Related papers: Multi-modal single-cell foundation models via dyna…

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

The design and implementation of regulation motifs ensuring robust perfect adaptation are challenging problems in synthetic biology. Indeed, the design of high-yield robust metabolic pathways producing, for instance, drug precursors and…

Deep learning has revolutionized many industries by enabling models to automatically learn complex patterns from raw data, reducing dependence on manual feature engineering. However, deep learning algorithms are sensitive to input data, and…

We describe the time evolution of gene expression levels by using a time translational matrix to predict future expression levels of genes based on their expression levels at some initial time. We deduce the time translational matrix for…

The advent of single-cell technology has significantly improved our understanding of cellular states and subpopulations in various tissues under normal and diseased conditions by employing data-driven approaches such as clustering and…

Multicellular organisms contain a wide variety of highly specialized cell types. The consistency and robustness of developmental trajectories suggest that complex gene regulatory networks effectively act as low-dimensional cell fate…

The mutation and selection of regulatory DNA sequences is presented as an ideal model system of molecular evolution where genotype, phenotype, and fitness can be explicitly and independently characterized. In this theoretical study, we…

Evolution of gene regulation is crucial for our understanding of the phenotypic differences between species, populations and individuals. Sequence-specific binding of transcription factors to the regulatory regions on the DNA is a key…

The road to Artificial General Intelligence goes through the generation of context-aware reactive behaviors, where the Transformer architecture has been proven to be the state-of-the-art. However, they still fail to develop reasoning.…

Next-token prediction serves as the dominant component in current neural language models. During the training phase, the model employs teacher forcing, which predicts tokens based on all preceding ground truth tokens. However, this approach…

A transversal topic of my research has been the development and application of computational methods for DNA sequence analysis. The methods I have been developing aim at improving our understanding of the regulation processes happening in…

Since its selection as the method of the year in 2013, single-cell technologies have become mature enough to provide answers to complex research questions. With the growth of single-cell profiling technologies, there has also been a…

The spatial positioning of chromosomes relative to functional nuclear bodies is intertwined with genome functions such as transcription. However, the sequence patterns and epigenomic features that collectively influence chromatin spatial…

Single-cell RNA-seq foundation models achieve strong performance on downstream tasks but remain black boxes, limiting their utility for biological discovery. Recent work has shown that sparse dictionary learning can extract concepts from…

In the brain, learning signals change over time and synaptic location, and are applied based on the learning history at the synapse, in the complex process of neuromodulation. Learning in artificial neural networks, on the other hand, is…

Deep dynamic generative models are developed to learn sequential dependencies in time-series data. The multi-layered model is designed by constructing a hierarchy of temporal sigmoid belief networks (TSBNs), defined as a sequential stack of…

Deep neural networks are among the most widely applied machine learning tools showing outstanding performance in a broad range of tasks. We present a method for folding a deep neural network of arbitrary size into a single neuron with…

Token representation strategies within large-scale neural architectures often rely on contextually refined embeddings, yet conventional approaches seldom encode structured relationships explicitly within token interactions. Self-attention…

Token representations influence the efficiency and adaptability of language models, yet conventional tokenization strategies impose rigid segmentation boundaries that do not adjust dynamically to evolving contextual relationships. The…

Single-cell RNA sequencing (scRNA-seq) data analysis is pivotal for understanding cellular heterogeneity. However, the high sparsity and complex noise patterns inherent in scRNA-seq data present significant challenges for traditional…