Join us at FastCompChem to reshape computational toxicology using 
quantum chemistry and machine learning.
 
You will be responsible for developing and implementing our new concept 
of electronic fingerprint, designated ESigns, totally based on quantum 
mechanics, that can cover the whole chemical space and relies on a small
number of parameters that are easily interpretable. The new approach 
introduces a momentous change in computational toxicology. It can cover 
the whole chemical space, uses fewer parameters, and can be related to 
the new trends in toxicology regarding use of pathways information. In 
fact, it is a powerful tool to allow accurate toxicology predictions 
solely on the basis of biochemical and chemical insight. 

Ideal candidates will have extensive experience with quantum chemistry, 
including CDFT, analysis of wavefunctions, MESP, electron density, etc. 
The work involves use of common software packages: Gamess-US, NWChem, 
Gaussian, etc. Differentiating skills for the position include 
experience in cheminformatics and in the use of cheminformatics 
software packages; machine learning; strong Python, Fortran and 
C/C++ programming skills; experience with development for HPC 
architectures; and familiarity with Linux/UNIX operating systems.  
Although expertise in these areas is important, specific knowledge 
of any of these areas is less critical than intellectual curiosity, 
adaptability, and a track record of achievement.

Working in collaboration with researchers at The University of 
Manchester (Manchester, UK), Liverpool John Moores University 
(Liverpool, UK) and Istituto di Ricerche Farmacologiche Mario Negri 
(Milan, Italy), you will develop reaction profiles of specific 
organic reactions, analyze reactivity data and develop electronic 
structure descriptors. The electronic structure descriptors will 
be derived from established methodologies (for example from CDFT, 
ELF, MESP, etc.). Coordinating with the collaborators in Manchester 
all sets of electronic structure descriptors will be incorporated 
into tentative ESign models. Suitable machine learning models using 
the ESigns will be developed using data curated by the collaborators 
in Milan and Liverpool.

Toxicology is at a crossroads. With ever more drugs going to market 
and more chemicals having an environmental impact, the need for fast, 
cheap and accurate technologies to assess toxic effects are pressing. 
Computational toxicology provides an array of tools and methods for 
toxicity prediction only using computer approaches. Conceptually, 
computational toxicology has significant advantages since testing is 
faster and cheaper than in vitro. However, currently computational 
toxicology has severe limitations. Predictions typically use 

Quantitative Structure-Activity Relationship (QSAR) models that rely 
on large sets of molecular descriptors. This causes severe problems 
since the methodologies cannot assess chemicals different from the ones 
used to develop the QSAR models, and when that is possible, the very 
large number of descriptors limits understandability. Therefore, new 
methodologies are needed to address those shortcomings.

Salary is highly competitive and the initial appointment is for 30 
months. There is, however, a very good chance of upgrading to a 
permanent position.

To explore the post further or for any queries you may have, please 
contact: 

Dr. Pedro Lopes, CSO, FastCompChem, Lda, Portugal

Tel: +351 961269227 or email: pemlopes*fastcompchem.pt