BOL: Related items

A guide to machine learning for biologists

Abhi — Tue, 28 Dec 2021 01:43:25 -0600

Because of the increasing size and inherent complexity of biological data, there has been an increase in the application of machine learning in biology to create useful and predictive models of the underlying biological processes. All machine learning techniques fit models to data; nevertheless, the specific methods are highly variable and can appear baffling at first glance. In this Review, we hope to give readers a moderate introduction to a few fundamental machine learning techniques, including the most recently created and frequently used deep neural network techniques. We illustrate how different algorithms may be adapted to specific types of biological data, as well as some best practises and points to consider when embarking on machine learning studies. There is also discussion of several upcoming directions in machine learning methodology.

Address of the bookmark: https://www.nature.com/articles/s41580-021-00407-0

Machine Learning for Genomics

Jit — Thu, 09 Sep 2021 11:26:32 -0500

Module 1: Statistics for genomics (2-8 August 2021)

A simple intro to statistical distributions
hypothesis testing
linear models.

reading: http://compgenomr.github.io/book/stats.html

slides: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week1/compgen2021_stats.pdf

exercises+code: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week1/

Module 2: Unsupervised learning for genomics (9-15 August 2021)

Understanding basic intuition behind machine learning approaches.
Using unsupervised learning to cluster and visualise data points
Dimension reduction techniques for visualisation and as input to clustering methods

reading: http://compgenomr.github.io/book/unsupervisedLearning.html

slides: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week2/compgen2021_unsupervisedLearning.pdf

exercises+code: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week2/

Module 3: Supervised learning for genomics (16-22 August 2021)

Understanding and using supervised learning methods for predictive purposes
How to measure prediction performance
Understand and use cross-validation and related concepts

reading: http://compgenomr.github.io/book/supervisedLearning.html

slides: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week3/compgen2021_supervisedLearning.pdf

exercises+code: https://github.com/BIMSBbioinfo/compgen2021/tree/main/week3/

https://github.com/BIMSBbioinfo/compgen2021

Address of the bookmark: https://github.com/BIMSBbioinfo/compgen2021

Machine learning training and courses in bioinformatics !

Rahul Nayak — Tue, 31 Dec 2019 19:33:07 -0600

Machine learning techniques have been successful in analyzing biological data because of their capabilities in handling randomness and uncertainty of data noise and in generalization. In this class, we will learn basics about probabilistic models and machine learning techniques. We will focus on probabilistic models (Markov models, Hidden Markov models, and Bayesian networks) for biological sequence analysis and systems biology. Other machine learning techniques, such as Naive bayes, neural networks and SVMs will only be covered briefly.

More at http://homes.sice.indiana.edu/yye/lab/teaching/spring2017-I529/

CrowdGO: Machine learning and semantic similarity guided consensus Gene Ontology annotation

Shruti Paniwala — Thu, 26 May 2022 00:59:49 -0500

CrowdGO is a protein Gene Ontology predictor using a meta approach, analyzing the predictions of other tools in order to get an improved precision and recall.

Please note that the CrowdGO snakemake workflow is currently only tested on Ubuntu. It should work on OSX, but please report any errors to maarten.reijnders@unil.ch or create an issue.

https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010075

Address of the bookmark: https://gitlab.com/mreijnders/crowdgo

modelStudio: a package automates the explanation of machine learning predictive models

Jit — Wed, 22 Jan 2020 23:58:11 -0600

The modelStudio package automates the explanation of machine learning predictive models. This package generates advanced interactive and animated model explanations in the form of a serverless HTML site.

It combines R with D3.js to produce plots and descriptions for various local and global explanations. Tools for model exploration unite with tools for EDA (Exploratory Data Analysis) to give a broad overview of the model behavior. modelStudio is a fast and condensed way to get all the answers without much effort. Break down your model and look into its ingredients with only a few lines of code.

Address of the bookmark: https://modeloriented.github.io/modelStudio/index.html

Bioinfo Lab

Fri, 04 Mar 2022 00:17:00 -0600

The Institute of Bioinformatics conducts internationally renowned research and provides profound education in bioinformatics. Its research focuses on development and application of machine learning and statistical methods in biology and medicine.

Contact:
Computer Science Building (Science Park 3)
Altenberger Str. 69, A-4040 Linz, Austria
Tel. +43 732 2468 4520 / Fax +43 732 2468 4539
E-mail secretary@bioinf.jku.at

http://www.bioinf.jku.at/

New Machine Learning Packages in R

Rahul Nayak — Fri, 27 Mar 2020 12:11:21 -0500

Machine Learning

autokeras v1.0.1: Implements an interface to AutoKeras, an open source software library for automated machine learning. See README for an example.

