<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Gaur, Neeraj K.</style></author><author><style face="normal" font="default" size="100%">Goyal, Venuka Durani</style></author><author><style face="normal" font="default" size="100%">Kulkarni, Kiran</style></author><author><style face="normal" font="default" size="100%">Makde, Ravindra D.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Machine learning classifiers aid virtual screening for efficient design of mini-protein therapeutics</style></title><secondary-title><style face="normal" font="default" size="100%">Bioorganic &amp; Medicinal Chemistry Letters</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Drug design</style></keyword><keyword><style  face="normal" font="default" size="100%">machine learning</style></keyword><keyword><style  face="normal" font="default" size="100%">Mini-proteins</style></keyword><keyword><style  face="normal" font="default" size="100%">Protein therapeutics</style></keyword><keyword><style  face="normal" font="default" size="100%">virtual screening</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2021</style></year><pub-dates><date><style  face="normal" font="default" size="100%">APR </style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">38</style></volume><pages><style face="normal" font="default" size="100%">127852</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;De novo design of mini-proteins (4-12 kDa) has recently been shown to produce new candidates for protein therapeutics. They are temperature stable molecules that bind to the drug target with high affinity for inhibiting its interactions. The development of mini-protein binders requires laboratory screening of tens of thousands of molecules for effective target binding. In this study we trained machine learning classifiers which can distinguish, with 90% accuracy and 80% precision, mini-protein binders from non-binding molecules designed for a particular target; this significantly reduces the number of mini protein candidates for experimental screening. Further, on the basis of our results we propose a multi-stage protocol where a small dataset (few hundred experimentally verified target-specific mini-proteins) can be used to train classifiers for improving the efficiency of mini-protein design for any specific target.&lt;/p&gt;</style></abstract><work-type><style face="normal" font="default" size="100%">Article</style></work-type><custom3><style face="normal" font="default" size="100%">&lt;p&gt;Foreign&lt;/p&gt;</style></custom3><custom4><style face="normal" font="default" size="100%">2.823</style></custom4></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Gaur, Neeraj K.</style></author><author><style face="normal" font="default" size="100%">Ghosh, Biplab</style></author><author><style face="normal" font="default" size="100%">Goyal, Venuka Durani</style></author><author><style face="normal" font="default" size="100%">Kulkarni, Kiran</style></author><author><style face="normal" font="default" size="100%">Makde, Ravindra D.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Evolutionary conservation of protein dynamics: insights from all-atom molecular dynamics simulations of `peptidase' domain of Spt16</style></title><secondary-title><style face="normal" font="default" size="100%">Journal of Biomolecular Structure and Dynamics</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Backbone fluctuations</style></keyword><keyword><style  face="normal" font="default" size="100%">FACT complex</style></keyword><keyword><style  face="normal" font="default" size="100%">histone binding</style></keyword><keyword><style  face="normal" font="default" size="100%">interdomain motion</style></keyword><keyword><style  face="normal" font="default" size="100%">M24 peptidase</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2023</style></year><pub-dates><date><style  face="normal" font="default" size="100%">MAR </style></date></pub-dates></dates><volume><style face="normal" font="default" size="100%">41</style></volume><pages><style face="normal" font="default" size="100%">1445-1457</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;
	Protein function is encoded in its sequence, manifested in its three-dimensional structure, and facilitated by its dynamics. Studies have suggested that protein structures with higher sequence similarity could have more similar patterns of dynamics. However, such studies of protein dynamics within and across protein families typically rely on coarse-grained models, or approximate metrics like crystallographic B-factors. This study uses mu s scale molecular dynamics (MD) simulations to explore the conservation of dynamics among homologs of similar to 50 kDa N-terminal module of Spt16 (Spt16N). Spt16N from Saccharomyces cerevisiae (Sc-Spt16N) and three of its homologs with 30-40% sequence identities were available in the PDB. To make our data-set more comprehensive, the crystal structure of an additional homolog (62% sequence identity with Sc-Spt16N) was solved at 1.7 angstrom resolution. Cumulative MD simulations of 6 mu s were carried out on these Spt16N structures and on two additional protein structures with varying degrees of similarity to it. The simulations revealed that correlation in patterns of backbone fluctuations vary linearly with sequence identity. This trend could not be inferred using crystallographic B-factors. Further, normal mode analysis suggested a similar pattern of inter-domain (inter-lobe) motions not only among Spt16N homologs, but also in the M24 peptidase structure. On the other hand, MD simulation results highlighted conserved motions that were found unique for Spt16N protein, this along with electrostatics trends shed light on functional aspects of Spt16N. Communicated by Ramaswamy H. Sarma.&lt;/p&gt;
</style></abstract><issue><style face="normal" font="default" size="100%">4</style></issue><work-type><style face="normal" font="default" size="100%">Article</style></work-type><custom3><style face="normal" font="default" size="100%">&lt;p&gt;
	Foreign&lt;/p&gt;
</style></custom3><custom4><style face="normal" font="default" size="100%">&lt;p&gt;
	4.4&lt;/p&gt;
</style></custom4></record></records></xml>