The 3Ranker: An AI-based Algorithm for Finding Non-animal Alternative Methods.

The search for existing non-animal alternative methods for use in experiments is currently challenging because of the lack of both comprehensive structured databases and balanced keyword-based search strategies to mine unstructured textual databases. In this paper we describe 3Ranker, which is a fast, keyword-independent algorithm for finding non-animal alternative methods for use in biomedical research. The 3Ranker algorithm was created by using a machine learning approach, consisting of a Random Forest model built on a dataset of 35 million abstracts and constructed with weak supervision, followed by iterative model improvement with expert curated data. We found a satisfactory trade-off between sensitivity and specificity, with Area Under the Curve (AUC) values ranging from 0.85-0.95. Trials showed that the AI-based classifier was able to identify articles that describe potential alternatives to animal use, among the thousands of articles returned by generic PubMed queries on dermatitis and Parkinson's disease. Application of the classification models on time series data showed the earlier implementation and acceptance of Three Rs principles in the area of cosmetics and skin research, as compared to the area of neurodegenerative disease research. The 3Ranker algorithm is freely available at www.open3r.org; the future goal is to expand this framework to cover multiple research domains and to enable its broad use by researchers, policymakers, funders and ethical review boards, in order to promote the replacement of animal use in research wherever possible.

Inducible MLL-AF9 Expression Drives an AML Program during Human Pluripotent Stem Cell-Derived Hematopoietic Differentiation.

A t(9;11)(p22;q23) translocation produces the MLL-AF9 fusion protein, which is found in up to 25% of de novo AML cases in children. Despite major advances, obtaining a comprehensive understanding of context-dependent MLL-AF9-mediated gene programs during early hematopoiesis is challenging. Here, we generated a human inducible pluripotent stem cell (hiPSC) model with a doxycycline dose-dependent MLL-AF9 expression. We exploited MLL-AF9 expression as an oncogenic hit to uncover epigenetic and transcriptomic effects on iPSC-derived hematopoietic development and the transformation into (pre-)leukemic states. In doing so, we observed a disruption in early myelomonocytic development. Accordingly, we identified gene profiles that were consistent with primary MLL-AF9 AML and uncovered high-confidence MLL-AF9-associated core genes that are faithfully represented in primary MLL-AF9 AML, including known and presently unknown factors. Using single-cell RNA-sequencing, we identified an increase of CD34 expressing early hematopoietic progenitor-like cell states as well as granulocyte-monocyte progenitor-like cells upon MLL-AF9 activation. Our system allows for careful chemically controlled and stepwise in vitro hiPSC-derived differentiation under serum-free and feeder-free conditions. For a disease that currently lacks effective precision medicine, our system provides a novel entry-point into exploring potential novel targets for personalized therapeutic strategies.