Despite important advances in medication, there may be nonetheless no efficient vaccine for the human immunodeficiency virus (HIV), though current hope has emerged via the invention of antibodies able to neutralizing numerous HIV strains. However, HIV can generally evade identified broadly neutralizing antibody responses by way of mutational pathways, which makes it all of the tougher to design an efficient answer.
An very best vaccine would elicit broadly neutralizing antibodies that concentrate on elements of the virus’s spike proteins the place mutations severely compromise viral health or the power to duplicate. This requires information of the health panorama, a mapping from sequence to health. To obtain this purpose, knowledge scientists from the HKUST and their collaborators from MIT have employed a computational method to estimate the health panorama of gp160, the polyprotein that includes HIV’s spike. The inferred panorama was then validated via comparisons with numerous experimental measurements.
Their findings had been revealed within the journal PNAS in January 2018.
“Without big data machine learning methods, it is simply impossible to make such a prediction,” mentioned Raymond Louie, co-author, Junior Fellow of HKUST’s Institute for Advanced Study and Research Assistant Professor within the Department of Electronic & Computer Engineering. “The number of parameters to be estimated came close to 4.4 million.”
The knowledge processed by the crew consisted of 815 residues and 20,043 sequences from 1,918 HIV-infected people.
“The computational method gave us fast and accurate results,” mentioned Matthew McKay, co-author and Hari Harilela Associate Professor within the Departments of Electronic & Computer Engineering and Chemical & Biological Engineering at HKUST. “The findings can assist biologists in proposing new immunogens and vaccination protocols that seek to force the virus to mutate to unfit states in order to evade immune responses, which is likely to thwart or limit viral infection.”
“While this method was developed to address the specific challenges posed by the gp160 protein, which we could not address using methods we developed to obtain the fitness landscapes of other HIV proteins, the approach is general and may be applied to other high-dimensional, maximum-entropy inference problems,” mentioned co-author Arup Ok. Chakraborty, the Robert T. Haslam Professor in Chemical Engineering, Physics, and Chemistry at MIT’s Institute for Medical Engineering & Science. “Specifically, our fitness landscape could be clinically useful in the future for the selection of combination bnAb therapy and immunogen design.”
“This is a multi-disciplinary study presenting an application of data science, and big data machine learning methods in particular, for addressing a challenging problem in biology,” mentioned McKay.
Researchers chart ‘health panorama’ to combat Hep C virus
Raymond H. Y. Louie et al, Fitness panorama of the human immunodeficiency virus envelope protein that’s focused by antibodies, Proceedings of the National Academy of Sciences (2018). DOI: 10.1073/pnas.1717765115