Artificial intelligence publications
-
Metabolic Modeling with MetaFlux
The MetaFlux software supports creating, executing, and solving quantitative metabolic flux models using flux balance analysis (FBA).
-
The EcoCyc Database in 2021
This article highlights recent improvements to the curated data in the areas of metabolism, transport, DNA repair, and regulation of gene expression.
-
What, Again? Automatic Deductive Synthesis of the Unification Algorithm
We describe work in progress towards deriving a unification algorithm automatically from a declarative specification using deductive methods.
-
The BioCyc Metabolic Network Explorer
The Metabolic Network Explorer is a new addition to the BioCyc.org website and the Pathway Tools software suite that supports the interactive exploration of metabolic networks.
-
Pathway Size Matters: The Influence of Pathway Granularity on Over-Representation (Enrichment) Statistics
We show that alternative pathway definitions can alter enrichment p -values by up to nine orders of magnitude, whereas statistical corrections typically alter enrichment p -values by only two orders…
-
Leveraging Curation Among Escherichia coli Pathway/Genome Databases Using Ortholog-Based Annotation Propagation
We have developed a method to automatically propagate multiple types of curated knowledge from genes and proteins in one genome database to their orthologs in uncurated databases for related strains,…
-
Prediction of Selected Biosynthetic Pathways for the Lipopolysaccharide Components in Porphyromonas gingivalis
We use bioinformatics tools to predict biosynthetic pathways for the production of the normal (O-type) lipopolysaccharide in the W50 strain Porphyromonas gingivalis and compare the pathway with other putative pathways…
-
Pathway Tools Visualization of Organism-Scale Metabolic Networks
We have developed bioinformatics software tools that automatically generate a full metabolic-network diagram for an organism, and that enable searching and analyses of the network.
-
Transformer Based Molecule Encoding for Property Prediction
We build a Transformer-based molecule encoder and property predictor network with novel input featurization that performs significantly better than existing methods.
-
Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents’ Capabilities and Limitations
We propose an explainable reinforcement learning (XRL) framework that analyzes an agent’s history of interaction with the environment to extract interestingness elements that explain its behavior.
-
Learning Procedures by Augmenting Sequential Pattern Mining with Planning Knowledge
This paper explores the use of filtering heuristics based on action models for automated planning to augment sequence mining techniques.
-
Exact Inference for Relational Graphical Models with Interpreted Functions: Lifted Probabilistic Inference Modulo Theories
In this paper, we expand PIMT to a lifted version that also processes random functions and relations.