Macs in Chemistry

Insanely Great Science

RRegrs: an R package for computer-aided model selection with multiple regression models


I just thought I'd flag a paper in Journal of Cheminformatics, RRegrs: an R package for computer-aided model selection with multiple regression models DOI.

We propose an integrated framework for creating multiple regression models, called RRegrs. The tool offers the option of ten simple and complex regression methods combined with repeated 10-fold and leave-one-out cross-validation. Methods include Multiple Linear regression, Generalized Linear Model with Stepwise Feature Selection, Partial Least Squares regression, Lasso regression, and Support Vector Machines Recursive Feature Elimination. The new framework is an automated fully validated procedure which produces standardized reports to quickly oversee the impact of choices in modelling algorithms and assess the model and cross-validation results. The methodology was implemented as an open source R package, available at, by reusing and extending on the caret package.


Wolfram Alpha has been updated


Wolfram Alpha has been updated.

Wolfram|Alpha. Building on 25 years of development led by Stephen Wolfram, Wolfram|Alpha has rapidly become the world's definitive source for instant expert knowledge and computation.


Wizard Pro updated


Wizard Pro has been updated.

What's New in Version 1.7.18 New in 1.7.18:

  • Added support for Numbers 3.6 files
  • Exporting data from the Summary view now has a progress bar and cancel button
  • Exporting data now writes directly to disk instead of building the file in memory first
  • Many other performance improvements throughout the program
  • Added support for generating the R command for the Friedman test
  • Added support for generating SAS/SPSS commands for repeated-measures tests
  • Report the combined significance of constant coefficients for models with multiple sets of coefficients
  • Fix a crash after exporting ROC curves
  • Fix a bug when exporting DTA files with missing values
  • Fix a bug where formatting options weren't showing in the Pivot view
  • Fix a number of minor interface glitches
  • Improved support for importing SAS and SPSS command files
  • Improved support for SAS catalog files

There is a review of Wizard Pro here, and a listing of data analysis tools for Mac OSX here.


Flagging potential aggregators in Vortex


Promiscuous inhibition caused by small molecule aggregation is a major source of false positive results in high-throughput screening. A recent particularly valuable publication, Irwin, Duan, Torosyan, Doak, Ziebart, Sterling, Tumanian and Shoichet, J Med Chem, 2015, 58(1 7), 7076-7087 DOI, has collated over 12,000 organic molecules known to act as aggregators at concentrations used in screening campaigns, and provides a resource Aggregation Advisor that can be used to try and predict possible false positives. However in many instances it would be unwise to submit proprietary information to the public web service. Potential aggregators are flagged based on calculated LogP >3 and/or similarity >0.85 to a known aggregator (using path based fingerprint) this script calculates xLogP using the algorithm provided by Dotmatics and then uses OpenBabel fast search to calculate the closest similarity to a known aggregator.

Full details of the Vortex script are here.



Findings Updated


Findings is an electronic notebook for scientists.

The main new features are:

  • Much improved export, with options to export multiple experiments based on projects and dates, and many more options for PDF output (and print).
  • A brand new archive format to export and import experiments and protocols, which makes it very easy to share documents and collaborate on their content. One subtle but powerful feature is that re-importing an experiment or protocol will not create a duplicate, but will instead merge the latest changes. This means collaborators can keep sending new versions of a document to each other, and it will magically update their library.
  • Full-text search across all experiments (or protocols).
  • Search within a document, with proper highlighting and keyboard-based navigation through the search matches.
  • Much nicer experiment cards, in particular using a vignette thumbnail, showing a project color, and with the calendar strip functioning as a progress bar for multi-day experiments.
  • In addition to the free Basic version, new unregistered users are now also offered a 30-day trial of the Pro version;for 30 days, the 20-day experiment limit is thus lifted.

There are also tons of improvements and bug fixes.

Collaboration also got better, you can also export experiments as archives, that anybody can read with the free Basic version of Findings.

There has also been some changes to the pricing structure, the basic individual version is free but there are discounts for group (5) purchases, and it sounds like if you have a bigger group it would be worth contacting them directly because larger discounts are available.