Drug Synergy Prediction Using Dynamic Mutation based Differential Evolution

Purpose: In cancer therapies, drug combinations have shown significance accuracy and minimal side effects than the single drug administration. Therefore, the drug synergy has drawn great interest from pharmaceutical companies and researchers. Unfortunately, the prediction of drug synergy score by purely investigational means is only possible on small groups of drugs. Methods: With an advancement in high-throughput screening (HTS), the size of drug synergy datasets has grown enormously in recent years. Therefore, recently, many machine learning models have been utilized to predict the drug synergy score. However, the majority of these machine learning models suffer from over-fitting and hyper-parameters tuning issues. Results: Therefore, a novel deep bidirectional mixture density network (BMDN) model is proposed. To optimize the hyperparameters of BMDN, a dynamic mutation based multi-objective differential evolution is used. Extensive experiments are drawn by using the NCI-ALMANAC drug synergy dataset with over 290,000 synergy determinations. Conclusions: Experimental results shows that BMDN outperforms the exisitng drug synergy models in terms of various performance metrics.

The dynamic mutation investigation and whole exome sequencing in a cohort of Chinese autosomal dominant cerebellar ataxia patients

Background Spinocerebellar ataxias (SCAs) are the autosomal dominant cerebellar ataxia (ADCA) with great clinical and genetic heterogeneity. Genetic testing will contribute to the final diagnosis. Methods A total of 204 Chinese ADCA patients were recruited and 190 had genetic testing. Dynamic mutations of SCA1, 2, 3, 6, 7, 8, 10, 12, 17 and dentatorubral-pallidoluysian atrophy (DRPLA) were screened firstly. For the patients with negative results, the dynamic mutations of HTT of Huntington Disease (HD), SCA31, 36 and even the whole exome sequencing (WES) were further performed. We investigated the genetic results and clinical characteristics retrospectively. Results Among these 190 index cases, 177(93.16%) were identified SCA dynamic mutations. SCA3 was the commonest, accounting for 70.06%, followed by SCA1 (9.6%), 2 (9.05%), 12 (3.39%), 6 (2.26%), DRPLA (2.26%), 7(1.13%), 8 (1.13%) and 17(0.56%). One patient carried a compound dynamic mutation of SCA6 and SCA17 (SCA6/17). No SCA10 or SCA36 was found. Among the remaining 13 patients, three were diagnosed with HD (1.58%) and one with Episodic Ataxia 2 (EA2). WES did reveal several variants with uncertain significance (VUS) in the remaining nine patients, but failed to detect causative mutations. Conclusion We illustrated the approach and challenge of genetic testing in Chinese ADCA patients. Dynamic mutations of SCAs should be screened firstly. When the results were negative, dynamic mutation of HTT would better be screened consequently. In early-onset ADCA patients, WES might be effective to identify causative mutations, but in adult-onset cases, WES might be less effective.