levseq 1.2.7__tar.gz → 1.2.9__tar.gz

{levseq-1.2.7/levseq.egg-info → levseq-1.2.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: levseq
-Version: 1.2.7
+Version: 1.2.9
 Home-page: https://github.com/fhalab/levseq/
 Author: Yueming Long, Emreay Gursoy, Ariane Mora, Francesca-Zhoufan Li
 Author-email: ylong@caltech.edu
@@ -49,7 +49,7 @@ Requires-Dist: biopandas
 
 In directed evolution, sequencing every variant enhances data insight and creates datasets suitable for AI/ML methods. This method is presented as an extension of the original Every Variant Sequencer using Illumina technology. With this approach, sequence variants can be generated within a day at an extremely low cost.
 
-![Figure 1: LevSeq Workflow](manuscript/figures/LevSeq_Figure-1.png)
+![Figure 1: LevSeq Workflow](manuscript/figures/LevSeq_Figure-1.jpeg)
 Figure 1: Overview of the LevSeq variant sequencing workflow using Nanopore technology. This diagram illustrates the key steps in the process, from sample preparation to data analysis and visualization.
 
 
@@ -60,7 +60,7 @@ Figure 1: Overview of the LevSeq variant sequencing workflow using Nanopore tech
 
 For setting up the experimental side of LevSeq we suggest the following preparations:
 
-- Order forward and reverse primers compatible with the desired plasmid, see methods section of [our paper](http://biorxiv.org/cgi/content/short/2024.09.04.611255v1?rss=1).
+- Order forward and reverse primers compatible with the desired plasmid, see methods section of [our paper](https://pubs.acs.org/doi/10.1021/acssynbio.4c00625).
 - Successfully install Oxford Nanopore's software (this is only for if you are doing basecalling/minION processing). [Link to installation guide](https://nanoporetech.com/).
 
 ## How to Use LevSeq
@@ -171,7 +171,17 @@ For more details or trouble shooting please look at our [computational_protocols
 
 #### Citing
 
-If you have found LevSeq useful, please cite out [paper](https://doi.org/10.1101/2024.09.04.611255).
+If you have found LevSeq useful, please cite our [paper](https://pubs.acs.org/doi/10.1021/acssynbio.4c00625).
+
+```bibtex
+@article{long2024levseq,
+  title={LevSeq: Rapid Generation of Sequence-Function Data for Directed Evolution and Machine Learning},
+  author={Long, Yueming and Mora, Ariane and Li, Francesca-Zhoufan and Gürsoy, Emre and Johnston, Kadina E and Arnold, Frances H},
+  journal={ACS Synthetic Biology},
+  year={2024},
+  publisher={American Chemical Society}
+}
+```
 
 #### Contact
 

{levseq-1.2.7 → levseq-1.2.9}/README.md

@@ -2,7 +2,7 @@
 
 In directed evolution, sequencing every variant enhances data insight and creates datasets suitable for AI/ML methods. This method is presented as an extension of the original Every Variant Sequencer using Illumina technology. With this approach, sequence variants can be generated within a day at an extremely low cost.
 
-![Figure 1: LevSeq Workflow](manuscript/figures/LevSeq_Figure-1.png)
+![Figure 1: LevSeq Workflow](manuscript/figures/LevSeq_Figure-1.jpeg)
 Figure 1: Overview of the LevSeq variant sequencing workflow using Nanopore technology. This diagram illustrates the key steps in the process, from sample preparation to data analysis and visualization.
 
 
@@ -13,7 +13,7 @@ Figure 1: Overview of the LevSeq variant sequencing workflow using Nanopore tech
 
 For setting up the experimental side of LevSeq we suggest the following preparations:
 
-- Order forward and reverse primers compatible with the desired plasmid, see methods section of [our paper](http://biorxiv.org/cgi/content/short/2024.09.04.611255v1?rss=1).
+- Order forward and reverse primers compatible with the desired plasmid, see methods section of [our paper](https://pubs.acs.org/doi/10.1021/acssynbio.4c00625).
 - Successfully install Oxford Nanopore's software (this is only for if you are doing basecalling/minION processing). [Link to installation guide](https://nanoporetech.com/).
 
