Name: Vitalii Kleshchevnikov
Type: User
Company: Wellcome Sanger Institute
Bio: Causal & mechanistic ML/AI models of cell identity & tissue architecture, w large sc multi-omics & spatial atlases. PhD w Dr Bayraktar, Dr Teichmann, Dr Stegle.
Twitter: vitaliikl
Location: Cambridge, UK
Vitalii Kleshchevnikov's Projects
Spatial mapping in the adult lung
just keeping materials easily findable: Supplementary files for vsbuffalo book, "Bioinformatics Data Skills"
Testing cell2location features
Translation of cell2location model into numpyro (https://github.com/BayraktarLab/cell2location)
Cell2location paper - Comprehensive mapping of tissue cell architecture via integrated single cell and spatial transcriptomics
cell2module: decomposing scRNA and scATAC cell identity into gene modules using count-based Bayesian NMF
TF activation experiments for cell2state model project
:bar_chart:added kappa score similarity to the original package: statistical analysis and visualization of functional profiles for genes and gene clusters
Mapping locations of cortical single astrocyte RNA-seq
Dark Space Project: how to find published but not curated interaction data
:mask:Disease Ontology Semantic and Enrichment analysis
Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch
Spatial mapping in the fetal gut using cell2location (accompanying paper ...)
Spatial mapping of human limb cell type mapping with cell2location
gene expression simulator: 2 sample groups, 2 gene modules, batch effect
Automated discovery of functional generality of gene expression
:golf:GO-terms Semantic Similarity Measures
Characterising molecular interaction data curated into IMEx databases (IntAct)
The official Inferelator repository maintained by current or former Bonneau lab members
just keeping materials easily findable: Rmd source files for the HarvardX series PH525x
A version of ArrayExpress R package that uses data.table::fread(..., data.table = F) to read processed data
Find enriched features of neighbours in a network
Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.
Formalizing and benchmarking open problems in single-cell genomics
One-liner for mapping orthologous genes in both R and python using ENSEMBL BioMART
R toolbox for Archetypal Analysis and Pareto Task Inference on single cell data (based on ParTI)
Protein interaction data tools, retrieving data from IntAct and most other databases
Study bias in the protein network
For online courses: Repository for Programming Assignment 2 for R Programming on Coursera
Work with InterPro Protein Domains and FASTA Sequences (UniProt)