网站开发it项目规划书,桐乡市城乡规划建设局网站,成都小程序系统定制开发,wordpress 页面下文章列表import theano
import numpy as np
import sys
import pandas as pd
import scipy
#scipy 模块是 Python 中用于科学计算和数据分析的重要模块之一。它包含了许多高级的数学函数和工具#xff0c;包括数值积分、优化、线性代数、统计等。
from scipy.stats import spearmanr
#…import theano
import numpy as np
import sys
import pandas as pd
import scipy
#scipy 模块是 Python 中用于科学计算和数据分析的重要模块之一。它包含了许多高级的数学函数和工具包括数值积分、优化、线性代数、统计等。
from scipy.stats import spearmanr
#scipy.stats模块是SciPy库中用于统计分析的模块它提供了许多用于概率分布和统计测试的函数。%matplotlib inline
import matplotlib.pyplot as plt我们将介绍加载模型和预测突变影响的基本函数。
下载预训练参数。
请首先使用 download_pretrained.sh 脚本下载预训练参数。
加载模型。
sys.path.insert(0, ../DeepSequence)import model
import helper
import train突变影响预测。
突变影响预测辅助函数始终针对比对中的焦点序列。我们可以单独请求预测突变效应。
为了获得可靠的突变效应预测结果我们建议从模型中取 Monte Carlo 500-2000 个样本使用 N_pred_iterations 参数。
我们可以预测单个、双重、三重突变等的影响。突变以元组列表的形式组织其中元组为Uniprot位置野生型氨基酸突变氨基酸。PABP
首先让我们加载一个模型。我们不需要在这里计算序列权重因为我们不是在训练模型而且在 CPU 上进行这项计算可能会很慢。
在 Explore model parameters.ipynb 笔记本中helper.py 代码被修改以预先指定 DataHelper 类使用的数据集。然而我们可以传入一个比对名称和一些额外参数这样就不必修改 helper.py 文件。data_params {alignment_file:datasets/PABP_YEAST_hmmerbit_plmc_n5_m30_f50_t0.2_r115-210_id100_b48.a2m}pabp_data_helper helper.DataHelper(alignment_filedata_params[alignment_file],working_dir.,#指定当前程序的工作目录为当前所在的目录。calc_weightsFalse#不计算权重)model_params {batch_size : 100,encode_dim_zero : 1500,encode_dim_one : 1500,decode_dim_zero : 100,decode_dim_one : 500,n_patterns : 4,n_latent : 30,logit_p : 0.001,sparsity : logit,encode_nonlin : relu,decode_nonlin : relu,final_decode_nonlin: sigmoid,output_bias : True,final_pwm_scale : True,conv_pat : True,d_c_size : 40}pabp_vae_model model.VariationalAutoencoder(pabp_data_helper,batch_size model_params[batch_size],encoder_architecture [model_params[encode_dim_zero],model_params[encode_dim_one]],decoder_architecture [model_params[decode_dim_zero],model_params[decode_dim_one]],n_latent model_params[n_latent],n_patterns model_params[n_patterns],convolve_patterns model_params[conv_pat],conv_decoder_size model_params[d_c_size],logit_p model_params[logit_p],sparsity model_params[sparsity],encode_nonlinearity_type model_params[encode_nonlin],decode_nonlinearity_type model_params[decode_nonlin],final_decode_nonlinearity model_params[final_decode_nonlin],output_bias model_params[output_bias],final_pwm_scale model_params[final_pwm_scale],working_dir .)print (Model built)我们查看一下datasets文件夹下的PABP_YEAST_hmmerbit_plmc_n5_m30_f50_t0.2_r115-210_id100_b48.a2m文件显示有456123行每三行为一组数据表明有152041组数据 可以看到比对文件是使用的类似于FASTA格式的氨基酸序列。
Encoding sequences
Neff 151528.0
Data Shape (151528, 82, 20)
Model built加载预训练模型在 ‘params’ 文件夹中的参数。
file_prefix PABP_YEAST
pabp_vae_model.load_parameters(file_prefixfile_prefix)
print (Parameters loaded)Parameters loadedprint (pabp_data_helper.delta_elbo(pabp_vae_model,[(126,G,A)], N_pred_iterations500))-2.03463650668print (pabp_data_helper.delta_elbo(pabp_vae_model,[(126,G,A), (137,I,P)], N_pred_iterations500))-10.8308351474注意这里我单独计算了(137,“I”,“P”)的elbo计算结果如下 print (pabp_data_helper.delta_elbo(pabp_vae_model,[(137,I,P)], N_pred_iterations500))