 ## How to Use LevSeq
@@ -124,7 +124,17 @@ For more details or trouble shooting please look at our [computational_protocols
 
 #### Citing
 
-If you have found LevSeq useful, please cite out [paper](https://doi.org/10.1101/2024.09.04.611255).
+If you have found LevSeq useful, please cite our [paper](https://pubs.acs.org/doi/10.1021/acssynbio.4c00625).
+
+```bibtex
+@article{long2024levseq,
+  title={LevSeq: Rapid Generation of Sequence-Function Data for Directed Evolution and Machine Learning},
+  author={Long, Yueming and Mora, Ariane and Li, Francesca-Zhoufan and Gürsoy, Emre and Johnston, Kadina E and Arnold, Frances H},
+  journal={ACS Synthetic Biology},
+  year={2024},
+  publisher={American Chemical Society}
+}
+```
 
 #### Contact
 

{levseq-1.2.7 → levseq-1.2.9}/levseq/__init__.py

@@ -18,7 +18,7 @@
 __title__ = 'levseq'
 __description__ = 'LevSeq nanopore sequencing'
 __url__ = 'https://github.com/fhalab/levseq/'
-__version__ = '1.2.7'
+__version__ = '1.2.9'
 __author__ = 'Yueming Long, Emreay Gursoy, Ariane Mora, Francesca-Zhoufan Li'
 __author_email__ = 'ylong@caltech.edu'
 __license__ = 'GPL3'

{levseq-1.2.7 → levseq-1.2.9}/levseq/utils.py

@@ -214,8 +214,10 @@ def calculate_mutation_significance_across_well(seq_df):
     # Do multiple test correction to correct each of the pvalues
     for p in ['p_value', 'p(a)', 'p(t)', 'p(g)', 'p(c)', 'p(n)', 'p(i)']:
         # Do B.H which is the simplest possibly change to have alpha be a variable! ToDo :D
-        padjs = multipletests(seq_df[p].values, alpha=0.05, method='fdr_bh')
-        seq_df[f'{p} adj.'] = padjs[1]
+        padjs = seq_df[p].values * len(seq_df)
+        # The multiple test correction was sometimes returning 0 so we're updating to just do bonferroni
+        #multipletests(seq_df[p].values, alpha=0.05, method='fdr_bh')
+        seq_df[f'{p} adj.'] = padjs #padjs[1]
     return seq_df
 
 def alignment_from_cigar(cigar: str, alignment: str, ref: str, query_qualities: list):
@@ -246,8 +248,8 @@ def alignment_from_cigar(cigar: str, alignment: str, ref: str, query_qualities:
             pos += op_len
             ref_pos += op_len
         elif op == 1:  # insertion to the reference
-            inserts[pos] = alignment[pos - 1:pos + op_len]
-            # new_seq += alignment[pos:pos + op_len]
+            inserts[ref_pos - 1] = alignment[pos - 1:pos + op_len]
+            new_seq = new_seq[:-1] + 'I'  # Set the previous position to be an insertion
             pos += op_len
         elif op == 2:  # deletion from the reference
             new_seq += '-' * op_len
@@ -487,12 +489,15 @@ def get_variant_label_for_well(seq_df, threshold):
         label = '_'.join(label)
         # Only keep the frequency of the most frequent mutation
         probability = np.mean([x for x in non_refs['percent_most_freq_mutation'].values])
-        # Combine the values
-        chi2_statistic, combined_p_value = combine_pvalues([x for x in non_refs['p_value adj.'].values], method='fisher')
+        # Combine the values -> looks like fishers works maybe only if there are > 1
+        if len(non_refs) > 1:
+            chi2_statistic, combined_p_value = combine_pvalues([x for x in non_refs['p_value adj.'].values], method='fisher')
+        else:
+            combined_p_value = non_refs['p_value adj.'].values[0]
     else:
         label = '#PARENT#'
         probability = np.mean([1 - x for x in non_refs['freq_non_ref'].values])
         combined_p_value = float("nan")
     # Return also the mean mutation rate for the well
     mean_mutation_rate = np.mean([1 - x for x in non_refs['freq_non_ref'].values])
-    return label, probability, combined_p_value, mixed_well, mean_mutation_rate
+    return label, probability, combined_p_value, mixed_well, mean_mutation_rate

