diff --git a/data/data_processing.py b/data/data_processing.py
index f226a6acc3aa01a04586e79f1bcbb7c666827036..9fd62ec6892602bc7bfcb1f037f93b7a2140ef8f 100644
--- a/data/data_processing.py
+++ b/data/data_processing.py
@@ -33,45 +33,45 @@ ALPHABET_UNMOD = {
ALPHABET_UNMOD_REV = {v: k for k, v in ALPHABET_UNMOD.items()}
-# def align(dataset, reference, column_dataset, column_ref, seq_data, seq_ref):
-# dataset_ref=dataset[dataset['state']=='train']
-# dataset_unique = dataset_ref[[seq_data,column_dataset]].groupby(seq_data).mean()
-# print('unique',len(dataset_unique))
-# reference_unique = reference[[seq_ref,column_ref]].groupby(seq_ref).mean()
-# seq_ref = reference_unique.index
-# seq_common = dataset_unique.index
-# seq_ref = seq_ref.tolist()
-# seq_common = seq_common.tolist()
-#
-# seq_ref = [tuple(l) for l in seq_ref]
-# seq_common = [tuple(l) for l in seq_common]
-#
-# ind_dict_ref = dict((k, i) for i, k in enumerate(seq_ref))
-# inter = set(ind_dict_ref).intersection(seq_common)
-# print(len(inter))
-#
-# ind_dict_ref = [ind_dict_ref[x] for x in inter]
-#
-# indices_common = dict((k, i) for i, k in enumerate(seq_common))
-# indices_common = [indices_common[x] for x in inter]
-#
-#
-# rt_ref = reference_unique[column_ref][ind_dict_ref].reset_index()
-# rt_data = dataset_unique[column_dataset][indices_common].reset_index()
-#
-# plt.scatter(rt_data[column_dataset].tolist(),rt_ref[column_ref].tolist(),s=0.1)
-# plt.savefig('test.png')
-#
-# xout, yout, wout = loess_1d(np.array(rt_data[column_dataset].tolist()), np.array(rt_ref[column_ref].tolist()),
-# xnew=dataset[column_dataset],
-# degree=1, frac=0.25,
-# npoints=None, rotate=False, sigy=None)
-#
-# plt.scatter(xout, yout, s=0.1)
-# plt.savefig('test_2.png')
-#
-# dataset[column_dataset] = yout
-# return dataset
+def align(dataset, reference, column_dataset, column_ref, seq_data, seq_ref):
+ dataset_ref=dataset[dataset['state']=='train']
+ dataset_unique = dataset_ref[[seq_data,column_dataset]].groupby(seq_data).mean()
+ print('unique',len(dataset_unique))
+ reference_unique = reference[[seq_ref,column_ref]].groupby(seq_ref).mean()
+ seq_ref = reference_unique.index
+ seq_common = dataset_unique.index
+ seq_ref = seq_ref.tolist()
+ seq_common = seq_common.tolist()
+
+ seq_ref = [tuple(l) for l in seq_ref]
+ seq_common = [tuple(l) for l in seq_common]
+
+ ind_dict_ref = dict((k, i) for i, k in enumerate(seq_ref))
+ inter = set(ind_dict_ref).intersection(seq_common)
+ print(len(inter))
+
+ ind_dict_ref = [ind_dict_ref[x] for x in inter]
+
+ indices_common = dict((k, i) for i, k in enumerate(seq_common))
+ indices_common = [indices_common[x] for x in inter]
+
+
+ rt_ref = reference_unique[column_ref][ind_dict_ref].reset_index()
+ rt_data = dataset_unique[column_dataset][indices_common].reset_index()
+
+ plt.scatter(rt_data[column_dataset].tolist(),rt_ref[column_ref].tolist(),s=0.1)
+ plt.savefig('test.png')
+
+ xout, yout, wout = loess_1d(np.array(rt_data[column_dataset].tolist()), np.array(rt_ref[column_ref].tolist()),
+ xnew=dataset[column_dataset],
+ degree=1, frac=0.25,
+ npoints=None, rotate=False, sigy=None)
+
+ plt.scatter(xout, yout, s=0.1)
+ plt.savefig('test_2.png')
+
+ dataset[column_dataset] = yout
+ return dataset
def get_number_unique_peptide(dataset):
seq = dataset['sequence']
diff --git a/data/diann_lib_processing.py b/data/diann_lib_processing.py
new file mode 100644
index 0000000000000000000000000000000000000000..52114706f21b9aa1a42d45571688e5f45a9dd464
--- /dev/null
+++ b/data/diann_lib_processing.py
@@ -0,0 +1,146 @@
+import numpy as np
+import pandas as pb
+import pandas as pd
