Machine Learning and Artificial Intelligence in Pharmaceutical Research and Development: a Review

Abstract

Graphical abstract Over the past decade, artificial intelligence (AI) and machine learning (ML) have become the breakthrough technology most anticipated to have a transformative effect on pharmaceutical research and development (R&D). This is partially driven by revolutionary advances in computational technology and the parallel dissipation of previous constraints to the collection/processing of large volumes of data. Meanwhile, the cost of bringing new drugs to market and to patients has become prohibitively expensive. Recognizing these headwinds, AI/ML techniques are appealing to the pharmaceutical industry due to their automated nature, predictive capabilities, and the consequent expected increase in efficiency. ML approaches have been used in drug discovery over the past 15–20 years with increasing sophistication. The most recent aspect of drug development where positive disruption from AI/ML is starting to occur, is in clinical trial design, conduct, and analysis. The COVID-19 pandemic may further accelerate utilization of AI/ML in clinical trials due to an increased reliance on digital technology in clinical trial conduct. As we move towards a world where there is a growing integration of AI/ML into R&D, it is critical to get past the related buzz-words and noise. It is equally important to recognize that the scientific method is not obsolete when making inferences about data. Doing so will help in separating hope from hype and lead to informed decision-making on the optimal use of AI/ML in drug development. This manuscript aims to demystify key concepts, present use-cases and finally offer insights and a balanced view on the optimal use of AI/ML methods in R&D.

Extending the High-Throughput Experimentation (HTE) Approach to Catalytic Olefin Polymerizations: From Catalysts to Materials

“…Chemistry is an empirical science, and high-throughput experimentation (HTE) has the potential to grow into a pervasive enabling technology. In areas adjacent to biology (e.g., biochemistry and pharmaceuticals), HTE tools and methods already represent the gold standard for quantitative structure–activity relationship (QSAR) studies due to a favorable mix of scientific, technological, and market aspects. − For instance, biological activity is a single property that can be measured with a combinatorial approach under the mild conditions at which biochemical processes typically occur, the commercial relevance of rapid automated assays is huge, and last but not least system complexity calls for statistical models in which large HTE databases are analyzed by means of advanced applications of artificial intelligence (AI) such as machine learning (ML). − …”

Accelerating 3D printing of pharmaceutical products using machine learning

“…In healthcare, ML-powered products are increasingly receiving regulatory clearance, with a 2020 study finding that AI/ML systems are winning approval from the US Food and Drug Administration (FDA) at an accelerating rate ( Benjamens et al, 2020 ; Rajpurkar et al, 2022 ). The transformative effect that ML has had on other industries has prompted the pharmaceutical industry to identify opportunities to re-invent traditional time-consuming processes in bringing medicines into market ( Abramov et al, 2022 ; Elbadawi et al, 2021a ; Kolluri et al, 2022 ; Lou et al, 2021 ; Paul et al, 2021 ; Thomas et al, 2021 ; Yang et al, 2019 ).…”

Prediksi Kuantitas Penggunaan Obat pada Layanan Kesehatan Menggunakan Algoritma Backpropagation Neural Network

“…Perkembangan Artificial Neural Network (ANN) sangat memungkinkan untuk melakukan prediksi [1]. Dari data yang ada pada sistem informasi [2], bisa dilakukan pengolahan sehingga menghasilkan informasi dan pengetahuan menggunakan Machine Learning atau pembelajaran mesin.…”

“…Pada saat melakukan konfigurasi ANN [20] [22]. Pada Puskesmas yang sama, [23], [1] melakukan prediksi kebutuhan obat menggunakan metode Learning Vector Quatization. Hasil prediksinya menunjukkan akurasi yang tidak jauh lebih baik dari Backpropagation yaitu 78.57%.…”