Live Updates: COVID-19 Cases
  • World 20,837,376
    World
    Confirmed: 20,837,376
    Active: 6,359,547
    Recovered: 13,729,930
    Death: 747,899
  • USA 5,360,488
    USA
    Confirmed: 5,360,488
    Active: 2,378,228
    Recovered: 2,813,125
    Death: 169,135
  • Brazil 3,170,474
    Brazil
    Confirmed: 3,170,474
    Active: 756,734
    Recovered: 2,309,477
    Death: 104,263
  • India 2,399,992
    India
    Confirmed: 2,399,992
    Active: 655,012
    Recovered: 1,697,811
    Death: 47,169
  • Russia 907,758
    Russia
    Confirmed: 907,758
    Active: 175,978
    Recovered: 716,396
    Death: 15,384
  • South Africa 568,919
    South Africa
    Confirmed: 568,919
    Active: 125,880
    Recovered: 432,029
    Death: 11,010
  • Peru 498,555
    Peru
    Confirmed: 498,555
    Active: 134,904
    Recovered: 341,938
    Death: 21,713
  • Mexico 498,380
    Mexico
    Confirmed: 498,380
    Active: 107,079
    Recovered: 336,635
    Death: 54,666
  • Chile 378,168
    Chile
    Confirmed: 378,168
    Active: 16,544
    Recovered: 351,419
    Death: 10,205
  • Spain 376,864
    Spain
    Confirmed: 376,864
    Active: 348,285
    Recovered: ?
    Death: 28,579
  • Iran 336,324
    Iran
    Confirmed: 336,324
    Active: 25,104
    Recovered: 292,058
    Death: 19,162
  • UK 313,798
    UK
    Confirmed: 313,798
    Active: 272,469
    Recovered: ?
    Death: 41,329
  • Saudi Arabia 293,037
    Saudi Arabia
    Confirmed: 293,037
    Active: 32,499
    Recovered: 257,269
    Death: 3,269
  • Pakistan 286,674
    Pakistan
    Confirmed: 286,674
    Active: 16,475
    Recovered: 264,060
    Death: 6,139
  • Bangladesh 269,115
    Bangladesh
    Confirmed: 269,115
    Active: 110,687
    Recovered: 154,871
    Death: 3,557
  • Italy 251,713
    Italy
    Confirmed: 251,713
    Active: 13,791
    Recovered: 202,697
    Death: 35,225
  • Turkey 244,392
    Turkey
    Confirmed: 244,392
    Active: 11,412
    Recovered: 227,089
    Death: 5,891
  • Germany 220,884
    Germany
    Confirmed: 220,884
    Active: 10,808
    Recovered: 200,800
    Death: 9,276
  • France 206,696
    France
    Confirmed: 206,696
    Active: 92,853
    Recovered: 83,472
    Death: 30,371
  • Canada 120,844
    Canada
    Confirmed: 120,844
    Active: 4,690
    Recovered: 107,148
    Death: 9,006
  • China 84,756
    China
    Confirmed: 84,756
    Active: 724
    Recovered: 79,398
    Death: 4,634
  • Netherlands 60,627
    Netherlands
    Confirmed: 60,627
    Active: 54,466
    Recovered: ?
    Death: 6,161
  • Australia 22,358
    Australia
    Confirmed: 22,358
    Active: 8,996
    Recovered: 13,001
    Death: 361
  • S. Korea 14,770
    S. Korea
    Confirmed: 14,770
    Active: 648
    Recovered: 13,817
    Death: 305
  • New Zealand 1,589
    New Zealand
    Confirmed: 1,589
    Active: 36
    Recovered: 1,531
    Death: 22

MIT researchers develop AI model with higher potencies to molecules

Author at TechGenyz Science
MIT Research Molecule
MIT Research Molecule

MIT researchers have found ways to implement AI to fast forward the procedure of designing new molecules with precise results, in the field of medical research.

The research was a part of Machine Learning for Pharmaceutical Discovery and Synthesis that’s being carried out by MIT researchers in concert with eight medical firms. The newly developed AI model by the researchers can select lead molecules, boost the structure for achieving higher potency, and at the same time keep it chemically valid.

The consortium was announced in May and has identified one key challenge in drug discovery: lead optimization.

The motivation behind this was to replace the inefficient human modification process of designing molecules with automated iteration and assure the validity of the molecules we generate. – Wengong Jin, lead author of the model’s paper

Co-author of the paper Tommi S. Barzilay talked about what’s coming next: “The next step is to take this technology from academia to use on real pharmaceutical design cases, and demonstrate that it can assist human chemists in doing their work, which can be challenging.”

The model was trained across 250,000 molecular graphs derived from the ZINC database, that’s a collection of 3D molecular structures made publicly available. The tasks conducted were generating valid molecules, finding the best lead molecules, and designing novel molecules with enhanced potencies.

The results involved 100% chemically valid molecules generated from a sample distribution. Also, the potency level has been observed to be 30% higher than traditional systems. Finally, the model can create new molecules from modifying 800 molecules for higher potency while closely staying true to the lead molecular structure, and it averaged over 80% improvement in potency.

Next will come testing the model on properties beyond solubility, the ones that are more therapeutically relevant. This requires more data, as the researchers point out. They are planning to develop a new model to deploy with a limited amount of training data.

Career

Subscribe