-9.21612828741可以看到计算的结果不是每个突变的简单叠加。
print (pabp_data_helper.delta_elbo(pabp_vae_model,[(126,G,A), (137,I,P), (155,S,A)], N_pred_iterations500))-16.058655309这里我将同样的程序跑了三遍但结果有略微出入。 print (pabp_data_helper.delta_elbo(pabp_vae_model,[(126,G,A), (137,I,P), (155,S,A)], N_pred_iterations500))
-15.8832967199print (pabp_data_helper.delta_elbo(pabp_vae_model,[(126,G,A), (137,I,P), (155,S,A)], N_pred_iterations500))
-15.7348273612print (pabp_data_helper.delta_elbo(pabp_vae_model,[(126,G,A), (137,I,P), (155,S,A)], N_pred_iterations500))
-15.6141800809我又计算了(155,“S”,“A”)的单独的突变影响结果如下 print (pabp_data_helper.delta_elbo(pabp_vae_model,[(155,S,A)], N_pred_iterations500))
-4.43953605237可见虽然不是每个位点突变的简单相加但也近似于相加的结果。
我们可以预测所有单个突变的影响。优选使用此函数及以下函数因为它们能够利用对突变数据进行小批量处理所带来的加速优势。
pabp_full_matr_mutant_name_list, pabp_full_matr_delta_elbos \ pabp_data_helper.single_mutant_matrix(pabp_vae_model, N_pred_iterations500)print (pabp_full_matr_mutant_name_list[0], pabp_full_matr_delta_elbos[0])(K123A, 0.5887526915685584)我们还可以以批处理模式从文件中预测突变的影响。pabp_custom_matr_mutant_name_list, pabp_custom_matr_delta_elbos \ pabp_data_helper.custom_mutant_matrix(mutations/PABP_YEAST_Fields2013-singles.csv, \pabp_vae_model, N_pred_iterations500)print (pabp_custom_matr_mutant_name_list[12], pabp_custom_matr_delta_elbos[12])(N127D, -6.426795215037501)我们也可以编写一个快速的函数来从一个突变文件计算 Spearman 系数rho。def generate_spearmanr(mutant_name_list, delta_elbo_list, mutation_filename, phenotype_name):measurement_df pd.read_csv(mutation_filename, sep,)mutant_list measurement_df.mutant.tolist()expr_values_ref_list measurement_df[phenotype_name].tolist()mutant_name_to_pred {mutant_name_list[i]:delta_elbo_list[i] for i in range(len(delta_elbo_list))}# If there are measurements wt_list []preds_for_spearmanr []measurements_for_spearmanr []for i,mutant_name in enumerate(mutant_list):expr_val expr_values_ref_list[i]# Make sure we have made a prediction for that mutantif mutant_name in mutant_name_to_pred:multi_mut_name_list mutant_name.split(:)# If there is no measurement for that mutant, pass over itif np.isnan(expr_val):pass# If it was a codon change, add it to the wt vals to averageelif mutant_name[0] mutant_name[-1] and len(multi_mut_name_list) 1:wt_list.append(expr_values_ref_list[i])# If it is labeled as the wt sequence, add it to the average listelif mutant_name wt or mutant_name WT:wt_list.append(expr_values_ref_list[i])else:measurements_for_spearmanr.append(expr_val)preds_for_spearmanr.append(mutant_name_to_pred[mutant_name])if wt_list ! []:measurements_for_spearmanr.append(np.mean(average_wt_list))preds_for_spearmanr.append(0.0)num_data len(measurements_for_spearmanr)spearman_r, spearman_pval spearmanr(measurements_for_spearmanr, preds_for_spearmanr)print (N: str(num_data), Spearmanr: str(spearman_r), p-val: str(spearman_pval))generate_spearmanr(pabp_custom_matr_mutant_name_list, pabp_custom_matr_delta_elbos, \mutations/PABP_YEAST_Fields2013-singles.csv, log)N: 1188, Spearmanr: 0.6509305755221257, p-val: 4.0800344026520655e-144PDZ
