AMELIE accelerates Mendelian patient diagnosis directly from the primary literature

Birgmeier, J.; Haeussler, M.; Deisseroth, C. A.; Jagadeesh, K. A.; Ratner, A. J.; Guturu, H.; Wenger, A. M.; Stenson, P. D.; Cooper, D. N.; Re, C.; Bernstein, J. A.; Bejerano, G.

doi:10.1101/171322

bioRxiv · 10.1101/171322

AMELIE accelerates Mendelian patient diagnosis directly from the primary literature

Birgmeier, J.·Haeussler, M.·Deisseroth, C. A.·Jagadeesh, K. A.·Ratner, A. J.·Guturu, H.·Wenger, A. M.·Stenson, P. D.·Cooper, D. N.·Re, C.·Bernstein, J. A.·Bejerano, G.

View original source ↗Export metadata ↓

Abstract

The diagnosis of Mendelian disorders requires labor-intensive literature research. Our software system AMELIE (Automatic Mendelian Literature Evaluation) greatly automates this process. AMELIE parses hundreds of thousands of full text articles to find an underlying diagnosis to explain a patients phenotypes given the patients exome. AMELIE prioritizes patient candidate genes for their likelihood of causing the patients phenotypes. Diagnosis of singleton patients (without relatives exomes) is the most time-consuming scenario. AMELIEs gene ranking method was tested on 215 singleton Mendelian patients with a clinical diagnosis. AMELIE ranked the causal gene among the top 2 in the majority (63%) of cases. Examining AMELIEs top 10 genes, amounting to 8% of 124 candidate genes with rare functional variants per patient, results in diagnosis for 95% of cases. Strikingly, training only on gene pathogenicity knowledge from 2011 leads to identical performance compared to training on current data. An accompanying analysis web portal has launched at AMELIE.stanford.edu.

Explore related subjects

genetics Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Birgmeier, J., Haeussler, M., Deisseroth, C. A., Jagadeesh, K. A., Ratner, A. J., Guturu, H., Wenger, A. M., Stenson, P. D., Cooper, D. N., Re, C., Bernstein, J. A., Bejerano, G.. 2017-08-02. AMELIE accelerates Mendelian patient diagnosis directly from the primary literature. https://doi.org/10.1101/171322

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

KEEP EXPLORING

Related preprints

bioRxiv2026

X-Chromosomal STR-based analysis of genetic diversity, structure, and phylogeny in the Sri Lankan Vedda population

The Vedda people are regarded as the direct descendants of Sri Lanka's Mesolithic hunter-gatherers and represent one of South Asia's oldest surviving indigenous populations. X-chromosomal short tandem repeat (X-STR) analysis provides a powerful framework to examine their genetic distinctiveness, as the X chromosome exhibits sex-biased biparental inheritance and greater sensitivity to demographic and evolutionary forces compared to autosomal markers. However, no X-STR-based genetic investigations have yet been conducted on this population. In the present study, we successfully genotyped 50 unrelated Veddas individuals using a recently developed 16 X-STR multiplex PCR system optimized for Sri Lankan populations. Our analyses revealed a statistically significant genetic differentiation (2.43%) between the Veddas and the principal local ethnic groups; Sinhalese, Sri Lankan Tamils, Indian Tamils, and Moors exceeding previous estimates based on autosomal STR markers. Comparative analysis with 32 global populations positioned the Veddas as a genetically distinct and isolated group, separated from clusters representing South Asians, Europeans, Middle Easterners, and other indigenous populations such as Australian Aboriginals, Bhil Indians, and Kedayans, emphasizing their unique genetic heritage. Reduced allelic (115) and haplotype (62) counts, alongside significant linkage disequilibrium detected among eight pairs of X-STR loci, reflect the influence of genetic drift within this small, endogamous, and historically isolated population. These findings highlight the evolutionary and demographic distinctiveness of the Veddas and provide essential baseline data for future population genomic studies. Furthermore, the demonstrated high discriminatory power of the 16 X-STR loci supports their continued application in population genetics and anthropological research within this unique community.

genetics↗

bioRxiv2026

Fss1, a CTNS/PQ domain protein, has dual roles in promoting fertility in Schizosaccharomyces pombe

Sexual reproduction is critical in most eukaryotes, but many genes required for the process remain to be identified and characterized. A previous saturation mutagenesis study in Schizosaccharomyces pombe implicated several unnamed genes in having roles in sexual reproduction. In this work, we provide an initial characterization of 13 of these genes and an in-depth characterization of one gene, fss1 (facilitates starvation sex). Fss1 has high structural homology to the human PQ-loop repeat family PQLC2 transceptor (amino acid transporter plus membrane receptor), but likely lacks the ability to transport amino acids due to loss of a critical PQ motif. fss1{Delta} mutants have no defects in meiosis but have pronounced defects in packaging the products of meiosis into spores, particularly in nutrient-poor environments. The spore formation phenotypes are recessive as fss1{Delta} spores produced by a fss1+/fss1{Delta} heterozygote develop normally. Immuno-gold electron microscopy shows Fss1 localizes to vesicles that fuse to the ephemeral outer spore membrane as the spore wall matures below. Fss1 protein is also produced within spores and this population is required for normal vacuole morphology and timely germination. We propose a model in which Fss1 is a vesicle receptor that facilitates spore wall formation from diploid-expressed protein, while spore-expressed protein acts at the vacuole to promote an internal cellular environment that facilitates germination. This work expands our catalog of genes that contribute to sexual reproduction and identifies two previously unknown tasks in spore biology that are both facilitated by Fss1.

genetics↗

bioRxiv2026

Expression of tardigrade intrinsically disordered proteins in C. elegans reveals variable effects on aging and stress

Tardigrades survive extreme environmental stress by expressing intrinsically disordered proteins that stabilize cellular structures during cryptobiosis. Because these proteins protect cells from desiccation, oxidative stress, and DNA damage, they have attracted interest as potential therapeutics to enhance stress resilience in other organisms. However, most studies have relied on cultured cells or germline expression, leaving their effects in somatic tissues largely unexplored. Here, we generated Caenorhabditis elegans strains expressing four tardigrade intrinsically disordered proteins, Damage Suppressor (DSUP), cytoplasmic-abundant heat-soluble (CAHS), mitochondrial-abundant heat-soluble (MAHS), and Ramazzottius varieornatus late embryogenesis abundant (RvLEAM), throughout somatic tissues. Surprisingly, constitutive expression of each protein reduced lifespan, impaired motility and reproduction, and failed to improve resistance to most environmental stressors. DSUP toxicity was tissue- and developmental stage-dependent, indicating that both spatial and temporal expression influence its physiological effects. Despite these detrimental phenotypes, several proteins reduced protein aggregation during desiccation-associated stress, demonstrating context-dependent protective effects. Together, our findings reveal that tardigrade stress proteins impose physiological tradeoffs in vivo and underscore the importance of evaluating candidate stress-protective proteins in physiologically relevant somatic models before therapeutic translation.

genetics↗