Search bioRxiv⌕ Search

Biology subjects

Pujara, N.

Publications and source records attributed to Pujara, N..

2 recordsLinked to original sources

MechAInistic: An LLM-guided Multi-Agent System for Reasoning over Genome-Scale Constraint-Based Metabolic Models

LLM agents are increasingly used for scientific reasoning, but their fluent-sounding outputs can diverge from verifiable computational evidence, limiting their reliability for biomedical hypothesis generation. We developed MechAInistic, a multi-agent system in which an independently configured Reviewer agent supervises a planning Architect agent at each stage of the workflow, with all reasoning grounded in executable mechanistic-model analyses rather than language-model text alone. The Reviewer scores plans and intermediate results against pre-specified rubrics and triggers re-planning or re-execution when scores fall below threshold, producing an auditable chain from a natural-language question to model-derived evidence and cited literature. We instantiate the system over paired constraint-based metabolic models using COBRApy, supporting pathway comparison, perturbation analysis, drug-target exploration, and literature interpretation across healthy and disease states. We evaluated MechAInistic on two immune-cell therapeutic hypothesis-generation tasks. For rheumatoid arthritis versus healthy naive B-cell models, it identified mitochondrial metabolic rewiring and nominated Devimistat/CPI-613 as an investigational OGDH-centered hypothesis. For multiple sclerosis CD4+ Th17 versus healthy models, it identified NADP-dependent isocitrate dehydrogenase as a candidate target and proposed ivosidenib, with vorasidenib as a mechanistically complementary alternative. Comparator analyses against general-purpose LLM systems showed that plausible biological narratives can lack auditable model grounding, whereas MechAInistic preserves the computational reasoning path from prompt to result. GRAPHICAL ABSTRACT O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=83 SRC="FIGDIR/small/723319v4_ufig1.gif" ALT="Figure 1"> View larger version (19K): org.highwire.dtl.DTLVardef@4e591eorg.highwire.dtl.DTLVardef@1bceee3org.highwire.dtl.DTLVardef@e7a0f4org.highwire.dtl.DTLVardef@f80b3a_HPS_FORMAT_FIGEXP M_FIG C_FIG

systems biology↗

Hatchling fish disperse using an efficient multisensory strategy

Animals improve fitness by choosing when and where to disperse in the environment using sensory cues. In freshwater habitats subject to flood and drought, dispersal can urgently challenge newly hatched fish. Here we manipulated rearing environment and sensory systems to reveal an adaptive sensorimotor strategy for dispersal. If we constrained hatchlings or blocked feedback about motion by simultaneously impairing the lateral line and vision, they gulped air and elevated their buoyancy to passively sail on faster surface waters. In stagnant water, hatchlings then covered more ground with hyperstable swimming, tightly steering based on graviception. In hydrodynamic simulations, these adaptations nearly tripled diffusivity and made dispersal robust to local conditions. Through combined use of three senses, hatchlings adapt their behavior to flexibly and efficiently disperse.

animal behavior and cognition↗