upload distribution to PyPI (similar to above)
237
238
 
238
239
  # verify PyPI install works
239
240
  python3 -m pip install phyddle
241
+ python3 -m pip install phyddle==x.x.x
240
242
 
241
243
  # should be able to import within Python session now, e.g.
242
244
  # >>> from phyddle import command_line
@@ -1,6 +1,6 @@
1
- Metadata-Version: 2.4
1
+ Metadata-Version: 2.5
2
2
  Name: phyddle
3
- Version: 0.3.0
3
+ Version: 0.3.1
4
4
  Summary: Software for phylogenetic model exploration with deep learning
5
5
  Project-URL: Homepage, https://github.com/mlandis/phyddle
6
6
  Project-URL: Bug Reports, https://github.com/mlandis/phyddle/issues
@@ -24,6 +24,7 @@ Requires-Dist: h5py>=3.10.0
24
24
  Requires-Dist: matplotlib>=3.8.2
25
25
  Requires-Dist: numpy>=1.26.4
26
26
  Requires-Dist: pandas>=2.2.0
27
+ Requires-Dist: pillow>=11.0.0
27
28
  Requires-Dist: pydot>=2.0.0
28
29
  Requires-Dist: pypdf>=4.0.0
29
30
  Requires-Dist: scikit-learn>=1.4.0
@@ -33,15 +34,15 @@ Requires-Dist: torchview>=0.2.6
33
34
  Requires-Dist: tqdm>=4.66.1
34
35
  Description-Content-Type: text/markdown
35
36
 
36
- # phyddle 0.3.0
37
+ # phyddle 0.3.1
37
38
 
38
- Phylogenetic model exploration with deep learning.
39
+ Software for exploring phylogenetic models with deep learning [[manuscript](https://doi.org/10.1093/sysbio/syaf036)]
39
40
 
40
41
  ## User guide
41
42
  Visit https://phyddle.org to learn how to use the software.
42
43
 
43
- ## Overview
44
44
 
45
+ ## Overview
45
46
  <img align="right" src="https://phyddle.org/_images/phyddle_pipeline.png" width="35%">
46
47
 
47
48
  A standard phyddle analysis performs the following tasks for you:
@@ -112,11 +113,21 @@ phyddle
112
113
 
113
114
  phyddle uses third-party simulators to generate training datasets. Example workflows assume that [R](https://cran.r-project.org), [RevBayes](https://revbayes.github.io), [Phylojunction](https://phylojunction.org/build/html/index.html), or [BEAST](https://www.beast2.org/) with [MASTER](https://github.com/tgvaughan/MASTER) (plugin) is installed on your machine and can be executed as a command from terminal. The documentation explains how to configure R for use with phyddle.
114
115
 
116
+ ## Need help?
117
+ Visit the [Discussions](https://github.com/mlandis/phyddle/discussions) page to interact with other phyddle users and receive help.
118
+
119
+ ## Citation
120
+ If you used phyddle, please cite:
121
+ > MJ Landis, A Thompson. 2025. phyddle: software for exploring phylogenetic models with deep learning. Systematic Biology (in press). doi:10.1093/sysbio/syaf036.<br>
122
+
123
+ > A Thompson, B Liebeskind, EJ Scully, MJ Landis. 2024. Deep learning and likelihood approaches for viral phylogeography converge on the same answers whether the inference model is right or wrong. Systematic Biology 73:183-206.
124
+
115
125
  ## Note on code stability
116
126
 
117
127
  Code on the [main](https://github.com/mlandis/phyddle/tree/main) branch is tested and stable with respect to the standard use cases. Code on the [development](https://github.com/mlandis/phyddle/tree/development) branch contains new features, but is not as rigorously tested. Most phyddle development occurs on a 16-core Intel Macbook Pro laptop and a 64-core Intel Ubuntu server. Any feedback is appreciated! [michael.landis@wustl.edu](mailto:michael.landis@wustl.edu)
118
128
 
