Although microbial communities are dynamic and critical for larval health in aquaculture, reliable early-warning tools remain scarce. Here, we combine flow cytometry (FCM) and 16S rRNA gene sequencing to identify microbial indicators that anticipate survival outcomes in barramundi (Lates calcarifer) hatcheries. Sequencing revealed 54 amplicon sequence variants (ASVs) that consistently distinguished high- and low-survival tanks. Machine-learning models trained on 134 FCM phenotypic fingerprints accurately inferred the abundances of selected ASVs and reproduced survival-linked patterns across 20 independent larviculture batches (n = 1206). Four detrimental ASVs - Citrobacter (asv28, asv78), Rhodopseudomonas (asv6), and Arcobacter (asv47) - were predictive of poor survival, with discriminatory signals detectable as early as day 0 post-hatch (DPH 0). Classification models based on these markers at DPH 0 achieved moderate accuracy (AUC <= 0.74), indicating that microbial signatures can predict survival trajectories before mortality becomes apparent at DPH 4-5. Importantly, FCM-based classifiers alone also captured sufficient discriminatory information at DPH 0, offering a practical route for rapid, high-throughput monitoring. Overall, our findings establish FCM-sequencing integration as a powerful approach to derive microbial survival markers and enabling proactive management in fish hatcheries.
All data in the Integrated Marine Information System (IMIS) is subject to the VLIZ privacy policy
