Showing papers by "Albert-László Barabási published in 2023"

Machine learning prediction of the degree of food processing

Abstract: Despite the accumulating evidence that increased consumption of ultra-processed food has adverse health implications, it remains difficult to decide what constitutes processed food. Indeed, the current processing-based classification of food has limited coverage and does not differentiate between degrees of processing, hindering consumer choices and slowing research on the health implications of processed food. Here we introduce a machine learning algorithm that accurately predicts the degree of processing for any food, indicating that over 73% of the US food supply is ultra-processed. We show that the increased reliance of an individual's diet on ultra-processed food correlates with higher risk of metabolic syndrome, diabetes, angina, elevated blood pressure and biological age, and reduces the bio-availability of vitamins. Finally, we find that replacing foods with less processed alternatives can significantly reduce the health implications of ultra-processed food, suggesting that access to information on the degree of processing, currently unavailable to consumers, could improve population health.

Improving the generalizability of protein-ligand binding predictions with AI-Bind

Abstract: Identifying novel drug-target interactions is a critical and rate-limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, here we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortcuts that leverage the topology of the protein-ligand bipartite network, rather than learning the node features. Here we introduce AI-Bind, a pipeline that combines network-based sampling strategies with unsupervised pre-training to improve binding predictions for novel proteins and ligands. We validate AI-Bind predictions via docking simulations and comparison with recent experimental evidence, and step up the process of interpreting machine learning prediction of protein-ligand binding by identifying potential active binding sites on the amino acid sequence. AI-Bind is a high-throughput approach to identify drug-target combinations with the potential of becoming a powerful tool in drug discovery.

Accelerating network layouts using graph neural networks

Abstract: Abstract Graph layout algorithms used in network visualization represent the first and the most widely used tool to unveil the inner structure and the behavior of complex networks. Current network visualization software relies on the force-directed layout (FDL) algorithm, whose high computational complexity makes the visualization of large real networks computationally prohibitive and traps large graphs into high energy configurations, resulting in hard-to-interpret “hairball” layouts. Here we use Graph Neural Networks (GNN) to accelerate FDL, showing that deep learning can address both limitations of FDL: it offers a 10 to 100 fold improvement in speed while also yielding layouts which are more informative. We analytically derive the speedup offered by GNN, relating it to the number of outliers in the eigenspectrum of the adjacency matrix, predicting that GNNs are particularly effective for networks with communities and local regularities. Finally, we use GNN to generate a three-dimensional layout of the Internet, and introduce additional measures to assess the layout quality and its interpretability, exploring the algorithm’s ability to separate communities and the link-length distribution. The novel use of deep neural networks can help accelerate other network-based optimization problems as well, with applications from reaction-diffusion systems to epidemics.

Reproducible Science of Science at scale: pySciSci

Abstract: Science of science (SciSci) is a growing field encompassing diverse interdisciplinary research programs that study the processes underlying science. The field has benefited greatly from access to massive digital databases containing the products of scientific discourse—including publications, journals, patents, books, conference proceedings, and grants. The subsequent proliferation of mathematical models and computational techniques for quantifying the dynamics of innovation and success in science has made it difficult to disentangle universal scientific processes from those dependent on specific databases, data-processing decisions, field practices, etc. Here we present pySciSci, a freely available and easily adaptable package for the analysis of large-scale bibliometric data. The pySciSci package standardizes access to many of the most common datasets in SciSci and provides efficient implementations of common and advanced analytical techniques. https://www.webofscience.com/api/gateway/wos/peer-review/10.1162/qss_a_00260

Social AI and the Challenges of the Human-AI Ecosystem

Abstract: The rise of large-scale socio-technical systems in which humans interact with artificial intelligence (AI) systems (including assistants and recommenders, in short AIs) multiplies the opportunity for the emergence of collective phenomena and tipping points, with unexpected, possibly unintended, consequences. For example, navigation systems' suggestions may create chaos if too many drivers are directed on the same route, and personalised recommendations on social media may amplify polarisation, filter bubbles, and radicalisation. On the other hand, we may learn how to foster the"wisdom of crowds"and collective action effects to face social and environmental challenges. In order to understand the impact of AI on socio-technical systems and design next-generation AIs that team with humans to help overcome societal problems rather than exacerbate them, we propose to build the foundations of Social AI at the intersection of Complex Systems, Network Science and AI. In this perspective paper, we discuss the main open questions in Social AI, outlining possible technical and scientific challenges and suggesting research avenues.

Assessment of community efforts to advance network-based prediction of protein–protein interactions

Abstract: Abstract Comprehensive understanding of the human protein-protein interaction (PPI) network, aka the human interactome, can provide important insights into the molecular mechanisms of complex biological processes and diseases. Despite the remarkable experimental efforts undertaken to date to determine the structure of the human interactome, many PPIs remain unmapped. Computational approaches, especially network-based methods, can facilitate the identification of previously uncharacterized PPIs. Many such methods have been proposed. Yet, a systematic evaluation of existing network-based methods in predicting PPIs is still lacking. Here, we report community efforts initiated by the International Network Medicine Consortium to benchmark the ability of 26 representative network-based methods to predict PPIs across six different interactomes of four different organisms: A. thaliana , C. elegans , S. cerevisiae , and H. sapiens . Through extensive computational and experimental validations, we found that advanced similarity-based methods, which leverage the underlying network characteristics of PPIs, show superior performance over other general link prediction methods in the interactomes we considered.

The Clinical Trials Puzzle: How Network Effects Limit Drug Discovery

Abstract: The depth of knowledge offered by post-genomic medicine has carried the promise of new drugs, and cures for multiple diseases. To explore the degree to which this capability has materialized, we extract meta-data from 356,403 clinical trials spanning four decades, aiming to offer mechanistic insights into the innovation practices in drug discovery. We find that convention dominates over innovation, as over 96% of the recorded trials focus on previously tested drug targets, and the tested drugs target only 12% of the human interactome. If current patterns persist, it would take 170 years to target all druggable proteins. We uncover two network-based fundamental mechanisms that currently limit target discovery: preferential attachment, leading to the repeated exploration of previously targeted proteins; and local network effects, limiting exploration to proteins interacting with highly explored proteins. We build on these insights to develop a quantitative network-based model of drug discovery. We demonstrate that the model is able to accurately recreate the exploration patterns observed in clinical trials. Most importantly, we show that a network-based search strategy can widen the scope of drug discovery by guiding exploration to novel proteins that are part of under explored regions in the human interactome. ar X iv :2 30 1. 10 70 9v 1 [ qbi o. Q M ] 2 5 Ja n 20 23