129
+
119
130
  ## About
120
- Thanks for your interest in phyddle. The phyddle project emerged from a phylogenetic deep learning study led by Ammon Thompson ([paper](https://doi.org/10.1093/sysbio/syad074)). The goal of phyddle is to provide its users with a generalizable pipeline workflow for phylogenetic modeling and deep learning. This hopefully will make it easier for phylogenetic model enthusiasts and developers to explore and apply models that do not have tractable likelihood functions. It's also intended for use by methods developers who want to characterize how deep learning methods perform under different conditions for standard phylogenetic estimation tasks.
131
+ Thanks for your interest in phyddle. The phyddle project emerged from a phylogenetic deep learning study led by Ammon Thompson ([paper](https://doi.org/10.1093/sysbio/syad074)). The goal of phyddle is to provide its users with a generalizable pipeline workflow for phylogenetic modeling and deep learning. This hopefully will make it easier for phylogenetic model enthusiasts and developers to explore and apply models that do not have tractable likelihood functions. It's also intended for use by methods developers who want to characterize how deep learning methods perform under different conditions for standard phylogenetic estimation tasks. Read more about phyddle at https://doi.org/10.1093/sysbio/syaf036.
121
132
 
122
- The phyddle project is developed by [Michael Landis](https://landislab.org) and [Ammon Thompson](https://scholar.google.com/citations?user=_EpmmTwAAAAJ&hl=en&oi=ao).
133
+ The phyddle project is developed by [Michael Landis](https://landislab.org) and [Ammon Thompson](https://scholar.google.com/citatio:wqns?user=_EpmmTwAAAAJ&hl=en&oi=ao).
@@ -1,12 +1,12 @@
1
- # phyddle 0.3.0
1
+ # phyddle 0.3.1
2
2
 
3
- Phylogenetic model exploration with deep learning.
3
+ Software for exploring phylogenetic models with deep learning [[manuscript](https://doi.org/10.1093/sysbio/syaf036)]
4
4
 
5
5
  ## User guide
6
6
  Visit https://phyddle.org to learn how to use the software.
7
7
 
8
- ## Overview
9
8
 
9
+ ## Overview
10
10
  <img align="right" src="https://phyddle.org/_images/phyddle_pipeline.png" width="35%">
11
11
 
12
12
  A standard phyddle analysis performs the following tasks for you:
@@ -77,11 +77,21 @@ phyddle
77
77
 
78
78
  phyddle uses third-party simulators to generate training datasets. Example workflows assume that [R](https://cran.r-project.org), [RevBayes](https://revbayes.github.io), [Phylojunction](https://phylojunction.org/build/html/index.html), or [BEAST](https://www.beast2.org/) with [MASTER](https://github.com/tgvaughan/MASTER) (plugin) is installed on your machine and can be executed as a command from terminal. The documentation explains how to configure R for use with phyddle.
79
79
 
80
+ ## Need help?
81
+ Visit the [Discussions](https://github.com/mlandis/phyddle/discussions) page to interact with other phyddle users and receive help.
82
+
83
+ ## Citation
84
+ If you used phyddle, please cite:
85
+ > MJ Landis, A Thompson. 2025. phyddle: software for exploring phylogenetic models with deep learning. Systematic Biology (in press). doi:10.1093/sysbio/syaf036.<br>
86
+
87
+ > A Thompson, B Liebeskind, EJ Scully, MJ Landis. 2024. Deep learning and likelihood approaches for viral phylogeography converge on the same answers whether the inference model is right or wrong. Systematic Biology 73:183-206.
88
+
80
89
  ## Note on code stability
81
90
 
82
91
  Code on the [main](https://github.com/mlandis/phyddle/tree/main) branch is tested and stable with respect to the standard use cases. Code on the [development](https://github.com/mlandis/phyddle/tree/development) branch contains new features, but is not as rigorously tested. Most phyddle development occurs on a 16-core Intel Macbook Pro laptop and a 64-core Intel Ubuntu server. Any feedback is appreciated! [michael.landis@wustl.edu](mailto:michael.landis@wustl.edu)
83
92
 