{levseq-1.2.7 → levseq-1.2.9}/levseq/variantcaller.py

@@ -27,6 +27,7 @@ from Bio import SeqIO
 import re
 from tqdm import tqdm
 import warnings
+import math
 '''
 Script for variant calling
 
@@ -213,7 +214,7 @@ class VariantCaller:
         self.variant_df['Variant'] = [self.variant_dict[b_id].get('Variant') for b_id in self.variant_df['ID'].values]
         self.variant_df['Mixed Well'] = [self.variant_dict[b_id].get('Mixed Well') for b_id in self.variant_df['ID'].values]
         self.variant_df['Average mutation frequency'] = [self.variant_dict[b_id].get('Average mutation frequency') for b_id in self.variant_df['ID'].values]
-        self.variant_df['P value'] = [self.variant_dict[b_id].get('P value') if self.variant_dict[b_id].get('P value') else 1.0 for b_id in self.variant_df['ID'].values]
+        self.variant_df['P value'] = [self.variant_dict[b_id].get('P value') for b_id in self.variant_df['ID'].values]
         self.variant_df['Alignment Count'] = [self.variant_dict[b_id].get('Alignment Count') for b_id in self.variant_df['ID'].values]
         self.variant_df['Average error rate'] = [self.variant_dict[b_id].get('Average error rate') for b_id in self.variant_df['ID'].values]
 

{levseq-1.2.7 → levseq-1.2.9/levseq.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: levseq
-Version: 1.2.7
+Version: 1.2.9
 Home-page: https://github.com/fhalab/levseq/
 Author: Yueming Long, Emreay Gursoy, Ariane Mora, Francesca-Zhoufan Li
 Author-email: ylong@caltech.edu
@@ -49,7 +49,7 @@ Requires-Dist: biopandas
 
 In directed evolution, sequencing every variant enhances data insight and creates datasets suitable for AI/ML methods. This method is presented as an extension of the original Every Variant Sequencer using Illumina technology. With this approach, sequence variants can be generated within a day at an extremely low cost.
 
-![Figure 1: LevSeq Workflow](manuscript/figures/LevSeq_Figure-1.png)
+![Figure 1: LevSeq Workflow](manuscript/figures/LevSeq_Figure-1.jpeg)
 Figure 1: Overview of the LevSeq variant sequencing workflow using Nanopore technology. This diagram illustrates the key steps in the process, from sample preparation to data analysis and visualization.
 
 
@@ -60,7 +60,7 @@ Figure 1: Overview of the LevSeq variant sequencing workflow using Nanopore tech
 
 For setting up the experimental side of LevSeq we suggest the following preparations:
 
-- Order forward and reverse primers compatible with the desired plasmid, see methods section of [our paper](http://biorxiv.org/cgi/content/short/2024.09.04.611255v1?rss=1).
+- Order forward and reverse primers compatible with the desired plasmid, see methods section of [our paper](https://pubs.acs.org/doi/10.1021/acssynbio.4c00625).
 - Successfully install Oxford Nanopore's software (this is only for if you are doing basecalling/minION processing). [Link to installation guide](https://nanoporetech.com/).
 
