NikolayOskolkov

tSNE_vs_UMAP_GlobalStructure

Here we address the global structure preservation by tSNE and UMAP

HowUMAPWorks

Here I explain the math behind UMAP and show how to program it from scratch in Python

DeepLearningDataIntegration

Here I show how to use Deep Learning for biological and biomedical Data Integration.

NormalizeSingleCell

Comparison of single cell normalization strategies

UMAPDataIntegration

Graph based data integration with UMAP

DeepLearningMicrobiome

LSTMNeanderthalDNA

Implementation of LSTM for detecting regions of Neanderthal introgression in modern human genomes

DimReductSingleCell

Here I cover linear and non-linear dimension reduction techniques for single cell genomics

SupervisedOMICsIntegration

Supervised intehration of CLL data with PLS-DA from DIABLO mixOmics

UnivariteVsMultivariteModels

Here we compare a few multivarite and univarite feature selection models

aMeta

DeepLearningNeanderthalIntrogression

Here I deposite input files and Jupyter notebooks on detecting Neanderthal introgression analysis

GenomicsNewClothes

Here I discuss common pitfalls in Genetics research due to the high-dimensional nature of genetic variation data that suffers from the Curse of Dimensionality

LMMFromScratch

Deriving and coding Linear Mixed Model (LMM) from scratch

HowToBatchCorrectSingleCell

Here I explain batch-effects correction techniques for scRNAseq experiments

HowToInitializeUMAPtSNE

Checking how tSNE and UMAP depend on different initialization scenarios

OsloBioinfoWeek2022

SBW2022

This is a teaching material for scRNAseq workshop within SBW2022

tSNELargePerplexityLimit

Here we investigate the degradation of tSNE to PCA / MDS at large perplexity values

UMAP_VarianceExplained

Here I show a simple way to estimate data variance explained by UMAP and tSNE components

UnsupervisedOMICsIntegration

Multi-OMICs Factor Analysis on scNMT data set

WhyPCALooksTriangular

Here I provide some insights on the peculiar triangular shape of PCA plots that can often be found in Life Science projects

COVID19

Corona infection related computations

HowLinearMixedModelWorks

REML

Deriving and coding Linear Mixed Model in Restricted Maximum Likelihood (REML) approach

AMDirT

Check validity of AncientMetagenomeDir dataset

AncientMetagenomeDir

Repository containing lists of all published ancient metagenome samples (and related)

Iceman_fungi

Here we provide scripts used for analysis of fungal community in Iceman metagenomic data

IntegrativeOmicsWorkflow

Here we provide a primer-workflow for biological data integration analysis.

PlagueRandomSample