@article{CaliskanCaliskanRasbachetal.2023, author = {Caliskan, Aylin and Caliskan, Deniz and Rasbach, Lauritz and Yu, Weimeng and Dandekar, Thomas and Breitenbach, Tim}, title = {Optimized cell type signatures revealed from single-cell data by combining principal feature analysis, mutual information, and machine learning}, series = {Computational and Structural Biotechnology Journal}, volume = {21}, journal = {Computational and Structural Biotechnology Journal}, issn = {2001-0370}, doi = {10.1016/j.csbj.2023.06.002}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349989}, pages = {3293-3314}, year = {2023}, abstract = {Machine learning techniques are excellent to analyze expression data from single cells. These techniques impact all fields ranging from cell annotation and clustering to signature identification. The presented framework evaluates gene selection sets how far they optimally separate defined phenotypes or cell groups. This innovation overcomes the present limitation to objectively and correctly identify a small gene set of high information content regarding separating phenotypes for which corresponding code scripts are provided. The small but meaningful subset of the original genes (or feature space) facilitates human interpretability of the differences of the phenotypes including those found by machine learning results and may even turn correlations between genes and phenotypes into a causal explanation. For the feature selection task, the principal feature analysis is utilized which reduces redundant information while selecting genes that carry the information for separating the phenotypes. In this context, the presented framework shows explainability of unsupervised learning as it reveals cell-type specific signatures. Apart from a Seurat preprocessing tool and the PFA script, the pipeline uses mutual information to balance accuracy and size of the gene set if desired. A validation part to evaluate the gene selection for their information content regarding the separation of the phenotypes is provided as well, binary and multiclass classification of 3 or 4 groups are studied. Results from different single-cell data are presented. In each, only about ten out of more than 30000 genes are identified as carrying the relevant information. The code is provided in a GitHub repository at https://github.com/AC-PHD/Seurat_PFA_pipeline.}, language = {en} } @article{DhillonDahmsKuebertFlocketal.2023, author = {Dhillon, Maninder Singh and Dahms, Thorsten and Kuebert-Flock, Carina and Rummler, Thomas and Arnault, Joel and Steffan-Dewenter, Ingolf and Ullmann, Tobias}, title = {Integrating random forest and crop modeling improves the crop yield prediction of winter wheat and oil seed rape}, series = {Frontiers in Remote Sensing}, volume = {3}, journal = {Frontiers in Remote Sensing}, issn = {2673-6187}, doi = {10.3389/frsen.2022.1010978}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-301462}, year = {2023}, abstract = {The fast and accurate yield estimates with the increasing availability and variety of global satellite products and the rapid development of new algorithms remain a goal for precision agriculture and food security. However, the consistency and reliability of suitable methodologies that provide accurate crop yield outcomes still need to be explored. The study investigates the coupling of crop modeling and machine learning (ML) to improve the yield prediction of winter wheat (WW) and oil seed rape (OSR) and provides examples for the Free State of Bavaria (70,550 km2), Germany, in 2019. The main objectives are to find whether a coupling approach [Light Use Efficiency (LUE) + Random Forest (RF)] would result in better and more accurate yield predictions compared to results provided with other models not using the LUE. Four different RF models [RF1 (input: Normalized Difference Vegetation Index (NDVI)), RF2 (input: climate variables), RF3 (input: NDVI + climate variables), RF4 (input: LUE generated biomass + climate variables)], and one semi-empiric LUE model were designed with different input requirements to find the best predictors of crop monitoring. The results indicate that the individual use of the NDVI (in RF1) and the climate variables (in RF2) could not be the most accurate, reliable, and precise solution for crop monitoring; however, their combined use (in RF3) resulted in higher accuracies. Notably, the study suggested the coupling of the LUE model variables to the RF4 model can reduce the relative root mean