Biology & Genomics

Build lncRNA-mRNA networks from target lists using local ceRNA reference tables

Clean and compare mass spectrometry spectra with reproducible similarity scoring

Move a mechanism finding from descriptive evidence to functional validation

Screen compound libraries with drug-likeness, PAINS alerts and complexity filters

Explain inheritance, Mendelian laws and Punnett squares as a genetics mentor

Query NIH Metabolomics Workbench studies, metabolites and MS data by API

Interpret alpha and beta diversity results from 16S rRNA sequencing studies

Script 3D animations and plain explanations of how drugs act in the body

Generate publication-quality sequence logos for DNA and protein motifs

Plan studies that combine Mendelian randomization with single-cell transcriptomics

Plan studies that integrate clinical variables with multi-omics data

Predict neoantigens that the immune system may recognize from variant data

Plan network toxicology and molecular docking studies for a toxicant and disease

Run Neuropixels spike sorting, motion correction and QC from raw recordings

Query Open Targets for target-disease associations and evidence scores

Write academic introductions to biological pathways with markers and inhibitors

Plan cancer transcriptome studies built around programmed cell death genes

Search and download RCSB Protein Data Bank structures by text, sequence or 3D shape

Write academic introductions to cellular phenotypes covering mechanisms and detection

Build protein-protein interaction networks from gene lists using an offline STRING cache

Fit preclinical pharmacokinetic and pharmacodynamic models with explicit checks

Plan diagnostic biomarker studies built on process-related genes and nomograms

Standardize scattered lab steps into reproducible protocols and flag missing parameters

Visualize single-cell pseudotime trajectories and branch structure in review-ready plots

Search PubChem for compound properties, similarity searches and bioactivity data

Run DESeq2-style differential expression on bulk RNA-seq counts in Python

Process mass spectrometry data in mzML and MGF with PyOpenMS for proteomics

Read and write SAM, BAM, VCF and FASTQ files and compute coverage in Python

Plan QTL colocalization studies linking eQTL or pQTL signals to GWAS loci

Query Reactome pathways, reactions and gene list enrichment results

Find validated alternative lab reagents using citation data from the literature

Check Sanger sequencing chromatograms for quality and flag unreliable base calls

Run single-cell RNA-seq QC, clustering, UMAP and differential expression with Scanpy

Compute diversity, ordination and statistics on FASTA, Newick and BIOM data

Label single-cell clusters with cell types using marker gene evidence

Correct batch effects and integrate single-cell omics with scVI deep generative models

Align nucleotide and protein sequences against databases using the NCBI BLAST API

Design complete single-cell research plans for disease, biomarker and validation studies

Plan network toxicology studies linking one compound to one disease with docking

Plan network pharmacology studies for one drug adverse effect using hub gene analysis

Plan network pharmacology studies for one drug adverse effect anchored on pathways

Plan oncology studies on one candidate gene covering expression and prognosis

Search Broad Single Cell Portal datasets by organism, tissue, disease or cell type

Map 10x Visium and Xenium spatial transcriptomics data onto tissue images

Estimate immune infiltration with ssGSEA or GSVA and compare case and control groups

Map protein IDs and pull STRING interaction networks with enrichment analysis

Score how novel a biological drug target is using literature mining

Identify regulating transcription factors for a gene list and plot a TF-target network

Screen compounds for toxic structural alerts and explain each flag