Commit 630db8d4 authored by Vladimir Reinharz's avatar Vladimir Reinharz
Browse files

redid figs intersections remu/mam, added fig trna to supp mat, fixed angstrom with siunitx

parent e4e9a187
This source diff could not be displayed because it is too large. You can view the blob instead.
......@@ -2,9 +2,11 @@ import matplotlib
from matplotlib import pyplot as plt
import networkx as nx
from itertools import combinations
import numpy as np
import arnhack
import remu
rdat_path = ['../Data/5SRRNA_SHP_0002.rdat',
'../Data/CIDGMP_SHP_0002.rdat',
......@@ -161,7 +163,50 @@ def check_ali_quality():
#plt.tight_layout()
plt.savefig('Figure_ss_dist.pdf')
def make_intersection_fig():
i = 0
j = 0
fig, ax = plt.subplots(2,3)
z = -1
for zz, x in enumerate(rdat_path):
if title[zz] not in ('5S', 'tRNA', 'c-di-GMP', 'Cobalamin', 'Adenine_2', 'Adenine_3'):
continue
z += 1
j = z % 3
i = 0 if z < 3 else 1
#plt.subplot(2,6,i+1)
print i, j, title[zz]
a = remu.RemuSHAPE(x)
a.add_msa(msa_path[zz])
a.msa_npmi()
nb_pos = len(a.remu_entropy)
to_plot = []
for x in range(100):
nb_percentile = nb_pos*(100-x)*1.0/100
dma = len(a.get_disruptive_muts(x))
tot = dma*1.0/nb_percentile
to_plot.append(tot)
ax[i,j].plot(range(100), to_plot,
lw=3)
ax[i,j].set_title(title[zz])
#ax[i,j].set_ylim([0,2])
#ax[i,j].set_xticks(range(len(a.wt_shape)), list(a.get_ss_msa_on_wt()))
#ax[i,j].set_xticks(range(len(a.wt_shape)))
#ax[i,j].set_xticklabels(list(a.get_ss_msa_on_wt()))
ax[0,0].set_ylabel('Fraction intersection', fontsize=14)
#print dir(ax[0,0].yaxis)
#ax[0,0].xaxis.set_offset_position(-10)
ax[1, 1].set_xlabel(r'Percentile', fontsize=14)
#plt.ylabel('Fraction intersection', fontsize=14)
#plt.xlabel('Percentile', fontsize=14)
#plt.subplots_adjust(top=0.85)
#plt.tight_layout()
plt.savefig('Figure_remuSHAPE.pdf')
if __name__ == '__main__':
#make_shape_fig()
#make_dist_fig()
check_ali_quality()
#check_ali_quality()
make_intersection_fig()
......@@ -23,7 +23,7 @@ from numpy import average
from analyze import Analyze
PATH_REMU = '/home/mcb/vreinh/Applications/remuRNA/remuRNA'
PATH_REMU = '/Users/vreinharz/Applications/remuRNA/remuRNA'
"""
rdat_path = ['../Data/5SRRNA_SHP_0002.rdat', '../Data/CIDGMP_SHP_0002.rdat']
......
......@@ -81,7 +81,7 @@
%\pgfsetlayers{backbackground,background,main,foreground}
\usepackage[noend,ruled,vlined]{algorithm2e}
\usepackage{siunitx}
%\usepackage{tikz}
%\usepackage{todonotes}
......@@ -451,11 +451,11 @@ For each mutation over the \shape profile percentile cutoff~$\delta$, the data s
{\color{red}
We used different strategies to determine the interaction sites (i.e. positive data set), depending of the nature and context of these interactions. All interactions were manually verified.
