Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.64898/2026.08.29.748046

TigerAI: An AI-powered genetic evidence platform to support clinical development

Zhang, Z.·Zhang, W.·Yang, X.·Li, Y.·Lin, J.·Wu, C.·Zhao, B.
View original source ↗Export metadata ↓

Abstract

Genetic evidence is a major determinant of clinical success in drug development, yet its aggregation has long relied on laborious human curation. Large language models (LLMs) have the potential to rapidly synthesize knowledge across biomedical resources, providing a route to scalable AI-driven genetic evidence generation. Here we develop a novel domain-grounded instruction framework to systematically evaluate GPT-5 for producing genetic evidence relevant to clinical trial success. Using 13,022 target-indication pairs from a comprehensive drug development database, we benchmark LLM-derived evidence against a recent exhaustive human expert-curated study. We find that GPT-5 yields genetic evidence that is at least as informative as expert curation for inferring clinical success, while substantially expanding coverage relative to traditional curation resources. Building on these results, we introduce TigerAI (https://tigerai.bio/), a dual-purpose platform for AI-powered genetic evidence that (i) benchmarks emerging state-of-the-art LLMs and (ii) provides an accessible service for querying reliable AI-generated genetic evidence. These contributions outline a practical, domain-grounded pathway for integrating AI-powered genetic evidence into drug development pipelines and for realizing the potential of LLMs to inform clinical success.

Explore related subjects

geneticsPreprint

Keep this discovery

BibTeXRIS

Zhang, Z., Zhang, W., Yang, X., Li, Y., Lin, J., Wu, C., Zhao, B.. 2026-09-01. TigerAI: An AI-powered genetic evidence platform to support clinical development. https://doi.org/10.64898/2026.08.29.748046

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

Preprint resourcePreprint subjectgenetics subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related discoveries

bioRxiv2026

Genetic legacy in soil seedbanks after grassland conversion to plantation forests: evidence from Potentilla freyniana

Semi-natural grasslands are important ecosystems supporting biodiversity in Japan, but their area has declined rapidly due to land-use change and abandonment of traditional management practices such as mowing and burning. Although the conservation of genetic diversity is essential for the long-term persistence of grassland plants, little is known about the genetic diversity retained in soil seedbanks following conversion of grasslands to plantation forests. In this study, we compared the genetic diversity and population structure of above-ground and soil seedbank populations of the grassland perennial forb Potentilla freyniana across three sites in each of three land-use types: burned grasslands, deciduous plantation forests, and evergreen plantation forests (plantation ages approximately 21-62 years) on the Kaida Plateau, central Japan. Soil seedbank populations were obtained from soil samples through germination experiments, and genetic analyses were conducted using newly developed simple sequence repeat (SSR) markers. Genetic diversity was assessed using expected heterozygosity, allelic richness, and private allelic richness, population structure was evaluated using analysis of molecular variance (AMOVA), STRUCTURE analyses, and pairwise FST. Soil seedbank populations maintained levels of genetic diversity comparable to those of above-ground populations, and no significant differences were detected between the two population types. Furthermore, soil seedbank populations in evergreen plantation forests, where above-ground individuals of P. freyniana were absent, retained genetic diversity comparable to that observed in burned grasslands. AMOVA detected no significant genetic differentiation between above-ground and soil seedbank populations. These results suggest that high levels of genetic diversity can persist in soil seedbank populations for decades after forest establishment and highlight the potential importance of soil seedbanks as genetic resources for grassland restoration.

ecology↗
bioRxiv2026

An agent-based 3D model of non-genetic adaptation in cancer tissues under electrical, mechanical, and hypoxic stress

Non-genetic adaptation enables cancer cells to alter their phenotype under stress without requiring new mutations. However, the mechanisms by which electrical, mechanical, and hypoxic cues combine to shape this process in 3D tissues remain poorly understood. This work presents an agent-based tumor model that integrates vascular oxygen supply, a globally imposed electric field, mechanically mediated crowding and compression cues, phenotype transitions, cell growth, mitosis, death, and inheritance of adaptive memory across division. The simulated tumors exhibit a three-stage trajectory consisting of necrosis onset, transient collapse of live mass, and partial regrowth accompanied by progressive accumulation of adapted cells. Continuous electrical stimulation produces a dose-dependent reduction in live mass while markedly increasing the adapted fraction, with comparatively limited changes in final necrotic burden. This response is strongly conditioned by mechanics and reshapes (and is reshaped by) adaptive capacity. Pulsed stimulation further shows that, in the model, electric field amplitude and temporal schedule jointly determine memory phenomena, phenotypic diversification, and growth recovery. These results show that coupling local oxygen availability, mechanical constraints, electrical forcing, and history-dependent phenotype transitions can generate distinct tissue-level patterns of phenotypic heterogeneity. Both stimulus magnitude and temporal protocol influenced the resulting population structure, suggesting that the history of physical stress may be an important determinant of adaptive dynamics in spatially organized tumor models.

biophysics↗
bioRxiv2026

Genetic Disruption at the CIP2A Locus Modulates T Cell Responses and Attenuates Experimental Autoimmune Encephalomyelitis

Multiple sclerosis (MS) is a chronic autoimmune disease of the central nervous system (CNS) driven by pathogenic T cell-mediated inflammation. Fingolimod (FTY720), an approved therapy for MS, is an established activator of protein phosphatase 2A (PP2A). However the contribution of PP2A in autoimmune neuroinflammation remains incompletely understood. Here, we addressed this question using experimental autoimmune encephalomyelitis (EAE), a murine model of MS, in mice carrying a genetic disruption of the locus encoding cancerous inhibitor of protein phosphatase 2A (CIP2A), an endogenous inhibitor of PP2A. Mice with disruption of the CIP2A locus, the knock out (KO) mice, exhibited attenuated EAE severity compared with wild-type (WT) controls. Histological and flow-cytometric analyses revealed markedly reduced infiltration of mononuclear cells, including CD4 and CD4CXCR6 encephalitogenic T cells, in the CNS of diseased KO mice. Reduced numbers of these T cell populations were also observed in peripheral lymphoid organs of the Cip2a-deficient mice during EAE, while T cell abundance was comparable under steady-state conditions, suggesting impaired activation-induced expansion rather than altered homeostasis or migration. Single-cell RNA sequencing of CNS and lymph node immune cells revealed changes in cell-type abundance and gene expression. Notably, Il17a expression was reduced in CNS CD8+ T cells and showed a similar trend in {gamma}{delta} T cells. Together, our findings reveal that genetic disruption at the CIP2A locus attenuates EAE, possibly by limiting the expansion and accumulation of encephalitogenic T cell populations in CNS. These results identify the CIP2A locus as a previously unrecognized regulator of T cell-driven autoimmune neuroinflammation and provide new insights into mechanisms that restrain pathogenic T cell responses during EAE.

immunology↗