There is a newer version of this record available.

Software Open Access

ljvmiranda921/gym-lattice: Major Release (v0.1.0)

Lester James Validad Miranda


DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="DOI">10.5281/zenodo.1218143</identifier>
  <creators>
    <creator>
      <creatorName>Lester James Validad Miranda</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-7872-6464</nameIdentifier>
      <affiliation>Waseda University</affiliation>
    </creator>
  </creators>
  <titles>
    <title>ljvmiranda921/gym-lattice: Major Release (v0.1.0)</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2018</publicationYear>
  <subjects>
    <subject>reinforcement learning</subject>
    <subject>protein folding problem</subject>
    <subject>open source software</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2018-04-14</date>
  </dates>
  <resourceType resourceTypeGeneral="Software"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/1218143</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsSupplementTo">https://github.com/ljvmiranda921/gym-lattice/tree/v0.1.0</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.1214967</relatedIdentifier>
  </relatedIdentifiers>
  <version>v0.1.0</version>
  <rightsList>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;Major Release (v0.1.0)&lt;/p&gt;

&lt;p&gt;Gym-lattice is an HP 2D Lattice Environment with a Gym-like API for the protein folding problem.&lt;/p&gt;

&lt;p&gt;This is a Python library that formulates Lau and Dill&amp;#39;s (1989) hydrophobic-polar two-dimensional lattice model as a reinforcement learning problem. It follows OpenAI Gym&amp;#39;s API, easing integration for reinforcement learning solutions.&lt;/p&gt;

&lt;p&gt;Features&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;OpenAI Integration: uses Gym&amp;#39;s API to ease compatibility to reinforcement learning solutions.&lt;/li&gt;
	&lt;li&gt;Lattice 2D Environment: implements Dill and Lau&amp;#39;s two-dimensional lattice as an RL problem.&lt;/li&gt;
	&lt;li&gt;Command-line rendering environment: the method &lt;code&gt;render()&lt;/code&gt; draws the chain on the command-line.&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;Additionally, there is an option to set the penalty parameters for training the agent, this includes:&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;Collision penalty (&lt;code&gt;collision_penalty&lt;/code&gt;): accounts for the time whenever the agent decides to assign a molecule to an already-occupied space; and&lt;/li&gt;
	&lt;li&gt;Trap penalty (&lt;code&gt;trap_penalty&lt;/code&gt;): induces heavy deductions whenever the agent traps itself and cannot accomplish the task anymore.&lt;/li&gt;
&lt;/ul&gt;

&lt;p&gt;Tests&lt;/p&gt;

&lt;ul&gt;
	&lt;li&gt;Error-handling: all public-facing methods now use &lt;code&gt;Exceptions&lt;/code&gt; instead of &lt;code&gt;asserts&lt;/code&gt; when catching errors.&lt;/li&gt;
	&lt;li&gt;Testing with pytest and tox: unit-testing is being done with &lt;code&gt;pytest&lt;/code&gt; and &lt;code&gt;tox&lt;/code&gt;.&lt;/li&gt;
&lt;/ul&gt;</description>
    <description descriptionType="Other">{"references": ["Lau, K.F. and Dill, K.A., 1989. A lattice statistical mechanics model of the conformational and sequence spaces of proteins. Macromolecules, 22(10), pp.3986-3997."]}</description>
  </descriptions>
</resource>
78
1
views
downloads
All versions This version
Views 788
Downloads 10
Data volume 102.2 kB0 Bytes
Unique views 708
Unique downloads 10

Share

Cite as