Computational and Mathematical Biology Centre
Our Tools
Here is an advanced, indigenously developed web-based platform designed by Dr. Samrat Chatterjee and his team.
1.
Konnect2Prot 1.0
Protein-protein interactions are central to understanding the functional relationship between proteins. We have curated the available information and augmented with context-specific analysis to ease your research journey.
Konnect2Prot 2.0
2.
konnect2prot 2.0 is an advanced, indigenously developed web-based platform designed by Dr. Samrat Chatterjee and his team. It takes protein analysis to the next level with a suite of robust analysis and enrichment tools. Built to cater to the needs of modern biological research, this version extends the core functionality of network generation with additional features for in-depth investigation of biological pathways, protein-protein interactions (PPIs), and functional enrichment.
3.
TCGAimmunosurv (R package)
We developed a pan-cancer R package called TCGAimmunosurv that integrates bulk RNA-Seq data from The Cancer Genome Atlas (TCGA) with scRNA-Seq data to identify the genes to investigate mutation-specific immune dynamics.
Key points
📍 Preloaded datasets, preprocessing, and visualization tools for analysis
📍 Mutation-specific survival analysis
📍 Immune-cell-specific pseudotime trajectory analysis
4.
HistoSpace
We developed a novel autoencoder-based algorithm , HistoSPACE, for spatial gene expression prediction from histological images. This algorithm seeks to balance model complexity and accuracy, providing a compact yet powerful solution for spatial transcriptomic profiling.
5.
FIRE
We present FIRE(Feature Identification and Refinement Engine), a novel machine learning(ML)-driven framework designed for integrative analysis and feature refinement. FIRE incorporates data merging and an ensemble ML approach capable of detecting both linear and non-linear patterns across diverse datasets. This enables robust extraction of biologically meaningful features from complex, heterogeneous omics data.
6.
FLASH
We present 'FLASH', (Feature Learning Augmented with Sampling and Heuristics ), a novel feature selection method combining filtration and heuristic-based systematic elimination. FLASH generates random samples and computes p-values for each feature using multiple statistical tests(t-test, ANOVA, Wilcoxon Rank-Sum, Brunner-Munzel, Mann-Whitney ). Features are scored by aggregating significant p-values across samples. The coefficient from the machine learning model with the highest accuracy on the filtered features is used to rank them.
