Machine learning model helps characterize compounds for drug discovery

Posted on

Credit: CC0 Public Domain

Tandem mass spectrometry is a powerful analytical tool used to characterize complex mixtures in drug discovery and other fields.

Now, Purdue University innovators have created a new method of applying machine learning concepts to the tandem mass spectrometry process to improve the flow of information in the development of new drugs. Their work is published in Chemical Science.

“Mass spectrometry plays an integral role in drug discovery and development,” said Gaurav Chopra, an assistant professor of analytical and physical chemistry in Purdue’s College of Science. “The specific implementation of bootstrapped machine learning with a small amount of positive and negative training data presented here will pave the way for becoming mainstream in day-to-day activities of automating characterization of compounds by chemists.”

Chopra said there are two major problems in the field of machine learning used for chemical sciences. Methods used do not provide chemical understanding of the decisions that are made by the algorithm, and new methods are not typically used to do blind experimental tests to see if the proposed models are accurate for use in a chemical laboratory.

“We have addressed both of these items for a methodology that is isomer selective and extremely useful in chemical sciences to characterize complex mixtures, identify chemical reactions and drug metabolites, and in fields such as proteomics and metabolomics,” Chopra said.

The Purdue researchers created statistically robust machine learning models to work with less training data—a technique that will be useful for drug discovery. The model looks at a common neutral reagent—called 2-methoxypropene (MOP) – and predicts how compounds will interact with MOP in a tandem mass spectrometer in order to obtain structural information for the compounds.

“This is the first time that machine learning has been coupled with diagnostic gas-phase ion-molecule reactions, and it is


Iksuda Therapeutics Enters License Agreement With University of Goettingen to Develop a New Generation of Antibody Drug Conjugates

Posted on

  • Iksuda licenses novel protein-alkylating, tumour-activated pro-drug payload series to develop ADCs with enhanced therapeutic index

  • Development to focus on targets associated with haematological and solid tumours

Iksuda Therapeutics (Iksuda), the developer of enhanced, new-generation of Antibody Drug Conjugates (ADCs), today announces it has executed its option to secure exclusive, worldwide rights to develop a novel class of tumour-activated prodrug payloads from the University of Goettingen, following a successful collaboration exemplifying the series in ADC formats. The highly potent and selective payload series represents a powerful new class within ADC development with novel protein alkylating cytotoxicity. Iksuda will drive onward development and commercialisation, incorporating the tuneable payload series in its ADC pipeline and payload armoury, to create best in class ADC therapeutics for nominated targets associated with haematological and solid tumours with high unmet need.

The partnership with the University of Goettingen was founded on Iksuda’s commitment to expand its payload armoury and optimise ADC design according to target antigen. The programme confirmed the value of tumour-selective activation of these powerful cytotoxic agents, conjugated with Iksuda’s stable conjugation technology (PermaLink®), in widening the therapeutic index of ADCs. The novel protein-alkylating mode-of-action of the payload series differs from the field’s primary focus of intra- or DNA inter-strand cross-linking, conferring benefits against drug resistance mechanisms. Through the combination of PermaLink technology and the protein alkylating prodrugs, the Company aims to enable the differentiated development of more powerful ADCs with improved tumour killing, aligned with improved safety index and an ability to overcome potential tumour resistance.

Iksuda has demonstrated the potential value of prodrug approaches for targeted cancer therapeutics through its recent license of a CD19-targeting ADC from LegoChem Biosciences (“LCB”) for hard-to-treat B-cell cancers, including diffuse large B-cell lymphoma and Burkitt lymphoma. The ADC contains LCB’s prodrug DNA-cross-linking payload, with preclinical


University of Texas in Trial Phase of Regeneron COVID Treatment Similar to Drug First Used by Trump

Posted on

Scientists at the are carrying out tests for a trial of a similar experimental antibody treatment than was first given to President Trump as he began treatment for the coronavirus.

a group of people standing on top of a desk: A doctor puts on hand sanitizer in the ER at Oakbend Medical Center in Richmond, Texas, on July 15, 2020. Researchers at The University of Texas Health Science Center at Houston are currently carrying out a number of trials of Covid-19 treatments, including one previously given to President Trump.

© Mark Felix / AFP/Getty Images
A doctor puts on hand sanitizer in the ER at Oakbend Medical Center in Richmond, Texas, on July 15, 2020. Researchers at The University of Texas Health Science Center at Houston are currently carrying out a number of trials of Covid-19 treatments, including one previously given to President Trump.

UTHealth researchers are studying the efficacy of an antibody treatment from drug maker Eli Lilly as well the first treatment of antibodies the president took, from Regeneron Pharmaceuticals.

Since being admitted to Walter Reed National Military Medical Center for further monitoring on Friday, specialists at the hospital opted to initiate Remdesivir therapy, according to a statement from the official presidential physician, Dr. Sean P. Conley.

World Reacts To Donald Trump, First Lady Melania Testing Positive For Coronavirus



“There’s been a history of using antibody’s to treat infections,” said Dr. Netanya Utay, Associate Professor of Internal Medicine at UTHealth. “The results that are out so far definitely look promising, but they’re from small trials.”

“We still need to enroll a lot more patients in these studies to really determine how effective they are for decreasing time to symptom resolution and decreasing hospitalizations,” the doctor said according to local news site ABC13.

UTHealth is undertaking several trial studies for antibody therapies and treatments from different drug makers for the coronavirus, including one investigating the use of blood plasma to treat the virus.

The trial being carried out by UTHealth with drugs from Regeneron, the same company behind the experimental drug first given to Trump, is with individuals who have been exposed