Biology subjects

Pinaya, W. H. L.

Publications and source records attributed to Pinaya, W. H. L..

4 recordsLinked to original sources

bioRxiv2024

Confounder-aware foundation modeling for accurate phenotype profiling in cell imaging

Image-based profiling is rapidly transforming drug discovery, offering unprecedented insights into cellular responses. However, experimental variability hinders accurate identification of mechanisms of action (MoA) and compound targets. Existing methods commonly fail to generalize to novel compounds, limiting their utility in exploring uncharted chemical space. To address this, we present a confounder-aware foundation model integrating a causal mechanism within a latent diffusion model, enabling the generation of balanced synthetic datasets for robust biological effect estimation. Trained on over 13 million Cell Painting images and 107 thousand compounds, our model learns robust cellular phenotype representations, mitigating confounder impact. We achieve state-of-the-art MoA and target prediction for both seen (0.66 and 0.65 ROC-AUC) and unseen compounds (0.65 and 0.73 ROC-AUC), significantly surpassing real and batch-corrected data. This innovative framework advances drug discovery by delivering robust biological effect estimations for novel compounds, potentially accelerating hit expansion. Our model establishes a scalable and adaptable foundation for cell imaging, holding the potential to become a cornerstone in data-driven drug discovery.

bioengineering↗

bioRxiv2024

A Graph Neural Network Approach to Investigate Brain Critical States Over Neurodevelopment

Recent studies show that functional resting-state dynamics may be modelled by lattice models near criticality, such as the 2D Ising model. The Ising temperature, which is the control parameter dictating the phase transitions of the model, can provide insight into the large-scale dynamics and is being used to better understand different brain states and neurodevelopment. This period is categorized by intricated changes in the microcircuits to consolidate networks. These changes influence the macroscopic brain dynamics and also its functional relations, which can be observed in functional Magnetic Resonance Imaging (fMRI). Therefore, this work investigates neurodevelopment through a novel method to estimate the Ising temperature of the brain from fMRI data using functional connectivity and Graph Neural Networks (GNNs) trained on Ising model networks. The main finding indicates a statistically significant negative correlation between age and temperature for typically developing children ( =- 0. 48, < 0. 0001) and also children with Attention deficit/hyperactivity disorder (ADHD) ( =- 0. 49, < 0. 0001). This study suggests that the brain gets distant from criticality as age increases, leading to a more ordered state. Author SummaryIn this study, we employed Graph Neural Networks to investigate functional connectivity patterns of resting-state fMRI data using the 2D Ising model as a theoretical framework to access critical dynamics. Our key finding is the significant decrease in Ising temperature with age in both typically developing children and those with ADHD, indicating a developmental transition from a high-entropy, disordered state to a more ordered, decreasing the availability of dynamical states that the system can occupy and transit in different conditions. Moreover, this decrease in temperature is crucial as it implies that the brain is moving away from criticality, leading the system to a more sub-critical regime. The correlation coefficients across the groups showed no significant differences, indicating the same developmental trajectory.

neuroscience↗

bioRxiv2020

Normative modelling using deep autoencoders: a multi-cohort study on mild cognitive impairment and Alzheimer's disease

Normative modelling is an emerging method for quantifying how individuals deviate from the healthy populational pattern. Several machine learning models have been implemented to develop normative models to investigate brain disorders, including regression, support vector machines and Gaussian process models. With the advance of deep learning technology, the use of deep neural networks has also been proposed. In this study, we assessed normative models based on deep autoencoders using structural neuroimaging data from patients with Alzheimers disease (n=206) and mild cognitive impairment (n=354). We first trained the autoencoder on an independent dataset (UK Biobank dataset) with 11,034 healthy controls. Then, we estimated how each patient deviated from this norm and established which brain regions were associated to this deviation. Finally, we compared the performance of our normative model against traditional classifiers. As expected, we found that patients exhibited deviations according to the severity of their clinical condition. The model identified medial temporal regions, including the hippocampus, and the ventricular system as critical regions for the calculation of the deviation score. Overall, the normative model had comparable cross-cohort generalizability to traditional classifiers. In order to promote open science, we are making all scripts and the trained models available to the wider research community.

neuroscience↗

bioRxiv2018

Unique individual factors shape brain hubs organization of the human functional connectome

Recent evidence suggests that the human functional connectome is stable at different time scales and unique. These characteristics posit the functional connectome not only as an individual marker but also as a powerful discriminatory measure characterized by high intersubject variability. Among distinct sources of intersubject variability, the long-term sources include functional patterns that emerge from genetic factors. Here, we sought to investigate the contribution of additive genetic factors to the variability of functional networks by determining the heritability of the connectivity strength in a multivariate fashion. First, we reproduced and extended the connectome fingerprinting analysis to the identification of twin pairs. Then, we estimated the heritability of functional networks by a multivariate ACE modeling approach with bootstrapping. Twin pairs were identified above chance level using connectome fingerprinting, with monozygotic twin identification accuracy equal to 57.2% on average for whole-brain connectome. Additionally, we found that a visual (0.37), the medial frontal (0.31) and the motor (0.30) functional networks were the most influenced by additive genetic factors. Our findings suggest that genetic factors not only partially determine intersubject variability of the functional connectome, such that twins can be identified using connectome fingerprinting, but also differentially influence connectivity strength in large-scale functional networks.

neuroscience↗