Adaptive immune receptor repertoires (AIRR) are key targets for biomedical research as they record past and ongoing adaptive immune responses. The capacity of machine learning (ML) to identify complex discriminative sequence patterns renders it an ideal approach for AIRR-based diagnostic and therapeutic discovery. To date, widespread adoption of AIRR ML has been inhibited by a lack of reproducibility, transparency, and interoperability. immuneML ( immuneml.uio.no ) addresses these concerns by implementing each step of the AIRR ML process in an extensible, open-source software ecosystem that is based on fully specified and shareable workflows. To facilitate widespread user adoption, immuneML is available as a command-line tool and through an intuitive Galaxy web interface, and extensive documentation of workflows is provided. We demonstrate the broad applicability of immuneML by (i) reproducing a large-scale study on immune state prediction, (ii) developing, integrating, and applying a novel method for antigen specificity prediction, and (iii) showcasing streamlined interpretability-focused benchmarking of AIRR ML. 1.
The GdFeO3-type perovskite NaFeF3 transforms to CaIrO3-type postperovskite at pressures as low as 9 GPa at room temperature. The details of such a transition were investigated by in situ synchrotron powder diffraction in a multianvil press. Fit of the p-V data showed that the perovskite phase is more compressible than related chemistries with a strongly anisotropic response of the lattice metrics to increasing pressure. The reduction in volume is accommodated by a rapid increase of the octahedral tilting angle, which reaches a critical value of 26° at the transition boundary. The postperovskite form, which is fully recoverable at ambient conditions, shows a regular geometry of the edge-sharing octahedra and its structural properties are comparable to those found in CaIrO3-type MgSiO3 at high pressure and temperature. Theoretical studies using density functional theory at the GGA + U level were also performed and describe a scenario where both perovskite and postperovskite phases can be considered Mott-Hubbard insulators with collinear magnetic G- and C-type antiferromagnetic structures, respectively. Magnetic measurements are in line with the theoretical predictions with both forms showing the typical behavior of canted antiferromagnets.
Adaptive immune receptor repertoires (AIRR) are key targets for biomedical research as they record past and ongoing adaptive immune responses. The capacity of machine learning (ML) to identify complex discriminative sequence patterns renders it an ideal approach for AIRR-based diagnostic and therapeutic discovery. To date, widespread adoption of AIRR ML has been inhibited by a lack of reproducibility, transparency, and interoperability. immuneML (immuneml.uio.no) addresses these concerns by implementing each step of the AIRR ML process in an extensible, open-source software ecosystem that is based on fully specified and shareable workflows. To facilitate widespread user adoption, immuneML is available as a command-line tool and through an intuitive Galaxy web interface, and extensive documentation of workflows is provided. We demonstrate the broad applicability of immuneML by (i) reproducing a large-scale study on immune state prediction, (ii) developing, integrating, and applying a novel method for antigen specificity prediction, and (iii) showcasing streamlined interpretability-focused benchmarking of AIRR ML.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.