Medgeclaw Guide

# Biomedical NER using scispaCy
import scispacy
import spacy
from scispacy.linking import EntityLinker

# Load biomedical NER model
nlp = spacy.load("en_ner_bionlp13cg_md")

# Add UMLS entity linker for concept normalization
nlp.add_pipe("scispacy_linker", config={
    "resolve_abbreviations": True,
    "linker_name": "umls",
})

def extract_biomedical_entities(text: str) -> dict:
    """
    Extract and normalize biomedical entities from text.
    Returns genes, chemicals, diseases, and their UMLS mappings.
    """
    doc = nlp(text)
    entities = {
        "genes": [],
        "chemicals": [],
        "diseases": [],
        "other": [],
    }

    category_map = {
        "GENE_OR_GENE_PRODUCT": "genes",
        "SIMPLE_CHEMICAL": "chemicals",
        "CANCER": "diseases",
        "ORGAN": "other",
        "CELL": "other",
    }

    for ent in doc.ents:
        category = category_map.get(ent.label_, "other")
        entity_info = {
            "text": ent.text,
            "label": ent.label_,
            "start": ent.start_char,
            "end": ent.end_char,
        }

        # Add UMLS links if available
        if hasattr(ent, "_") and hasattr(ent._, "kb_ents"):
            if ent._.kb_ents:
                top_link = ent._.kb_ents[0]
                entity_info["umls_cui"] = top_link[0]
                entity_info["confidence"] = round(top_link[1], 3)

        entities[category].append(entity_info)

    return entities

from Bio import Entrez
import time

Entrez.email = "researcher@university.edu"

def systematic_pubmed_search(
    query: str,
    max_results: int = 1000,
    date_range: tuple = ("2020/01/01", "2025/12/31"),
) -> list:
    """
    Conduct a systematic PubMed search with structured result extraction.
    Suitable for systematic reviews and meta-analyses.
    """
    # Step 1: Search PubMed
    handle = Entrez.esearch(
        db="pubmed",
        term=query,
        retmax=max_results,
        datetype="pdat",
        mindate=date_range[0],
        maxdate=date_range[1],
        sort="relevance",
    )
    results = Entrez.read(handle)
    handle.close()

    pmids = results["IdList"]
    print(f"Found {results['Count']} results, retrieving {len(pmids)}")

    # Step 2: Fetch article details in batches
    articles = []
    batch_size = 100
    for i in range(0, len(pmids), batch_size):
        batch = pmids[i:i + batch_size]
        handle = Entrez.efetch(
            db="pubmed", id=",".join(batch),
            rettype="xml", retmode="xml"
        )
        records = Entrez.read(handle)
        handle.close()

        for article in records["PubmedArticle"]:
            medline = article["MedlineCitation"]
            art = medline["Article"]
            articles.append({
                "pmid": str(medline["PMID"]),
                "title": art["ArticleTitle"],
                "abstract": art.get("Abstract", {}).get("AbstractText", [""])[0],
                "journal": art["Journal"]["Title"],
                "year": art["Journal"]["JournalIssue"]["PubDate"].get("Year", "N/A"),
                "mesh_terms": [
                    d["DescriptorName"]
                    for d in medline.get("MeshHeadingList", [])
                ] if "MeshHeadingList" in medline else [],
            })

        time.sleep(0.4)  # Respect NCBI rate limits

    return articles

# Complete RNA-seq differential expression analysis with DESeq2
# This is the standard workflow for biomedical RNA-seq papers

library(DESeq2)
library(ggplot2)
library(EnhancedVolcano)
library(clusterProfiler)
library(org.Hs.eg.db)

# --- 1. Load count matrix and metadata ---
counts <- read.csv("raw_counts.csv", row.names = 1)
coldata <- read.csv("sample_info.csv", row.names = 1)

# Verify sample order matches
stopifnot(all(colnames(counts) == rownames(coldata)))

# --- 2. Create DESeq2 object ---
dds <- DESeqDataSetFromMatrix(
  countData = counts,
  colData = coldata,
  design = ~ condition  # Simple two-group comparison
)

# Pre-filtering: remove low-count genes
keep <- rowSums(counts(dds)) >= 10
dds <- dds[keep, ]

# --- 3. Run differential expression ---
dds <- DESeq(dds)
res <- results(dds, contrast = c("condition", "treatment", "control"),
               alpha = 0.05)

# Summary
summary(res)

# --- 4. Results with shrinkage (recommended for visualization) ---
res_shrunk <- lfcShrink(dds, coef = "condition_treatment_vs_control",
                         type = "apeglm")

# --- 5. Export significant genes ---
sig_genes <- subset(res, padj < 0.05 & abs(log2FoldChange) > 1)
write.csv(as.data.frame(sig_genes), "significant_genes.csv")