skills/claude-scientific-skills
1
0
Fork 0
mirror of https://github.com/K-Dense-AI/claude-scientific-skills.git synced 2026-01-26 16:58:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

Enhance README.md with detailed instructions for various workflows, emphasizing the importance of organized output and the creation of comprehensive documentation and visualizations.

Browse Source
This commit is contained in:
Timothy Kassis
2025-10-24 09:30:56 -07:00
parent 0e03bbcf38
commit 1871693348
1 changed files with 30 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
README.md
View File

@@ -111,19 +111,22 @@ Once you've installed the skills, you can ask Claude to execute complex multi-st
### End-to-End Drug Discovery Pipeline ### End-to-End Drug Discovery Pipeline
``` ```
"Always use available 'skills' when possible "Always use available 'skills' when possible. Keep the output organized.
I need to find novel EGFR inhibitors for lung cancer treatment. Query ChEMBL for existing I need to find novel EGFR inhibitors for lung cancer treatment. Query ChEMBL for existing
EGFR inhibitors with IC50 < 50nM, analyze their structure-activity relationships using RDKit, EGFR inhibitors with IC50 < 50nM, analyze their structure-activity relationships using RDKit,
generate similar molecules with improved properties using datamol, perform virtual screening generate similar molecules with improved properties using datamol, perform virtual screening
with DiffDock against the AlphaFold-predicted EGFR structure, and search PubMed for recent with DiffDock against the AlphaFold-predicted EGFR structure, and search PubMed for recent
papers on resistance mechanisms to prioritize scaffolds. Finally, check COSMIC for common papers on resistance mechanisms to prioritize scaffolds. Finally, check COSMIC for common
EGFR mutations and assess how our candidates might interact with mutant forms." EGFR mutations and assess how our candidates might interact with mutant forms.
Create useful visualizations in the form of scientific figures as you go (if needed).
When done, create a comprehensive README.md and a well formatted pdf summarizing the methodology,
results, conclusions and providing recommendations."
``` ```
### Comprehensive Single-Cell Analysis Workflow ### Comprehensive Single-Cell Analysis Workflow
``` ```
"Always use available 'skills' when possible "Always use available 'skills' when possible. Keep the output organized.
Load this 10X Genomics dataset using Scanpy, perform quality control and doublet removal, Load this 10X Genomics dataset using Scanpy, perform quality control and doublet removal,
integrate with public data from Cellxgene Census for the same tissue type, identify cell integrate with public data from Cellxgene Census for the same tissue type, identify cell
@@ -131,24 +134,30 @@ populations using known markers from NCBI Gene, perform differential expression
with PyDESeq2, run gene regulatory network inference with Arboreto, query Reactome and with PyDESeq2, run gene regulatory network inference with Arboreto, query Reactome and
KEGG for pathway enrichment, and create publication-quality visualizations with matplotlib. KEGG for pathway enrichment, and create publication-quality visualizations with matplotlib.
Then cross-reference top dysregulated genes with Open Targets to identify potential Then cross-reference top dysregulated genes with Open Targets to identify potential
therapeutic targets." therapeutic targets.
Create useful visualizations in the form of scientific figures as you go (if needed).
When done, create a comprehensive README.md and a well formatted pdf summarizing the methodology,
results, conclusions and providing recommendations."
``` ```
### Multi-Omics Integration for Biomarker Discovery ### Multi-Omics Integration for Biomarker Discovery
``` ```
"Always use available 'skills' when possible "Always use available 'skills' when possible. Keep the output organized.
I have RNA-seq, proteomics, and metabolomics data from cancer patients. Use PyDESeq2 for I have RNA-seq, proteomics, and metabolomics data from cancer patients. Use PyDESeq2 for
differential expression, pyOpenMS to analyze mass spec data, and integrate metabolite differential expression, pyOpenMS to analyze mass spec data, and integrate metabolite
information from HMDB and Metabolomics Workbench. Map proteins to pathways using UniProt information from HMDB and Metabolomics Workbench. Map proteins to pathways using UniProt
and KEGG, identify protein-protein interactions via STRING, correlate multi-omics layers and KEGG, identify protein-protein interactions via STRING, correlate multi-omics layers
using statsmodels, and build a machine learning model with scikit-learn to predict patient using statsmodels, and build a machine learning model with scikit-learn to predict patient
outcomes. Search ClinicalTrials.gov for ongoing trials targeting the top candidates." outcomes. Search ClinicalTrials.gov for ongoing trials targeting the top candidates.