For the 5S RNA, we implemented a PyMOL script to extract nucleotides of each PDB model, whose position any of their atom is at most at $5$\AA{} from any atom of another chain the the complex. An implementation of this script is included in the distribution of \soft
For the 5S RNA, we implemented a PyMOL script to extract nucleotides of each PDB model, whose position any of their atom is at most at \SI{5}{\angstrom} from any atom of another chain the the complex. An implementation of this script is included in the distribution of \soft
For the tRNA, we extracted positions that are at most $5$\AA{} away from another chain in the two tRNAs found inside the structure of the yeast 80S ribosome-tRNA complexes (PDB identifier \texttt{3J78}). However, because those were not phenylalanine tRNAs, we aligned them to the MaM sequence with \texttt{LocaRNA}\cite{will2007inferring}, and used this alignment to map the interaction sites on the latter. We identified the positions 1, 19, $34\mhyphen 36$, $56\mhyphen 57$, $73 \mhyphen76$ (containing the anticodon) in this positive set. Among them, only the anticodon and T-$\psi$-C-G, known to bind the 5S RNA in the 50S ribosomal subunit~\cite{schwarz1976codon}, motif appeared to us to be strongly conserved. Thus, we considered only these two interactions sites in our experiments and presented the results separately. For completeness, the results obtained on other positions have been included in the supplementary material. Finally, we also confirmed the location of the anticodon using \texttt{tRNAscan-SE}~\cite{schattner2005trnascan}.
For the tRNA, we extracted positions that are at most \SI{5}{\angstrom} away from another chain in the two tRNAs found inside the structure of the yeast 80S ribosome-tRNA complexes (PDB identifier \texttt{3J78}). However, because those were not phenylalanine tRNAs, we aligned them to the MaM sequence with \texttt{LocaRNA}\cite{will2007inferring}, and used this alignment to map the interaction sites on the latter. We identified the positions 1, 19, $34\mhyphen 36$, $56\mhyphen 57$, $73 \mhyphen76$ (containing the anticodon) in this positive set. Among them, only the anticodon and T-$\psi$-C-G, known to bind the 5S RNA in the 50S ribosomal subunit~\cite{schwarz1976codon}, motif appeared to us to be strongly conserved. Thus, we considered only these two interactions sites in our experiments and presented the results separately. For completeness, the results obtained on other positions have been included in the supplementary material. Finally, we also confirmed the location of the anticodon using \texttt{tRNAscan-SE}~\cite{schattner2005trnascan}.
For the riboswitches, we used \texttt{Ligand Explorer}~\cite{moreland2005molecular} to identify nucleotide at most $5$\AA{} from the ligand in their respective crystal structures.
For the riboswitches, we used \texttt{Ligand Explorer}~\cite{moreland2005molecular} to identify nucleotide at most \SI{5}{\angstrom} from the ligand in their respective crystal structures.
The set of all positions is found in the Supplementary Material Table 1.}
......@@ -489,7 +489,7 @@ We evaluated \soft on a comprehensive set of values for $\delta$ the \shape pro
\caption{{\bf Overall performances of \soft using experimental and computationally-predicted structural disruption data.} For a set of extreme percentile cutoff of the \shape profile disruption in the first {\color{red} row} (computational \remu disruption in the second {\color{red} row) $\delta$ and a minimal distance $\gamma$ from the mutation we show the average AUC.
5S positive set composed of the binding interfaces with other chains present in its four PDB models.
The tRNA positive set is divided between the anticodon positions and the A-$\psi$-C-G motif positions, obtained from the litterature.
The c-di-GMP, cobalamin and adenine riboswitches positive sets are composed of the positions at most 5$\AA$ from their ligands in their PDB structures. Four different models exist for
The c-di-GMP, cobalamin and adenine riboswitches positive sets are composed of the positions at most \SI{5}{\angstrom} from their ligands in their PDB structures. Four different models exist for
c-di-GMP and the AUC values are averaged.