 ## How to Use LevSeq
@@ -171,7 +171,17 @@ For more details or trouble shooting please look at our [computational_protocols
 
 #### Citing
 
-If you have found LevSeq useful, please cite out [paper](https://doi.org/10.1101/2024.09.04.611255).
+If you have found LevSeq useful, please cite our [paper](https://pubs.acs.org/doi/10.1021/acssynbio.4c00625).
+
+```bibtex
+@article{long2024levseq,
+  title={LevSeq: Rapid Generation of Sequence-Function Data for Directed Evolution and Machine Learning},
+  author={Long, Yueming and Mora, Ariane and Li, Francesca-Zhoufan and Gürsoy, Emre and Johnston, Kadina E and Arnold, Frances H},
+  journal={ACS Synthetic Biology},
+  year={2024},
+  publisher={American Chemical Society}
+}
+```
 
 #### Contact
 

{levseq-1.2.7 → levseq-1.2.9}/levseq.egg-info/SOURCES.txt

@@ -30,6 +30,7 @@ levseq/barcoding/demultiplex-arm64
 levseq/barcoding/demultiplex-x86
 levseq/barcoding/minion_barcodes.fasta
 tests/test_demultiplex_docker.py
+tests/test_deploy.py
 tests/test_opligopools.py
 tests/test_seqfitvis.py
 tests/test_seqs.py

levseq-1.2.9/tests/test_deploy.py

@@ -0,0 +1,91 @@
+###############################################################################
+#                                                                             #
+#    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 <http://www.gnu.org/licenses/>.     #
+#                                                                             #
+###############################################################################
+
+import shutil
+import tempfile
+import unittest
+import matplotlib.pyplot as plt
+from levseq import *
+from levseq.run_levseq import process_ref_csv
+u = SciUtil()
+import math
+
+class TestClass(unittest.TestCase):
+
+    @classmethod
+    def setup_class(self):
+        local = True
+        # Create a base object since it will be the same for all the tests
+        THIS_DIR = os.path.dirname(os.path.abspath(__file__))
+
+        self.data_dir = os.path.join(THIS_DIR, 'test_data/')
+        if local:
+            self.tmp_dir = os.path.join(THIS_DIR, 'test_data/tmp/')
+            if os.path.exists(self.tmp_dir):
+                shutil.rmtree(self.tmp_dir)
+            os.mkdir(self.tmp_dir)
+        else:
+            self.tmp_dir = tempfile.mkdtemp(prefix='test_data')
+
+    @classmethod
+    def teardown_class(self):
+        shutil.rmtree(self.tmp_dir)
+
+class TestDeploy(TestClass):
+    
+    def test_deploy(self):
+        cmd_list = [
+            'docker',  # Needs to be installed as vina.
+            'run',
+            '--rm',
+            '-v',
+            f'{os.getcwd()}:/levseq_results',
+            'levseq',
+            'test_deploy',
+            'test_data/laragen_run/levseq-1.2.7/',
+            'test_data/laragen_run/20241116-LevSeq-Review-Validation-levseq_ref.csv'
+        ]
+        # ToDo: add in scoring function for ad4
+        cmd_return = subprocess.run(cmd_list, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
+        print(cmd_return.stdout, cmd_return)
+    
+    def test_variant_calling(self):
+        # Take as input the demultiplexed fastq files and the reference csv file
+        cl_args = {'skip_demultiplexing': True, 'skip_variantcalling': False}
+        cl_args["name"] = 'test_deploy'
+        cl_args['path'] = 'test_data/laragen_run/levseq-1.2.7/'
+        cl_args["summary"] = 'test_data/laragen_run/20241116-LevSeq-Review-Validation-levseq_ref.csv'
+        variant_df, ref_df = process_ref_csv(cl_args)
+        # Now we want to check all the variants are the same as in the original case:
+        checked_variants_df = pd.read_csv('test_data/laragen_run/levseq-1.2.7/variants_gold_standard.csv')
+        checked_variants = checked_variants_df['Variant'].values
+        checked_sig = checked_variants_df['P adj. value'].values
+        i = 0
+        for variant, pval in variant_df[['Variant', 'P adj. value']].values:
+            print(variant, checked_variants[i])
+            if checked_variants[i]:
+                if variant:
+                    assert variant == checked_variants[i]
+            # if pval < 0.05:
+            #     assert checked_sig[i] < 0.05
+            # elif math.isnan(pval):
+            #     assert math.isnan(checked_sig[i])
+            # else:
+            #     assert checked_sig[i] >= 0.05
+            print(pval, checked_sig[i])
+            i += 1
+