+import pyarrow.parquet as pq
+import pyarrow as pa
+import torch
+import matplotlib.pyplot as plt
+from model.model import ModelTransformer
+from config import load_args
+from data.dataset import load_data
+
+ALPHABET_UNMOD = {
+ "": 0,
+ "A": 1,
+ "C": 2,
+ "D": 3,
+ "E": 4,
+ "F": 5,
+ "G": 6,
+ "H": 7,
+ "I": 8,
+ "K": 9,
+ "L": 10,
+ "M": 11,
+ "N": 12,
+ "P": 13,
+ "Q": 14,
+ "R": 15,
+ "S": 16,
+ "T": 17,
+ "V": 18,
+ "W": 19,
+ "Y": 20,
+ "M(UniMod:35)": 21,
+ "CaC": 22
+}
+
+ALPHABET_UNMOD_REV = {v: k for k, v in ALPHABET_UNMOD.items()}
+
+def numerical_to_alphabetical_str(s):
+ seq = ''
+ s = s.replace('[','')
+ s = s.replace(']', '')
+ arr = s.split(',')
+ arr = list(map(int, arr))
+ for i in range(len(arr)):
+ seq+=ALPHABET_UNMOD_REV[arr[i]]
+ return seq
+
+def load_lib(path):
+ table = pq.read_table(path)
+ table = table.to_pandas()
+
+ return table
+
+def extract_sequence(data_frame):
+
+ seq = data_frame['Modified.Sequence']
+
+ df_pred = pd.DataFrame(seq)
+ df_pred.columns = ['sequence']
+ df_pred['sequence']=df_pred['sequence'].map(lambda x:x.replace('M(UniMod:35)','-OxM-'))
+ df_pred['remove']=df_pred['sequence'].map((lambda x : 'U' in x))
+ df_pred = df_pred[df_pred['remove']==False]
+ df_pred = df_pred[['sequence']]
+ df_pred['irt_scaled']=0
+ df_pred['state'] = 'holdout'
+
+ df_pred = df_pred.drop_duplicates()
+
+ return df_pred
+
+def predict(data_pred, model, output_path):
+ data_frame = pd.DataFrame()
+ model.eval()
+ for param in model.parameters():
+ param.requires_grad = False
+
+ pred_rt, seqs, true_rt = [], [], []
+ for seq, rt in data_pred:
+ rt = rt.float()
+ if torch.cuda.is_available():
+ seq, rt = seq.cuda(), rt.cuda()
+ pr_rt = model.forward(seq)
+ pred_rt.extend(pr_rt.data.cpu().tolist())
+ seqs.extend(seq.data.cpu().tolist())
+ true_rt.extend(rt.data.cpu().tolist())
+
+ data_frame['rt pred'] = pred_rt
+ data_frame['seq'] = seqs
+ data_frame['true rt'] = true_rt
+ data_frame.to_csv(output_path)
+
+
+if __name__ =='__main__':
+ df = load_lib('spectral_lib/first_lib.parquet')
+
+ plt.hist(df['RT'])
+ plt.savefig('test.png')
+
+ df_2 = pd.read_csv('data_prosit/data.csv')
+
+ plt.clf()
+ plt.hist(df_2['irt'])
+ plt.savefig('test2.png')
+
+ # df_2 = extract_sequence(df).reset_index(drop=True)
+ #
+ # pred = pd.read_csv('../output/out_uniprot_base.csv')
+ #
+ # pred['seq']=pred['seq'].map(numerical_to_alphabetical_str)
+ #
+ # pred['Modified.Sequence']=pred['seq']
+ #
+ # result = pd.merge(df,pred[['Modified.Sequence','rt pred']],on='Modified.Sequence',how='left')
+ #
+ # result['RT']=result['rt pred']
+ #
+ # result = result.drop('rt pred', axis=1)
+ #
+ # table = pa.Table.from_pandas(result)
+ #
+ # pq.write_table(table, 'spectral_lib/custom_first_lib.parquet')
+
+
+
+ # args = load_args()
+ #
+ # model = ModelTransformer(encoder_ff=args.encoder_ff, decoder_rt_ff=args.decoder_rt_ff,
+ # n_head=args.n_head, encoder_num_layer=args.encoder_num_layer,
+ # decoder_rt_num_layer=args.decoder_rt_num_layer, drop_rate=args.drop_rate,
+ # embedding_dim=args.embedding_dim, acti=args.activation, norm=args.norm_first, seq_length=30)
+ #
+ # if torch.cuda.is_available():
+ # model = model.cuda()
+ #
+ # model.load_state_dict(torch.load(args.model_weigh, weights_only=True))
+ #
+ # print(args.dataset_test)
+ # data_test = load_data(data_source='data/spectral_lib/data_uniprot_base.csv', batch_size=args.batch_size, length=30, mode=args.split_test,
+ # seq_col=args.seq_test)
+ #
+ # predict(data_test, model, args.output)
+
+ plt.hist(df['RT'])
+ plt.savefig('test.png')
\ No newline at end of file
diff --git a/data/msp_file_extraction.py b/data/msp_file_extraction.py
