Parkhurst, C. N. | bioRxiv Science

bioRxiv2026

Charting the small-molecule universe from mass spectra with neuro-symbolic AI

Mass spectrometry (MS) has revealed millions of small organic molecules across organisms, yet most remain uncharacterized, limiting progress in biology and medicine. Despite computational advances, MS workflows rely heavily on expert input and reference libraries that cover only a fraction of known chemical space. Here, we introduce AIMe (AI Molecule Explorer), a multi-agent neuro-symbolic AI framework that transforms the interpretation of unknown spectra into an omics-scale exploration across the known structural space, providing chemically interpretable annotations. At its core, AIMe combines chemical reasoning with structure- informed learning to predict MS2 spectra by modeling fragmentation as a sequence of actions, outperforming existing methods. AIMe dynamically constructs fragmentation pathways by assigning likelihoods to individual fragmentation actions, linking spectral peaks to explicit fragment molecular formulas and structures. At scale, AIMe predicted MS2 spectra for over 100 million small organic molecules in PubChem and organized them into MS2KOSMOS, a substructure-informed community resource comprising over 800 million predicted spectra that expands the searchable small-molecule universe by roughly three orders of magnitude relative to experimental libraries. Analogous to sequence homology-based searches in genomics and proteomics, AIMe maps unknown spectra to molecular neighborhoods in MS2KOSMOS. Exact- formula indexing enables ranked retrieval of candidates and related structures, with peak-level structural and fragmentation-pathway annotations. Applied to mouse microbiota-dependent metabolites, AIMe enabled putative annotation of knowns and guided structure elucidation of unknowns, revealing previously unreported types of microbiota-dependent polyamines that also occur in humans. At repository scale, AIMe enabled putative annotation of roughly a third of 7 million spectral clusters representing most of the unknowns in the GNPS database. By extending MS2 annotation beyond curated-library matching to interpretable search across the known small-molecule universe, AIMe accelerates discovery and large-scale exploration of small molecules across biomedicine, agriculture, and ecology.

biochemistry↗

bioRxiv2023

WNK1 enforces macrophage lineage fidelity

The appropriate development of macrophages, the bodys professional phagocyte, is essential for organismal development, especially in mammals. This dependence is exemplified by the observation that loss-of-function mutations in colony stimulating factor 1 receptor (CSF1R) results in multiple tissue abnormalities owing to an absence of macrophages. Despite this importance, little is known about the molecular and cell biological regulation of macrophage development. Here, we report the surprising finding that the chloride-sensing kinase With-no-lysine 1 (WNK1) is required for development of tissue-resident macrophages (TRMs). Myeloid-specific deletion of Wnk1 resulted in a dramatic loss of TRMs, disrupted organ development, systemic neutrophilia, and mortality between 3 and 4 weeks of age. Strikingly, we found that myeloid progenitors or precursors lacking WNK1 not only failed to differentiate into macrophages, but instead differentiated into neutrophils. Mechanistically, the cognate CSF1R cytokine macrophage-colony stimulating factor (M-CSF) stimulates macropinocytosis by both mouse and human myeloid progenitors and precursor cells. Macropinocytosis, in turn, induces chloride flux and WNK1 phosphorylation. Importantly, blocking macropinocytosis, perturbing chloride flux during macropinocytosis, and inhibiting WNK1 chloride-sensing activity each skewed myeloid progenitor differentiation from macrophages into neutrophils. Thus, we have elucidated a role for WNK1 during macropinocytosis and discovered a novel function of macropinocytosis in myeloid progenitors and precursor cells to ensure macrophage lineage fidelity. Highlights- Myeloid-specific WNK1 loss causes failed macrophage development and premature death - M-CSF-stimulated myeloid progenitors and precursors become neutrophils instead of macrophages - M-CSF induces macropinocytosis by myeloid progenitors, which depends on WNK1 - Macropinocytosis enforces macrophage lineage commitment

immunology↗