\documentclass[10pt,a4paper]{article} % Packages \usepackage{fancyhdr} % For header and footer \usepackage{multicol} % Allows multicols in tables \usepackage{tabularx} % Intelligent column widths \usepackage{tabulary} % Used in header and footer \usepackage{hhline} % Border under tables \usepackage{graphicx} % For images \usepackage{xcolor} % For hex colours %\usepackage[utf8x]{inputenc} % For unicode character support \usepackage[T1]{fontenc} % Without this we get weird character replacements \usepackage{colortbl} % For coloured tables \usepackage{setspace} % For line height \usepackage{lastpage} % Needed for total page number \usepackage{seqsplit} % Splits long words. %\usepackage{opensans} % Can't make this work so far. Shame. Would be lovely. \usepackage[normalem]{ulem} % For underlining links % Most of the following are not required for the majority % of cheat sheets but are needed for some symbol support. \usepackage{amsmath} % Symbols \usepackage{MnSymbol} % Symbols \usepackage{wasysym} % Symbols %\usepackage[english,german,french,spanish,italian]{babel} % Languages % Document Info \author{Nimisha (lemonbuzz)} \pdfinfo{ /Title (data-analysis-in-genomics-and-transdriptomics.pdf) /Creator (Cheatography) /Author (Nimisha (lemonbuzz)) /Subject (Data Analysis in Genomics and Transdriptomics Cheat Sheet) } % Lengths and widths \addtolength{\textwidth}{6cm} \addtolength{\textheight}{-1cm} \addtolength{\hoffset}{-3cm} \addtolength{\voffset}{-2cm} \setlength{\tabcolsep}{0.2cm} % Space between columns \setlength{\headsep}{-12pt} % Reduce space between header and content \setlength{\headheight}{85pt} % If less, LaTeX automatically increases it \renewcommand{\footrulewidth}{0pt} % Remove footer line \renewcommand{\headrulewidth}{0pt} % Remove header line \renewcommand{\seqinsert}{\ifmmode\allowbreak\else\-\fi} % Hyphens in seqsplit % This two commands together give roughly % the right line height in the tables \renewcommand{\arraystretch}{1.3} \onehalfspacing % Commands \newcommand{\SetRowColor}[1]{\noalign{\gdef\RowColorName{#1}}\rowcolor{\RowColorName}} % Shortcut for row colour \newcommand{\mymulticolumn}[3]{\multicolumn{#1}{>{\columncolor{\RowColorName}}#2}{#3}} % For coloured multi-cols \newcolumntype{x}[1]{>{\raggedright}p{#1}} % New column types for ragged-right paragraph columns \newcommand{\tn}{\tabularnewline} % Required as custom column type in use % Font and Colours \definecolor{HeadBackground}{HTML}{333333} \definecolor{FootBackground}{HTML}{666666} \definecolor{TextColor}{HTML}{333333} \definecolor{DarkBackground}{HTML}{6B248A} \definecolor{LightBackground}{HTML}{F5F1F7} \renewcommand{\familydefault}{\sfdefault} \color{TextColor} % Header and Footer \pagestyle{fancy} \fancyhead{} % Set header to blank \fancyfoot{} % Set footer to blank \fancyhead[L]{ \noindent \begin{multicols}{3} \begin{tabulary}{5.8cm}{C} \SetRowColor{DarkBackground} \vspace{-7pt} {\parbox{\dimexpr\textwidth-2\fboxsep\relax}{\noindent \hspace*{-6pt}\includegraphics[width=5.8cm]{/web/www.cheatography.com/public/images/cheatography_logo.pdf}} } \end{tabulary} \columnbreak \begin{tabulary}{11cm}{L} \vspace{-2pt}\large{\bf{\textcolor{DarkBackground}{\textrm{Data Analysis in Genomics and Transdriptomics Cheat Sheet}}}} \\ \normalsize{by \textcolor{DarkBackground}{Nimisha (lemonbuzz)} via \textcolor{DarkBackground}{\uline{cheatography.com/132716/cs/40775/}}} \end{tabulary} \end{multicols}} \fancyfoot[L]{ \footnotesize \noindent \begin{multicols}{3} \begin{tabulary}{5.8cm}{LL} \SetRowColor{FootBackground} \mymulticolumn{2}{p{5.377cm}}{\bf\textcolor{white}{Cheatographer}} \\ \vspace{-2pt}Nimisha (lemonbuzz) \\ \uline{cheatography.com/lemonbuzz} \\ \end{tabulary} \vfill \columnbreak \begin{tabulary}{5.8cm}{L} \SetRowColor{FootBackground} \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Cheat Sheet}} \\ \vspace{-2pt}Not Yet Published.