# Highly accurate protein structure prediction-based virtual docking pipeline accelerating the identification of anti-schistosomal compounds

## TL;DR

This study uses AI to predict protein structures in parasitic worms and identifies new drug candidates to treat schistosomiasis, a tropical disease.

## Contribution

A novel drug discovery framework combining AI-based protein structure prediction with virtual screening and molecular validation for schistosomiasis.

## Key findings

- Virtual screening identified 268 candidate compounds, seven of which showed strong anti-schistosomal activity.
- Carubicin hydrochloride (CH) was the most potent compound, targeting the splicing factor U2AF65.
- CH treatment and gene knockdown of U2AF65 disrupted splicing events and parasite viability.

## Abstract

Schistosomiasis is a major neglected tropical disease that lacks an effective vaccine and faces increasing challenges from praziquantel resistance, underscoring the urgent need for novel therapeutics. Target-based drug discovery (TBDD) is a powerful strategy for drug development. In this study, we utilized AlphaFold to predict the structures of target proteins from Schistosoma mansoni and S. japonicum, followed by virtual molecular screening to identify potential inhibitors. Among 202 potential therapeutic targets, we identified 37 proteins with high-accuracy structural predictions suitable for molecular docking with 14,600 compounds. This screening yielded 268 candidate compounds, which were further evaluated ex vivo for activity against both adult and juvenile S. mansoni and S. japonicum. Seven compounds exhibited strong anti-schistosomal activity, with HY-B2171A (Carubicin hydrochloride, CH) emerging as the most potent. CH was predicted to target the splicing factor U2AF65, and knockdown of its coding gene Smp_019690 resulted in a phenotype similar to CH treatment. RNA sequencing revealed that both CH treatment and Smp_019690 RNA interference (RNAi) disrupted splicing events in the parasites. Further studies demonstrated that CH impairs parasite viability by inhibiting U2AF65 function in mRNA splicing regulation. By integrating RNAi-based target identification with structure-based virtual screening, alongside ex vivo phenotypic and molecular analyses of compound-treated schistosomes, our study provides a comprehensive framework for anti-schistosomal drug discovery and identifies promising candidates for further preclinical development.

Schistosomiasis is a debilitating disease caused by parasitic worms and affects over 230 million people worldwide. For decades, control of the disease has relied on a single drug, praziquantel, which is less effective against juvenile parasites and increasingly threatened by the risk of drug resistance. To accelerate the discovery of new treatments, we integrated advanced computational tools with molecular validation. Using AlphaFold-predicted structures of 37 key schistosome proteins, we performed large-scale virtual screening to identify promising drug candidates. Over 200 compounds were prioritized for phenotypic screening on two major human-infective schistosome species, leading to the discovery of seven with potent anti-parasitic activity. Among them, Carubicin hydrochloride showed strong efficacy by targeting a critical splicing factor, U2AF65. Inhibiting this protein—either chemically or through gene silencing—disrupted parasite movement, suppressed cell proliferation, and altered splicing events. Our work highlights the power of integrating AI-based protein modeling with phenotypic and mechanistic validation to accelerate drug discovery for neglected tropical diseases like schistosomiasis.