# MOLIERE: Automatic Biomedical Hypothesis Generation System

arXiv: https://arxiv.org/abs/1702.06176 · HTML: https://mlsanity.com/paper/1702.06176/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2017.

## Built on by (most cited first, 12 of 12)

- [Interpretable bias mitigation for textual data: Reducing gender bias in patient notes while maintaining classification performance](https://mlsanity.com/paper/2103.05841/) (2021)
- [HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses](https://mlsanity.com/paper/2609.15938/) (2026)
- [Accelerating COVID-19 research with graph mining and transformer-based learning](https://mlsanity.com/paper/2102.07631/) (2021)
- [Towards Practical Explainability with Cluster Descriptors](https://mlsanity.com/paper/2210.10662/) (2022)
- [Literature-based Discovery for Landscape Planning](https://mlsanity.com/paper/2306.02588/) (2023)
- [SALSA: Sequential Approximate Leverage-Score Algorithm with Application in Analyzing Big Time Series Data](https://mlsanity.com/paper/2401.00122/) (2023)
- [Interestingness First Classifiers](https://mlsanity.com/paper/2508.19780/) (2025)
- [GreedyML: A Parallel Algorithm for Maximizing Constrained Submodular Functions](https://mlsanity.com/paper/2403.10332/) (2024)
- [Biomedical Hypothesis Explainability with Graph-Based Context Retrieval](https://mlsanity.com/paper/2511.05498/) (2025)
- [From Literature to Hypotheses: An AI Co-Scientist System for Biomarker-Guided Drug Combination Hypothesis Generation](https://mlsanity.com/paper/2603.00612/) (2026)
- [Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in Nanomedicine](https://mlsanity.com/paper/2605.18144/) (2026)
- [Historical Anchors for Scientific Forecasting on Human-Aware Knowledge Graphs](https://mlsanity.com/paper/2610.14023/) (2026)

## Abstract (arXiv)

Hypothesis generation is becoming a crucial time-saving technique which allows biomedical researchers to quickly discover implicit connections between important concepts. Typically, these systems operate on domain-specific fractions of public medical data. MOLIERE, in contrast, utilizes information from over 24.5 million documents. At the heart of our approach lies a multi-modal and multi-relational network of biomedical objects extracted from several heterogeneous datasets from the National Center for Biotechnology Information (NCBI). These objects include but are not limited to scientific papers, keywords, genes, proteins, diseases, and diagnoses. We model hypotheses using Latent Dirichlet Allocation applied on abstracts found near shortest paths discovered within this network, and demonstrate the effectiveness of MOLIERE by performing hypothesis generation on historical data. Our network, implementation, and resulting data are all publicly available for the broad scientific community.