PMID- 24959206
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20140624
LR  - 20211021
IS  - 1758-2946 (Print)
IS  - 1758-2946 (Electronic)
IS  - 1758-2946 (Linking)
VI  - 6
DP  - 2014
TI  - Self organising hypothesis networks: a new approach for representing and 
      structuring SAR knowledge.
PG  - 21
LID - 10.1186/1758-2946-6-21 [doi]
AB  - BACKGROUND: Combining different sources of knowledge to build improved structure 
      activity relationship models is not easy owing to the variety of knowledge 
      formats and the absence of a common framework to interoperate between learning 
      techniques. Most of the current approaches address this problem by using 
      consensus models that operate at the prediction level. We explore the possibility 
      to directly combine these sources at the knowledge level, with the aim to harvest 
      potentially increased synergy at an earlier stage. Our goal is to design a 
      general methodology to facilitate knowledge discovery and produce accurate and 
      interpretable models. RESULTS: To combine models at the knowledge level, we 
      propose to decouple the learning phase from the knowledge application phase using 
      a pivot representation (lingua franca) based on the concept of hypothesis. A 
      hypothesis is a simple and interpretable knowledge unit. Regardless of its 
      origin, knowledge is broken down into a collection of hypotheses. These 
      hypotheses are subsequently organised into hierarchical network. This unification 
      permits to combine different sources of knowledge into a common formalised 
      framework. The approach allows us to create a synergistic system between 
      different forms of knowledge and new algorithms can be applied to leverage this 
      unified model. This first article focuses on the general principle of the Self 
      Organising Hypothesis Network (SOHN) approach in the context of binary 
      classification problems along with an illustrative application to the prediction 
      of mutagenicity. CONCLUSION: It is possible to represent knowledge in the unified 
      form of a hypothesis network allowing interpretable predictions with performances 
      comparable to mainstream machine learning techniques. This new approach offers 
      the potential to combine knowledge from different sources into a common framework 
      in which high level reasoning and meta-learning can be applied; these latter 
      perspectives will be explored in future work.
FAU - Hanser, Thierry
AU  - Hanser T
AD  - Lhasa Limited, Leeds, UK.
FAU - Barber, Chris
AU  - Barber C
AD  - Lhasa Limited, Leeds, UK.
FAU - Rosser, Edward
AU  - Rosser E
AD  - Lhasa Limited, Leeds, UK.
FAU - Vessey, Jonathan D
AU  - Vessey JD
AD  - Lhasa Limited, Leeds, UK.
FAU - Webb, Samuel J
AU  - Webb SJ
AD  - Lhasa Limited, Leeds, UK.
FAU - Werner, Stephane
AU  - Werner S
AD  - Lhasa Limited, Leeds, UK.
LA  - eng
PT  - Journal Article
DEP - 20140508
PL  - England
TA  - J Cheminform
JT  - Journal of cheminformatics
JID - 101516718
PMC - PMC4048587
OTO - NOTNLM
OT  - Confidence metric
OT  - Data mining
OT  - Hypothesis Network
OT  - Interpretable model
OT  - Knowledge discovery
OT  - Machine learning
OT  - QSAR
OT  - SAR
OT  - SOHN
EDAT- 2014/06/25 06:00
MHDA- 2014/06/25 06:01
PMCR- 2014/05/08
CRDT- 2014/06/25 06:00
PHST- 2013/11/29 00:00 [received]
PHST- 2014/03/28 00:00 [accepted]
PHST- 2014/06/25 06:00 [entrez]
PHST- 2014/06/25 06:00 [pubmed]
PHST- 2014/06/25 06:01 [medline]
PHST- 2014/05/08 00:00 [pmc-release]
AID - 1758-2946-6-21 [pii]
AID - 10.1186/1758-2946-6-21 [doi]
PST - epublish
SO  - J Cheminform. 2014 May 8;6:21. doi: 10.1186/1758-2946-6-21. eCollection 2014.