93
+
84
94
  ## About
85
- Thanks for your interest in phyddle. The phyddle project emerged from a phylogenetic deep learning study led by Ammon Thompson ([paper](https://doi.org/10.1093/sysbio/syad074)). The goal of phyddle is to provide its users with a generalizable pipeline workflow for phylogenetic modeling and deep learning. This hopefully will make it easier for phylogenetic model enthusiasts and developers to explore and apply models that do not have tractable likelihood functions. It's also intended for use by methods developers who want to characterize how deep learning methods perform under different conditions for standard phylogenetic estimation tasks.
95
+ Thanks for your interest in phyddle. The phyddle project emerged from a phylogenetic deep learning study led by Ammon Thompson ([paper](https://doi.org/10.1093/sysbio/syad074)). The goal of phyddle is to provide its users with a generalizable pipeline workflow for phylogenetic modeling and deep learning. This hopefully will make it easier for phylogenetic model enthusiasts and developers to explore and apply models that do not have tractable likelihood functions. It's also intended for use by methods developers who want to characterize how deep learning methods perform under different conditions for standard phylogenetic estimation tasks. Read more about phyddle at https://doi.org/10.1093/sysbio/syaf036.
86
96
 
87
- The phyddle project is developed by [Michael Landis](https://landislab.org) and [Ammon Thompson](https://scholar.google.com/citations?user=_EpmmTwAAAAJ&hl=en&oi=ao).
97
+ The phyddle project is developed by [Michael Landis](https://landislab.org) and [Ammon Thompson](https://scholar.google.com/citatio:wqns?user=_EpmmTwAAAAJ&hl=en&oi=ao).
@@ -1,4 +1,19 @@
1
- **phyddle v0.3.0** -- 25.02.xx
1
+ **phyddle v0.3.1** -- 26.11.11
2
+
3
+ * Add support for ancestral state estimation (https://doi.org/10.64898/2026.03.19.712918); read the paper, documentation, and tutorial to use
4
+ * Add support for adaptive conformal prediction for generating calibrated prediction intervals, configured with `cpi_method` setting
5
+ * Train allows you use "total" or "consecutive" count of decreasing performance to stop training, configured with `early_stop_rule` setting
6
+ * Train can now use "sum" or (learned) "weighted_sum" for multitarget training, configured with `loss_aggregation` setting
7
+ * Train now supports dropout layers, configured with new `phy_dropout_prop`, `aux_dropout_prop`, and `lbl_dropout_prop` settings
8
+ * Plot now uses x_est ~ x_true instead of x_true ~ x_est to show parameter estimation accuracy
9
+ * Plot handles fixed variables for KDE better now, but still not perfect
10
+ * Format handles presence/absence of "taxa" header in data file more gracefully
11
+ * Estimate more reliably predicts shape of categorical labels (rare crashes before)
12
+ * Increased default proportion of validation/test examples from 0.05 to 0.10
13
+ * Simulate/Format/Train now report number of CPUs used
14
+ * Fix various issues with dependencies and library updates
15
+
16
+ **phyddle v0.3.0** -- 25.02.27
2
17
 
3
18
  * Includes new safety features, settings, bug fixes, and documentation
4
19
  * Estimate now warns user if empirical input/labels are out-of-distribution
Binary file
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
4
4
 
5
5
  [project]
6
6
  name = "phyddle"
7
- version = "0.3.0"
7
+ version = "0.3.1"
8
8
  authors = [
9
9
  { name="Michael Landis", email="michael.landis@wustl.edu" },
10
10
  { name="Ammon Thompson", email="ammonthompson@gmail.com" },
@@ -23,6 +23,7 @@ dependencies = [
23
23
  "pandas>=2.2.0",
24
24
  "pydot>=2.0.0",
25
25
  "pypdf>=4.0.0",
26
+ "Pillow>=11.0.0",
26
27
  "scikit-learn>=1.4.0",
27
28
  "scipy>=1.14.0",
28
29
  "torch>=2.2.0",
@@ -14,7 +14,7 @@ License: MIT
14
14
  from multiprocessing import set_start_method
15
15
 
16
16
  __project__ = 'phyddle'
17
- __version__ = '0.3.0'
17
+ __version__ = '0.3.1'
18
18
  __author__ = 'Michael Landis and Ammon Thompson'
19
19
  __copyright__ = '(c) 2022-2025, Michael Landis and Ammon Thompson'
20
20
  __citation__ = 'MJ Landis, A Thompson. 2024. phyddle: software for phylogenetic model exploration with deep learning. bioRxiv 2024.08.06.606717.'