Sergey Kolchenko azkalot1

MLE at Cellarity. MIPT (2017), the University of Chicago (2021). Bioinformatics and deep learning.

azkalot1 / train_main.py

Created December 18, 2020 05:31

	callbacks = [
	# Each criterion is calculated separately.
	CriterionCallback(
	input_key="mask",
	prefix="loss_dice",
	criterion_key="dice"
	),
	CriterionCallback(
	input_key="mask",
	prefix="loss_bce",

azkalot1 / make_model.py

Created December 18, 2020 05:28

	import torch
	import segmentation_models_pytorch as smp
	import numpy as np
	import matplotlib.pyplot as plt
	from catalyst import dl, metrics, core, contrib, utils
	import torch.nn as nn
	from skimage.io import imread
	import os
	from sklearn.model_selection import train_test_split
	from catalyst.dl import CriterionCallback, MetricAggregationCallback

azkalot1 / augs_dataset.py

Last active December 18, 2020 05:27

Augs_dataset

	import albumentations as A
	from torch.utils.data import Dataset, DataLoader
	from collections import OrderedDict

	class ChestXRayDataset(Dataset):
	def __init__(
	self,
	images,
	masks,
	transforms):

azkalot1 / train_correct.py

Created April 25, 2019 11:45


	import torch
	import torch.nn as nn
	import torch.nn.functional as F
	import torch.optim as optim
	from torch.autograd import Variable
	from torchvision import datasets, transforms
	from torch.optim import Optimizer
	from torch.utils import data
	import pretrainedmodels

azkalot1 / dataset_loader.py

Created April 25, 2019 11:36

	import torch
	import torch.nn as nn
	import torch.nn.functional as F
	import torch.optim as optim
	from torch.autograd import Variable
	from torchvision import datasets, transforms
	from torch.optim import Optimizer
	from torch.utils import data

	class DataGenerator(data.Dataset):

azkalot1 / clustering.py

Created February 12, 2019 22:53

	#basically like at https://scikit-learn.org/stable/auto_examples/cluster/plot_cluster_comparison.html, but our data is reall
	#prepre paramets
	params = {'quantile': .3,
	'eps': .3,
	'damping': .9,
	'preference': -200,
	'n_neighbors': 10,
	'n_clusters': 5}
	bandwidth = estimate_bandwidth(embedding, quantile=params['quantile'])
	connectivity = kneighbors_graph(

azkalot1 / pca_umap_plot.py

Created February 12, 2019 22:49

	pca = PCA(n_components=100)
	pca.fit(mat)
	mat_reduce = pca.transform(mat)
	embedding = umap.UMAP(n_neighbors=5,
	min_dist=0.5,
	metric='euclidean').fit_transform(mat_reduce)
	plt.figure(figsize=(15,15))
	plt.scatter(embedding[:,0],embedding[:,1],s=0.2);
	plt.title('Naive clustering');

azkalot1 / filtering.py

Created February 12, 2019 22:43

	cells_expression = mat.sum(axis=1)
	mat = mat[cells_expression>=100,:]
	mat = np.log(mat+1)

azkalot1 / EDA_2.py

Created February 12, 2019 22:40

	mat = mat[:,CV>=10]
	f, ax = plt.subplots(1,2,figsize=(15,5))
	per_cell_sum = mat.sum(axis=1)
	ax[0].hist(np.log10(per_cell_sum+1));
	ax[0].set_title('Distribtion of #UMIs per cell\n min {}, max {}, mean {} +- {}'.format(min(per_cell_sum),
	max(per_cell_sum), np.mean(per_cell_sum),
	np.sqrt(np.std(per_cell_sum))));
	per_gene_sum = mat.sum(axis=0)
	ax[1].hist(np.log10(per_gene_sum+1));
	ax[1].set_title('Distribtion of #UMIs per gene\n min {}, max {}, mean {} +- {}'.format(min(per_gene_sum),

azkalot1 / CV_plot.py

Created February 12, 2019 22:38

	low_expr_thr = 100
	high_expr_thr = 100000
	mat = mat[:,(per_gene_sum>=low_expr_thr) & (per_gene_sum<=high_expr_thr)] #just remove extreme outliers
	mean_exp = mat.mean(axis=0)
	std_exp = np.sqrt(mat.std(axis=0))
	CV = std_exp/mean_exp
	plt.hist(CV);
	plt.title('Distribution of CV, mean {} sd {}'.format(np.mean(CV), np.std(CV)**0.5));