11 March 2022 in Bioinformatics
Motivation: Exploring drug–protein interactions (DPIs) provides a rapid and precise approach to assist in laboratory experiments for discovering new drugs. Network-based methods usually utilize a drug–protein association network and predict DPIs by the information of its associated proteins or drugs, called ‘guilt-by-association’ principle. However, the ‘guilt-by-association’ principle is not always true because sometimes similar proteins cannot interact with similar drugs. Recently, learning-based methods learn molecule properties underlying DPIs by utilizing existing databases of characterized interactions but neglect the network-level information.Results: We propose a novel method, namely BridgeDPI. We devise a class of virtual nodes to bridge the gap between drugs and proteins and construct a learnable drug–protein association network. The network is optimized based on the supervised signals from the downstream task—the DPI prediction. Through information passing on this drug–protein association network, a Graph Neural Network can capture the network-level information among diverse drugs and proteins. By combining the network-level information and the learning-based method, BridgeDPI achieves significant improvement in three real-world DPI datasets. Moreover, the case study further verifies the effectiveness and reliability of BridgeDPI.Availability and implementation: The source code of BridgeDPI can be accessed at https://github.com/SenseTime-Knowledge-Mining/BridgeDPI. The source data used in this study is available on the https://github.com/IBM/InterpretableDTIP (for the BindingDB dataset), https://github.com/masashitsubaki/CPI_prediction (for the C.ELEGANS and HUMAN) datasets, http://dude.docking.org/ (for the DUD-E dataset), repectively.
7 November 2022 in Nature Machine Intelligence
Most natural and synthetic antibodies are ‘unseen’. That is, the demonstration of their neutralization effects with any antigen requires laborious and costly wet-lab experiments. The existing methods that learn antibody representations from known antibody–antigen interactions are unsuitable for unseen antibodies owing to the absence of interaction instances. The DeepAAI method proposed herein learns unseen antibody representations by constructing two adaptive relation graphs among antibodies and antigens and applying Laplacian smoothing between unseen and seen antibodies’ representations. Rather than using static protein descriptors, DeepAAI learns representations and relation graphs ‘dynamically’, optimized towards the downstream tasks of neutralization prediction and 50% inhibition concentration estimation. The performance of DeepAAI is demonstrated on human immunodeficiency virus, severe acute respiratory syndrome coronavirus 2, influenza and dengue. Moreover, the relation graphs have rich interpretability. The antibody relation graph implies similarity in antibody neutralization reactions, and the antigen relation graph indicates the relation among a virus’s different variants. We accordingly recommend probable broad-spectrum antibodies against new variants of these viruses.
1 April 2006 in Mini-Reviews in Medicinal Chemistry
Neuraminidase (NA) is the major surface glycoprotein of the influenza virus. It has been considered a suitable target for designing agents against influenza viruses. Rational drug design of NA inhibitors is now in the clinic and is effective for the treatment of influenza. Recently, research of structure-based NA inhibitors is becoming an interesting field, leading to a breakthrough in the control of influenza. Here we review a series of neuraminidase inhibitors and the recent progress in this field.
24 March 2023 in Computers in Biology and Medicine
18 January 2007 in International Journal of Technology Assessment in Health Care
Objectives: The cost-effectiveness of prenatal diagnosis intervention for Down's syndrome (DS) in China was assessed and evidence-based information for policy makers and providers is presented.Methods: Based on field surveys in four selected cities in China and a literature review, the economic evaluation of prenatal diagnosis for DS from a societal perspective is conducted by cost-effectiveness analysis.Results: In current clinical practice, for a cohort of 10,000 pregnant women, the strategy that delivers karyotyping by chorionic villus sampling (CVS) or amniocentesis (AC) only to those pregnant women 35 years of age and older (maternal age screening strategy) can detect .67 DS births. The strategy that offers the diagnostic test after maternal serum screening with α-fetoprotein and human chorionic gonadotrophin (maternal serum screening strategy) can detect 1.41 DS births. The cost per prevented DS birth by the maternal age screening strategy and maternal serum screening strategy is US$13,091 and US$56,048, respectively. Sensitivity analysis shows that the maternal serum screening strategy can be cost-effective if uptake rate of CVS or AC for patients with positive serum tests increase while the cost of serum screening decreases.Conclusions: Although, in general, serum screening has been found to be more cost-effective than maternal age screening, this appears not to be the case in China. The reasons appear to be low uptake rate of the maternal serum strategy, low uptake rate of CVS or AC, and the high price of serum screening. Our findings are that health system factors concerning technology utilization are important determinants of the technology's efficiency.
27 April 2025 in Bioorganic & Medicinal Chemistry