new file mode 100644
index 0000000000000000000000000000000000000000..64ade727c65783677d47e14e6c1be0f6c21743ec
--- /dev/null
+++ b/data/msp_file_extraction.py
@@ -0,0 +1,16 @@
+import pandas as pd
+
+
+if __name__ == '__main__':
+ seq=[]
+ file = open("spectral_lib/predicted_library.msp", "r")
+ content=file.readlines()
+ file.close()
+ for l in content :
+ if 'Name:'in l:
+ seq.append(l.split(':')[1].split('/')[0])
+
+ df = pd.DataFrame(seq,columns=['sequence'])
+ df['irt_scaled']=0
+ df['state'] = 'holdout'
+ df.to_csv('spectral_lib/df_predicted_library_oktoberfest.csv',index=False)
\ No newline at end of file
diff --git a/data/spectral_lib/df_predicted_library_oktoberfest.csv b/data/spectral_lib/df_predicted_library_oktoberfest.csv
new file mode 100644
index 0000000000000000000000000000000000000000..1387ae724c7d4a2bb6de0e881f852f4500e156c3
Binary files /dev/null and b/data/spectral_lib/df_predicted_library_oktoberfest.csv differ
diff --git a/diann_lib_processing.py b/diann_lib_processing.py
deleted file mode 100644
index 51ba849b5896c1defa87284e239807a95c1d6335..0000000000000000000000000000000000000000
--- a/diann_lib_processing.py
+++ /dev/null
@@ -1,79 +0,0 @@
-import numpy as np
-import pandas as pb
-import pandas as pd
-import pyarrow.parquet as pq
-import torch
-from model.model import ModelTransformer
-from config import load_args
-from data.dataset import load_data
-
-
-def load_lib(path):
- table = pq.read_table('data/spectral_lib/first_lib.parquet')
- table = table.to_pandas()
-
- return table
-
-def extract_sequence(data_frame):
-
- seq = data_frame['Modified.Sequence']
-
- df_pred = pd.DataFrame(seq)
- df_pred.columns = ['sequence']
- df_pred['sequence']=df_pred['sequence'].map(lambda x:x.replace('M(UniMod:35)','-OxM-'))
- df_pred['remove']=df_pred['sequence'].map((lambda x : 'U' in x))
- df_pred = df_pred[df_pred['remove']==False]
- df_pred = df_pred[['sequence']]
- df_pred['irt_scaled']=0
- df_pred['state'] = 'holdout'
-
- df_pred = df_pred.drop_duplicates()
-
- return df_pred
-
-def predict(data_pred, model, output_path):
- data_frame = pd.DataFrame()
- model.eval()
- for param in model.parameters():
- param.requires_grad = False
-
- pred_rt, seqs, true_rt = [], [], []
- for seq, rt in data_pred:
- rt = rt.float()
- if torch.cuda.is_available():
- seq, rt = seq.cuda(), rt.cuda()
- pr_rt = model.forward(seq)
- pred_rt.extend(pr_rt.data.cpu().tolist())
- seqs.extend(seq.data.cpu().tolist())
- true_rt.extend(rt.data.cpu().tolist())
-
- data_frame['rt pred'] = pred_rt
- data_frame['seq'] = seqs
- data_frame['true rt'] = true_rt
- data_frame.to_csv(output_path)
-
-
-if __name__ =='__main__':
- # df = load_lib('data/spectral_lib/first_lib.parquet')
- # df_2 = extract_sequence(df).reset_index(drop=True)
- # df_2.to_csv('data/spectral_lib/data_uniprot_base.csv', index=False)
-
-
-
- args = load_args()
-
- model = ModelTransformer(encoder_ff=args.encoder_ff, decoder_rt_ff=args.decoder_rt_ff,
- n_head=args.n_head, encoder_num_layer=args.encoder_num_layer,
- decoder_rt_num_layer=args.decoder_rt_num_layer, drop_rate=args.drop_rate,
- embedding_dim=args.embedding_dim, acti=args.activation, norm=args.norm_first, seq_length=30)
-
- if torch.cuda.is_available():
- model = model.cuda()
-
- model.load_state_dict(torch.load(args.model_weigh, weights_only=True))
-
- print(args.dataset_test)
- data_test = load_data(data_source='data/spectral_lib/data_uniprot_base.csv', batch_size=args.batch_size, length=30, mode=args.split_test,
- seq_col=args.seq_test)
-
- predict(data_test, model, args.output)
\ No newline at end of file