arXiv subjects

Adrián E. Granada

Publications and source records attributed to Adrián E. Granada.

3 recordsLinked to original sources

arXiv2026

Understanding Cell Fate Decisions with Temporal Attention

Understanding non-genetic determinants of cell fate is critical for developing and improving cancer therapies, as genetically identical cells can exhibit divergent outcomes under the same treatment conditions. In this work, we present a deep learning approach for cell fate prediction from raw long-term live-cell recordings of cancer cell populations under chemotherapeutic treatment. Our Transformer model is trained to predict cell fate directly from raw image sequences, without relying on predefined morphological or molecular features. Beyond classification, we introduce a comprehensive explainability framework for interpreting the temporal and morphological cues guiding the model's predictions. We demonstrate that prediction of cell outcomes is possible based on the video only, our model achieves balanced accuracy of 0.94 and an F1-score of 0.93. Attention and masking experiments further indicate that the signal predictive of the cell fate is not uniquely located in the final frames of a cell trajectory, as reliable predictions are possible up to 10 h before the event. Our analysis reveals distinct temporal distribution of predictive information in the mitotic and apoptotic sequences, as well as the role of cell morphology and p53 signaling in determining cell outcomes. Together, these findings demonstrate that attention-based temporal models enable accurate cell fate prediction while providing biologically interpretable insights into non-genetic determinants of cellular decision-making. The code is available at https://github.com/bozeklab/Cell-Fate-Prediction.

cs.CV↗

arXiv2025

TransientTrack: Advanced Multi-Object Tracking and Classification of Cancer Cells with Transient Fluorescent Signals

Tracking cells in time-lapse videos is an essential technique for monitoring cell population dynamics at a single-cell level. Current methods for cell tracking are developed on videos with mostly single, constant signals and do not detect pivotal events such as cell death. Here, we present TransientTrack, a deep learning-based framework for cell tracking in multi-channel microscopy video data with transient fluorescent signals that fluctuate over time following processes such as the circadian rhythm of cells. By identifying key cellular events - mitosis (cell division) and apoptosis (cell death) our method allows us to build complete trajectories, including cell lineage information. TransientTrack is lightweight and performs matching on cell detection embeddings directly, without the need for quantification of tracking-specific cell features. Furthermore, our approach integrates Transformer Networks, multi-stage matching using all detection boxes, and the interpolation of missing tracklets with the Kalman Filter. This unified framework achieves strong performance across diverse conditions, effectively tracking cells and capturing cell division and death. We demonstrate the use of TransientTrack in an analysis of the efficacy of a chemotherapeutic drug at a single-cell level. The proposed framework could further advance quantitative studies of cancer cell dynamics, enabling detailed characterization of treatment response and resistance mechanisms. The code is available at https://github.com/bozeklab/TransientTrack.

cs.CV↗

arXiv2021

Analysis of complex circadian time series data using wavelets

Experiments that compare rhythmic properties across different genetic alterations and entrainment conditions underlie some of the most important breakthroughs in circadian biology. A robust estimation of the rhythmic properties of the circadian signals goes hand in hand with these discoveries. Widely applied traditional signal analysis methods such as fitting cosine functions or Fourier transformations rely on the assumption that oscillation periods do not change over time. However, novel high-resolution recording techniques have shown that, most commonly, circadian signals exhibit time-dependent changes of periods and amplitudes which cannot be captured with the traditional approaches. In this chapter we introduce a method to determine time-dependent properties of oscillatory signals, using the novel open-source Python-based Biological Oscillations Analysis Toolkit (pyBOAT). We show with examples how to detect rhythms, compute and interpret high-resolution time-dependent spectral results, analyze the main oscillatory component and to subsequently determine these main components time-dependent instantaneous period, amplitude and phase. We introduce step-by-step how such an analysis can be done by means of the easy-to-use point-and-click graphical user interface (GUI) provided by pyBOAT or executed within a Python programming environment. Concepts are explained using simulated signals as well as experimentally obtained time series.

q-bio.QM↗