add abs and fig

Author: yhadevol

_bibliography/papers.bib

@@ -5,6 +5,8 @@ @article{yuan2024computational
   title={Computational strategies for cross-species knowledge transfer and translational biomedicine},
   author={Yuan, Hao and Mancuso, Christopher A and Johnson, Kayla and Braasch, Ingo and Krishnan, Arjun},
   journal={arXiv preprint arXiv:2408.08503},
+  abstract = {Research organisms provide invaluable insights into human biology and diseases, serving as essential tools for functional experiments, disease modeling, and drug testing. However, evolutionary divergence between humans and research organisms hinders effective knowledge transfer across species. Here, we review state-of-the-art methods for computationally transferring knowledge across species, primarily focusing on methods that utilize transcriptome data and/or molecular networks. We introduce the term "agnology" to describe the functional equivalence of molecular components regardless of evolutionary origin, as this concept is becoming pervasive in integrative data-driven models where the role of evolutionary origin can become unclear. Our review addresses four key areas of information and knowledge transfer across species: (1) transferring disease and gene annotation knowledge, (2) identifying agnologous molecular components, (3) inferring equivalent perturbed genes or gene sets, and (4) identifying agnologous cell types. We conclude with an outlook on future directions and several key challenges that remain in cross-species knowledge transfer.},
+  preview = {yuan2024computational.png},
   year={2024}
 }
 
@@ -14,6 +16,8 @@ @article{yuan2024annotating
   journal={bioRxiv},
   pages={2024--06},
   year={2024},
+  abstract = {Reusing massive collections of publicly available biomedical data can significantly impact knowledge discovery. However, these public samples and studies are typically described using unstructured plain text, hindering the findability and further reuse of the data. To combat this problem, we propose txt2onto 2.0, a general-purpose method based on natural language processing and machine learning for annotating biomedical unstructured metadata to controlled vocabularies of diseases and tissues. Compared to the previous version (txt2onto 1.0), which uses numerical embeddings as features, this new version uses words as features, resulting in improved interpretability and performance, especially when few positive training instances are available. Txt2onto 2.0 uses embeddings from a large language model during prediction to deal with unseen-yet-relevant words in the input text and to highlight biomedical concepts in the input text that are related to each disease and tissue term being predicted, thereby explaining the basis of every annotation. We demonstrate the generalizability of txt2onto 2.0 by accurately predicting disease annotations for studies from independent datasets, using proteomics and clinical trials as examples. Overall, our approach can annotate biomedical text regardless of experimental types or sources. Code, data, and trained models are available at https://github.com/krishnanlab/txt2onto2.0.},
+  preview = {yuan2024annotating.png},
   publisher={Cold Spring Harbor Laboratory}
 }
 
@@ -23,6 +27,8 @@ @article{ai2024estimation
   journal={bioRxiv},
   pages={2024--04},
   year={2024},
+  abstract = {The advance of environmental DNA (eDNA) has enabled rapid and non-invasive species detection in aquatic environments. Although most studies focus on species detections, some recent studies explored the potential of using eDNA concentration to quantify species abundance. However, the differential individual DNA contribution to eDNA samples could easily obscure the concentration-species abundance relationship. We propose using the number of segregating sites as a proxy for estimating species abundance. Since segregating sites reflects the genetic diversity of the population, which is less sensitive to differential individual DNA contribution than eDNA concentration. We examined the relationship between the number of segregating sites and species abundance in silico, in vitro, and in situ using two brackish goby species, Acanthogobius hasta and Tridentiger bifasciatus. Analyses of the simulated data and in vitro data with DNA mixed from a known number of individuals showed a strong correlation between the number of segregating sites and species abundance (R2 > 0.9; P < 0.01). Results from the in situ experiment further validated the correlation (R2 = 0.70, P < 0.01), and such correlation was not affected by biotic factors, including body size and feeding behavior (P > 0.05). Results of the cross-validation test also showed that the number of segregating sites predicted species abundance with less bias and variability than the eDNA concentration. Overall, the number of segregating sites correlates stronger with species abundance and also provides a better estimate than eDNA concentration. This advancement can significantly enhance the quantitative capabilities of eDNA technology.},
+  preview = {ai2024estimation.png},
   publisher={Cold Spring Harbor Laboratory}
 }