Biology subjects

Jacob, E.

Publications and source records attributed to Jacob, E..

7 recordsLinked to original sources

bioRxiv2026

Integrating longitudinal hyperspectral phenotyping with AI and GWAS to dissect barley waterlogging responses

Waterlogging is a major constraint on barley productivity, yet its dynamic, multi-phase nature makes it challenging to dissect using traditional phenotyping approaches. High-throughput phenotyping (HTP) platforms address this by enabling temporal, multi-sensor imaging of large populations, but generate complex datasets that demand new analytical frameworks. Here, we imaged 230 barley accessions over 14 days of waterlogging stress and seven days of recovery using visible, chlorophyll fluorescence, and hyperspectral sensors. Explainable AI was applied to classify stress responses into early stress, late stress, and recovery phases, achieving 86% classification accuracy, and to identify the hyperspectral indices most informative for each phase. Water index (WATER1) and structure insensitive pigment index (SIPI) emerged as primary predictors of stress response. Longitudinal genome-wide association studies (GWAS), using a treatment-by-marker interaction model, identified 236 significant loci across 12 linkage disequilibrium blocks, implicating candidate genes involved in oxidative stress regulation, transcriptional control, and auxin transport. MYB transcription factors were consistently identified across all stress phases, underscoring their central role in waterlogging adaptation. To support interpretation of longitudinal GWAS results, we developed 3D-QTLVis, an interactive visualisation tool that extends Manhattan plots across time, enabling clearer identification of dynamic genomic regions underlying stress tolerance.

plant biology↗

bioRxiv2024

An artificial intelligence-based model for prediction of Clonal Hematopoiesis mutants in cell-free DNA samples

Circulating tumor DNA is a critical biomarker in cancer diagnostics, but its accurate interpretation requires careful consideration of clonal hematopoiesis (CH), which can contribute to variants in cell-free DNA and potentially obscure true tumor-derived signals. Accurate detection of somatic variants of CH origin in plasma samples remains challenging in the absence of matched white blood cells sequencing. Here we present an open-source machine learning framework (MetaCHIP) which classifies variants in cfDNA from plasma-only samples as CH or tumor origin, surpassing state-of-the-art classification rates.

bioinformatics↗

bioRxiv2024

Integrating Knowledge Graphs into Machine Learning Models for Survival Prediction and Biomarker Discovery in Patients with Non-Small-Cell Lung Cancer

Survival prediction is a critical aspect of clinical study design and biomarker discovery. It is a highly complex task, given the large number of "omics" and clinical features, as well as the high degrees of freedom that drive patient survival. Prior knowledge can play a critical role in uncovering the complexity of a disease and understanding the driving factors affecting a patients survival. We introduce a methodology for incorporating prior knowledge into machine learning-based models for prediction of patient survival through knowledge graphs, demonstrating the advantage of such an approach for patients with non-small-cell lung cancer. Using data from patients treated with immuno-oncologic therapies in the POPLAR (NCT01903993) and OAK (NCT02008227) clinical trials, we found that the use of knowledge graphs yielded significantly improved hazard ratios, including in the POPLAR cohort, for models based on biomarker tumor mutation burden compared with those based on knowledge graphs. Use of a model-defined mutational 10-gene signature led to significant overall survival differentiation for both trials. We provide parameterized code for incorporating knowledge graphs into survival analyses for use by the wider scientific community.

bioinformatics↗

bioRxiv2024

Quantifying the advantage of multimodal data fusion for survival prediction in cancer patients

The last decade has seen an unprecedented advance in technologies at the level of high-throughput molecular assays and image capturing and analysis, as well as clinical phenotyping and digitization of patient data. For decades, genotyping (identification of genomic alterations), the casual anchor in biological processes, has been an essential component in interrogating disease progression and a guiding step in clinical decision making. Indeed, survival rates in patients tested with next-generation sequencing have been found to be significantly higher in those who received a genome-guided therapy than in those who did not. Nevertheless, DNA is only a small part of the complex pathophysiology of cancer development and progression. To assess a more complete picture, researchers have been using data taken from multiple modalities, such as transcripts, proteins, metabolites, and epigenetic factors, that are routinely captured for many patients. Multimodal machine learning offers the potential to leverage information across different bioinformatics modalities to improve predictions of patient outcome. Identifying a multiomics data fusion strategy that clearly demonstrates an improved performance over unimodal approaches is challenging, primarily due to increased dimensionality and other factors, such as small sample sizes and the sparsity and heterogeneity of data. Here we present a flexible pipeline for systematically exploring and comparing multiple multimodal fusion strategies. Using multiple independent data sets from The Cancer Genome Atlas, we developed a late fusion strategy that consistently outperformed unimodal models, clearly demonstrating the advantage of a multimodal fusion model.

