Skill UI

PyTDC (Therapeutics Data Commons) is an open-science platform providing standardized, AI-ready datasets and benchmarks for drug discovery and development. It supports three core types of tasks: single-instance prediction (e.g., ADME, toxicity), multi-instance prediction (e.g., DDI, DTI), and novel molecule generation. It is essential for benchmarking and developing therapeutic machine learning models.

A comprehensive Python library for simulating quantum mechanical systems. It models both closed (unitary) and open (dissipative) quantum dynamics, covering key concepts like master equations, decoherence, and quantum optics. Users can simulate time evolution, calculate entanglement (concurrence), and visualize quantum states (Wigner functions).

RDKit is a comprehensive Python library providing robust APIs for molecular structure handling, analysis, and manipulation. It supports reading/writing diverse molecular formats (SMILES, SDF, MOL, InChI), calculating physicochemical descriptors (e.g., LogP, TPSA, MW), performing substructure searching, and analyzing stereochemistry. Ideal for use in drug discovery, computational chemistry, and academic research.

This skill provides real-time, comprehensive research information lookup. It intelligently routes queries to the optimal backend—using fast web search for general queries, deep synthesis APIs for complex topics, or specialized academic search engines for scholarly papers. Ideal for fact-checking, academic literature review, and industry trend analysis.

scikit-bio is a comprehensive Python library designed for advanced bioinformatics and biological data analysis. It provides robust tools for sequence manipulation (DNA, RNA, Protein), performing sophisticated sequence alignments (global, local, multiple), constructing and analyzing phylogenetic trees, and conducting complex ecological statistics. Key features include calculating diversity metrics (alpha/beta), running ordination analyses (PCoA), and handling diverse biological file formats (FASTA, Newick, BIOM). Ideal for researchers in microbiology, genomics, and ecology.

This is a powerful Python library built on scikit-learn for conducting advanced survival analysis and time-to-event modeling. It excels at handling censored data (e.g., right-censored) and allows users to fit various models, including Cox proportional hazards, Random Survival Forests, and Gradient Boosting. Users can also evaluate model performance using metrics like the Concordance Index (C-index) and Brier score, making it ideal for biomedical, clinical, or reliability engineering applications.

scvi-tools is a comprehensive Python framework utilizing deep generative models and variational inference for analyzing diverse single-cell data modalities. It excels in complex analyses such as probabilistic batch correction (scVI), multi-modal integration (MultiVI), and differential expression analysis with uncertainty. It supports single-cell RNA-seq, ATAC-seq, and various multi-omics datasets, providing advanced tools for modern genomic research.

Seaborn is a powerful Python library designed for creating high-level, publication-quality statistical graphics. It integrates seamlessly with pandas DataFrames, allowing users to easily visualize complex statistical relationships, distributions, and comparisons (e.g., box plots, violin plots, heatmaps). It simplifies multivariate analysis and exploratory data analysis (EDA) with minimal code.

SymPy is a powerful Python library designed for symbolic mathematics. Unlike numerical libraries, it allows for exact computation using mathematical symbols, enabling precise solutions for algebra, calculus (derivatives, integrals), linear algebra, and solving complex equations. This tool is ideal for academic research, physics modeling, and advanced scientific computing requiring non-approximate results. It also supports code generation in various languages.

Access the U.S. Department of the Treasury's free, open REST API to retrieve comprehensive federal financial data. This tool allows users to query key metrics such as national debt, interest rates, exchange rates, daily treasury statements, and auction data. Built with Python and Pandas, it is perfect for financial analysis, economic monitoring, and tracking public sector finances without needing an API key.

Vaex is a high-performance Python library designed for lazy, out-of-core DataFrames. It enables processing and visualization of massive tabular datasets (billions of rows) that exceed available RAM. Users can perform fast statistics, aggregations, and build robust ML pipelines on big data files (CSV, Parquet, HDF5) without relying on distributed clusters, making it ideal for single-machine, large-scale analytics.

Access 78 public REST APIs spanning biomedical, materials science, physics, environment, and economics. This skill allows users to query vast datasets for compounds, genes, proteins, patents, and economic indicators by selecting the relevant database and executing precise API calls. Ideal for comprehensive scientific research and data gathering.