PMID- 37585609
OWN - NLM
STAT- MEDLINE
DCOM- 20230829
LR  - 20230829
IS  - 1549-960X (Electronic)
IS  - 1549-9596 (Linking)
VI  - 63
IP  - 16
DP  - 2023 Aug 28
TI  - pBRICS: A Novel Fragmentation Method for Explainable Property Prediction of 
      Drug-Like Small Molecules.
PG  - 5066-5076
LID - 10.1021/acs.jcim.3c00689 [doi]
AB  - Generative artificial intelligence algorithms have shown to be successful in 
      exploring large chemical spaces and designing novel and diverse molecules. There 
      has been considerable interest in developing predictive models using artificial 
      intelligence for drug-like properties, which can potentially reduce the 
      late-stage attrition of drug candidates or predict the properties of novel 
      AI-designed molecules. Concurrently, it is important to understand the 
      contribution of functional groups toward these properties and modify them to 
      obtain property-optimized lead compounds. As a result, there is an increasing 
      interest in the development of explainable property prediction models. However, 
      current explainable approaches are mostly atom-based, where, often, only a 
      fraction of a fragment is shown to be significant. To address the above 
      challenges, we have developed a novel domain-aware molecular fragmentation 
      approach termed post-processing of BRICS (pBRICS), which can fragment small 
      molecules into their functional groups. Multitask models were developed to 
      predict various properties, including the absorption, distribution, metabolism, 
      excretion, and toxicity (ADMET) properties. The fragment importance was explained 
      using the gradient-weighted class activation mapping (Grad-CAM) approach. The 
      method was validated on data sets of experimentally available matched molecular 
      pairs (MMPs). The explanations from the model can be useful for medicinal 
      chemists to identify the fragments responsible for poor drug-like properties and 
      optimize the molecule. The explainability approach was also used to identify the 
      reason behind false positive and false negative MMP predictions. Based on 
      evidence from the existing literature and our analysis, some of these 
      mispredictions were justified. We propose that the quantity, quality, and 
      diversity of the training data will improve the accuracy of property prediction 
      algorithms for novel molecules.
FAU - Vangala, Sarveswara Rao
AU  - Vangala SR
AD  - TCS Research (Life Sciences Division), Tata Consultancy Services Limited, 
      Hyderabad 500081, India.
FAU - Krishnan, Sowmya Ramaswamy
AU  - Krishnan SR
AUID- ORCID: 0000-0001-5404-3266
AD  - TCS Research (Life Sciences Division), Tata Consultancy Services Limited, 
      Hyderabad 500081, India.
FAU - Bung, Navneet
AU  - Bung N
AUID- ORCID: 0000-0002-6376-277X
AD  - TCS Research (Life Sciences Division), Tata Consultancy Services Limited, 
      Hyderabad 500081, India.
FAU - Srinivasan, Rajgopal
AU  - Srinivasan R
AD  - TCS Research (Life Sciences Division), Tata Consultancy Services Limited, 
      Hyderabad 500081, India.
FAU - Roy, Arijit
AU  - Roy A
AUID- ORCID: 0000-0002-1961-2483
AD  - TCS Research (Life Sciences Division), Tata Consultancy Services Limited, 
      Hyderabad 500081, India.
LA  - eng
PT  - Journal Article
DEP - 20230816
PL  - United States
TA  - J Chem Inf Model
JT  - Journal of chemical information and modeling
JID - 101230060
SB  - IM
MH  - *Artificial Intelligence
MH  - *Algorithms
EDAT- 2023/08/16 18:42
MHDA- 2023/08/29 12:42
CRDT- 2023/08/16 14:33
PHST- 2023/08/29 12:42 [medline]
PHST- 2023/08/16 18:42 [pubmed]
PHST- 2023/08/16 14:33 [entrez]
AID - 10.1021/acs.jcim.3c00689 [doi]
PST - ppublish
SO  - J Chem Inf Model. 2023 Aug 28;63(16):5066-5076. doi: 10.1021/acs.jcim.3c00689. 
      Epub 2023 Aug 16.