Create useful visualizations in the form of scientific figures as you go (if needed).
When done, create a comprehensive README.md and a well formatted pdf summarizing the methodology,
results, conclusions and providing recommendations."
``` ```
### Structure-Based Virtual Screening Campaign ### Structure-Based Virtual Screening Campaign
``` ```
"Always use available 'skills' when possible "Always use available 'skills' when possible. Keep the output organized.
I want to discover allosteric modulators for a protein-protein interaction. Retrieve the I want to discover allosteric modulators for a protein-protein interaction. Retrieve the
AlphaFold structure for both proteins, identify the interaction interface using BioPython, AlphaFold structure for both proteins, identify the interaction interface using BioPython,
@@ -156,12 +165,15 @@ search ZINC15 for molecules with suitable properties for allosteric binding (MW
logP 2-4), filter for drug-likeness using RDKit, perform molecular docking with DiffDock logP 2-4), filter for drug-likeness using RDKit, perform molecular docking with DiffDock
to identify potential allosteric sites, rank candidates using DeepChem's property prediction to identify potential allosteric sites, rank candidates using DeepChem's property prediction
models, check PubChem for suppliers, and search USPTO patents to assess freedom to operate. models, check PubChem for suppliers, and search USPTO patents to assess freedom to operate.
Finally, generate analogs with MedChem and molfeat for lead optimization." Finally, generate analogs with MedChem and molfeat for lead optimization.
Create useful visualizations in the form of scientific figures as you go (if needed).
When done, create a comprehensive README.md and a well formatted pdf summarizing the methodology,
results, conclusions and providing recommendations."
``` ```
### Clinical Genomics Variant Interpretation Pipeline ### Clinical Genomics Variant Interpretation Pipeline
``` ```
"Always use available 'skills' when possible "Always use available 'skills' when possible. Keep the output organized.
Analyze this VCF file from a patient with suspected hereditary cancer. Use pysam to parse Analyze this VCF file from a patient with suspected hereditary cancer. Use pysam to parse
variants, annotate with Ensembl for functional consequences, query ClinVar for known variants, annotate with Ensembl for functional consequences, query ClinVar for known
@@ -169,12 +181,15 @@ pathogenic variants, check COSMIC for somatic mutations in cancer, retrieve gene
from NCBI Gene, analyze protein impact using UniProt, search PubMed for case reports of from NCBI Gene, analyze protein impact using UniProt, search PubMed for case reports of
similar variants, query ClinPGx for pharmacogenomic implications, and generate a clinical similar variants, query ClinPGx for pharmacogenomic implications, and generate a clinical
report with ReportLab. Then search ClinicalTrials.gov for precision medicine trials matching report with ReportLab. Then search ClinicalTrials.gov for precision medicine trials matching
the patient's profile." the patient's profile.
Create useful visualizations in the form of scientific figures as you go (if needed).
When done, create a comprehensive README.md and a well formatted pdf summarizing the methodology,
results, conclusions and providing recommendations."
``` ```
### Systems Biology Network Analysis ### Systems Biology Network Analysis
``` ```
"Always use available 'skills' when possible "Always use available 'skills' when possible. Keep the output organized.
Starting with a list of differentially expressed genes from my RNA-seq experiment, query Starting with a list of differentially expressed genes from my RNA-seq experiment, query
NCBI Gene for detailed annotations, retrieve protein sequences from UniProt, identify NCBI Gene for detailed annotations, retrieve protein sequences from UniProt, identify
@@ -182,7 +197,10 @@ protein-protein interactions using STRING, map to biological pathways in Reactom
analyze network topology with Torch Geometric, identify hub genes and bottleneck proteins, analyze network topology with Torch Geometric, identify hub genes and bottleneck proteins,
perform gene regulatory network reconstruction with Arboreto, integrate with Open Targets perform gene regulatory network reconstruction with Arboreto, integrate with Open Targets
for druggability assessment, use PyMC for Bayesian network modeling, and create interactive for druggability assessment, use PyMC for Bayesian network modeling, and create interactive
network visualizations. Finally, search GEO for similar expression patterns across diseases." network visualizations. Finally, search GEO for similar expression patterns across diseases.
Create useful visualizations in the form of scientific figures as you go (if needed).
When done, create a comprehensive README.md and a well formatted pdf summarizing the methodology,
results, conclusions and providing recommendations."
``` ```
--- ---