bioinformatics↗

bioRxiv2024

Biological insights from plasma proteomics of non-small cell lung cancer patients treated with immunotherapy

IntroductionImmune checkpoint inhibitors have made a paradigm shift in the treatment of non-small cell lung cancer (NSCLC). However, clinical response varies widely and robust predictive biomarkers for patient stratification are lacking. Here, we characterize early on-treatment proteomic changes in blood plasma to gain a better understanding of treatment response and resistance. MethodsPre-treatment (T0) and on-treatment (T1) plasma samples were collected from 225 NSCLC patients receiving PD-1/PD-L1 inhibitor-based regimens. Plasma was profiled using aptamer-based technology to quantify approximately 7000 plasma proteins per sample. Proteins displaying significant fold changes (T1:T0) were analyzed further to identify associations with clinical outcomes. Bioinformatic analyses of upregulated proteins were performed to determine potential cell origins and enriched biological processes. ResultsThe levels of 142 proteins were significantly increased in the plasma of NSCLC patients following ICI-based treatments. Soluble PD-1 exhibited the highest increase, with a positive correlation to tumor PD-L1 status. Bioinformatic analysis of the ICI monotherapy dataset revealed a set of 30 upregulated proteins that formed a single, highly interconnected network with CD8A serving as a central hub, suggesting T cell activation during ICI treatment. Notably, the T cell-related network was detected regardless of clinical benefit. Lastly, circulating proteins of alveolar origin were identified as potential biomarkers of limited clinical benefit, possibly due to a link with cellular stress and lung damage. ConclusionsOur study provides insights into the biological processes activated during ICI-based therapy, highlighting the potential of plasma proteomics to identify mechanisms of therapy resistance and potential biomarkers for outcome.

bioinformatics↗

bioRxiv2022

Empirical methods for the validation of Time-To-Event mathematical models taking into account uncertainty and variability: Application to EGFR+ Lung Adenocarcinoma.

BackgroundOver the past several decades, metrics have been defined to assess the quality of various types of models and to compare their performance depending on their capacity to explain the variance found in real-life data. However, available validation methods are mostly designed for statistical regressions rather than for mechanistic models. To our knowledge, in the latter case, there are no consensus standards, for instance for the validation of predictions against real-world data given the variability and uncertainty of the data. In this work, we focus on the prediction of time-to-event curves using as an application example a mechanistic model of non-small cell lung cancer. We designed four empirical methods to assess both model performance and reliability of predictions: two methods based on bootstrapped versions of parametric statistical tests: log-rank and combined weighted log-ranks (MaxCombo); and two methods based on bootstrapped prediction intervals, referred to here as raw coverage and the juncture metric. We also introduced the notion of observation time uncertainty to take into consideration the real life delay between the moment when an event happens, and the moment when it is observed and reported. ResultsWe highlight the advantages and disadvantages of these methods according to their application context. We have shown that the context of use of the model has an impact on the model validation process. Thanks to the use of several validation metrics we have highlighted the limit of the model to predict the evolution of the disease in the whole population of mutations at the same time, and that it was more efficient with specific predictions in the target mutation populations. The choice and use of a single metric could have led to an erroneous validation of the model and its context of use. ConclusionsWith this work, we stress the importance of making judicious choices for a metric, and how using a combination of metrics could be more relevant, with the objective of validating a given model and its predictions within a specific context of use. We also show how the reliability of the results depends both on the metric and on the statistical comparisons, and that the conditions of application and the type of available information need to be taken into account to choose the best validation strategy.

systems biology↗

bioRxiv2022

Transgenerational transcriptional heterogeneity from cytoplasmic chromatin

Transcriptional heterogeneity from plasticity of the epigenetic state of chromatin is thought to contribute to tumor evolution, metastasis, and drug resistance 1-3. However, the mechanisms leading to nongenetic cell-to-cell variation in gene expression remain poorly understood. Here we demonstrate that heritable transcriptional changes can result from the formation of micronuclei, aberrations of the nucleus that are common in cancer4,5. Micronuclei have fragile nuclear envelopes (NE) that are prone to spontaneous rupture, which exposes chromosomes to the cytoplasm and disrupts many nuclear activities 6,7. Using a combination of long-term live-cell imaging and same-cell, single-cell RNA sequencing (Look-Seq2), we identified significant reduction of gene expression in micronuclei, both before and after NE rupture. Furthermore, chromosomes in micronuclei fail to normally recover histone 3 lysine 27 acetylation, a critical step for the reestablishment of normal transcription after mitosis 8-10. These transcription and chromatin defects can persist into the next generation in a subset of cells, even after these chromosomes are incorporated into normal daughter nuclei. Moreover, persistent transcriptional repression is strongly associated with, and may be explained by, surprisingly long-lived DNA damage to these reincorporated chromosomes. Therefore, heritable alterations in transcription can originate from aberrations of nuclear architecture.

cell biology↗