Debit, A. | bioRxiv Science

bioRxiv2023

LncPlankton V1.0: a comprehensive collection of plankton long non-coding RNAs

Long considered as transcriptional noise, long non-coding RNAs (lncRNAs) are emerging as central, regulatory molecules in a multitude of eukaryotic species, from plants to animals to fungi. Yet, our knowledge about the occurrence of these molecules in the marine environment, namely in planktonic protists, is still elusive. To fill this gap of knowledge we developed LncPlankton v1.0, which is the first comprehensive database of marine plankton lncRNAs. By integrating the predictions derived from ten distinctive coding potential prediction tools in a majority voting setting, we identified 2,210,359 lncRNAs distributed across 414 marine plankton species from over nine different phyla. A user-friendly, open-access web interface for the exploration of the database was implemented (https://www.lncplankton.bio.ens.psl.eu/). We believe LncPlankton v1.0 will serve as a rich resource for studies of lncRNAs that will contribute to small- and large-scale analyses in a wide range of marine plankton species and allow comparative analysis well beyond the marine environment.

plant biology↗

bioRxiv2023

Assessing Random Forest self-reproducibility for optimal short biomarker signature discovery

Biomarker signature discovery remains the main path to develop clinical diagnostic tools when the biological knowledge on a pathology is weak. Shortest signatures are often preferred to reduce the cost of the diagnostic. The ability to find the best and shortest signature relies on the robustness of the models that can be built on such set of molecules. The classification algorithm that will be used is selected based on the average performance of its models, often expressed via the average AUC. However, it is not garanteed that an algorithm with a large AUC distribution will keep a stable performance when facing data. Here, we propose two AUC-derived hyper-stability scores, the HRS and the HSS, as complementary metrics to the average AUC, that should bring confidence in the choice for the best classification algorithm. To emphasize the importance of these scores, we compared 15 different Random Forests implementation. Additionally, the modelization time of each implementation was computed to further help deciding the best strategy. Our findings show that the Random Forest implementation should be chosen according to the data at hand and the classification question being evaluated. No Random Forest implementation can be used universally for any classification and on any dataset. Each of them should be tested for both their average AUC performance and AUC-derived stability, prior to analysis. Author summaryTo better measure the performance of a Machine Learning (ML) implementation, we introduce a new metric, the AUC hyper-stability, to be used in parallel with the average AUC. This AUC hyper-stability is able to discriminate ML implementations that show the same AUC performance. This metric can therefore help researchers in choosing the best ML method to get stable short predictive biomarker signatures. More specifically, we advocate a tradeoff between the average AUC performance, the hyper-stability scores, and the modeling time.

bioinformatics↗