mikropml: User-Friendly R Package for Supervised Machine Learning Pipelines

ABSTRACTBiological processes are inherently continuous, and the chance of phenotypic discovery is significantly restricted by discretising them. Using multi-parametric active regression we introduce a novel concept to describe and explore biological data in a continuous manner. We have implemented Regression Plane (RP), the first user-friendly discovery tool enabling class-free phenotypic supervised machine learning.

Download Full-text

Umpire 2.0: Simulating realistic, mixed-type, clinical data for machine learning

F1000Research ◽

10.12688/f1000research.25877.1 ◽

2020 ◽

Vol 9 ◽

pp. 1186

Author(s):

Caitlin E. Coombes ◽

Zachary B. Abrams ◽

Samantha Nakayiza ◽

Guy Brock ◽

Kevin R. Coombes

Keyword(s):

Machine Learning ◽

Clinical Data ◽

Mixed Type ◽

R Package ◽

Fine Tuning ◽

Supervised Machine Learning ◽

Mixed Data ◽

Operating Characteristics ◽

Data Types ◽

Type Data

The Umpire 2.0 R-package offers a streamlined, user-friendly workflow to simulate complex, heterogeneous, mixed-type data with known subgroup identities, dichotomous outcomes, and time-to-event data, while providing ample opportunities for fine-tuning and flexibility. Here, we describe how we have expanded the core Umpire 1.0 R-package, developed to simulate gene expression data, to generate clinically realistic, mixed-type data for use in evaluating unsupervised and supervised machine learning (ML) methods. As the availability of large-scale clinical data for ML has increased, clinical data has posed unique challenges, including widely variable size, individual biological heterogeneity, data collection and measurement noise, and mixed data types. Developing and validating ML methods for clinical data requires data sets with known ground truth, generated from simulation. Umpire 2.0 addresses challenges to simulating realistic clinical data by providing the user a series of modules to generate survival parameters and subgroups, apply meaningful additive noise, and discretize to single or mixed data types. Umpire 2.0 provides broad functionality across sample sizes, feature spaces, and data types, allowing the user to simulate correlated, heterogeneous, binary, continuous, categorical, or mixed type data from the scale of a small clinical trial to data on thousands of patients drawn from electronic health records. The user may generate elaborate simulations by varying parameters in order to compare algorithms or interrogate operating characteristics of an algorithm in both supervised and unsupervised ML.

Download Full-text

PipeMaster: inferring population divergence and demographic history with approximate Bayesian computation and supervised machine-learning in R

10.1101/2020.12.04.410670 ◽

2020 ◽

Author(s):

Marcelo Gehara ◽

Guilherme G. Mazzochinni ◽

Frank Burbrink

Keyword(s):

Machine Learning ◽

Approximate Bayesian Computation ◽

Demographic History ◽

Divergence Time ◽

R Package ◽

Supervised Machine Learning ◽

Population Divergence ◽

Bayesian Computation ◽

Approximate Bayesian ◽

Recent Bottleneck

AbstractUnderstanding population divergence involves testing diversification scenarios and estimating historical parameters, such as divergence time, population size and migration rate. There is, however, an immense space of possible highly parameterized scenarios that are difsficult or impossible to solve analytically. To overcome this problem researchers have used alternative simulation-based approaches, such as approximate Bayesian computation (ABC) and supervised machine learning (SML), to approximate posterior probabilities of hypotheses. In this study we demonstrate the utility of our newly developed R-package to simulate summary statistics to perform ABC and SML inferences. We compare the power of both ABC and SML methods and the influence of the number of loci in the accuracy of inferences; and we show three empirical examples: (i) the Muller’s termite frog genomic data from Southamerica; (ii) the cottonmouth and (iii) and the copperhead snakes sanger data from Northamerica. We found that SML is more efficient than ABC. It is generally more accurate and needs fewer simulations to perform an inference. We found support for a divergence model without migration, with a recent bottleneck for one of the populations of the southamerican frog. For the cottonmouth we found support for divergence with migration and recent expansion and for the copperhead we found support for a model of divergence with migration and recent bottleneck. Interestingly, by using an SML method it was possible to achieve high accuracy in model selection even when several models were compared in a single inference. We also found a higher accuracy when inferring parameters with SML.

Download Full-text

ELeFHAnt: A supervised machine learning approach for label harmonization and annotation of single cell RNA-seq data

10.1101/2021.09.07.459342 ◽

2021 ◽

Author(s):

Konrad Thorner ◽

Aaron M. Zorn ◽

Praneet Chaturvedi

Keyword(s):

Machine Learning ◽

Single Cell ◽

Single Cell Analysis ◽

Single Cells ◽

A Priori ◽

Cell Types ◽

R Package ◽

Supervised Machine Learning ◽

Support Vector ◽

Rna Seq

AbstractAnnotation of single cells has become an important step in the single cell analysis framework. With advances in sequencing technology thousands to millions of cells can be processed to understand the intricacies of the biological system in question. Annotation through manual curation of markers based on a priori knowledge is cumbersome given this exponential growth. There are currently ~200 computational tools available to help researchers automatically annotate single cells using supervised/unsupervised machine learning, cell type markers, or tissue-based markers from bulk RNA-seq. But with the expansion of publicly available data there is also a need for a tool which can help integrate multiple references into a unified atlas and understand how annotations between datasets compare. Here we present ELeFHAnt: Ensemble learning for harmonization and annotation of single cells. ELeFHAnt is an easy-to-use R package that employs support vector machine and random forest algorithms together to perform three main functions: 1) CelltypeAnnotation 2) LabelHarmonization 3) DeduceRelationship. CelltypeAnnotation is a function to annotate cells in a query Seurat object using a reference Seurat object with annotated cell types. LabelHarmonization can be utilized to integrate multiple cell atlases (references) into a unified cellular atlas with harmonized cell types. Finally, DeduceRelationship is a function that compares cell types between two scRNA-seq datasets. ELeFHAnt can be accessed from GitHub at https://github.com/praneet1988/ELeFHAnt.