MTPS v0.1.9: Implements functions to predict simultaneous multiple outcomes based on revised stacking algorithms as described in Xing et al. (2019). See the vignette to get started.

quanteda.textmodels v0.9.1: Implements methods for scaling models and classifiers based on sparse matrix objects representing textual data. It includes implementations of the Laver et al. (2003) wordscores model, the Perry & Benoit’s (2017) class affinity scaling model, and the Slapin & Proksch (2008) wordfish model. See the vignette to get started.

SeqDetect v1.0.7: Implements the automaton model found in Krleža, Vrdoljak & Brčić (2019) to detect and process sequences. See the vignette for examples and theory.

studyStrap v1.0.0: Implements multi-Study Learning algorithms such as Merging, Study-Specific Ensembling (Trained-on-Observed-Studies Ensemble), the Study Strap, and the Covariate-Matched Study Strap. and offers over 20 similarity measures. See Kishida, et al. (2019) for background and the vignette for how to use the package.

Machine learning in Perl

Jit — Sun, 16 Feb 2020 15:32:03 -0600

this is a fourth blog post in the Machine learning in Perl series, focusing on the AI::MXNet, a Perl interface to Apache MXNet, a modern and powerful machine learning library.

If you're interested in refreshing your memory or just new to the series, please check previous entries over here: 1 2 3

https://metacpan.org/pod/AI::MXNet

Address of the bookmark: http://blogs.perl.org/users/sergey_kolychev/2018/07/machine-learning-in-perl-kyuubi-goes-to-a-modelzoo-during-the-starry-night.html

One page R survival guide !!

Rahul Nayak — Thu, 28 May 2015 21:10:12 -0500

There any many of the documents have been developed and tested by scientist around the world. I found this one really useful. The data used is available for download as data.zip.

Reference@http://www.datasciencecentral.com/profiles/blogs/one-page-r-a-survival-guide-to-data-science-with-r

Templates for the Data Scientist
1. A Template for Preparing Data: *OnePageR - *R
2. A Template for Building Models: *OnePageR - *R
Getting Started as a Data Scientist
1. Getting Started with R and Rattle: *Lecture - *Laboratory
2. Introducing and Interacting with R: *Lecture - *Laboratory
3. BasicR - OnePage(R) - Writing R scripts
Dealing With Data
1. Read Data into R: *OnePageR - *R
2. Explore and Summarise Data: *OnePageR - *R
3. Transform Data: *OnePageR - *R
4. Dealing with Dates and Time: (PDF, R) Dates and Time
5. Visualising Data with GGPlot2: *OnePageR - *R
6. Visualising Data with Maps *OnePageR - *R
7. Spatial (R) Spatial Analysis
8. Handling Big Data *OnePageR - *R
Descriptive Analytics
1. Cluster Analysis: *Lecture - *OnePageR - *R
2. Association Analysis: *Lecture
Predictive Analytics
1. Decision Trees: *Lecture - *OnePageR - *R - *Rattle
2. Ensembles of Decision Trees: *Lecture - *OnePageR - *R
3. SVM (R)
4. KernLab (R)
5. NeuralNetworks (R)
6. NNet (R)
Model Delivery
1. Evaluating Models: *OnePageR - *R
2. Evaluation (R)
3. Scoring (R)
4. PMML (R) Exporting Models for Deployment
Advanced Topics
1. Text Mining: *OnePageR - *R
Advanced R Topics
1. Plots (PDF, R) Miscellaneous Plots
2. Functions (PDF, R) Writing Functions in R
3. Parallel (PDF, R) Parallel Execution
4. Packaging (R) Pulling it Together into a Package
5. Doing R with Style: *OnePageR - *R
6. Literate Data Mining with KnitR: *Lecture - *OnePageR - *

BioToolbox

Jit — Fri, 19 Feb 2016 09:14:44 -0600

This is a collection of libraries and high-quality end-user scripts for bioinformatic analysis, including working with gene annotation, collecting data scores from a variety of modern file formats, and conversion between file formats. The Bio::ToolBox libraries provide a unified, abstracted interface to multiple common gene annotation formats and the collection of data from multiple data files. They rely on BioPerl SeqFeature libraries and related adaptors to access binary file formats including Bam, BigWig, BigBed, and USeq. The Bio::ToolBox package includes scripts for setting up databases of annotation, collecting annotated features, collecting genomic data relative to features, manipulating and analyzing data, and data format conversion.

More at http://cpansearch.perl.org/src/TJPARNELL/

Address of the bookmark: http://cpansearch.perl.org/src/TJPARNELL/