\\ Updated 11th October, 2023.\\ Page {\thepage} of \pageref{LastPage}. \end{tabulary} \vfill \columnbreak \begin{tabulary}{5.8cm}{L} \SetRowColor{FootBackground} \mymulticolumn{1}{p{5.377cm}}{\bf\textcolor{white}{Sponsor}} \\ \SetRowColor{white} \vspace{-5pt} %\includegraphics[width=48px,height=48px]{dave.jpeg} Measure your website readability!\\ www.readability-score.com \end{tabulary} \end{multicols}} \begin{document} \raggedright \raggedcolumns % Set font size to small. Switch to any value % from this page to resize cheat sheet text: % www.emerson.emory.edu/services/latex/latex_169.html \footnotesize % Small font. \begin{multicols*}{3} \begin{tabularx}{5.377cm}{p{0.4977 cm} x{4.4793 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Self-Organizing Map (SOM)}} \tn % Row 0 \SetRowColor{LightBackground} & - create a 1D/2D lattice of artificial neurons \{\{nl\}\} - define no of neurons in each dimension \{\{nl\}\} - assign random weights in same dim as input \{\{nl\}\} - select random data point from input \{\{nl\}\} - choose winning neuron based on similarity with input \{\{nl\}\} - update weights of winning and neighboring neurons (based on learning rate \& neighborhood function) \{\{nl\}\} - repeat for all data points until convergence \tn % Row Count 12 (+ 12) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{x{0.89586 cm} x{4.08114 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{Principle Component Analysis (PCA)}} \tn % Row 0 \SetRowColor{LightBackground} \seqsplit{Algorithm} & - obtain distance matrix \{\{nl\}\}- construct matric matrix\{\{nl\}\}- compute eigen values and eigen vectors of matric matrix \{\{nl\}\}- compute cartesian coordinates \tn % Row Count 5 (+ 5) % Row 1 \SetRowColor{white} \mymulticolumn{2}{x{5.377cm}}{PCA focuses on maximizing variance, and compromises resolution of proximal clusters.} \tn % Row Count 7 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{2}{x{5.377cm}}{A distance matrix doesn't reveal the underlying dimensionality of the space in which these points exist.} \tn % Row Count 10 (+ 3) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{x{0.89586 cm} x{4.08114 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{t-distributed Stochastic Neighbor Embedding (tSNE)}} \tn % Row 0 \SetRowColor{LightBackground} \seqsplit{Algorithm} & - {\bf{Similarity score}} for all points against all points are computed. \{\{nl\}\}- The points are then randomly placed on 2- or 3-dimensional space. \{\{nl\}\}- Using an {\bf{optimization}} method, points are moved step by step based on the similarity score until convergence is achieved \tn % Row Count 9 (+ 9) % Row 1 \SetRowColor{white} \mymulticolumn{2}{x{5.377cm}}{Retains resolution for close clusters, while scaling the farther clusters to fit in frame.} \tn % Row Count 11 (+ 2) % Row 2 \SetRowColor{LightBackground} \mymulticolumn{2}{x{5.377cm}}{Used in combination with PCA.} \tn % Row Count 12 (+ 1) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} \begin{tabularx}{5.377cm}{p{0.4977 cm} p{0.4977 cm} } \SetRowColor{DarkBackground} \mymulticolumn{2}{x{5.377cm}}{\bf\textcolor{white}{K-Means Clustering}} \tn % Row 0 \SetRowColor{LightBackground} \mymulticolumn{2}{x{5.377cm}}{- choose no of clusters (k) \{\{nl\}\} - randomly initialise k cluster centroids \{\{nl\}\} - calculate distance between each data point and each centroid (euclidean or manhattan distance) \{\{nl\}\} - assign data point to cluster whose centroid is closest \{\{nl\}\} - recalculate centroid by taking mean of all data points assigned to the cluster \{\{nl\}\} - iterate until stopping criteria met: \{\{nl\}\} 1. max no of iterations reached \{\{nl\}\} 2. centroids no longer change significantly} \tn % Row Count 10 (+ 10) \hhline{>{\arrayrulecolor{DarkBackground}}--} \end{tabularx} \par\addvspace{1.3em} % That's all folks \end{multicols*} \end{document}