Download Full-text

Umpire 2.0: Simulating realistic, mixed-type, clinical data for machine learning

F1000Research ◽

10.12688/f1000research.25877.2 ◽

2021 ◽

Vol 9 ◽

pp. 1186

Author(s):

Caitlin E. Coombes ◽

Zachary B. Abrams ◽

Samantha Nakayiza ◽

Guy Brock ◽

Kevin R. Coombes

Keyword(s):

Machine Learning ◽

Clinical Data ◽

Mixed Type ◽

R Package ◽

Fine Tuning ◽

Supervised Machine Learning ◽

Mixed Data ◽

Operating Characteristics ◽

Data Types ◽

Type Data

The Umpire 2.0 R-package offers a streamlined, user-friendly workflow to simulate complex, heterogeneous, mixed-type data with known subgroup identities, dichotomous outcomes, and time-to-event data, while providing ample opportunities for fine-tuning and flexibility. Here, we describe how we have expanded the core Umpire 1.0 R-package, developed to simulate gene expression data, to generate clinically realistic, mixed-type data for use in evaluating unsupervised and supervised machine learning (ML) methods. As the availability of large-scale clinical data for ML has increased, clinical data has posed unique challenges, including widely variable size, individual biological heterogeneity, data collection and measurement noise, and mixed data types. Developing and validating ML methods for clinical data requires data sets with known ground truth, generated from simulation. Umpire 2.0 addresses challenges to simulating realistic clinical data by providing the user a series of modules to generate survival parameters and subgroups, apply meaningful additive noise, and discretize to single or mixed data types. Umpire 2.0 provides broad functionality across sample sizes, feature spaces, and data types, allowing the user to simulate correlated, heterogeneous, binary, continuous, categorical, or mixed type data from the scale of a small clinical trial to data on thousands of patients drawn from electronic health records. The user may generate elaborate simulations by varying parameters in order to compare algorithms or interrogate operating characteristics of an algorithm in both supervised and unsupervised ML.

Download Full-text

Exploring the Use of Machine Learning to Automate the Qualitative Coding of Church-related Tweets

Fieldwork in Religion ◽

10.1558/firn.40610 ◽

2020 ◽

Vol 14 (2) ◽

pp. 140-159

Author(s):

Anthony-Paul Cooper ◽

Emmanuel Awuni Kolog ◽

Erkki Sutinen

Keyword(s):

Machine Learning ◽

Online Community ◽

High Volume ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Social Media Data ◽

Twitter Data ◽

Resource Intensity ◽

Media Data ◽

Better Than

This article builds on previous research around the exploration of the content of church-related tweets. It does so by exploring whether the qualitative thematic coding of such tweets can, in part, be automated by the use of machine learning. It compares three supervised machine learning algorithms to understand how useful each algorithm is at a classification task, based on a dataset of human-coded church-related tweets. The study finds that one such algorithm, Naïve-Bayes, performs better than the other algorithms considered, returning Precision, Recall and F-measure values which each exceed an acceptable threshold of 70%. This has far-reaching consequences at a time where the high volume of social media data, in this case, Twitter data, means that the resource-intensity of manual coding approaches can act as a barrier to understanding how the online community interacts with, and talks about, church. The findings presented in this article offer a way forward for scholars of digital theology to better understand the content of online church discourse.

Download Full-text

Application of Supervised Machine Learning Algorithms for Lithofacies Classification.

10.2523/19349-ms ◽

2019 ◽

Author(s):

Subhadeep Sarkar ◽

Chandan Majumdar

Keyword(s):

Machine Learning ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Lithofacies Classification

Download Full-text

Mol2vec: Unsupervised Machine Learning Approach with Chemical Intuition

10.26434/chemrxiv.5513581.v1 ◽

2017 ◽

Author(s):

Sabrina Jaeger ◽

Simone Fulle ◽

Samo Turk

Keyword(s):

Machine Learning ◽

Language Processing ◽

Supervised Machine Learning ◽

Learning Approach ◽

Learning Approaches ◽

Unsupervised Machine Learning ◽

Feature Representations ◽

Machine Learning Approach ◽

The Individual ◽

Vector Representations

Inspired by natural language processing techniques we here introduce Mol2vec which is an unsupervised machine learning approach to learn vector representations of molecular substructures. Similarly, to the Word2vec models where vectors of closely related words are in close proximity in the vector space, Mol2vec learns vector representations of molecular substructures that are pointing in similar directions for chemically related substructures. Compounds can finally be encoded as vectors by summing up vectors of the individual substructures and, for instance, feed into supervised machine learning approaches to predict compound properties. The underlying substructure vector embeddings are obtained by training an unsupervised machine learning approach on a so-called corpus of compounds that consists of all available chemical matter. The resulting Mol2vec model is pre-trained once, yields dense vector representations and overcomes drawbacks of common compound feature representations such as sparseness and bit collisions. The prediction capabilities are demonstrated on several compound property and bioactivity data sets and compared with results obtained for Morgan fingerprints as reference compound representation. Mol2vec can be easily combined with ProtVec, which employs the same Word2vec concept on protein sequences, resulting in a proteochemometric approach that is alignment independent and can be thus also easily used for proteins with low sequence similarities.

Download Full-text