-
IOCB Prague / Charles University
- Prague
- https://prankweb.cz
- @rdkbio
- in/radoslavkrivak
- https://scholar.google.cz/citations?user=mq86xg0AAAAJ
- @rdkbio.bsky.social
- All languages
- C
- C#
- C++
- CSS
- Clojure
- Common Workflow Language
- Cuda
- Cython
- Dockerfile
- Elixir
- Fortran
- Go
- Groovy
- HTML
- Java
- JavaScript
- Jupyter Notebook
- Kotlin
- Lua
- M4
- MATLAB
- MDX
- Makefile
- Max
- Nextflow
- PHP
- Perl
- PostScript
- PureScript
- Python
- R
- Rich Text Format
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Swift
- TeX
- TypeScript
- Typst
- Vim Script
- Visual Basic
- Vue
- Zig
Starred repositories
GPU tensor unlock source for RTX 4090 and experimental RTX 4070 Ti SUPER; firmware generated locally
A tool for evaluating the predictive performance on activity cliff compounds of machine learning models
Monroe: A Molecular Foundation Model for In-Context Probabilistic Inference
top for Google Colab: compute units, runtimes and live GPU graphs in your terminal
Neural synthon factorization: distill molecular property models into cached factors for fast Cartesian scoring
The Modular and Open-source Implicit Solvation Toolkit (MOIST): smooth, differentiable molecular cavities, efficient PCMs, pressure (GOSTSHYP) and statistical (RISM) solvation models in modern Fort…
A library to handle molecular point group symmetry.
Sandbox, execution tracer, and flight recorder for potentially dangerous Linux binaries - layered ptrace/L2 tracing, simulated-internet sink + TLS-MITM, memory snapshots, YARA, and a Svelte web UI.
PaperOrchestra is a multi-agent framework for automated AI research paper writing.
Exact molecular similarity search and protected training pools with packed fingerprints, resumable jobs, and cluster shards.
A Multi-modal and Multi-scale Unified Deep Learning Framework for Drug-Target Interaction Prediction
My private personal paper manager, holding all the notes and all the papers.
The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
Modular, open-source framework for ensemble virtual screening: sequence → conformational ensemble → docking → ranked hits.
Official implementation of Scallop: "Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps".
An Open Source implementation of Notebook LM with more flexibility and features
A curated collection of resources and research related to the geometry of representations in the brain, deep networks, and beyond
Transformer fusion pipeline for protein binding-site prediction using ESM2 protein embeddings, physicochemical surface descriptors, and neighbourhood-aware attention.
IPSAE2: calculates ipSAE scores for protein/protein, protein/ligand, protein/nucleic-acid complexes, etc.
Trainable protein folding and co-folding models with a protein language model.