square error (RRMSE) from -8\% (WW) and -1.6\% (OSR) and increase the R 2 by 14.3\% (for both WW and OSR), compared to results just relying on LUE. Moreover, the research compares models yield outputs by inputting three different spatial inputs: Sentinel-2(S)-MOD13Q1 (10 m), Landsat (L)-MOD13Q1 (30 m), and MOD13Q1 (MODIS) (250 m). The S-MOD13Q1 data has relatively improved the performance of models with higher mean R 2 [0.80 (WW), 0.69 (OSR)], and lower RRMSE (\%) (9.18, 10.21) compared to L-MOD13Q1 (30 m) and MOD13Q1 (250 m). Satellite-based crop biomass, solar radiation, and temperature are found to be the most influential variables in the yield prediction of both crops.}, language = {en} } @article{VeyKapsnerFuchsetal.2019, author = {Vey, Johannes and Kapsner, Lorenz A. and Fuchs, Maximilian and Unberath, Philipp and Veronesi, Giulia and Kunz, Meik}, title = {A toolbox for functional analysis and the systematic identification of diagnostic and prognostic gene expression signatures combining meta-analysis and machine learning}, series = {Cancers}, volume = {11}, journal = {Cancers}, number = {10}, issn = {2072-6694}, doi = {10.3390/cancers11101606}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-193240}, year = {2019}, abstract = {The identification of biomarker signatures is important for cancer diagnosis and prognosis. However, the detection of clinical reliable signatures is influenced by limited data availability, which may restrict statistical power. Moreover, methods for integration of large sample cohorts and signature identification are limited. We present a step-by-step computational protocol for functional gene expression analysis and the identification of diagnostic and prognostic signatures by combining meta-analysis with machine learning and survival analysis. The novelty of the toolbox lies in its all-in-one functionality, generic design, and modularity. It is exemplified for lung cancer, including a comprehensive evaluation using different validation strategies. However, the protocol is not restricted to specific disease types and can therefore be used by a broad community. The accompanying R package vignette runs in ~1 h and describes the workflow in detail for use by researchers with limited bioinformatics training.}, language = {en} } @article{KaltdorfTheissMarkertetal.2018, author = {Kaltdorf, Kristin Verena and Theiss, Maria and Markert, Sebastian Matthias and Zhen, Mei and Dandekar, Thomas and Stigloher, Christian and Kollmannsberger, Philipp}, title = {Automated classification of synaptic vesicles in electron tomograms of C. elegans using machine learning}, series = {PLoS ONE}, volume = {13}, journal = {PLoS ONE}, number = {10}, doi = {10.1371/journal.pone.0205348}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-176831}, pages = {e0205348}, year = {2018}, abstract = {Synaptic vesicles (SVs) are a key component of neuronal signaling and fulfil different roles depending on their composition. In electron micrograms of neurites, two types of vesicles can be distinguished by morphological criteria, the classical "clear core" vesicles (CCV) and the typically larger "dense core" vesicles (DCV), with differences in electron density due to their diverse cargos. Compared to CCVs, the precise function of DCVs is less defined. DCVs are known to store neuropeptides, which function as neuronal messengers and modulators [1]. In C. elegans, they play a role in locomotion, dauer formation, egg-laying, and mechano- and chemosensation [2]. Another type of DCVs, also referred to as granulated vesicles, are known to transport Bassoon, Piccolo and further constituents of the presynaptic density in the center of the active zone (AZ), and therefore are important for synaptogenesis [3]. To better understand the role of different types of SVs, we present here a new automated approach to classify vesicles. We combine machine learning with an extension of our previously developed vesicle segmentation workflow, the ImageJ macro 3D ART VeSElecT. With that we reliably distinguish CCVs and DCVs in electron tomograms of C. elegans NMJs using image-based features. Analysis of the underlying ground truth data shows an increased fraction of DCVs as well as a higher mean distance between DCVs and AZs in dauer larvae compared to young adult hermaphrodites. Our machine learning based tools are adaptable and can be applied to study properties of different synaptic vesicle pools in electron tomograms of diverse model organisms.}, language = {en} }