Orchestrating literature landscaping in drug discovery by coupling citation expansion with large language models

Systematic literature reviews guide decisions in drug discovery, yet keyword-based retrieval misses relevant work hidden behind synonyms, compound codes and cross-disciplinary vocabulary. Manual screening of large literature pools is slow and costly. Large language models (LLMs) could relieve this bottleneck, but existing tools address either citation-based retrieval or LLM screening, and rarely validate how well the combination performs. We present CESAR (Citation Expansion for Systematic Academic Reviewing), an open-source workflow that assembles domain corpora by following references and citing works through OpenAlex. It screens titles and abstracts with LLMs calibrated against human-annotated reference sets. We demonstrate CESAR on a broad methodological field, total synthesis, and on a narrow drug target, monoacylglycerol lipase (MAGL). For total synthesis, the collected corpus contained 78% of an independently curated reference collection published 2000–2023. The classifier retained 99.3% of those that reached screening, and inexpensive models performed close to the most expensive ones. For MAGL, an open-weight model reduced more than 20,000 records to 893 at no cost, with an estimated 79% of them relevant, while extracting target selectivity, evidence level and compound names in the same step. Run on a single local GPU, the same model matched cloud performance, enabling screening of confidential material without external data transfer. CESAR turns screening of tens of thousands of abstracts into a task of hours to days, at costs from zero to about one US dollar per thousand papers, and keeps expert attention for the decisions that require it.