Nowadays, scientific collaboration has dramatically increased as a result of web-based technologies, advanced communication systems, and development of information and scientific databases. The present study aims to provide a predictive model for author collaborations in bioinformatics research output using graph mining techniques and big data applications. The study is an applied-developmental research adopting a mixed-method approach, i.e. a mix of quantitative and qualitative measures. The research population consisted of all bioinformatics research documents indexed in PubMed (n = 699160). The correlations of bioinformatics articles were examined in terms of weight and strength based on article sections including title, abstract, keywords, journal title, and author affiliation using graph mining techniques and big data applications. Eventually, the prediction model of author collaboration in bioinformatics research was developed using the abovementioned tools and expert-assigned weights. The calculations and data analysis were carried out using Expert Choice, Excel, Spark as well as Scala and Python programming languages in a big data server. Accordingly, the research was conducted in three phases: 1) identifying and weighting the factors contributing to authors’ similarity measurement; 2) implementing co-authorship prediction model; and 3) integrating the first and second phases (i.e. integrating the weights obtained in the previous phases). The results showed that journal title, citation, article title, author affiliation, keywords, and abstract scored 0.374, 0.374, 0.091, 0.075, 0.055, and 0.031, respectively. Moreover, the journal title achieved the highest score in the model for the co-author recommender system. As the data in bibliometric information networks is static, it was proved remarkably effective to use content-based features for similarity measures so that the recommender system can offer the best and most suitable collaboration suggestions. It is expected that the model work efficiently in other databases and provide suitable recommendations for author collaborations in other subject areas. By integrating expert opinion and systemic weights, the model can help alleviate the contemporary information overload and facilitate collaborator lookup by authors.