data_params {alignment_file:datasets/DLG4_RAT_hmmerbit_plmc_n5_m30_f50_t0.2_r300-400_id100_b50.a2m}pdz_data_helper helper.DataHelper(alignment_filedata_params[alignment_file],working_dir.,calc_weightsFalse)pdz_vae_model model.VariationalAutoencoder(pdz_data_helper,batch_size model_params[batch_size],encoder_architecture [model_params[encode_dim_zero],model_params[encode_dim_one]],decoder_architecture [model_params[decode_dim_zero],model_params[decode_dim_one]],n_latent model_params[n_latent],n_patterns model_params[n_patterns],convolve_patterns model_params[conv_pat],conv_decoder_size model_params[d_c_size],logit_p model_params[logit_p],sparsity model_params[sparsity],encode_nonlinearity_type model_params[encode_nonlin],decode_nonlinearity_type model_params[decode_nonlin],final_decode_nonlinearity model_params[final_decode_nonlin],output_bias model_params[output_bias],final_pwm_scale model_params[final_pwm_scale],working_dir .)print (Model built)file_prefix DLG4_RAT
pdz_vae_model.load_parameters(file_prefixfile_prefix)print (Parameters loaded\n\n)pdz_custom_matr_mutant_name_list, pdz_custom_matr_delta_elbos \ pdz_data_helper.custom_mutant_matrix(mutations/DLG4_RAT_Ranganathan2012.csv, \pdz_vae_model, N_pred_iterations500)generate_spearmanr(pdz_custom_matr_mutant_name_list, pdz_custom_matr_delta_elbos, \mutations/DLG4_RAT_Ranganathan2012.csv, CRIPT)Encoding sequences
Neff 102246.0
Data Shape (102246, 84, 20)
Model built
Parameters loadedN: 1577, Spearmanr: 0.6199244929585085, p-val: 4.31636475994128e-168B-lactamase
对于包含更多待预测突变的较大蛋白质运行时间可能会更长。针对这种情况我们建议使用支持 GPU 的计算。data_params {dataset:BLAT_ECOLX}blat_data_helper helper.DataHelper(datasetdata_params[dataset],working_dir.,calc_weightsFalse)blat_vae_model model.VariationalAutoencoder(blat_data_helper,batch_size model_params[batch_size],encoder_architecture [model_params[encode_dim_zero],model_params[encode_dim_one]],decoder_architecture [model_params[decode_dim_zero],model_params[decode_dim_one]],n_latent model_params[n_latent],n_patterns model_params[n_patterns],convolve_patterns model_params[conv_pat],conv_decoder_size model_params[d_c_size],logit_p model_params[logit_p],sparsity model_params[sparsity],encode_nonlinearity_type model_params[encode_nonlin],decode_nonlinearity_type model_params[decode_nonlin],final_decode_nonlinearity model_params[final_decode_nonlin],output_bias model_params[output_bias],final_pwm_scale model_params[final_pwm_scale],working_dir .)print (Model built)file_prefix BLAT_ECOLX
blat_vae_model.load_parameters(file_prefixfile_prefix)print (Parameters loaded\n\n)blat_custom_matr_mutant_name_list, blat_custom_matr_delta_elbos \ blat_data_helper.custom_mutant_matrix(mutations/BLAT_ECOLX_Ranganathan2015.csv, \blat_vae_model, N_pred_iterations500)generate_spearmanr(blat_custom_matr_mutant_name_list, blat_custom_matr_delta_elbos, \mutations/BLAT_ECOLX_Ranganathan2015.csv, 2500)Encoding sequences
Neff 8355.0
Data Shape (8355, 253, 20)
Model built
Parameters loadedN: 4807, Spearmanr: 0.743886370415797, p-val: 0.0
