Editing AI for Scientific Literature Review (section)

== <span style="color: #FFFFFF;">Applying</span> ==
'''Semantic paper search and summarization pipeline:'''
<syntaxhighlight lang="python">
import requests
from sentence_transformers import SentenceTransformer
import numpy as np
from openai import OpenAI

# Semantic Scholar API for paper search
def search_semantic_scholar(query: str, limit: int = 20) -> list:
    url = "https://api.semanticscholar.org/graph/v1/paper/search"
    params = {
        "query": query,
        "limit": limit,
        "fields": "title,abstract,year,citationCount,authors,tldr"
    }
    resp = requests.get(url, params=params)
    return resp.json().get("data", [])

# Embed papers for semantic search
embedder = SentenceTransformer("allenai-specter")  # SPECTER2 for scientific papers

def find_most_relevant(query: str, papers: list, top_k: int = 5) -> list:
    """Find most semantically relevant papers using SPECTER embeddings."""
    q_emb = embedder.encode(query + " [SEP] ")  # SPECTER uses title+abstract sep
    paper_texts = [f"{p['title']} [SEP] {p.get('abstract','')}" for p in papers]
    p_embs = embedder.encode(paper_texts)
    similarities = np.dot(p_embs, q_emb) / (
        np.linalg.norm(p_embs, axis=1) * np.linalg.norm(q_emb) + 1e-10
    )
    top_idx = similarities.argsort()[-top_k:][::-1]
    return [papers[i] for i in top_idx]

# LLM-powered synthesis of retrieved papers
client = OpenAI()
def synthesize_literature(question: str, papers: list) -> str:
    paper_summaries = "\n\n".join([
        f"Paper: {p['title']} ({p.get('year', 'n/a')})\n"
        f"TLDR: {p.get('tldr', {}).get('text', p.get('abstract','')[:300])}"
        for p in papers
    ])
    prompt = f"""Based on these scientific papers, answer: {question}

{paper_summaries}

Provide a balanced synthesis citing specific papers. Note any contradictions."""
    resp = client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role":"user","content":prompt}],
        temperature=0.1
    )
    return resp.choices[0].message.content

# Full pipeline
question = "What is the effect of sleep deprivation on immune function?"
papers = search_semantic_scholar(question)
relevant = find_most_relevant(question, papers)
synthesis = synthesize_literature(question, relevant)
print(synthesis)
</syntaxhighlight>

; Scientific literature AI tools
: '''Search/discovery''' → Semantic Scholar, Google Scholar (AI features), Litmaps, Connected Papers
: '''Synthesis/QA''' → Elicit, Consensus, ChatPDF, SciSpace
: '''Systematic reviews''' → Rayyan (screening), Abstrackr, Covidence + AI screening
: '''Knowledge graphs''' → SciKnowMine, INDRA, BEL (Biological Expression Language)
: '''Paper writing''' → Scite (citation context), ResearchRabbit (exploration), Paperpal (editing)
</div>

<div style="background-color: #8B4500; color: #FFFFFF; padding: 20px; border-radius: 8px; margin-bottom: 15px;">