Your one stop solution for all your machine learning & bio-informatics needs.
Relevant projects:
Topic 1: “Clustering Single-cell data (10X) from differentiating cell lines for differentiation Biomarker’s identification”
Analyzed both client single-cell (10X) data and public (Drop-seq) single-cell data for differentiating cell lines. Performed data QC, across platform integration, and post-clustering collection of differentially expressed genes, and expression maps. Specifications of the different biomarkers.
Topic 2: “Assessing quality and biological relevance of DNA Methylation”
Analyzed both Illumina EPIC DNA methylation array and Reduced representation bisulfite sequence (RRBS) data sets at methylation mapping, quality control assessment and analysis with differential methylation (DM) of many different genome regions.
Topic 3: “Applied polypharmacology”
Develop and test methods of applied system pharmacology to analysis of an invitro characterization of a complete “drug to target” specificity map for a set of unspecific inhibitors and an in vivo phenotypic assay of a subset of these drugs. Construction of cocktails of drugs specific to some kinases using the “drug to target” specificity map.
Topic 4: “Comprehensive characterization of protein dynamics”
Developing quantitative machine learning methods to compute the synthesis and degradations rates including the confidence intervals which allow to deeper explore the functional subgroups of proteins and their properties. Performing clustering of protein dynamic patterns and gene enrichment analysis corresponding to these clusters allow to identify the transition point from the morphogenesis to organogenesis.
Topic 5: “Genome Analysis”
Developing computational tools (with web interface) for the comprehensive redundancy analysis for proteomes using various state-of-the-art numerical algorithms for sequence homology detection and specification of putative functions assigned to genes in unstudied organisms. In addition, performed a Bayesian confidence interval assignment in quantitative proteomics.
Topic 6: “Machine Learning in protein analysis”
Developing of a suitable predictive model assessing the effect of amino acid changes on a protein and its behavior. Report of data characteristics affecting the binding properties of proteins. Implemented predictive approach towards the impact on binding properties. Developing and implementing computational tools that assist in automating and streamlining structural protein screening.