From 794d5f106c0105759ccef29093d2d31892b855b8 Mon Sep 17 00:00:00 2001
From: Schneider Leo <leo.schneider@etu.ec-lyon.fr>
Date: Fri, 21 Mar 2025 16:53:48 +0100
Subject: [PATCH] =?UTF-8?q?modelisation=20biais=20collecte=20de=20donn?=
=?UTF-8?q?=C3=A9es?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
---
main.py | 65 +++++++++++++++++++++++++++++++++++++++-
modelisation_flyer.py | 70 +++++++++++++++++++++++++++++++++++++++++++
2 files changed, 134 insertions(+), 1 deletion(-)
create mode 100644 modelisation_flyer.py
diff --git a/main.py b/main.py
index cc98a85..76475bd 100644
--- a/main.py
+++ b/main.py
@@ -1,8 +1,15 @@
import numpy as np
import pandas as pd
+import tensorflow as tf
+import dlomix
+import sys
+import os
from dlomix.models import DetectabilityModel
from dlomix.constants import CLASSES_LABELS, alphabet, aa_to_int_dict
from dlomix.data import DetectabilityDataset
+from datasets import load_dataset, DatasetDict
+from dlomix.reports.DetectabilityReport import DetectabilityReport, predictions_report
+WANDB_REPORT_API_DISABLE_MESSAGE=True
def fasta_like_to_data(path):
file = open(path, "r")
@@ -19,6 +26,61 @@ def strip_lines(s):
s = s.split(' ')[1]
return s
+def test_model():
+ total_num_classes = len(CLASSES_LABELS)
+ input_dimension = len(alphabet)
+ num_cells = 64
+
+ model = DetectabilityModel(num_units=num_cells, num_clases=total_num_classes)
+ model.built = True
+ model_save_path = 'pretrained_model/original_detectability_fine_tuned_model_FINAL'
+ model.load_weights(model_save_path)
+
+ # hf_data_name = "Wilhelmlab/detectability-sinitcyn"
+ # hf_data_name = "Wilhelmlab/detectability-wang"
+ hf_data_name = "Wilhelmlab/detectability-proteometools"
+
+ hf_dataset_split = load_dataset(hf_data_name, split="test")
+ hf_dataset = DatasetDict({"test": hf_dataset_split})
+ max_pep_length = 40
+ BATCH_SIZE = 128
+
+ detectability_data = DetectabilityDataset(data_source=hf_dataset,
+ data_format='hf',
+ max_seq_len=max_pep_length,
+ label_column="Classes",
+ sequence_column="Sequences",
+ dataset_columns_to_keep=None,
+ batch_size=BATCH_SIZE,
+ with_termini=False,
+ alphabet=aa_to_int_dict)
+ predictions = model.predict(detectability_data.tensor_test_data)
+ test_targets = detectability_data["test"]["Classes"]
+ test_data_df = pd.DataFrame(
+ {
+ "Sequences": detectability_data["test"]["_parsed_sequence"], # get the raw parsed sequences
+ "Classes": test_targets, # get the test targets from above
+ # get the Proteins column from the dataset object
+ }
+ )
+
+ test_data_df.Sequences = test_data_df.Sequences.apply(
+ lambda x: "".join(x)) # join the sequences since they are a list of string amino acids.
+ num_classes = np.max(test_targets) + 1
+ test_targets_one_hot = np.eye(num_classes)[test_targets]
+ test_targets_one_hot.shape, len(test_targets)
+ report = DetectabilityReport(targets=test_targets_one_hot,
+ predictions=predictions,
+ input_data_df=test_data_df,
+ output_path="./output/report_on_Sinitcyn_2000_proteins_test_set_labeled",
+ history=None,
+ rank_by_prot=True,
+ threshold=None,
+ name_of_dataset='Sinitcyn 2000 proteins test set',
+ name_of_model='Fine-tuned model (Original)')
+ results_df = report.detectability_report_table
+
+
def main(input_data_path):
print('Reading file')
file = open(input_data_path, "r")
@@ -102,4 +164,5 @@ def main(input_data_path):
new_file.close()
if __name__ == '__main__':
- main('250107_FASTA_RP_GroEL_GroES_Tuf_5pct_assemble_peptides_list.txt')
+ # main()
+ main('241205_list_test_peptide_detectability.txt')
diff --git a/modelisation_flyer.py b/modelisation_flyer.py
new file mode 100644
index 0000000..c04ccdd
--- /dev/null
+++ b/modelisation_flyer.py
@@ -0,0 +1,70 @@
+import matplotlib.pyplot as plt
+import numpy as np
+import numpy.random
+import pandas as pd
+from tensorflow_probability.python.layers.distribution_layer import sample
+
+rng = np.random.default_rng()
+
+PROT_NUM = 1000
+
+peptide_per_prot = rng.normal(10,3,PROT_NUM)
+plt.hist(peptide_per_prot)
+plt.show()
+plt.savefig('dist_peptide_prot.png')
+plt.clf()
+
+log_intensity_test = rng.normal(8,0.8,1000)
+plt.hist(log_intensity_test)
+plt.show()
+plt.savefig('dist_log_intensity.png')
+plt.clf()
+
+no_id=0
+int_total = np.array([])
+int_normalized_first = np.array([])
+for num_peptides in peptide_per_prot :
+ if int(num_peptides)>0:
+ coverage = rng.binomial(num_peptides,0.4)
+ log_intensities = rng.normal(8,2,coverage)
+ if coverage > 3 and coverage > 0.2*num_peptides:
+ no_id+=int(num_peptides)-coverage
+ intensities = np.exp(log_intensities)
+ int_total = np.concatenate((int_total, intensities))
+ int_normalized = intensities/np.max(intensities)
+ int_normalized_first = np.concatenate((int_normalized_first, int_normalized))
+
+int_normalized_after = int_total/np.max(int_total)
+
+threshold_true_weak_flyer = sorted(int_normalized_after)[int(len(int_normalized_after)/3)]
+threshold_true_medium_flyer = sorted(int_normalized_after)[int(2*len(int_normalized_after)/3)]
+
+threshold_measure_weak_flyer = sorted(int_normalized_first)[int(len(int_normalized_first)/3)]
+threshold_measure_medium_flyer = sorted(int_normalized_first)[int(2*len(int_normalized_first)/3)]
+
+
+label_true = []
+label_measure = []
+
+for i in range(int_normalized_after.size):
+ if int_normalized_after[i] < threshold_true_weak_flyer :
+ label_true.append('Weak flyer')
+ elif int_normalized_after[i] < threshold_true_medium_flyer:
+ label_true.append('Medium flyer')
+ else:
+ label_true.append('Strong flyer')
+
+
+ if int_normalized_first[i] < threshold_measure_weak_flyer :
+ label_measure.append('Weak flyer')
+ elif int_normalized_first[i] < threshold_measure_medium_flyer:
+ label_measure.append('Medium flyer')
+ else:
+ label_measure.append('Strong flyer')
+
+data = {'True label':label_true, 'Measured label':label_measure}
+
+df = pd.DataFrame(data=data)
+
+acc_measure = df[df['True label']==df['Measured label']].shape[0]/df.shape[0]
+acc_with_no_id = (no_id + df[df['True label']==df['Measured label']].shape[0])/(no_id + df.shape[0])
\ No newline at end of file
--
GitLab