}}
\label{fig:aucremumam}
......@@ -538,7 +538,7 @@ We conjecture that the differences in the influence of the $\gamma$ parameter, m
In Fig.~\ref{fig:5s_3d} we visualize one prediction from our method, for the 5s chain of \texttt{3OFC}. The disrupting mutation (red) is found in the top right corner behind the black spheres, and the positions with high mutual information are showed in green. The black spheres represent the subset of the residues for a chain of the complex, that are positioned at less than $5$\AA\xspace from the RNA. The other spheres belong to other molecules, each being color-coded to indicate its chain. Interestingly, we notice that, although many different chains are close to the RNA, and the position with high mutual information are far from the mutation,
In Fig.~\ref{fig:5s_3d} we visualize one prediction from our method, for the 5s chain of \texttt{3OFC}. The disrupting mutation (red) is found in the top right corner behind the black spheres, and the positions with high mutual information are showed in green. The black spheres represent the subset of the residues for a chain of the complex, that are positioned at less than \SI{5}{\angstrom} from the RNA. The other spheres belong to other molecules, each being color-coded to indicate its chain. Interestingly, we notice that, although many different chains are close to the RNA, and the position with high mutual information are far from the mutation,
there is chain A (in black) close to the mutation and interacting with chain Z (purple) which binds with the mutation. Chain A builds a bridge up to chains O (beige) and F (yellow), themselves interacting with the compensatory mutations. We believe this example suggests the existence of mechanisms
similar to compensatory mutations, but at the level of the quaternary structure.
......@@ -548,7 +548,7 @@ by compensating the effect of a disruptive mutation.
\begin{figure}[ht!]
\centering
\includegraphics[width=0.47\textwidth]{Figure7.png}
\caption{{\bf Predicted positions and interacting chains of the 5S rRNA \texttt{3OFC} structure.} In red on the top right behind purple spheres is the disrupting mutation, in green the predicted position with high mutual information. The spheres around the RNA represent the subset of nucleotides at most at $5$\AA\xspace from the rRNA, from other chains in the complex. The other spheres belong to other molecules. Each sphere is color-coded to indicate its chain as follows. Chain A is black, Z purple, W pink, V light blue, O beige, F yellow and M orange.}
\caption{{\bf Predicted positions and interacting chains of the 5S rRNA \texttt{3OFC} structure.} In red on the top right behind purple spheres is the disrupting mutation, in green the predicted position with high mutual information. The spheres around the RNA represent the subset of nucleotides at most at \SI{5}{\angstrom} from the rRNA, from other chains in the complex. The other spheres belong to other molecules. Each sphere is color-coded to indicate its chain as follows. Chain A is black, Z purple, W pink, V light blue, O beige, F yellow and M orange.}
\label{fig:5s_3d}
\end{figure}
......
......@@ -148,24 +148,17 @@ Given the mutation ranked by structural disruption by \shape experiments and \re
intersection between the elements in those set over their respective percentile. In Fig.~\ref{fig:percentile} we show on the $y$ axis the percentiles and on the $x$ the ratio of those sizes over the maximal number possible.
\begin{figure}[ht!]
\centering
\begin{subfigure}[b]{0.45\textwidth}
\includegraphics[width=\textwidth]{FigureS4a}
\caption{5S RRNA}
\end{subfigure}
\begin{subfigure}[b]{0.45\textwidth}
\includegraphics[width=\textwidth]{FigureS4b}
\caption{c-di-GMP}
\end{subfigure}
\includegraphics[width=0.96\textwidth]{FigureS4}
\caption{Fraction in intersection for \shape and \remu over different percentile cutoffs}
\label{fig:percentile}
\end{figure}
\end{figure}
We then evaluated the AUCs using for every cutoff percentile $\delta$ the mutations such that their \shape experiments and \remu disruption are over that percentile. Those results are presented in Fig.~\ref{fig:remushape}.
\begin{figure}[ht!]
\centering
\includegraphics[width=0.49\textwidth]{FigureS5}
\includegraphics[width=0.96\textwidth]{FigureS5}
\caption{For a given $\delta$, select the disruptive mutation at the intersection between \shape experiments and \remu}
\label{fig:remushape}
\end{figure}
......@@ -233,6 +226,17 @@ We show in Fig.~\ref{fig:adenine_4} the results for the adenine riboswitch when
\label{fig:adenine_4}
\end{figure}
\subsection{tRNA positions extrapolated from PDB \texttt{3J78}}
We show in Fig.~\ref{fig:trna} the results for the tRNA when binding interfaces are extrapolated form PDB \texttt{3J78}.
\begin{figure}[ht!]
\centering
\includegraphics[width=\textwidth]{FigureS10}
\caption{AUC results for the tRNA when the binding interfaces are extrapolated form PDB \texttt{3J78}}
\label{fig:trna}
\end{figure}
\section{Dataset binding positions}
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment