3. Data, Science & AI

Enables API integration for Coze smart agents, supporting conversational AI and workflow execution in applications.

Guides developers in building collaborative AI agent teams, structured workflows, and production-ready automation with CrewAI framework.

Converts PDF, Office, images, audio, and web content to LLM-optimized Markdown with OCR, transcription, and batch processing capabilities.

Provides best practices for creating publication-ready molecular graphics in Coot, including color schemes, ribbon representations, and molecular visualization techniques.

Analyzes transcription factor motif accessibility variability across ATAC-seq samples using chromVAR to identify condition-dependent motif changes.

End-to-end CLIP-seq analysis pipeline processing FASTQ data to identify protein-RNA binding sites and perform motif enrichment analysis.

Identifies differential m6A methylation patterns between biological conditions using MeRIP-seq data for epitranscriptomic research.

Annotates CLIP-seq binding sites to genomic features (3'UTR, CDS, introns, ncRNAs) for RNA-binding protein (RBP) binding characterization in transcriptomics.

Performs differential miRNA expression analysis between biological conditions using DESeq2 or edgeR with small RNA-specific parameters.

End-to-end small RNA-seq analysis pipeline processing FASTQ data to differential miRNA/piRNA expression results for genomic research.

Detects m6A epitranscriptomic modifications in Oxford Nanopore long-read RNA sequencing data using m6Anet without immunoprecipitation.

Generates publication-quality phylogenetic trees using IQ-TREE2 and RAxML-ng with model selection, ultrafast bootstrap, and partitioned analyses from sequence alignments.

Analyzes CLIP-seq binding sites to identify enriched sequence motifs, characterizing RNA-binding protein (RBP) sequence preferences for molecular biology research.

Identifies m6A modification sites in RNA by analyzing MeRIP-seq immunoprecipitation versus input data through peak calling algorithms.

Preprocesses raw CLIP, iCLIP, and eCLIP sequencing data through adapter trimming, UMI extraction, and PCR duplicate removal for peak calling analysis.

Preprocesses MeRIP-seq data for m6A analysis through read alignment and quality control of IP/input samples.

Analyzes single-cell TCR and BCR data with gene expression using scirpy, enabling immune receptor profiling in scRNA-seq datasets.

Queries gnomAD database to retrieve population allele frequencies for variant rarity assessment in rare disease analysis.

Calculates translation efficiency (TE) from ribosome occupancy and mRNA abundance data to compare translational regulation between biological conditions.

Analyzes TCR and BCR sequencing data using MiXCR for V(D)J alignment and clonotype identification in immune repertoire studies.

Aligns CLIP-seq reads to a genome with crosslink site awareness for precise peak calling in protein-RNA interaction studies.

End-to-end Ribo-seq analysis pipeline processing FASTQ data to compute translation efficiency and detect open reading frames (ORFs).

Predicts protein structures for novel proteins and complexes using advanced ML models like AlphaFold3 and ESMFold, enabling structural biology research.

Analyzes multiple CRISPR screens simultaneously to model sgRNA efficacy and gene essentiality across experiments.