Related papers: Multimodal Modeling of CRISPR-Cas12 Activity Using…
The precise layout of gene expression patterns is a crucial step in development. Formation of a sharp boundary between high and low expression domains requires a genetic mechanism which is both sensitive and robust to fluctuations, a demand…
It is well known that the integration among different data-sources is reliable because of its potential of unveiling new functionalities of the genomic expressions which might be dormant in a single source analysis. Moreover, different…
In this paper, we use the biological domain knowledge incorporated into stochastic models for ab initio RNA secondary-structure prediction to improve the state of the art in joint compression of RNA sequence and structure data (Liu et al.,…
Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen…
Electrocardiogram (ECG) diagnosis remains challenging due to limited labeled data and the need to capture subtle yet clinically meaningful variations in rhythm and morphology. We present CREMA (Contrastive Regularized Masked Autoencoder), a…
Data analysis focuses on harnessing advanced statistics, programming, and machine learning techniques to extract valuable insights from vast datasets. An increasing volume and variety of research emerged, addressing datasets of diverse…
We report a flexible language-model based deep learning strategy, applied here to solve complex forward and inverse problems in protein modeling, based on an attention neural network that integrates transformer and graph convolutional…
Despite substantial efforts, deep learning has not yet delivered a transformative impact on elucidating regulatory biology, particularly in the realm of predicting gene expression profiles. Here, we argue that genuine "foundation models" of…
Graph pre-training strategies have been attracting a surge of attention in the graph mining community, due to their flexibility in parameterizing graph neural networks (GNNs) without any label information. The key idea lies in encoding…
Although RNAs play many cellular functions little is known about the dynamics and thermodynamics of these molecules. In principle, all-atom molecular dynamics simulations can investigate these issues, but with current computer facilities,…
The pre-trained foundation models (PFMs) have become essential for facilitating large-scale multimodal learning. Researchers have effectively employed the ``pre-train, prompt, and predict'' paradigm through prompt learning to induce…
In biology, predicting RNA secondary structures plays a vital role in determining its physical and chemical properties. Although we have powerful energy models to predict them as well as parametric analysis to understand the models…
Raman spectroscopy's capability to provide meaningful composition predictions is heavily reliant on a pre-processing step to remove insignificant spectral variation. This is crucial in biofluid analysis. Widespread adoption of diagnostics…
We present a methodology for training foundational transformer models capable of processing collider data with diverse kinematic signatures. Our universal foundation model is designed for simultaneous analysis of all processes involving…
This dissertation explores how deep generative models can advance the analysis of challenging biological problems by integrating domain knowledge with deep learning. It focuses on two areas: DNA reaction kinetics and cryogenic electron…
Pre-trained machine learning (ML) models have shown great performance for a wide range of applications, in particular in natural language processing (NLP) and computer vision (CV). Here, we study how pre-training could be used for…
A simple way to get insights about the possible functional motions of a protein is to perform a normal mode analysis (NMA). Indeed, it has been shown that low-frequency modes thus obtained are often closely related to domain motions…
Many applications of machine learning require a model to make accurate pre-dictions on test examples that are distributionally different from training ones, while task-specific labels are scarce during training. An effective approach to…
ECG foundation models are increasingly popular due to their adaptability across various tasks. However, their clinical applicability is often limited by performance gaps compared to task-specific models, even after pre-training on large ECG…
Foundation models have achieved remarkable success across many domains, relying on pretraining over vast amounts of data. Graph-structured data often lacks the same scale as unstructured data, making the development of graph foundation…