Optimisation-based modelling for explainable lead discovery in malaria.

BACKGROUND: The search for new antimalarial treatments is urgent due to growing resistance to existing therapies. The Open Source Malaria (OSM) project offers a promising starting point, having extensively screened various compounds for their effectiveness. Further analysis of the chemical space surrounding these compounds could provide the means for innovative drugs. METHODS: We report an optimisation-based method for quantitative structure-activity relationship (QSAR) modelling that provides explainable modelling of ligand activity through a mathematical programming formulation. The methodology is based on piecewise regression principles and offers optimal detection of breakpoint features, efficient allocation of samples into distinct sub-groups based on breakpoint feature values, and insightful regression coefficients. Analysis of OSM antimalarial compounds yields interpretable results through rules generated by the model that reflect the contribution of individual fingerprint fragments in ligand activity prediction. Using knowledge of fragment prioritisation and screening of commercially available compound libraries, potential lead compounds for antimalarials are identified and evaluated experimentally via a Plasmodium falciparum asexual growth inhibition assay (PfGIA) and a human cell cytotoxicity assay. CONCLUSIONS: Three compounds are identified as potential leads for antimalarials using the methodology described above. This work illustrates how explainable predictive models based on mathematical optimisation can pave the way towards more efficient fragment-based lead discovery as applied in malaria.

Mathematical optimisation of extruded mixed plant protein-based meat analogues based on amino acid compositions.

Developing meat analogues of superior amino acid (AA) profiles in the food industry is a challenge as plant proteins contain less of some essential AA than animal proteins. Mathematical optimisation models such as linear/non-linear programming models were used to overcome this challenge and create high-moisture meat analogues (HMMA) with AA profiles as close as possible to chicken breast meat. The effect on the physiochemical properties and specific mechanical energy (SME) of the HMMA was investigated. The AA content of HMMA was generally lower than chicken. Strong intermolecular bonds present in the globulin fraction could hinder protein acid hydrolysis of HMMA. Plant proteins also affect the HMMA colour as certain AA forms Maillard reaction products with higher browning intensity. Lastly, different characteristics of plant proteins resulted in different SME values under the same extrusion conditions. While mathematical programming can optimise plant protein combinations, fortification is required to match the AA profile of HMMA to an animal source.